diff options
| author | Dmitry Torokhov | 2017-01-24 12:37:43 -0800 |
|---|---|---|
| committer | Dmitry Torokhov | 2017-01-24 12:37:43 -0800 |
| commit | 0cce284537fb42d9c28b9b31038ffc9b464555f5 (patch) | |
| tree | e7af3b5fe2d04ef6527b5da50851d498ee13184e /include/net | |
| parent | cefb26d4b37c329f624eb235a1bdc7b6b8dd9430 (diff) | |
| parent | 7a308bb3016f57e5be11a677d15b821536419d36 (diff) | |
Merge tag 'v4.10-rc5' into next
Sync up with mainline to bring up improvements in various subsystems.
Diffstat (limited to 'include/net')
104 files changed, 2544 insertions, 887 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index 82f3c912a5b1..1d716449209e 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -36,13 +36,12 @@ struct tc_action { struct tcf_t tcfa_tm; struct gnet_stats_basic_packed tcfa_bstats; struct gnet_stats_queue tcfa_qstats; - struct gnet_stats_rate_est64 tcfa_rate_est; + struct net_rate_estimator __rcu *tcfa_rate_est; spinlock_t tcfa_lock; struct rcu_head tcfa_rcu; struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; }; -#define tcf_act common.tcfa_act #define tcf_head common.tcfa_head #define tcf_index common.tcfa_index #define tcf_refcnt common.tcfa_refcnt @@ -120,6 +119,8 @@ struct tc_action_ops { int (*walk)(struct net *, struct sk_buff *, struct netlink_callback *, int, const struct tc_action_ops *); void (*stats_update)(struct tc_action *, u64, u32, u64); + int (*get_dev)(const struct tc_action *a, struct net *net, + struct net_device **mirred_dev); }; struct tc_action_net { diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 9826d3a9464c..8f998afc1384 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -1,8 +1,9 @@ #ifndef _ADDRCONF_H #define _ADDRCONF_H -#define MAX_RTR_SOLICITATIONS 3 +#define MAX_RTR_SOLICITATIONS -1 /* unlimited */ #define RTR_SOLICITATION_INTERVAL (4*HZ) +#define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */ #define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ @@ -173,6 +174,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); +void __ipv6_sock_mc_close(struct sock *sk); void ipv6_sock_mc_close(struct sock *sk); bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, const struct in6_addr *src_addr); diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 7b0f88699b25..1061a472a3e3 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -12,42 +12,39 @@ #ifndef _NET_RXRPC_H #define _NET_RXRPC_H -#include <linux/skbuff.h> #include <linux/rxrpc.h> +struct key; +struct sock; +struct socket; struct rxrpc_call; -/* - * the mark applied to socket buffers that may be intercepted - */ -enum rxrpc_skb_mark { - RXRPC_SKB_MARK_DATA, /* data message */ - RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */ - RXRPC_SKB_MARK_BUSY, /* server busy message */ - RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */ - RXRPC_SKB_MARK_LOCAL_ABORT, /* local abort message */ - RXRPC_SKB_MARK_NET_ERROR, /* network error message */ - RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */ - RXRPC_SKB_MARK_NEW_CALL, /* local error message */ -}; +typedef void (*rxrpc_notify_rx_t)(struct sock *, struct rxrpc_call *, + unsigned long); +typedef void (*rxrpc_notify_new_call_t)(struct sock *, struct rxrpc_call *, + unsigned long); +typedef void (*rxrpc_discard_new_call_t)(struct rxrpc_call *, unsigned long); +typedef void (*rxrpc_user_attach_call_t)(struct rxrpc_call *, unsigned long); -typedef void (*rxrpc_interceptor_t)(struct sock *, unsigned long, - struct sk_buff *); -void rxrpc_kernel_intercept_rx_messages(struct socket *, rxrpc_interceptor_t); +void rxrpc_kernel_new_call_notification(struct socket *, + rxrpc_notify_new_call_t, + rxrpc_discard_new_call_t); struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *, struct sockaddr_rxrpc *, struct key *, unsigned long, - gfp_t); -int rxrpc_kernel_send_data(struct rxrpc_call *, struct msghdr *, size_t); -void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); -void rxrpc_kernel_abort_call(struct rxrpc_call *, u32); -void rxrpc_kernel_end_call(struct rxrpc_call *); -bool rxrpc_kernel_is_data_last(struct sk_buff *); -u32 rxrpc_kernel_get_abort_code(struct sk_buff *); -int rxrpc_kernel_get_error_number(struct sk_buff *); -void rxrpc_kernel_free_skb(struct sk_buff *); -struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *, unsigned long); -int rxrpc_kernel_reject_call(struct socket *); + gfp_t, + rxrpc_notify_rx_t); +int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *, + struct msghdr *, size_t); +int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *, + void *, size_t, size_t *, bool, u32 *); +void rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, + u32, int, const char *); +void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); +void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, + struct sockaddr_rxrpc *); +int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, + rxrpc_user_attach_call_t, unsigned long, gfp_t); #endif /* _NET_RXRPC_H */ diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index bfd1590821d6..01487192f628 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -29,7 +29,8 @@ #include <net/sock.h> #include <linux/seq_file.h> -#define BT_SUBSYS_VERSION "2.21" +#define BT_SUBSYS_VERSION 2 +#define BT_SUBSYS_REVISION 22 #ifndef AF_BLUETOOTH #define AF_BLUETOOTH 31 @@ -196,7 +197,7 @@ typedef struct { #define BDADDR_LE_PUBLIC 0x01 #define BDADDR_LE_RANDOM 0x02 -static inline bool bdaddr_type_is_valid(__u8 type) +static inline bool bdaddr_type_is_valid(u8 type) { switch (type) { case BDADDR_BREDR: @@ -208,7 +209,7 @@ static inline bool bdaddr_type_is_valid(__u8 type) return false; } -static inline bool bdaddr_type_is_le(__u8 type) +static inline bool bdaddr_type_is_le(u8 type) { switch (type) { case BDADDR_LE_PUBLIC: @@ -278,15 +279,16 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock); /* Skb helpers */ struct l2cap_ctrl { - __u8 sframe:1, + u8 sframe:1, poll:1, final:1, fcs:1, sar:2, super:2; - __u16 reqseq; - __u16 txseq; - __u8 retries; + + u16 reqseq; + u16 txseq; + u8 retries; __le16 psm; bdaddr_t bdaddr; struct l2cap_chan *chan; @@ -302,7 +304,7 @@ typedef void (*hci_req_complete_skb_t)(struct hci_dev *hdev, u8 status, #define HCI_REQ_SKB BIT(1) struct hci_ctrl { - __u16 opcode; + u16 opcode; u8 req_flags; u8 req_event; union { @@ -312,10 +314,10 @@ struct hci_ctrl { }; struct bt_skb_cb { - __u8 pkt_type; - __u8 force_active; - __u16 expect; - __u8 incoming:1; + u8 pkt_type; + u8 force_active; + u16 expect; + u8 incoming:1; union { struct l2cap_ctrl l2cap; struct hci_ctrl hci; @@ -365,12 +367,13 @@ out: return NULL; } -int bt_to_errno(__u16 code); +int bt_to_errno(u16 code); void hci_sock_set_flag(struct sock *sk, int nr); void hci_sock_clear_flag(struct sock *sk, int nr); int hci_sock_test_flag(struct sock *sk, int nr); unsigned short hci_sock_get_channel(struct sock *sk); +u32 hci_sock_get_cookie(struct sock *sk); int hci_sock_init(void); void hci_sock_cleanup(void); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 003b25283407..99aa5e5e3100 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -63,6 +63,7 @@ #define HCI_SDIO 6 #define HCI_SPI 7 #define HCI_I2C 8 +#define HCI_SMD 9 /* HCI controller types */ #define HCI_PRIMARY 0x00 @@ -207,7 +208,11 @@ enum { HCI_MGMT_INDEX_EVENTS, HCI_MGMT_UNCONF_INDEX_EVENTS, HCI_MGMT_EXT_INDEX_EVENTS, - HCI_MGMT_GENERIC_EVENTS, + HCI_MGMT_EXT_INFO_EVENTS, + HCI_MGMT_OPTION_EVENTS, + HCI_MGMT_SETTING_EVENTS, + HCI_MGMT_DEV_CLASS_EVENTS, + HCI_MGMT_LOCAL_NAME_EVENTS, HCI_MGMT_OOB_DATA_EVENTS, }; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index ee7fc47680a1..554671c81f4a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -211,6 +211,7 @@ struct hci_dev { __u8 dev_name[HCI_MAX_NAME_LENGTH]; __u8 short_name[HCI_MAX_SHORT_NAME_LENGTH]; __u8 eir[HCI_MAX_EIR_LENGTH]; + __u16 appearance; __u8 dev_class[3]; __u8 major_class; __u8 minor_class; @@ -399,7 +400,9 @@ struct hci_dev { struct delayed_work rpa_expired; bdaddr_t rpa; +#if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; +#endif int (*open)(struct hci_dev *hdev); int (*close)(struct hci_dev *hdev); @@ -1015,7 +1018,7 @@ static inline void hci_set_drvdata(struct hci_dev *hdev, void *data) } struct hci_dev *hci_dev_get(int index); -struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src); +struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, u8 src_type); struct hci_dev *hci_alloc_dev(void); void hci_free_dev(struct hci_dev *hdev); @@ -1026,8 +1029,8 @@ int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); -void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...); -void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...); +__printf(2, 3) void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...); +__printf(2, 3) void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...); int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); int hci_dev_do_close(struct hci_dev *hdev); @@ -1404,6 +1407,9 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, int flag, struct sock *skip_sk); void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); +void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event, + void *data, u16 data_len, ktime_t tstamp, + int flag, struct sock *skip_sk); void hci_sock_dev_event(struct hci_dev *hdev, int event); @@ -1449,6 +1455,7 @@ void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); #define DISCOV_BREDR_INQUIRY_LEN 0x08 #define DISCOV_LE_RESTART_DELAY msecs_to_jiffies(200) /* msec */ +void mgmt_fill_version_info(void *ver); int mgmt_new_settings(struct hci_dev *hdev); void mgmt_index_added(struct hci_dev *hdev); void mgmt_index_removed(struct hci_dev *hdev); diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index 587d0131b349..240786b04a46 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -45,6 +45,10 @@ struct hci_mon_hdr { #define HCI_MON_VENDOR_DIAG 11 #define HCI_MON_SYSTEM_NOTE 12 #define HCI_MON_USER_LOGGING 13 +#define HCI_MON_CTRL_OPEN 14 +#define HCI_MON_CTRL_CLOSE 15 +#define HCI_MON_CTRL_COMMAND 16 +#define HCI_MON_CTRL_EVENT 17 struct hci_mon_new_index { __u8 type; diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 7647964b1efa..72a456bbbcd5 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -586,6 +586,24 @@ struct mgmt_rp_get_adv_size_info { #define MGMT_OP_START_LIMITED_DISCOVERY 0x0041 +#define MGMT_OP_READ_EXT_INFO 0x0042 +#define MGMT_READ_EXT_INFO_SIZE 0 +struct mgmt_rp_read_ext_info { + bdaddr_t bdaddr; + __u8 version; + __le16 manufacturer; + __le32 supported_settings; + __le32 current_settings; + __le16 eir_len; + __u8 eir[0]; +} __packed; + +#define MGMT_OP_SET_APPEARANCE 0x0043 +struct mgmt_cp_set_appearance { + __u16 appearance; +} __packed; +#define MGMT_SET_APPEARANCE_SIZE 2 + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; @@ -800,3 +818,9 @@ struct mgmt_ev_advertising_added { struct mgmt_ev_advertising_removed { __u8 instance; } __packed; + +#define MGMT_EV_EXT_INFO_CHANGED 0x0025 +struct mgmt_ev_ext_info_changed { + __le16 eir_len; + __u8 eir[0]; +} __packed; diff --git a/include/net/bonding.h b/include/net/bonding.h index 6360c259da6d..3c857778a6ca 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -37,18 +37,6 @@ #ifndef __long_aligned #define __long_aligned __attribute__((aligned((sizeof(long))))) #endif -/* - * Less bad way to call ioctl from within the kernel; this needs to be - * done some other way to get the call out of interrupt context. - * Needs "ioctl" variable to be supplied by calling context. - */ -#define IOCTL(dev, arg, cmd) ({ \ - int res = 0; \ - mm_segment_t fs = get_fs(); \ - set_fs(get_ds()); \ - res = ioctl(dev, arg, cmd); \ - set_fs(fs); \ - res; }) #define BOND_MODE(bond) ((bond)->params.mode) @@ -693,7 +681,7 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) } /* exported from bond_main.c */ -extern int bond_net_id; +extern unsigned int bond_net_id; extern const struct bond_parm_tbl bond_lacp_tbl[]; extern const struct bond_parm_tbl xmit_hashtype_tbl[]; extern const struct bond_parm_tbl arp_validate_tbl[]; diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 2fbeb1313c0f..d73b849e29a6 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -58,10 +58,9 @@ static inline unsigned long busy_loop_end_time(void) return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_busy_poll); } -static inline bool sk_can_busy_loop(struct sock *sk) +static inline bool sk_can_busy_loop(const struct sock *sk) { - return sk->sk_ll_usec && sk->sk_napi_id && - !need_resched() && !signal_pending(current); + return sk->sk_ll_usec && sk->sk_napi_id && !signal_pending(current); } @@ -81,11 +80,6 @@ static inline void skb_mark_napi_id(struct sk_buff *skb, skb->napi_id = napi->napi_id; } -/* used in the protocol hanlder to propagate the napi_id to the socket */ -static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb) -{ - sk->sk_napi_id = skb->napi_id; -} #else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) @@ -108,10 +102,6 @@ static inline void skb_mark_napi_id(struct sk_buff *skb, { } -static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb) -{ -} - static inline bool busy_loop_timeout(unsigned long end_time) { return true; @@ -123,4 +113,23 @@ static inline bool sk_busy_loop(struct sock *sk, int nonblock) } #endif /* CONFIG_NET_RX_BUSY_POLL */ + +/* used in the protocol hanlder to propagate the napi_id to the socket */ +static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + sk->sk_napi_id = skb->napi_id; +#endif +} + +/* variant used for unconnected sockets */ +static inline void sk_mark_napi_id_once(struct sock *sk, + const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + if (!sk->sk_napi_id) + sk->sk_napi_id = skb->napi_id; +#endif +} + #endif /* _LINUX_NET_BUSY_POLL_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index beb7610d64e9..814be4b4200c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5,7 +5,7 @@ * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright 2015 Intel Deutschland GmbH + * Copyright 2015-2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -593,6 +593,8 @@ struct survey_info { s8 noise; }; +#define CFG80211_MAX_WEP_KEYS 4 + /** * struct cfg80211_crypto_settings - Crypto settings * @wpa_versions: indicates which, if any, WPA versions are enabled @@ -610,6 +612,9 @@ struct survey_info { * allowed through even on unauthorized ports * @control_port_no_encrypt: TRUE to prevent encryption of control port * protocol frames. + * @wep_keys: static WEP keys, if not NULL points to an array of + * CFG80211_MAX_WEP_KEYS WEP keys + * @wep_tx_key: key index (0..3) of the default TX static WEP key */ struct cfg80211_crypto_settings { u32 wpa_versions; @@ -621,6 +626,8 @@ struct cfg80211_crypto_settings { bool control_port; __be16 control_port_ethertype; bool control_port_no_encrypt; + struct key_params *wep_keys; + int wep_tx_key; }; /** @@ -676,6 +683,18 @@ struct cfg80211_acl_data { struct mac_address mac_addrs[]; }; +/* + * cfg80211_bitrate_mask - masks for bitrate control + */ +struct cfg80211_bitrate_mask { + struct { + u32 legacy; + u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; + u16 vht_mcs[NL80211_VHT_NSS_MAX]; + enum nl80211_txrate_gi gi; + } control[NUM_NL80211_BANDS]; +}; + /** * struct cfg80211_ap_settings - AP configuration * @@ -700,6 +719,7 @@ struct cfg80211_acl_data { * MAC address based access control * @pbss: If set, start as a PCP instead of AP. Relevant for DMG * networks. + * @beacon_rate: bitrate to be used for beacons */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -719,6 +739,7 @@ struct cfg80211_ap_settings { bool p2p_opp_ps; const struct cfg80211_acl_data *acl; bool pbss; + struct cfg80211_bitrate_mask beacon_rate; }; /** @@ -751,6 +772,30 @@ struct cfg80211_csa_settings { }; /** + * struct iface_combination_params - input parameters for interface combinations + * + * Used to pass interface combination parameters + * + * @num_different_channels: the number of different channels we want + * to use for verification + * @radar_detect: a bitmap where each bit corresponds to a channel + * width where radar detection is needed, as in the definition of + * &struct ieee80211_iface_combination.@radar_detect_widths + * @iftype_num: array with the number of interfaces of each interface + * type. The index is the interface type as specified in &enum + * nl80211_iftype. + * @new_beacon_int: set this to the beacon interval of a new interface + * that's not operating yet, if such is to be checked as part of + * the verification + */ +struct iface_combination_params { + int num_different_channels; + u8 radar_detect; + int iftype_num[NUM_NL80211_IFTYPES]; + u32 new_beacon_int; +}; + +/** * enum station_parameters_apply_mask - station parameter values to apply * @STATION_PARAM_APPLY_UAPSD: apply new uAPSD parameters (uapsd_queues, max_sp) * @STATION_PARAM_APPLY_CAPABILITY: apply new capability @@ -775,9 +820,9 @@ enum station_parameters_apply_mask { * (or NULL for no change) * @supported_rates_len: number of supported rates * @sta_flags_mask: station flags that changed - * (bitmask of BIT(NL80211_STA_FLAG_...)) + * (bitmask of BIT(%NL80211_STA_FLAG_...)) * @sta_flags_set: station flags values - * (bitmask of BIT(NL80211_STA_FLAG_...)) + * (bitmask of BIT(%NL80211_STA_FLAG_...)) * @listen_interval: listen interval or -1 for no change * @aid: AID or zero for no change * @peer_aid: mesh peer AID or zero for no change @@ -1351,6 +1396,7 @@ struct mesh_config { * @beacon_interval: beacon interval to use * @mcast_rate: multicat rate for Mesh Node [6Mbps is the default for 802.11a] * @basic_rates: basic rates to use when creating the mesh + * @beacon_rate: bitrate to be used for beacons * * These parameters are fixed when the mesh is created. */ @@ -1371,6 +1417,7 @@ struct mesh_setup { u16 beacon_interval; int mcast_rate[NUM_NL80211_BANDS]; u32 basic_rates; + struct cfg80211_bitrate_mask beacon_rate; }; /** @@ -1738,9 +1785,11 @@ const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 ie); * @key_len: length of WEP key for shared key authentication * @key_idx: index of WEP key for shared key authentication * @key: WEP key for shared key authentication - * @sae_data: Non-IE data to use with SAE or %NULL. This starts with - * Authentication transaction sequence number field. - * @sae_data_len: Length of sae_data buffer in octets + * @auth_data: Fields and elements in Authentication frames. This contains + * the authentication frame body (non-IE and IE data), excluding the + * Authentication algorithm number, i.e., starting at the Authentication + * transaction sequence number field. + * @auth_data_len: Length of auth_data buffer in octets */ struct cfg80211_auth_request { struct cfg80211_bss *bss; @@ -1749,8 +1798,8 @@ struct cfg80211_auth_request { enum nl80211_auth_type auth_type; const u8 *key; u8 key_len, key_idx; - const u8 *sae_data; - size_t sae_data_len; + const u8 *auth_data; + size_t auth_data_len; }; /** @@ -1791,6 +1840,12 @@ enum cfg80211_assoc_req_flags { * @ht_capa_mask: The bits of ht_capa which are to be used. * @vht_capa: VHT capability override * @vht_capa_mask: VHT capability mask indicating which fields to use + * @fils_kek: FILS KEK for protecting (Re)Association Request/Response frame or + * %NULL if FILS is not used. + * @fils_kek_len: Length of fils_kek in octets + * @fils_nonces: FILS nonces (part of AAD) for protecting (Re)Association + * Request/Response frame or %NULL if FILS is not used. This field starts + * with 16 octets of STA Nonce followed by 16 octets of AP Nonce. */ struct cfg80211_assoc_request { struct cfg80211_bss *bss; @@ -1802,6 +1857,9 @@ struct cfg80211_assoc_request { struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; struct ieee80211_vht_cap vht_capa, vht_capa_mask; + const u8 *fils_kek; + size_t fils_kek_len; + const u8 *fils_nonces; }; /** @@ -1993,6 +2051,18 @@ struct cfg80211_connect_params { }; /** + * enum cfg80211_connect_params_changed - Connection parameters being updated + * + * This enum provides information of all connect parameters that + * have to be updated as part of update_connect_params() call. + * + * @UPDATE_ASSOC_IES: Indicates whether association request IEs are updated + */ +enum cfg80211_connect_params_changed { + UPDATE_ASSOC_IES = BIT(0), +}; + +/** * enum wiphy_params_flags - set_wiphy_params bitfield values * @WIPHY_PARAM_RETRY_SHORT: wiphy->retry_short has changed * @WIPHY_PARAM_RETRY_LONG: wiphy->retry_long has changed @@ -2010,17 +2080,6 @@ enum wiphy_params_flags { WIPHY_PARAM_DYN_ACK = 1 << 5, }; -/* - * cfg80211_bitrate_mask - masks for bitrate control - */ -struct cfg80211_bitrate_mask { - struct { - u32 legacy; - u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; - u16 vht_mcs[NL80211_VHT_NSS_MAX]; - enum nl80211_txrate_gi gi; - } control[NUM_NL80211_BANDS]; -}; /** * struct cfg80211_pmksa - PMK Security Association * @@ -2302,6 +2361,98 @@ struct cfg80211_qos_map { }; /** + * struct cfg80211_nan_conf - NAN configuration + * + * This struct defines NAN configuration parameters + * + * @master_pref: master preference (1 - 255) + * @dual: dual band operation mode, see &enum nl80211_nan_dual_band_conf + */ +struct cfg80211_nan_conf { + u8 master_pref; + u8 dual; +}; + +/** + * enum cfg80211_nan_conf_changes - indicates changed fields in NAN + * configuration + * + * @CFG80211_NAN_CONF_CHANGED_PREF: master preference + * @CFG80211_NAN_CONF_CHANGED_DUAL: dual band operation + */ +enum cfg80211_nan_conf_changes { + CFG80211_NAN_CONF_CHANGED_PREF = BIT(0), + CFG80211_NAN_CONF_CHANGED_DUAL = BIT(1), +}; + +/** + * struct cfg80211_nan_func_filter - a NAN function Rx / Tx filter + * + * @filter: the content of the filter + * @len: the length of the filter + */ +struct cfg80211_nan_func_filter { + const u8 *filter; + u8 len; +}; + +/** + * struct cfg80211_nan_func - a NAN function + * + * @type: &enum nl80211_nan_function_type + * @service_id: the service ID of the function + * @publish_type: &nl80211_nan_publish_type + * @close_range: if true, the range should be limited. Threshold is + * implementation specific. + * @publish_bcast: if true, the solicited publish should be broadcasted + * @subscribe_active: if true, the subscribe is active + * @followup_id: the instance ID for follow up + * @followup_reqid: the requestor instance ID for follow up + * @followup_dest: MAC address of the recipient of the follow up + * @ttl: time to live counter in DW. + * @serv_spec_info: Service Specific Info + * @serv_spec_info_len: Service Specific Info length + * @srf_include: if true, SRF is inclusive + * @srf_bf: Bloom Filter + * @srf_bf_len: Bloom Filter length + * @srf_bf_idx: Bloom Filter index + * @srf_macs: SRF MAC addresses + * @srf_num_macs: number of MAC addresses in SRF + * @rx_filters: rx filters that are matched with corresponding peer's tx_filter + * @tx_filters: filters that should be transmitted in the SDF. + * @num_rx_filters: length of &rx_filters. + * @num_tx_filters: length of &tx_filters. + * @instance_id: driver allocated id of the function. + * @cookie: unique NAN function identifier. + */ +struct cfg80211_nan_func { + enum nl80211_nan_function_type type; + u8 service_id[NL80211_NAN_FUNC_SERVICE_ID_LEN]; + u8 publish_type; + bool close_range; + bool publish_bcast; + bool subscribe_active; + u8 followup_id; + u8 followup_reqid; + struct mac_address followup_dest; + u32 ttl; + const u8 *serv_spec_info; + u8 serv_spec_info_len; + bool srf_include; + const u8 *srf_bf; + u8 srf_bf_len; + u8 srf_bf_idx; + struct mac_address *srf_macs; + int srf_num_macs; + struct cfg80211_nan_func_filter *rx_filters; + struct cfg80211_nan_func_filter *tx_filters; + u8 num_tx_filters; + u8 num_rx_filters; + u8 instance_id; + u64 cookie; +}; + +/** * struct cfg80211_ops - backend description for wireless configuration * * This struct is registered by fullmac card drivers and/or wireless stacks @@ -2432,8 +2583,18 @@ struct cfg80211_qos_map { * cases, the result of roaming is indicated with a call to * cfg80211_roamed() or cfg80211_roamed_bss(). * (invoked with the wireless_dev mutex held) - * @disconnect: Disconnect from the BSS/ESS. + * @update_connect_params: Update the connect parameters while connected to a + * BSS. The updated parameters can be used by driver/firmware for + * subsequent BSS selection (roaming) decisions and to form the + * Authentication/(Re)Association Request frames. This call does not + * request an immediate disassociation or reassociation with the current + * BSS, i.e., this impacts only subsequent (re)associations. The bits in + * changed are defined in &enum cfg80211_connect_params_changed. * (invoked with the wireless_dev mutex held) + * @disconnect: Disconnect from the BSS/ESS or stop connection attempts if + * connection is in progress. Once done, call cfg80211_disconnected() in + * case connection was already established (invoked with the + * wireless_dev mutex held), otherwise call cfg80211_connect_timeout(). * * @join_ibss: Join the specified IBSS (or create if necessary). Once done, call * cfg80211_ibss_joined(), also call that function when changing BSSID due @@ -2588,6 +2749,21 @@ struct cfg80211_qos_map { * and returning to the base channel for communication with the AP. * @tdls_cancel_channel_switch: Stop channel-switching with a TDLS peer. Both * peers must be on the base channel when the call completes. + * @start_nan: Start the NAN interface. + * @stop_nan: Stop the NAN interface. + * @add_nan_func: Add a NAN function. Returns negative value on failure. + * On success @nan_func ownership is transferred to the driver and + * it may access it outside of the scope of this function. The driver + * should free the @nan_func when no longer needed by calling + * cfg80211_free_nan_func(). + * On success the driver should assign an instance_id in the + * provided @nan_func. + * @del_nan_func: Delete a NAN function. + * @nan_change_conf: changes NAN configuration. The changed parameters must + * be specified in @changes (using &enum cfg80211_nan_conf_changes); + * All other parameters must be ignored. + * + * @set_multicast_to_unicast: configure multicast to unicast conversion for BSS */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -2702,6 +2878,10 @@ struct cfg80211_ops { int (*connect)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_connect_params *sme); + int (*update_connect_params)(struct wiphy *wiphy, + struct net_device *dev, + struct cfg80211_connect_params *sme, + u32 changed); int (*disconnect)(struct wiphy *wiphy, struct net_device *dev, u16 reason_code); @@ -2853,6 +3033,21 @@ struct cfg80211_ops { void (*tdls_cancel_channel_switch)(struct wiphy *wiphy, struct net_device *dev, const u8 *addr); + int (*start_nan)(struct wiphy *wiphy, struct wireless_dev *wdev, + struct cfg80211_nan_conf *conf); + void (*stop_nan)(struct wiphy *wiphy, struct wireless_dev *wdev); + int (*add_nan_func)(struct wiphy *wiphy, struct wireless_dev *wdev, + struct cfg80211_nan_func *nan_func); + void (*del_nan_func)(struct wiphy *wiphy, struct wireless_dev *wdev, + u64 cookie); + int (*nan_change_conf)(struct wiphy *wiphy, + struct wireless_dev *wdev, + struct cfg80211_nan_conf *conf, + u32 changes); + + int (*set_multicast_to_unicast)(struct wiphy *wiphy, + struct net_device *dev, + const bool enabled); }; /* @@ -2899,6 +3094,8 @@ struct cfg80211_ops { * @WIPHY_FLAG_SUPPORTS_5_10_MHZ: Device supports 5 MHz and 10 MHz channels. * @WIPHY_FLAG_HAS_CHANNEL_SWITCH: Device supports channel switch in * beaconing mode (AP, IBSS, Mesh, ...). + * @WIPHY_FLAG_HAS_STATIC_WEP: The device supports static WEP key installation + * before connection. */ enum wiphy_flags { /* use hole at 0 */ @@ -2924,6 +3121,7 @@ enum wiphy_flags { WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL = BIT(21), WIPHY_FLAG_SUPPORTS_5_10_MHZ = BIT(22), WIPHY_FLAG_HAS_CHANNEL_SWITCH = BIT(23), + WIPHY_FLAG_HAS_STATIC_WEP = BIT(24), }; /** @@ -2948,6 +3146,12 @@ struct ieee80211_iface_limit { * only in special cases. * @radar_detect_widths: bitmap of channel widths supported for radar detection * @radar_detect_regions: bitmap of regions supported for radar detection + * @beacon_int_min_gcd: This interface combination supports different + * beacon intervals. + * = 0 - all beacon intervals for different interface must be same. + * > 0 - any beacon interval for the interface part of this combination AND + * *GCD* of all beacon intervals from beaconing interfaces of this + * combination must be greater or equal to this value. * * With this structure the driver can describe which interface * combinations it supports concurrently. @@ -2956,47 +3160,54 @@ struct ieee80211_iface_limit { * * 1. Allow #STA <= 1, #AP <= 1, matching BI, channels = 1, 2 total: * - * struct ieee80211_iface_limit limits1[] = { - * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), }, - * { .max = 1, .types = BIT(NL80211_IFTYPE_AP}, }, - * }; - * struct ieee80211_iface_combination combination1 = { - * .limits = limits1, - * .n_limits = ARRAY_SIZE(limits1), - * .max_interfaces = 2, - * .beacon_int_infra_match = true, - * }; + * .. code-block:: c + * + * struct ieee80211_iface_limit limits1[] = { + * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), }, + * { .max = 1, .types = BIT(NL80211_IFTYPE_AP}, }, + * }; + * struct ieee80211_iface_combination combination1 = { + * .limits = limits1, + * .n_limits = ARRAY_SIZE(limits1), + * .max_interfaces = 2, + * .beacon_int_infra_match = true, + * }; * * * 2. Allow #{AP, P2P-GO} <= 8, channels = 1, 8 total: * - * struct ieee80211_iface_limit limits2[] = { - * { .max = 8, .types = BIT(NL80211_IFTYPE_AP) | - * BIT(NL80211_IFTYPE_P2P_GO), }, - * }; - * struct ieee80211_iface_combination combination2 = { - * .limits = limits2, - * .n_limits = ARRAY_SIZE(limits2), - * .max_interfaces = 8, - * .num_different_channels = 1, - * }; + * .. code-block:: c + * + * struct ieee80211_iface_limit limits2[] = { + * { .max = 8, .types = BIT(NL80211_IFTYPE_AP) | + * BIT(NL80211_IFTYPE_P2P_GO), }, + * }; + * struct ieee80211_iface_combination combination2 = { + * .limits = limits2, + * .n_limits = ARRAY_SIZE(limits2), + * .max_interfaces = 8, + * .num_different_channels = 1, + * }; * * * 3. Allow #STA <= 1, #{P2P-client,P2P-GO} <= 3 on two channels, 4 total. * - * This allows for an infrastructure connection and three P2P connections. + * This allows for an infrastructure connection and three P2P connections. + * + * .. code-block:: c + * + * struct ieee80211_iface_limit limits3[] = { + * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), }, + * { .max = 3, .types = BIT(NL80211_IFTYPE_P2P_GO) | + * BIT(NL80211_IFTYPE_P2P_CLIENT), }, + * }; + * struct ieee80211_iface_combination combination3 = { + * .limits = limits3, + * .n_limits = ARRAY_SIZE(limits3), + * .max_interfaces = 4, + * .num_different_channels = 2, + * }; * - * struct ieee80211_iface_limit limits3[] = { - * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), }, - * { .max = 3, .types = BIT(NL80211_IFTYPE_P2P_GO) | - * BIT(NL80211_IFTYPE_P2P_CLIENT), }, - * }; - * struct ieee80211_iface_combination combination3 = { - * .limits = limits3, - * .n_limits = ARRAY_SIZE(limits3), - * .max_interfaces = 4, - * .num_different_channels = 2, - * }; */ struct ieee80211_iface_combination { const struct ieee80211_iface_limit *limits; @@ -3006,6 +3217,7 @@ struct ieee80211_iface_combination { bool beacon_int_infra_match; u8 radar_detect_widths; u8 radar_detect_regions; + u32 beacon_int_min_gcd; }; struct ieee80211_txrx_stypes { @@ -3301,6 +3513,8 @@ struct wiphy_iftype_ext_capab { * @bss_select_support: bitmask indicating the BSS selection criteria supported * by the driver in the .connect() callback. The bit position maps to the * attribute indices defined in &enum nl80211_bss_select_attr. + * + * @cookie_counter: unique generic cookie counter, used to identify objects. */ struct wiphy { /* assign these fields before you register the wiphy */ @@ -3430,6 +3644,8 @@ struct wiphy { u32 bss_select_support; + u64 cookie_counter; + char priv[0] __aligned(NETDEV_ALIGN); }; @@ -3609,7 +3825,8 @@ struct cfg80211_cached_keys; * @beacon_interval: beacon interval used on this device for transmitting * beacons, 0 when not valid * @address: The address for this device, valid only if @netdev is %NULL - * @p2p_started: true if this is a P2P Device that has been started + * @is_running: true if this is a non-netdev device that has been started, e.g. + * the P2P Device. * @cac_started: true if DFS channel availability check has been started * @cac_start_time: timestamp (jiffies) when the dfs state was entered. * @cac_time_ms: CAC time in ms @@ -3641,7 +3858,7 @@ struct wireless_dev { struct mutex mtx; - bool use_4addr, p2p_started; + bool use_4addr, is_running; u8 address[ETH_ALEN] __aligned(sizeof(u16)); @@ -3698,6 +3915,13 @@ static inline u8 *wdev_address(struct wireless_dev *wdev) return wdev->address; } +static inline bool wdev_running(struct wireless_dev *wdev) +{ + if (wdev->netdev) + return netif_running(wdev->netdev); + return wdev->is_running; +} + /** * wdev_priv - return wiphy priv from wireless_dev * @@ -3903,14 +4127,29 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr); */ /** + * ieee80211_data_to_8023_exthdr - convert an 802.11 data frame to 802.3 + * @skb: the 802.11 data frame + * @ehdr: pointer to a &struct ethhdr that will get the header, instead + * of it being pushed into the SKB + * @addr: the device MAC address + * @iftype: the virtual interface type + * Return: 0 on success. Non-zero on error. + */ +int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, + const u8 *addr, enum nl80211_iftype iftype); + +/** * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3 * @skb: the 802.11 data frame * @addr: the device MAC address * @iftype: the virtual interface type * Return: 0 on success. Non-zero on error. */ -int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, - enum nl80211_iftype iftype); +static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, + enum nl80211_iftype iftype) +{ + return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype); +} /** * ieee80211_data_from_8023 - convert an 802.3 frame to 802.11 @@ -3928,22 +4167,23 @@ int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, /** * ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame * - * Decode an IEEE 802.11n A-MSDU frame and convert it to a list of - * 802.3 frames. The @list will be empty if the decode fails. The - * @skb is consumed after the function returns. + * Decode an IEEE 802.11 A-MSDU and convert it to a list of 802.3 frames. + * The @list will be empty if the decode fails. The @skb must be fully + * header-less before being passed in here; it is freed in this function. * - * @skb: The input IEEE 802.11n A-MSDU frame. + * @skb: The input A-MSDU frame without any headers. * @list: The output list of 802.3 frames. It must be allocated and * initialized by by the caller. * @addr: The device MAC address. * @iftype: The device interface type. * @extra_headroom: The hardware extra headroom for SKBs in the @list. - * @has_80211_header: Set it true if SKB is with IEEE 802.11 header. + * @check_da: DA to check in the inner ethernet header, or NULL + * @check_sa: SA to check in the inner ethernet header, or NULL */ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, const u8 *addr, enum nl80211_iftype iftype, const unsigned int extra_headroom, - bool has_80211_header); + const u8 *check_da, const u8 *check_sa); /** * cfg80211_classify8021d - determine the 802.1p/1d tag for a data frame @@ -3955,6 +4195,34 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, struct cfg80211_qos_map *qos_map); /** + * cfg80211_find_ie_match - match information element and byte array in data + * + * @eid: element ID + * @ies: data consisting of IEs + * @len: length of data + * @match: byte array to match + * @match_len: number of bytes in the match array + * @match_offset: offset in the IE where the byte array should match. + * If match_len is zero, this must also be set to zero. + * Otherwise this must be set to 2 or more, because the first + * byte is the element id, which is already compared to eid, and + * the second byte is the IE length. + * + * Return: %NULL if the element ID could not be found or if + * the element is invalid (claims to be longer than the given + * data) or if the byte array doesn't match, or a pointer to the first + * byte of the requested element, that is the byte containing the + * element ID. + * + * Note: There are no checks on the element length other than + * having to fit into the given data and being large enough for the + * byte array to match. + */ +const u8 *cfg80211_find_ie_match(u8 eid, const u8 *ies, int len, + const u8 *match, int match_len, + int match_offset); + +/** * cfg80211_find_ie - find information element in data * * @eid: element ID @@ -3969,7 +4237,31 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, * Note: There are no checks on the element length other than * having to fit into the given data. */ -const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len); +static inline const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len) +{ + return cfg80211_find_ie_match(eid, ies, len, NULL, 0, 0); +} + +/** + * cfg80211_find_ext_ie - find information element with EID Extension in data + * + * @ext_eid: element ID Extension + * @ies: data consisting of IEs + * @len: length of data + * + * Return: %NULL if the extended element ID could not be found or if + * the element is invalid (claims to be longer than the given + * data), or a pointer to the first byte of the requested + * element, that is the byte containing the element ID. + * + * Note: There are no checks on the element length other than + * having to fit into the given data. + */ +static inline const u8 *cfg80211_find_ext_ie(u8 ext_eid, const u8 *ies, int len) +{ + return cfg80211_find_ie_match(WLAN_EID_EXTENSION, ies, len, + &ext_eid, 1, 2); +} /** * cfg80211_find_vendor_ie - find vendor specific information element in data @@ -4371,7 +4663,8 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr); * moves to cfg80211 in this call * @buf: authentication frame (header + body) * @len: length of the frame data - * @uapsd_queues: bitmap of ACs configured to uapsd. -1 if n/a. + * @uapsd_queues: bitmap of queues configured for uapsd. Same format + * as the AC bitmap in the QoS info field * * After being asked to associate via cfg80211_ops::assoc() the driver must * call either this function or cfg80211_auth_timeout(). @@ -4393,6 +4686,17 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, void cfg80211_assoc_timeout(struct net_device *dev, struct cfg80211_bss *bss); /** + * cfg80211_abandon_assoc - notify cfg80211 of abandoned association attempt + * @dev: network device + * @bss: The BSS entry with which association was abandoned. + * + * Call this whenever - for reasons reported through other API, like deauth RX, + * an association attempt was abandoned. + * This function may sleep. The caller must hold the corresponding wdev's mutex. + */ +void cfg80211_abandon_assoc(struct net_device *dev, struct cfg80211_bss *bss); + +/** * cfg80211_tx_mlme_mgmt - notification of transmitted deauth/disassoc frame * @dev: network device * @buf: 802.11 frame (header + body) @@ -5407,36 +5711,20 @@ unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy); * cfg80211_check_combinations - check interface combinations * * @wiphy: the wiphy - * @num_different_channels: the number of different channels we want - * to use for verification - * @radar_detect: a bitmap where each bit corresponds to a channel - * width where radar detection is needed, as in the definition of - * &struct ieee80211_iface_combination.@radar_detect_widths - * @iftype_num: array with the numbers of interfaces of each interface - * type. The index is the interface type as specified in &enum - * nl80211_iftype. + * @params: the interface combinations parameter * * This function can be called by the driver to check whether a * combination of interfaces and their types are allowed according to * the interface combinations. */ int cfg80211_check_combinations(struct wiphy *wiphy, - const int num_different_channels, - const u8 radar_detect, - const int iftype_num[NUM_NL80211_IFTYPES]); + struct iface_combination_params *params); /** * cfg80211_iter_combinations - iterate over matching combinations * * @wiphy: the wiphy - * @num_different_channels: the number of different channels we want - * to use for verification - * @radar_detect: a bitmap where each bit corresponds to a channel - * width where radar detection is needed, as in the definition of - * &struct ieee80211_iface_combination.@radar_detect_widths - * @iftype_num: array with the numbers of interfaces of each interface - * type. The index is the interface type as specified in &enum - * nl80211_iftype. + * @params: the interface combinations parameter * @iter: function to call for each matching combination * @data: pointer to pass to iter function * @@ -5445,9 +5733,7 @@ int cfg80211_check_combinations(struct wiphy *wiphy, * purposes. */ int cfg80211_iter_combinations(struct wiphy *wiphy, - const int num_different_channels, - const u8 radar_detect, - const int iftype_num[NUM_NL80211_IFTYPES], + struct iface_combination_params *params, void (*iter)(const struct ieee80211_iface_combination *c, void *data), void *data); @@ -5518,6 +5804,67 @@ wiphy_ext_feature_isset(struct wiphy *wiphy, return (ft_byte & BIT(ftidx % 8)) != 0; } +/** + * cfg80211_free_nan_func - free NAN function + * @f: NAN function that should be freed + * + * Frees all the NAN function and all it's allocated members. + */ +void cfg80211_free_nan_func(struct cfg80211_nan_func *f); + +/** + * struct cfg80211_nan_match_params - NAN match parameters + * @type: the type of the function that triggered a match. If it is + * %NL80211_NAN_FUNC_SUBSCRIBE it means that we replied to a subscriber. + * If it is %NL80211_NAN_FUNC_PUBLISH, it means that we got a discovery + * result. + * If it is %NL80211_NAN_FUNC_FOLLOW_UP, we received a follow up. + * @inst_id: the local instance id + * @peer_inst_id: the instance id of the peer's function + * @addr: the MAC address of the peer + * @info_len: the length of the &info + * @info: the Service Specific Info from the peer (if any) + * @cookie: unique identifier of the corresponding function + */ +struct cfg80211_nan_match_params { + enum nl80211_nan_function_type type; + u8 inst_id; + u8 peer_inst_id; + const u8 *addr; + u8 info_len; + const u8 *info; + u64 cookie; +}; + +/** + * cfg80211_nan_match - report a match for a NAN function. + * @wdev: the wireless device reporting the match + * @match: match notification parameters + * @gfp: allocation flags + * + * This function reports that the a NAN function had a match. This + * can be a subscribe that had a match or a solicited publish that + * was sent. It can also be a follow up that was received. + */ +void cfg80211_nan_match(struct wireless_dev *wdev, + struct cfg80211_nan_match_params *match, gfp_t gfp); + +/** + * cfg80211_nan_func_terminated - notify about NAN function termination. + * + * @wdev: the wireless device reporting the match + * @inst_id: the local instance id + * @reason: termination reason (one of the NL80211_NAN_FUNC_TERM_REASON_*) + * @cookie: unique NAN function identifier + * @gfp: allocation flags + * + * This function reports that the a NAN function is terminated. + */ +void cfg80211_nan_func_terminated(struct wireless_dev *wdev, + u8 inst_id, + enum nl80211_nan_func_term_reason reason, + u64 cookie, gfp_t gfp); + /* ethtool helper */ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info); diff --git a/include/net/checksum.h b/include/net/checksum.h index 5c30891e84e5..35d0fabd2782 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -22,7 +22,7 @@ #include <linux/errno.h> #include <asm/types.h> #include <asm/byteorder.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/checksum.h> #ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER diff --git a/include/net/devlink.h b/include/net/devlink.h index c99ffe8cef3c..d29e5fc82582 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -50,7 +50,6 @@ struct devlink_sb_pool_info { }; struct devlink_ops { - size_t priv_size; int (*port_type_set)(struct devlink_port *devlink_port, enum devlink_port_type port_type); int (*port_split)(struct devlink *devlink, unsigned int port_index, @@ -93,6 +92,8 @@ struct devlink_ops { int (*eswitch_mode_get)(struct devlink *devlink, u16 *p_mode); int (*eswitch_mode_set)(struct devlink *devlink, u16 mode); + int (*eswitch_inline_mode_get)(struct devlink *devlink, u8 *p_inline_mode); + int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode); }; static inline void *devlink_priv(struct devlink *devlink) diff --git a/include/net/dsa.h b/include/net/dsa.h index 2217a3f817f8..b122196d5a1f 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -26,6 +26,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_TRAILER, DSA_TAG_PROTO_EDSA, DSA_TAG_PROTO_BRCM, + DSA_TAG_PROTO_QCA, DSA_TAG_LAST, /* MUST BE LAST */ }; @@ -142,6 +143,7 @@ struct dsa_port { struct net_device *netdev; struct device_node *dn; unsigned int ageing_time; + u8 stp_state; }; struct dsa_switch { @@ -165,9 +167,9 @@ struct dsa_switch { struct dsa_chip_data *cd; /* - * The used switch driver. + * The switch operations. */ - struct dsa_switch_driver *drv; + struct dsa_switch_ops *ops; /* * An array of which element [a] indicates which port on this @@ -234,19 +236,21 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) struct switchdev_trans; struct switchdev_obj; struct switchdev_obj_port_fdb; +struct switchdev_obj_port_mdb; struct switchdev_obj_port_vlan; -struct dsa_switch_driver { +struct dsa_switch_ops { struct list_head list; - enum dsa_tag_protocol tag_protocol; - /* * Probing and setup. */ const char *(*probe)(struct device *dsa_dev, struct device *host_dev, int sw_addr, void **priv); + + enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds); + int (*setup)(struct dsa_switch *ds); int (*set_addr)(struct dsa_switch *ds, u8 *addr); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); @@ -336,6 +340,7 @@ struct dsa_switch_driver { void (*port_bridge_leave)(struct dsa_switch *ds, int port); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); + void (*port_fast_age)(struct dsa_switch *ds, int port); /* * VLAN support @@ -368,17 +373,27 @@ struct dsa_switch_driver { int (*port_fdb_dump)(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, int (*cb)(struct switchdev_obj *obj)); + + /* + * Multicast database + */ + int (*port_mdb_prepare)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb, + struct switchdev_trans *trans); + void (*port_mdb_add)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb, + struct switchdev_trans *trans); + int (*port_mdb_del)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb); + int (*port_mdb_dump)(struct dsa_switch *ds, int port, + struct switchdev_obj_port_mdb *mdb, + int (*cb)(struct switchdev_obj *obj)); }; -void register_switch_driver(struct dsa_switch_driver *type); -void unregister_switch_driver(struct dsa_switch_driver *type); +void register_switch_driver(struct dsa_switch_ops *type); +void unregister_switch_driver(struct dsa_switch_ops *type); struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev); -static inline void *ds_to_priv(struct dsa_switch *ds) -{ - return ds->priv; -} - static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) { return dst->rcv != NULL; @@ -386,4 +401,18 @@ static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds, struct device_node *np); +#ifdef CONFIG_PM_SLEEP +int dsa_switch_suspend(struct dsa_switch *ds); +int dsa_switch_resume(struct dsa_switch *ds); +#else +static inline int dsa_switch_suspend(struct dsa_switch *ds) +{ + return 0; +} +static inline int dsa_switch_resume(struct dsa_switch *ds) +{ + return 0; +} +#endif /* CONFIG_PM_SLEEP */ + #endif diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 5db9f5910428..701fc814d0af 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -112,12 +112,14 @@ static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb return &dst->u.tun_info; } -static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, - __be16 flags, - __be64 tunnel_id, - int md_size) +static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, + __be32 daddr, + __u8 tos, __u8 ttl, + __be16 tp_dst, + __be16 flags, + __be64 tunnel_id, + int md_size) { - const struct iphdr *iph = ip_hdr(skb); struct metadata_dst *tun_dst; tun_dst = tun_rx_dst(md_size); @@ -125,17 +127,31 @@ static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, return NULL; ip_tunnel_key_init(&tun_dst->u.tun_info.key, - iph->saddr, iph->daddr, iph->tos, iph->ttl, - 0, 0, 0, tunnel_id, flags); + saddr, daddr, tos, ttl, + 0, 0, tp_dst, tunnel_id, flags); return tun_dst; } -static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, +static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, __be16 flags, __be64 tunnel_id, int md_size) { - const struct ipv6hdr *ip6h = ipv6_hdr(skb); + const struct iphdr *iph = ip_hdr(skb); + + return __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, + 0, flags, tunnel_id, md_size); +} + +static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u8 tos, __u8 ttl, + __be16 tp_dst, + __be32 label, + __be16 flags, + __be64 tunnel_id, + int md_size) +{ struct metadata_dst *tun_dst; struct ip_tunnel_info *info; @@ -148,16 +164,28 @@ static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, info->key.tun_flags = flags; info->key.tun_id = tunnel_id; info->key.tp_src = 0; - info->key.tp_dst = 0; + info->key.tp_dst = tp_dst; - info->key.u.ipv6.src = ip6h->saddr; - info->key.u.ipv6.dst = ip6h->daddr; + info->key.u.ipv6.src = *saddr; + info->key.u.ipv6.dst = *daddr; - info->key.tos = ipv6_get_dsfield(ip6h); - info->key.ttl = ip6h->hop_limit; - info->key.label = ip6_flowlabel(ip6h); + info->key.tos = tos; + info->key.ttl = ttl; + info->key.label = label; return tun_dst; } +static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, + __be16 flags, + __be64 tunnel_id, + int md_size) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + + return __ipv6_tun_set_dst(&ip6h->saddr, &ip6h->daddr, + ipv6_get_dsfield(ip6h), ip6h->hop_limit, + 0, ip6_flowlabel(ip6h), flags, tunnel_id, + md_size); +} #endif /* __NET_DST_METADATA_H */ diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 456e4a6006ab..8dbfdf728cd8 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -8,6 +8,11 @@ #include <net/flow.h> #include <net/rtnetlink.h> +struct fib_kuid_range { + kuid_t start; + kuid_t end; +}; + struct fib_rule { struct list_head list; int iifindex; @@ -30,6 +35,7 @@ struct fib_rule { int suppress_prefixlen; char iifname[IFNAMSIZ]; char oifname[IFNAMSIZ]; + struct fib_kuid_range uid_range; struct rcu_head rcu; }; @@ -92,7 +98,8 @@ struct fib_rules_ops { [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \ [FRA_GOTO] = { .type = NLA_U32 }, \ - [FRA_L3MDEV] = { .type = NLA_U8 } + [FRA_L3MDEV] = { .type = NLA_U8 }, \ + [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) } static inline void fib_rule_get(struct fib_rule *rule) { diff --git a/include/net/flow.h b/include/net/flow.h index d47ef4bb5423..6984f1913dc1 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -11,6 +11,7 @@ #include <linux/in6.h> #include <linux/atomic.h> #include <net/flow_dissector.h> +#include <linux/uidgid.h> /* * ifindex generation is per-net namespace, and loopback is @@ -34,10 +35,10 @@ struct flowi_common { __u8 flowic_flags; #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_KNOWN_NH 0x02 -#define FLOWI_FLAG_L3MDEV_SRC 0x04 -#define FLOWI_FLAG_SKIP_NH_OIF 0x08 +#define FLOWI_FLAG_SKIP_NH_OIF 0x04 __u32 flowic_secid; struct flowi_tunnel flowic_tun_key; + kuid_t flowic_uid; }; union flowi_uli { @@ -75,6 +76,7 @@ struct flowi4 { #define flowi4_flags __fl_common.flowic_flags #define flowi4_secid __fl_common.flowic_secid #define flowi4_tun_key __fl_common.flowic_tun_key +#define flowi4_uid __fl_common.flowic_uid /* (saddr,daddr) must be grouped, same order as in IP header */ __be32 saddr; @@ -94,7 +96,8 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, __u32 mark, __u8 tos, __u8 scope, __u8 proto, __u8 flags, __be32 daddr, __be32 saddr, - __be16 dport, __be16 sport) + __be16 dport, __be16 sport, + kuid_t uid) { fl4->flowi4_oif = oif; fl4->flowi4_iif = LOOPBACK_IFINDEX; @@ -105,6 +108,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, fl4->flowi4_flags = flags; fl4->flowi4_secid = 0; fl4->flowi4_tun_key.tun_id = 0; + fl4->flowi4_uid = uid; fl4->daddr = daddr; fl4->saddr = saddr; fl4->fl4_dport = dport; @@ -132,6 +136,7 @@ struct flowi6 { #define flowi6_flags __fl_common.flowic_flags #define flowi6_secid __fl_common.flowic_secid #define flowi6_tun_key __fl_common.flowic_tun_key +#define flowi6_uid __fl_common.flowic_uid struct in6_addr daddr; struct in6_addr saddr; /* Note: flowi6_tos is encoded in flowlabel, too. */ @@ -177,6 +182,7 @@ struct flowi { #define flowi_flags u.__fl_common.flowic_flags #define flowi_secid u.__fl_common.flowic_secid #define flowi_tun_key u.__fl_common.flowic_tun_key +#define flowi_uid u.__fl_common.flowic_uid } __attribute__((__aligned__(BITS_PER_LONG/8))); static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4) @@ -240,6 +246,7 @@ struct flow_cache_object *flow_cache_lookup(struct net *net, void *ctx); int flow_cache_init(struct net *net); void flow_cache_fini(struct net *net); +void flow_cache_hp_init(void); void flow_cache_flush(struct net *net); void flow_cache_flush_deferred(struct net *net); diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index d3d60dccd19f..d896a33e00d4 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -32,8 +32,13 @@ struct flow_dissector_key_basic { }; struct flow_dissector_key_tags { - u32 vlan_id:12, - flow_label:20; + u32 flow_label; +}; + +struct flow_dissector_key_vlan { + u16 vlan_id:12, + vlan_priority:3; + u16 padding; }; struct flow_dissector_key_keyid { @@ -99,6 +104,22 @@ struct flow_dissector_key_ports { }; }; +/** + * flow_dissector_key_icmp: + * @ports: type and code of ICMP header + * icmp: ICMP type (high) and code (low) + * type: ICMP type + * code: ICMP code + */ +struct flow_dissector_key_icmp { + union { + __be16 icmp; + struct { + u8 type; + u8 code; + }; + }; +}; /** * struct flow_dissector_key_eth_addrs: @@ -117,12 +138,18 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */ + FLOW_DISSECTOR_KEY_ICMP, /* struct flow_dissector_key_icmp */ FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */ FLOW_DISSECTOR_KEY_TIPC_ADDRS, /* struct flow_dissector_key_tipc_addrs */ - FLOW_DISSECTOR_KEY_VLANID, /* struct flow_dissector_key_flow_tags */ + FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_flow_vlan */ FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_flow_tags */ FLOW_DISSECTOR_KEY_GRE_KEYID, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_MPLS_ENTROPY, /* struct flow_dissector_key_keyid */ + FLOW_DISSECTOR_KEY_ENC_KEYID, /* struct flow_dissector_key_keyid */ + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ + FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ + FLOW_DISSECTOR_KEY_ENC_CONTROL, /* struct flow_dissector_key_control */ + FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_MAX, }; @@ -148,6 +175,7 @@ struct flow_keys { #define FLOW_KEYS_HASH_START_FIELD basic struct flow_dissector_key_basic basic; struct flow_dissector_key_tags tags; + struct flow_dissector_key_vlan vlan; struct flow_dissector_key_keyid keyid; struct flow_dissector_key_ports ports; struct flow_dissector_key_addrs addrs; @@ -177,7 +205,7 @@ struct flow_keys_digest { void make_flow_keys_digest(struct flow_keys_digest *digest, const struct flow_keys *flow); -static inline bool flow_keys_have_l4(struct flow_keys *keys) +static inline bool flow_keys_have_l4(const struct flow_keys *keys) { return (keys->ports.ports || keys->tags.flow_label); } diff --git a/include/net/flowcache.h b/include/net/flowcache.h index c8f665ec6e0d..9caf3bfc8d2d 100644 --- a/include/net/flowcache.h +++ b/include/net/flowcache.h @@ -17,7 +17,7 @@ struct flow_cache_percpu { struct flow_cache { u32 hash_shift; struct flow_cache_percpu __percpu *percpu; - struct notifier_block hotcpu_notifier; + struct hlist_node node; int low_watermark; int high_watermark; struct timer_list rnd_timer; diff --git a/include/net/fq.h b/include/net/fq.h index 268b49049c37..6d8521a30c5c 100644 --- a/include/net/fq.h +++ b/include/net/fq.h @@ -72,9 +72,12 @@ struct fq { u32 flows_cnt; u32 perturbation; u32 limit; + u32 memory_limit; + u32 memory_usage; u32 quantum; u32 backlog; u32 overlimit; + u32 overmemory; u32 collisions; }; diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index 163f3ed0f05a..4e6131cd3f43 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -29,6 +29,7 @@ static struct sk_buff *fq_flow_dequeue(struct fq *fq, tin->backlog_packets--; flow->backlog -= skb->len; fq->backlog--; + fq->memory_usage -= skb->truesize; if (flow->backlog == 0) { list_del_init(&flow->backlogchain); @@ -154,6 +155,7 @@ static void fq_tin_enqueue(struct fq *fq, flow->backlog += skb->len; tin->backlog_bytes += skb->len; tin->backlog_packets++; + fq->memory_usage += skb->truesize; fq->backlog++; fq_recalc_backlog(fq, tin, flow); @@ -166,7 +168,7 @@ static void fq_tin_enqueue(struct fq *fq, __skb_queue_tail(&flow->queue, skb); - if (fq->backlog > fq->limit) { + if (fq->backlog > fq->limit || fq->memory_usage > fq->memory_limit) { flow = list_first_entry_or_null(&fq->backlogs, struct fq_flow, backlogchain); @@ -181,6 +183,8 @@ static void fq_tin_enqueue(struct fq *fq, flow->tin->overlimit++; fq->overlimit++; + if (fq->memory_usage > fq->memory_limit) + fq->overmemory++; } } @@ -251,6 +255,7 @@ static int fq_init(struct fq *fq, int flows_cnt) fq->perturbation = prandom_u32(); fq->quantum = 300; fq->limit = 8192; + fq->memory_limit = 16 << 20; /* 16 MBytes */ fq->flows = kcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL); if (!fq->flows) diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 231e121cc7d9..8b7aa370e7a4 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -11,6 +11,8 @@ struct gnet_stats_basic_cpu { struct u64_stats_sync syncp; }; +struct net_rate_estimator; + struct gnet_dump { spinlock_t * lock; struct sk_buff * skb; @@ -42,8 +44,7 @@ void __gnet_stats_copy_basic(const seqcount_t *running, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); int gnet_stats_copy_rate_est(struct gnet_dump *d, - const struct gnet_stats_basic_packed *b, - struct gnet_stats_rate_est64 *r); + struct net_rate_estimator __rcu **ptr); int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue __percpu *cpu_q, struct gnet_stats_queue *q, __u32 qlen); @@ -53,16 +54,16 @@ int gnet_stats_finish_copy(struct gnet_dump *d); int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, - struct gnet_stats_rate_est64 *rate_est, + struct net_rate_estimator __rcu **rate_est, spinlock_t *stats_lock, seqcount_t *running, struct nlattr *opt); -void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_rate_est64 *rate_est); +void gen_kill_estimator(struct net_rate_estimator __rcu **ptr); int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, - struct gnet_stats_rate_est64 *rate_est, + struct net_rate_estimator __rcu **ptr, spinlock_t *stats_lock, seqcount_t *running, struct nlattr *opt); -bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, - const struct gnet_stats_rate_est64 *rate_est); +bool gen_estimator_active(struct net_rate_estimator __rcu **ptr); +bool gen_estimator_read(struct net_rate_estimator __rcu **ptr, + struct gnet_stats_rate_est64 *sample); #endif diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 8d4608ce8716..a34275be3600 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -20,7 +20,7 @@ struct genl_info; /** * struct genl_family - generic netlink family - * @id: protocol family idenfitier + * @id: protocol family identifier (private) * @hdrsize: length of user specific header in bytes * @name: name of family * @version: protocol version @@ -39,16 +39,16 @@ struct genl_info; * Note that unbind() will not be called symmetrically if the * generic netlink family is removed while there are still open * sockets. - * @attrbuf: buffer to store parsed attributes - * @family_list: family list - * @mcgrps: multicast groups used by this family (private) - * @n_mcgrps: number of multicast groups (private) + * @attrbuf: buffer to store parsed attributes (private) + * @mcgrps: multicast groups used by this family + * @n_mcgrps: number of multicast groups * @mcgrp_offset: starting number of multicast group IDs in this family - * @ops: the operations supported by this family (private) - * @n_ops: number of operations supported by this family (private) + * (private) + * @ops: the operations supported by this family + * @n_ops: number of operations supported by this family */ struct genl_family { - unsigned int id; + int id; /* private */ unsigned int hdrsize; char name[GENL_NAMSIZ]; unsigned int version; @@ -64,15 +64,16 @@ struct genl_family { int (*mcast_bind)(struct net *net, int group); void (*mcast_unbind)(struct net *net, int group); struct nlattr ** attrbuf; /* private */ - const struct genl_ops * ops; /* private */ - const struct genl_multicast_group *mcgrps; /* private */ - unsigned int n_ops; /* private */ - unsigned int n_mcgrps; /* private */ + const struct genl_ops * ops; + const struct genl_multicast_group *mcgrps; + unsigned int n_ops; + unsigned int n_mcgrps; unsigned int mcgrp_offset; /* private */ - struct list_head family_list; /* private */ struct module *module; }; +struct nlattr **genl_family_attrbuf(const struct genl_family *family); + /** * struct genl_info - receiving information * @snd_seq: sending sequence number @@ -130,64 +131,13 @@ struct genl_ops { u8 flags; }; -int __genl_register_family(struct genl_family *family); - -static inline int genl_register_family(struct genl_family *family) -{ - family->module = THIS_MODULE; - return __genl_register_family(family); -} - -/** - * genl_register_family_with_ops - register a generic netlink family with ops - * @family: generic netlink family - * @ops: operations to be registered - * @n_ops: number of elements to register - * - * Registers the specified family and operations from the specified table. - * Only one family may be registered with the same family name or identifier. - * - * The family id may equal GENL_ID_GENERATE causing an unique id to - * be automatically generated and assigned. - * - * Either a doit or dumpit callback must be specified for every registered - * operation or the function will fail. Only one operation structure per - * command identifier may be registered. - * - * See include/net/genetlink.h for more documenation on the operations - * structure. - * - * Return 0 on success or a negative error code. - */ -static inline int -_genl_register_family_with_ops_grps(struct genl_family *family, - const struct genl_ops *ops, size_t n_ops, - const struct genl_multicast_group *mcgrps, - size_t n_mcgrps) -{ - family->module = THIS_MODULE; - family->ops = ops; - family->n_ops = n_ops; - family->mcgrps = mcgrps; - family->n_mcgrps = n_mcgrps; - return __genl_register_family(family); -} - -#define genl_register_family_with_ops(family, ops) \ - _genl_register_family_with_ops_grps((family), \ - (ops), ARRAY_SIZE(ops), \ - NULL, 0) -#define genl_register_family_with_ops_groups(family, ops, grps) \ - _genl_register_family_with_ops_grps((family), \ - (ops), ARRAY_SIZE(ops), \ - (grps), ARRAY_SIZE(grps)) - -int genl_unregister_family(struct genl_family *family); -void genl_notify(struct genl_family *family, struct sk_buff *skb, +int genl_register_family(struct genl_family *family); +int genl_unregister_family(const struct genl_family *family); +void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags); void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, - struct genl_family *family, int flags, u8 cmd); + const struct genl_family *family, int flags, u8 cmd); /** * genlmsg_nlhdr - Obtain netlink header from user specified header @@ -196,8 +146,8 @@ void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, * * Returns pointer to netlink header. */ -static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr, - struct genl_family *family) +static inline struct nlmsghdr * +genlmsg_nlhdr(void *user_hdr, const struct genl_family *family) { return (struct nlmsghdr *)((char *)user_hdr - family->hdrsize - @@ -233,7 +183,7 @@ static inline int genlmsg_parse(const struct nlmsghdr *nlh, */ static inline void genl_dump_check_consistent(struct netlink_callback *cb, void *user_hdr, - struct genl_family *family) + const struct genl_family *family) { nl_dump_check_consistent(cb, genlmsg_nlhdr(user_hdr, family)); } @@ -250,7 +200,7 @@ static inline void genl_dump_check_consistent(struct netlink_callback *cb, */ static inline void *genlmsg_put_reply(struct sk_buff *skb, struct genl_info *info, - struct genl_family *family, + const struct genl_family *family, int flags, u8 cmd) { return genlmsg_put(skb, info->snd_portid, info->snd_seq, family, @@ -287,7 +237,7 @@ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) * @group: offset of multicast group in groups array * @flags: allocation flags */ -static inline int genlmsg_multicast_netns(struct genl_family *family, +static inline int genlmsg_multicast_netns(const struct genl_family *family, struct net *net, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { @@ -305,7 +255,7 @@ static inline int genlmsg_multicast_netns(struct genl_family *family, * @group: offset of multicast group in groups array * @flags: allocation flags */ -static inline int genlmsg_multicast(struct genl_family *family, +static inline int genlmsg_multicast(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { @@ -323,7 +273,7 @@ static inline int genlmsg_multicast(struct genl_family *family, * * This function must hold the RTNL or rcu_read_lock(). */ -int genlmsg_multicast_allns(struct genl_family *family, +int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags); @@ -407,8 +357,9 @@ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags) * This function returns the number of broadcast listeners that have set the * NETLINK_RECV_NO_ENOBUFS socket option. */ -static inline int genl_set_err(struct genl_family *family, struct net *net, - u32 portid, u32 group, int code) +static inline int genl_set_err(const struct genl_family *family, + struct net *net, u32 portid, + u32 group, int code) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; @@ -416,7 +367,7 @@ static inline int genl_set_err(struct genl_family *family, struct net *net, return netlink_set_err(net->genl_sock, portid, group, code); } -static inline int genl_has_listeners(struct genl_family *family, +static inline int genl_has_listeners(const struct genl_family *family, struct net *net, unsigned int group) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) diff --git a/include/net/gre.h b/include/net/gre.h index 73ea256eb7d7..d25d836c129b 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -7,7 +7,15 @@ struct gre_base_hdr { __be16 flags; __be16 protocol; -}; +} __packed; + +struct gre_full_hdr { + struct gre_base_hdr fixed_header; + __be16 csum; + __be16 reserved1; + __be32 key; + __be32 seq; +} __packed; #define GRE_HEADER_SECTION 4 #define GREPROTO_CISCO 0 diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h index d15214d673b2..2a1abbf8da74 100644 --- a/include/net/gro_cells.h +++ b/include/net/gro_cells.h @@ -68,6 +68,9 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); __skb_queue_head_init(&cell->napi_skbs); + + set_bit(NAPI_STATE_NO_BUSY_POLL, &cell->napi.state); + netif_napi_add(dev, &cell->napi, gro_cell_poll, 64); napi_enable(&cell->napi); } diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index b0fd9476c538..d0e7e3f8e67a 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -190,6 +190,10 @@ struct ieee80211_radiotap_header { * IEEE80211_RADIOTAP_VHT u16, u8, u8, u8[4], u8, u8, u16 * * Contains VHT information about this frame. + * + * IEEE80211_RADIOTAP_TIMESTAMP u64, u16, u8, u8 variable + * + * Contains timestamp information for this frame. */ enum ieee80211_radiotap_type { IEEE80211_RADIOTAP_TSFT = 0, @@ -214,6 +218,7 @@ enum ieee80211_radiotap_type { IEEE80211_RADIOTAP_MCS = 19, IEEE80211_RADIOTAP_AMPDU_STATUS = 20, IEEE80211_RADIOTAP_VHT = 21, + IEEE80211_RADIOTAP_TIMESTAMP = 22, /* valid in every it_present bitmap, even vendor namespaces */ IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29, @@ -321,6 +326,22 @@ enum ieee80211_radiotap_type { #define IEEE80211_RADIOTAP_CODING_LDPC_USER2 0x04 #define IEEE80211_RADIOTAP_CODING_LDPC_USER3 0x08 +/* For IEEE80211_RADIOTAP_TIMESTAMP */ +#define IEEE80211_RADIOTAP_TIMESTAMP_UNIT_MASK 0x000F +#define IEEE80211_RADIOTAP_TIMESTAMP_UNIT_MS 0x0000 +#define IEEE80211_RADIOTAP_TIMESTAMP_UNIT_US 0x0001 +#define IEEE80211_RADIOTAP_TIMESTAMP_UNIT_NS 0x0003 +#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_MASK 0x00F0 +#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_BEGIN_MDPU 0x0000 +#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_PLCP_SIG_ACQ 0x0010 +#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_EO_PPDU 0x0020 +#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_EO_MPDU 0x0030 +#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_UNKNOWN 0x00F0 + +#define IEEE80211_RADIOTAP_TIMESTAMP_FLAG_64BIT 0x00 +#define IEEE80211_RADIOTAP_TIMESTAMP_FLAG_32BIT 0x01 +#define IEEE80211_RADIOTAP_TIMESTAMP_FLAG_ACCURACY 0x02 + /* helpers */ static inline int ieee80211_get_radiotap_len(unsigned char *data) { diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 1c8b6820b694..0fa4c324b713 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -55,6 +55,7 @@ struct inet6_ifaddr { __u8 stable_privacy_retry; __u16 scope; + __u64 dad_nonce; unsigned long cstamp; /* created timestamp */ unsigned long tstamp; /* updated timestamp */ @@ -190,8 +191,8 @@ struct inet6_dev { __u32 if_flags; int dead; + u32 desync_factor; u8 rndid[8]; - struct timer_list regen_timer; struct list_head tempaddr_list; struct in6_addr token; @@ -201,6 +202,7 @@ struct inet6_dev { struct ipv6_devstat stats; struct timer_list rs_timer; + __s32 rs_interval; /* in jiffies */ __u8 rs_probes; __u8 addr_gen_mode; diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 954ad6bfb56a..3212b39b5bfc 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -22,7 +22,8 @@ struct sock; struct sockaddr; int inet6_csk_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb, bool relax); + const struct inet_bind_bucket *tb, bool relax, + bool soreuseport_ok); struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, const struct request_sock *req, u8 proto); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 49dcad4fe99e..85ee3879499e 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -63,7 +63,8 @@ struct inet_connection_sock_af_ops { #endif void (*addr2sockaddr)(struct sock *sk, struct sockaddr *); int (*bind_conflict)(const struct sock *sk, - const struct inet_bind_bucket *tb, bool relax); + const struct inet_bind_bucket *tb, + bool relax, bool soreuseport_ok); void (*mtu_reduced)(struct sock *sk); }; @@ -134,8 +135,8 @@ struct inet_connection_sock { } icsk_mtup; u32 icsk_user_timeout; - u64 icsk_ca_priv[64 / sizeof(u64)]; -#define ICSK_CA_PRIV_SIZE (8 * sizeof(u64)) + u64 icsk_ca_priv[88 / sizeof(u64)]; +#define ICSK_CA_PRIV_SIZE (11 * sizeof(u64)) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ @@ -261,7 +262,8 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); int inet_csk_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb, bool relax); + const struct inet_bind_bucket *tb, bool relax, + bool soreuseport_ok); int inet_csk_get_port(struct sock *sk, unsigned short snum); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, @@ -289,11 +291,6 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk) return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue); } -static inline int inet_csk_reqsk_queue_young(const struct sock *sk) -{ - return reqsk_queue_len_young(&inet_csk(sk)->icsk_accept_queue); -} - static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 236a81034fef..c9cff977a7fb 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -228,6 +228,7 @@ struct inet_sock { #define IP_CMSG_PASSSEC BIT(5) #define IP_CMSG_ORIGDSTADDR BIT(6) #define IP_CMSG_CHECKSUM BIT(7) +#define IP_CMSG_RECVFRAGSIZE BIT(8) /** * sk_to_full_sk - Access to a full socket diff --git a/include/net/ip.h b/include/net/ip.h index 9742b92dc933..ab6761a7c883 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -38,7 +38,7 @@ struct sock; struct inet_skb_parm { int iif; struct ip_options opt; /* Compiled IP options */ - unsigned char flags; + u16 flags; #define IPSKB_FORWARDED BIT(0) #define IPSKB_XFRM_TUNNEL_SIZE BIT(1) @@ -47,11 +47,16 @@ struct inet_skb_parm { #define IPSKB_REROUTED BIT(4) #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) -#define IPSKB_FRAG_SEGS BIT(7) +#define IPSKB_L3SLAVE BIT(7) u16 frag_max_size; }; +static inline bool ipv4_l3mdev_skb(u16 flags) +{ + return !!(flags & IPSKB_L3SLAVE); +} + static inline unsigned int ip_hdrlen(const struct sk_buff *skb) { return ip_hdr(skb)->ihl * 4; @@ -173,6 +178,7 @@ struct ip_reply_arg { /* -1 if not needed */ int bound_dev_if; u8 tos; + kuid_t uid; }; #define IP_REPLY_ARG_NOSRCCHECK 1 @@ -219,6 +225,29 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o } #endif +#define snmp_get_cpu_field64_batch(buff64, stats_list, mib_statistic, offset) \ +{ \ + int i, c; \ + for_each_possible_cpu(c) { \ + for (i = 0; stats_list[i].name; i++) \ + buff64[i] += snmp_get_cpu_field64( \ + mib_statistic, \ + c, stats_list[i].entry, \ + offset); \ + } \ +} + +#define snmp_get_cpu_field_batch(buff, stats_list, mib_statistic) \ +{ \ + int i, c; \ + for_each_possible_cpu(c) { \ + for (i = 0; stats_list[i].name; i++) \ + buff[i] += snmp_get_cpu_field( \ + mib_statistic, \ + c, stats_list[i].entry); \ + } \ +} + void inet_get_local_port_range(struct net *net, int *low, int *high); #ifdef CONFIG_SYSCTL @@ -549,7 +578,8 @@ int ip_options_rcv_srr(struct sk_buff *skb); */ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb); -void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset); +void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb, int tlen, int offset); int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6); int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, @@ -571,7 +601,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) { - ip_cmsg_recv_offset(msg, skb, 0); + ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0); } bool icmp_global_allow(void); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index fb961a576abe..a74e2aa40ef4 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -230,6 +230,8 @@ struct fib6_table { rwlock_t tb6_lock; struct fib6_node tb6_root; struct inet_peer_base tb6_peers; + unsigned int flags; +#define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; #define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index d97305d0e71f..9dc2c182a263 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -32,6 +32,7 @@ struct route_info { #define RT6_LOOKUP_F_SRCPREF_TMP 0x00000008 #define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010 #define RT6_LOOKUP_F_SRCPREF_COA 0x00000020 +#define RT6_LOOKUP_F_IGNORE_LINKSTATE 0x00000040 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675) * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header @@ -64,6 +65,9 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) } void ip6_route_input(struct sk_buff *skb); +struct dst_entry *ip6_route_input_lookup(struct net *net, + struct net_device *dev, + struct flowi6 *fl6, int flags); struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags); @@ -136,9 +140,10 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr); void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, - u32 mark); + u32 mark, kuid_t uid); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu); -void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark); +void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, + kuid_t uid); void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif, u32 mark); void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk); diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 43a5a0e4524c..1b1cf33cbfb0 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -23,6 +23,7 @@ struct __ip6_tnl_parm { __u8 proto; /* tunnel protocol */ __u8 encap_limit; /* encapsulation limit for tunnel */ __u8 hop_limit; /* hop limit for tunnel */ + bool collect_md; __be32 flowinfo; /* traffic class and flowlabel for tunnel */ __u32 flags; /* tunnel flags */ struct in6_addr laddr; /* local tunnel end-point address */ @@ -145,6 +146,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, { int pkt_len, err; + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); pkt_len = skb->len - skb_inner_network_offset(skb); err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); if (unlikely(net_xmit_eval(err))) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 7d4a72e75f33..5f376af377c7 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -22,6 +22,7 @@ #include <net/fib_rules.h> #include <net/inetpeer.h> #include <linux/percpu.h> +#include <linux/notifier.h> struct fib_config { u8 fc_dst_len; @@ -122,6 +123,7 @@ struct fib_info { #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_weight; #endif + unsigned int fib_offload_cnt; struct rcu_head rcu; struct fib_nh fib_nh[0]; #define fib_dev fib_nh[0].nh_dev @@ -173,6 +175,18 @@ struct fib_result_nl { __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh); +static inline void fib_info_offload_inc(struct fib_info *fi) +{ + fi->fib_offload_cnt++; + fi->fib_flags |= RTNH_F_OFFLOAD; +} + +static inline void fib_info_offload_dec(struct fib_info *fi) +{ + if (--fi->fib_offload_cnt == 0) + fi->fib_flags &= ~RTNH_F_OFFLOAD; +} + #define FIB_RES_SADDR(net, res) \ ((FIB_RES_NH(res).nh_saddr_genid == \ atomic_read(&(net)->ipv4.dev_addr_genid)) ? \ @@ -185,6 +199,34 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh); #define FIB_RES_PREFSRC(net, res) ((res).fi->fib_prefsrc ? : \ FIB_RES_SADDR(net, res)) +struct fib_notifier_info { + struct net *net; +}; + +struct fib_entry_notifier_info { + struct fib_notifier_info info; /* must be first */ + u32 dst; + int dst_len; + struct fib_info *fi; + u8 tos; + u8 type; + u32 tb_id; + u32 nlflags; +}; + +enum fib_event_type { + FIB_EVENT_ENTRY_ADD, + FIB_EVENT_ENTRY_DEL, + FIB_EVENT_RULE_ADD, + FIB_EVENT_RULE_DEL, +}; + +int register_fib_notifier(struct notifier_block *nb, + void (*cb)(struct notifier_block *nb)); +int unregister_fib_notifier(struct notifier_block *nb); +int call_fib_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info); + struct fib_table { struct hlist_node tb_hlist; u32 tb_id; @@ -196,11 +238,11 @@ struct fib_table { int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); -int fib_table_insert(struct fib_table *, struct fib_config *); -int fib_table_delete(struct fib_table *, struct fib_config *); +int fib_table_insert(struct net *, struct fib_table *, struct fib_config *); +int fib_table_delete(struct net *, struct fib_table *, struct fib_config *); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); -int fib_table_flush(struct fib_table *table); +int fib_table_flush(struct net *net, struct fib_table *table); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); @@ -315,7 +357,6 @@ static inline int fib_num_tclassid_users(struct net *net) } #endif int fib_unmerge(struct net *net); -void fib_flush_external(struct net *net); /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); @@ -357,6 +398,11 @@ static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) void free_fib_info(struct fib_info *fi); +static inline void fib_info_hold(struct fib_info *fi) +{ + atomic_inc(&fi->fib_clntref); +} + static inline void fib_info_put(struct fib_info *fi) { if (atomic_dec_and_test(&fi->fib_clntref)) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index a5e7035fb93f..e893fe43dd13 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -129,7 +129,7 @@ struct ip_tunnel { #endif struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */ unsigned int prl_count; /* # of entries in PRL */ - int ip_tnl_net_id; + unsigned int ip_tnl_net_id; struct gro_cells gro_cells; bool collect_md; bool ignore_df; @@ -222,6 +222,25 @@ static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info return tun_info->mode & IP_TUNNEL_INFO_IPV6 ? AF_INET6 : AF_INET; } +static inline __be64 key32_to_tunnel_id(__be32 key) +{ +#ifdef __BIG_ENDIAN + return (__force __be64)key; +#else + return (__force __be64)((__force u64)key << 32); +#endif +} + +/* Returns the least-significant 32 bits of a __be64. */ +static inline __be32 tunnel_id_to_key32(__be64 tun_id) +{ +#ifdef __BIG_ENDIAN + return (__force __be32)tun_id; +#else + return (__force __be32)((__force u64)tun_id >> 32); +#endif +} + #ifdef CONFIG_INET int ip_tunnel_init(struct net_device *dev); @@ -229,13 +248,15 @@ void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); struct net *ip_tunnel_get_link_net(const struct net_device *dev); int ip_tunnel_get_iflink(const struct net_device *dev); -int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, +int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname); void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); +void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, + const u8 proto); int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); @@ -254,7 +275,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p); -void ip_tunnel_setup(struct net_device *dev, int net_id); +void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); struct ip_tunnel_encap_ops { size_t (*encap_hlen)(struct ip_tunnel_encap *e); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 8fed1cd78658..487e57391664 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -932,7 +932,8 @@ int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); */ void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, - u8 *proto, struct in6_addr **daddr_p); + 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); @@ -970,6 +971,8 @@ int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); +int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, + int addr_len); int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); diff --git a/include/net/kcm.h b/include/net/kcm.h index 2840b5825dcc..2a8965819db0 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -13,6 +13,7 @@ #include <linux/skbuff.h> #include <net/sock.h> +#include <net/strparser.h> #include <uapi/linux/kcm.h> extern unsigned int kcm_net_id; @@ -21,16 +22,8 @@ extern unsigned int kcm_net_id; #define KCM_STATS_INCR(stat) ((stat)++) struct kcm_psock_stats { - unsigned long long rx_msgs; - unsigned long long rx_bytes; unsigned long long tx_msgs; unsigned long long tx_bytes; - unsigned int rx_aborts; - unsigned int rx_mem_fail; - unsigned int rx_need_more_hdr; - unsigned int rx_msg_too_big; - unsigned int rx_msg_timeouts; - unsigned int rx_bad_hdr_len; unsigned long long reserved; unsigned long long unreserved; unsigned int tx_aborts; @@ -64,13 +57,6 @@ struct kcm_tx_msg { struct sk_buff *last_skb; }; -struct kcm_rx_msg { - int full_len; - int accum_len; - int offset; - int early_eaten; -}; - /* Socket structure for KCM client sockets */ struct kcm_sock { struct sock sk; @@ -87,6 +73,7 @@ struct kcm_sock { struct work_struct tx_work; struct list_head wait_psock_list; struct sk_buff *seq_skb; + u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ bool tx_wait; @@ -104,11 +91,11 @@ struct bpf_prog; /* Structure for an attached lower socket */ struct kcm_psock { struct sock *sk; + struct strparser strp; struct kcm_mux *mux; int index; u32 tx_stopped : 1; - u32 rx_stopped : 1; u32 done : 1; u32 unattaching : 1; @@ -121,18 +108,12 @@ struct kcm_psock { struct kcm_psock_stats stats; /* Receive */ - struct sk_buff *rx_skb_head; - struct sk_buff **rx_skb_nextp; - struct sk_buff *ready_rx_msg; struct list_head psock_ready_list; - struct work_struct rx_work; - struct delayed_work rx_delayed_work; struct bpf_prog *bpf_prog; struct kcm_sock *rx_kcm; unsigned long long saved_rx_bytes; unsigned long long saved_rx_msgs; - struct timer_list rx_msg_timer; - unsigned int rx_need_bytes; + struct sk_buff *ready_rx_msg; /* Transmit */ struct kcm_sock *tx_kcm; @@ -146,6 +127,7 @@ struct kcm_net { struct mutex mutex; struct kcm_psock_stats aggregate_psock_stats; struct kcm_mux_stats aggregate_mux_stats; + struct strp_aggr_stats aggregate_strp_stats; struct list_head mux_list; int count; }; @@ -163,6 +145,7 @@ struct kcm_mux { struct kcm_mux_stats stats; struct kcm_psock_stats aggregate_psock_stats; + struct strp_aggr_stats aggregate_strp_stats; /* Receive */ spinlock_t rx_lock ____cacheline_aligned_in_smp; @@ -190,14 +173,6 @@ static inline void aggregate_psock_stats(struct kcm_psock_stats *stats, /* Save psock statistics in the mux when psock is being unattached. */ #define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat) - SAVE_PSOCK_STATS(rx_msgs); - SAVE_PSOCK_STATS(rx_bytes); - SAVE_PSOCK_STATS(rx_aborts); - SAVE_PSOCK_STATS(rx_mem_fail); - SAVE_PSOCK_STATS(rx_need_more_hdr); - SAVE_PSOCK_STATS(rx_msg_too_big); - SAVE_PSOCK_STATS(rx_msg_timeouts); - SAVE_PSOCK_STATS(rx_bad_hdr_len); SAVE_PSOCK_STATS(tx_msgs); SAVE_PSOCK_STATS(tx_bytes); SAVE_PSOCK_STATS(reserved); diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index e90095091aa0..3832099289c5 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -11,6 +11,7 @@ #ifndef _NET_L3MDEV_H_ #define _NET_L3MDEV_H_ +#include <net/dst.h> #include <net/fib_rules.h> /** @@ -18,30 +19,24 @@ * * @l3mdev_fib_table: Get FIB table id to use for lookups * - * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device + * @l3mdev_l3_rcv: Hook in L3 receive path * - * @l3mdev_get_saddr: Get source address for a flow + * @l3mdev_l3_out: Hook in L3 output path * - * @l3mdev_get_rt6_dst: Get cached IPv6 rt6_info (dst_entry) for device + * @l3mdev_link_scope_lookup: IPv6 lookup for linklocal and mcast destinations */ struct l3mdev_ops { u32 (*l3mdev_fib_table)(const struct net_device *dev); struct sk_buff * (*l3mdev_l3_rcv)(struct net_device *dev, struct sk_buff *skb, u16 proto); - - /* IPv4 ops */ - struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev, - const struct flowi4 *fl4); - int (*l3mdev_get_saddr)(struct net_device *dev, - struct flowi4 *fl4); + struct sk_buff * (*l3mdev_l3_out)(struct net_device *dev, + struct sock *sk, struct sk_buff *skb, + u16 proto); /* IPv6 ops */ - struct dst_entry * (*l3mdev_get_rt6_dst)(const struct net_device *dev, + struct dst_entry * (*l3mdev_link_scope_lookup)(const struct net_device *dev, struct flowi6 *fl6); - int (*l3mdev_get_saddr6)(struct net_device *dev, - const struct sock *sk, - struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV @@ -49,6 +44,8 @@ struct l3mdev_ops { int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg); +void l3mdev_update_flow(struct net *net, struct flowi *fl); + int l3mdev_master_ifindex_rcu(const struct net_device *dev); static inline int l3mdev_master_ifindex(struct net_device *dev) { @@ -80,7 +77,7 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) } static inline -const struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) +struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) { /* netdev_master_upper_dev_get_rcu calls * list_first_or_null_rcu to walk the upper dev list. @@ -89,7 +86,7 @@ const struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) * typecast to remove the const */ struct net_device *dev = (struct net_device *)_dev; - const struct net_device *master; + struct net_device *master; if (!dev) return NULL; @@ -104,26 +101,6 @@ const struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) return master; } -/* get index of an interface to use for FIB lookups. For devices - * enslaved to an L3 master device FIB lookups are based on the - * master index - */ -static inline int l3mdev_fib_oif_rcu(struct net_device *dev) -{ - return l3mdev_master_ifindex_rcu(dev) ? : dev->ifindex; -} - -static inline int l3mdev_fib_oif(struct net_device *dev) -{ - int oif; - - rcu_read_lock(); - oif = l3mdev_fib_oif_rcu(dev); - rcu_read_unlock(); - - return oif; -} - u32 l3mdev_fib_table_rcu(const struct net_device *dev); u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); static inline u32 l3mdev_fib_table(const struct net_device *dev) @@ -137,15 +114,6 @@ static inline u32 l3mdev_fib_table(const struct net_device *dev) return tb_id; } -static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, - const struct flowi4 *fl4) -{ - if (netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_get_rtable) - return dev->l3mdev_ops->l3mdev_get_rtable(dev, fl4); - - return NULL; -} - static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { struct net_device *dev; @@ -165,11 +133,7 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) return rc; } -int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4); - -struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6); -int l3mdev_get_saddr6(struct net *net, const struct sock *sk, - struct flowi6 *fl6); +struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6); static inline struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) @@ -199,6 +163,34 @@ struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) return l3mdev_l3_rcv(skb, AF_INET6); } +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; + + if (netif_is_l3_slave(dev)) { + struct net_device *master; + + 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); + } + + return skb; +} + +static inline +struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) +{ + return l3mdev_l3_out(sk, skb, AF_INET); +} + +static inline +struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) +{ + return l3mdev_l3_out(sk, skb, AF_INET6); +} #else static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev) @@ -216,20 +208,11 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) } static inline -const struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) +struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) { return NULL; } -static inline int l3mdev_fib_oif_rcu(struct net_device *dev) -{ - return dev ? dev->ifindex : 0; -} -static inline int l3mdev_fib_oif(struct net_device *dev) -{ - return dev ? dev->ifindex : 0; -} - static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev) { return 0; @@ -243,43 +226,37 @@ static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) return 0; } -static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, - const struct flowi4 *fl4) -{ - return NULL; -} - static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { return false; } -static inline int l3mdev_get_saddr(struct net *net, int ifindex, - struct flowi4 *fl4) +static inline +struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6) { - return 0; + return NULL; } static inline -struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6) +struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { - return NULL; + return skb; } -static inline int l3mdev_get_saddr6(struct net *net, const struct sock *sk, - struct flowi6 *fl6) +static inline +struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { - return 0; + return skb; } static inline -struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) +struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline -struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) +struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return skb; } @@ -290,6 +267,10 @@ int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, { return 1; } +static inline +void l3mdev_update_flow(struct net *net, struct flowi *fl) +{ +} #endif #endif /* _NET_L3MDEV_H_ */ diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index e9f116e29c22..d4c1c75b8862 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -13,14 +13,22 @@ /* lw tunnel state flags */ #define LWTUNNEL_STATE_OUTPUT_REDIRECT BIT(0) #define LWTUNNEL_STATE_INPUT_REDIRECT BIT(1) +#define LWTUNNEL_STATE_XMIT_REDIRECT BIT(2) + +enum { + LWTUNNEL_XMIT_DONE, + LWTUNNEL_XMIT_CONTINUE, +}; + struct lwtunnel_state { __u16 type; __u16 flags; + __u16 headroom; atomic_t refcnt; int (*orig_output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*orig_input)(struct sk_buff *); - int len; + struct rcu_head rcu; __u8 data[0]; }; @@ -28,19 +36,18 @@ struct lwtunnel_encap_ops { int (*build_state)(struct net_device *dev, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **ts); + void (*destroy_state)(struct lwtunnel_state *lws); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*input)(struct sk_buff *skb); int (*fill_encap)(struct sk_buff *skb, struct lwtunnel_state *lwtstate); int (*get_encap_size)(struct lwtunnel_state *lwtstate); int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b); + int (*xmit)(struct sk_buff *skb); }; #ifdef CONFIG_LWTUNNEL -static inline void lwtstate_free(struct lwtunnel_state *lws) -{ - kfree(lws); -} +void lwtstate_free(struct lwtunnel_state *lws); static inline struct lwtunnel_state * lwtstate_get(struct lwtunnel_state *lws) @@ -75,6 +82,25 @@ static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) return false; } + +static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) +{ + if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_XMIT_REDIRECT)) + return true; + + return false; +} + +static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, + unsigned int mtu) +{ + if ((lwtunnel_xmit_redirect(lwtstate) || + lwtunnel_output_redirect(lwtstate)) && lwtstate->headroom < mtu) + return lwtstate->headroom; + + return 0; +} + int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, @@ -90,6 +116,7 @@ struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb); int lwtunnel_input(struct sk_buff *skb); +int lwtunnel_xmit(struct sk_buff *skb); #else @@ -117,6 +144,17 @@ static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) return false; } +static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) +{ + return false; +} + +static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, + unsigned int mtu) +{ + return 0; +} + static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num) { @@ -170,6 +208,11 @@ static inline int lwtunnel_input(struct sk_buff *skb) return -EOPNOTSUPP; } +static inline int lwtunnel_xmit(struct sk_buff *skb) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_LWTUNNEL */ #define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" __stringify(encap_type)) diff --git a/include/net/mac80211.h b/include/net/mac80211.h index cca510a585c3..5345d358a510 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -715,6 +715,7 @@ enum mac80211_tx_info_flags { * frame (PS-Poll or uAPSD). * @IEEE80211_TX_CTRL_RATE_INJECT: This frame is injected with rate information * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame + * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path * * These flags are used in tx_info->control.flags. */ @@ -723,6 +724,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_PS_RESPONSE = BIT(1), IEEE80211_TX_CTRL_RATE_INJECT = BIT(2), IEEE80211_TX_CTRL_AMSDU = BIT(3), + IEEE80211_TX_CTRL_FAST_XMIT = BIT(4), }; /* @@ -809,14 +811,18 @@ enum mac80211_rate_control_flags { * in the control information, and it will be filled by the rate * control algorithm according to what should be sent. For example, * if this array contains, in the format { <idx>, <count> } the - * information + * information:: + * * { 3, 2 }, { 2, 2 }, { 1, 4 }, { -1, 0 }, { -1, 0 } + * * then this means that the frame should be transmitted * up to twice at rate 3, up to twice at rate 2, and up to four * times at rate 1 if it doesn't get acknowledged. Say it gets * acknowledged by the peer after the fifth attempt, the status - * information should then contain + * information should then contain:: + * * { 3, 2 }, { 2, 2 }, { 1, 1 }, { -1, 0 } ... + * * since it was transmitted twice at rate 3, twice at rate 2 * and once at rate 1 after which we received an acknowledgement. */ @@ -1166,8 +1172,8 @@ enum mac80211_rx_vht_flags { * @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) * @vht_nss: number of streams (VHT only) - * @flag: %RX_FLAG_* - * @vht_flag: %RX_VHT_FLAG_* + * @flag: %RX_FLAG_\* + * @vht_flag: %RX_VHT_FLAG_\* * @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 @@ -1430,13 +1436,13 @@ enum ieee80211_vif_flags { * @probe_req_reg: probe requests should be reported to mac80211 for this * interface. * @drv_priv: data area for driver use, will always be aligned to - * sizeof(void *). + * sizeof(void \*). * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) */ struct ieee80211_vif { enum nl80211_iftype type; struct ieee80211_bss_conf bss_conf; - u8 addr[ETH_ALEN]; + u8 addr[ETH_ALEN] __aligned(2); bool p2p; bool csa_active; bool mu_mimo_owner; @@ -1735,12 +1741,16 @@ struct ieee80211_sta_rates { * @supp_rates: Bitmap of supported rates (per band) * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities + * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU + * that this station is allowed to transmit to us. + * Can be modified by driver. * @wme: indicates whether the STA supports QoS/WME (if local devices does, * otherwise always false) * @drv_priv: data area for driver use, will always be aligned to - * sizeof(void *), size is determined in hw information. + * sizeof(void \*), size is determined in hw information. * @uapsd_queues: bitmap of queues configured for uapsd. Only valid - * if wme is supported. + * if wme is supported. The bits order is like in + * IEEE80211_WMM_IE_STA_QOSINFO_AC_*. * @max_sp: max Service Period. Only valid if wme is supported. * @bandwidth: current bandwidth the station can receive with * @rx_nss: in HT/VHT, the maximum number of spatial streams the @@ -1775,6 +1785,7 @@ struct ieee80211_sta { u16 aid; struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; + u8 max_rx_aggregation_subframes; bool wme; u8 uapsd_queues; u8 max_sp; @@ -2014,6 +2025,15 @@ struct ieee80211_txq { * @IEEE80211_HW_TX_FRAG_LIST: Hardware (or driver) supports sending frag_list * skbs, needed for zero-copy software A-MSDU. * + * @IEEE80211_HW_REPORTS_LOW_ACK: The driver (or firmware) reports low ack event + * by ieee80211_report_low_ack() based on its own algorithm. For such + * drivers, mac80211 packet loss mechanism will not be triggered and driver + * is completely depending on firmware event for station kickout. + * + * @IEEE80211_HW_SUPPORTS_TX_FRAG: Hardware does fragmentation by itself. + * The stack will not do fragmentation. + * The callback for @set_frag_threshold should be set as well. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2054,6 +2074,8 @@ enum ieee80211_hw_flags { IEEE80211_HW_USES_RSS, IEEE80211_HW_TX_AMSDU, IEEE80211_HW_TX_FRAG_LIST, + IEEE80211_HW_REPORTS_LOW_ACK, + IEEE80211_HW_SUPPORTS_TX_FRAG, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -2134,12 +2156,20 @@ enum ieee80211_hw_flags { * * @radiotap_mcs_details: lists which MCS information can the HW * reports, by default it is set to _MCS, _GI and _BW but doesn't - * include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_* values, only + * include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_\* values, only * adding _BW is supported today. * * @radiotap_vht_details: lists which VHT MCS information the HW reports, * the default is _GI | _BANDWIDTH. - * Use the %IEEE80211_RADIOTAP_VHT_KNOWN_* values. + * Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values. + * + * @radiotap_timestamp: Information for the radiotap timestamp field; if the + * 'units_pos' member is set to a non-negative value it must be set to + * a combination of a IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a + * IEEE80211_RADIOTAP_TIMESTAMP_SPOS_* value, and then the timestamp + * field will be added and populated from the &struct ieee80211_rx_status + * device_timestamp. If the 'accuracy' member is non-negative, it's put + * into the accuracy radiotap field and the accuracy known flag is set. * * @netdev_features: netdev features to be set in each netdev created * from this HW. Note that not all features are usable with mac80211, @@ -2159,6 +2189,8 @@ enum ieee80211_hw_flags { * @n_cipher_schemes: a size of an array of cipher schemes definitions. * @cipher_schemes: a pointer to an array of cipher scheme definitions * supported by HW. + * @max_nan_de_entries: maximum number of NAN DE functions supported by the + * device. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -2184,11 +2216,16 @@ struct ieee80211_hw { u8 offchannel_tx_hw_queue; u8 radiotap_mcs_details; u16 radiotap_vht_details; + struct { + int units_pos; + s16 accuracy; + } radiotap_timestamp; netdev_features_t netdev_features; u8 uapsd_queues; u8 uapsd_max_sp_len; u8 n_cipher_schemes; const struct ieee80211_cipher_scheme *cipher_schemes; + u8 max_nan_de_entries; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, @@ -2459,6 +2496,7 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * in the software stack cares about, we will, in the future, have mac80211 * tell the driver which information elements are interesting in the sense * that we want to see changes in them. This will include + * * - a list of information element IDs * - a list of OUIs for the vendor information element * @@ -3066,8 +3104,9 @@ enum ieee80211_reconfig_type { * The callback must be atomic. * * @set_frag_threshold: Configuration of fragmentation threshold. Assign this - * if the device does fragmentation by itself; if this callback is - * implemented then the stack will not do fragmentation. + * if the device does fragmentation by itself. Note that to prevent the + * stack from doing fragmentation IEEE80211_HW_SUPPORTS_TX_FRAG + * should be set as well. * The callback can sleep. * * @set_rts_threshold: Configuration of RTS threshold (if device needs it) @@ -3085,11 +3124,8 @@ enum ieee80211_reconfig_type { * * @sta_add_debugfs: Drivers can use this callback to add debugfs files * when a station is added to mac80211's station list. This callback - * and @sta_remove_debugfs should be within a CONFIG_MAC80211_DEBUGFS - * conditional. This callback can sleep. - * - * @sta_remove_debugfs: Remove the debugfs files which were added using - * @sta_add_debugfs. This callback can sleep. + * should be within a CONFIG_MAC80211_DEBUGFS conditional. This + * callback can sleep. * * @sta_notify: Notifies low level driver about power state transition of an * associated station, AP, IBSS/WDS/mesh peer etc. For a VIF operating @@ -3147,6 +3183,12 @@ enum ieee80211_reconfig_type { * required function. * The callback can sleep. * + * @offset_tsf: Offset the TSF timer by the specified value in the + * firmware/hardware. Preferred to set_tsf as it avoids delay between + * calling set_tsf() and hardware getting programmed, which will show up + * as TSF delay. Is not a required function. + * The callback can sleep. + * * @reset_tsf: Reset the TSF timer and allow firmware/hardware to synchronize * with other STAs in the IBSS. This is only used in IBSS mode. This * function is optional if the firmware/hardware takes full care of @@ -3401,6 +3443,21 @@ enum ieee80211_reconfig_type { * synchronization which is needed in case driver has in its RSS queues * pending frames that were received prior to the control path action * currently taken (e.g. disassociation) but are not processed yet. + * + * @start_nan: join an existing NAN cluster, or create a new one. + * @stop_nan: leave the NAN cluster. + * @nan_change_conf: change NAN configuration. The data in cfg80211_nan_conf + * contains full new configuration and changes specify which parameters + * are changed with respect to the last NAN config. + * The driver gets both full configuration and the changed parameters since + * some devices may need the full configuration while others need only the + * changed parameters. + * @add_nan_func: Add a NAN function. Returns 0 on success. The data in + * cfg80211_nan_func must not be referenced outside the scope of + * this call. + * @del_nan_func: Remove a NAN function. The driver must call + * ieee80211_nan_func_terminated() with + * NL80211_NAN_FUNC_TERM_REASON_USER_REQUEST reason code upon removal. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -3485,10 +3542,6 @@ struct ieee80211_ops { struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct dentry *dir); - void (*sta_remove_debugfs)(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta, - struct dentry *dir); #endif void (*sta_notify)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum sta_notify_cmd, struct ieee80211_sta *sta); @@ -3516,6 +3569,8 @@ struct ieee80211_ops { u64 (*get_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*set_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 tsf); + void (*offset_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + s64 offset); void (*reset_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*tx_last_beacon)(struct ieee80211_hw *hw); int (*ampdu_action)(struct ieee80211_hw *hw, @@ -3640,6 +3695,21 @@ struct ieee80211_ops { void (*wake_tx_queue)(struct ieee80211_hw *hw, struct ieee80211_txq *txq); void (*sync_rx_queues)(struct ieee80211_hw *hw); + + int (*start_nan)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct cfg80211_nan_conf *conf); + int (*stop_nan)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); + int (*nan_change_conf)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct cfg80211_nan_conf *conf, u32 changes); + int (*add_nan_func)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + const struct cfg80211_nan_func *nan_func); + void (*del_nan_func)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u8 instance_id); }; /** @@ -4029,6 +4099,10 @@ void ieee80211_sta_pspoll(struct ieee80211_sta *sta); * This must be used in conjunction with ieee80211_sta_ps_transition() * and possibly ieee80211_sta_pspoll(); calls to all three must be * serialized. + * %IEEE80211_NUM_TIDS can be passed as the tid if the tid is unknown. + * In this case, mac80211 will not check that this tid maps to an AC + * that is trigger enabled and assume that the caller did the proper + * checks. */ void ieee80211_sta_uapsd_trigger(struct ieee80211_sta *sta, u8 tid); @@ -5713,4 +5787,36 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, void ieee80211_txq_get_depth(struct ieee80211_txq *txq, unsigned long *frame_cnt, unsigned long *byte_cnt); + +/** + * ieee80211_nan_func_terminated - notify about NAN function termination. + * + * This function is used to notify mac80211 about NAN function termination. + * Note that this function can't be called from hard irq. + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @inst_id: the local instance id + * @reason: termination reason (one of the NL80211_NAN_FUNC_TERM_REASON_*) + * @gfp: allocation flags + */ +void ieee80211_nan_func_terminated(struct ieee80211_vif *vif, + u8 inst_id, + enum nl80211_nan_func_term_reason reason, + gfp_t gfp); + +/** + * ieee80211_nan_func_match - notify about NAN function match event. + * + * This function is used to notify mac80211 about NAN function match. The + * cookie inside the match struct will be assigned by mac80211. + * Note that this function can't be called from hard irq. + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @match: match event information + * @gfp: allocation flags + */ +void ieee80211_nan_func_match(struct ieee80211_vif *vif, + struct cfg80211_nan_match_params *match, + gfp_t gfp); + #endif /* MAC80211_H */ diff --git a/include/net/mpls.h b/include/net/mpls.h index 5b3b5addfb08..1dbc669b770e 100644 --- a/include/net/mpls.h +++ b/include/net/mpls.h @@ -19,21 +19,18 @@ #define MPLS_HLEN 4 +struct mpls_shim_hdr { + __be32 label_stack_entry; +}; + static inline bool eth_p_mpls(__be16 eth_type) { return eth_type == htons(ETH_P_MPLS_UC) || eth_type == htons(ETH_P_MPLS_MC); } -/* - * For non-MPLS skbs this will correspond to the network header. - * For MPLS skbs it will be before the network_header as the MPLS - * label stack lies between the end of the mac header and the network - * header. That is, for MPLS skbs the end of the mac header - * is the top of the MPLS label stack. - */ -static inline unsigned char *skb_mpls_header(struct sk_buff *skb) +static inline struct mpls_shim_hdr *mpls_hdr(const struct sk_buff *skb) { - return skb_mac_header(skb) + skb->mac_len; + return (struct mpls_shim_hdr *)skb_network_header(skb); } #endif diff --git a/include/net/ncsi.h b/include/net/ncsi.h index 1dbf42f79750..68680baac0fd 100644 --- a/include/net/ncsi.h +++ b/include/net/ncsi.h @@ -31,6 +31,7 @@ struct ncsi_dev { struct ncsi_dev *ncsi_register_dev(struct net_device *dev, void (*notifier)(struct ncsi_dev *nd)); int ncsi_start_dev(struct ncsi_dev *nd); +void ncsi_stop_dev(struct ncsi_dev *nd); void ncsi_unregister_dev(struct ncsi_dev *nd); #else /* !CONFIG_NET_NCSI */ static inline struct ncsi_dev *ncsi_register_dev(struct net_device *dev, @@ -44,6 +45,10 @@ static inline int ncsi_start_dev(struct ncsi_dev *nd) return -ENOTTY; } +static void ncsi_stop_dev(struct ncsi_dev *nd) +{ +} + static inline void ncsi_unregister_dev(struct ncsi_dev *nd) { } diff --git a/include/net/ndisc.h b/include/net/ndisc.h index be1fe2283254..d562a2fe4860 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -31,6 +31,7 @@ enum { ND_OPT_PREFIX_INFO = 3, /* RFC2461 */ ND_OPT_REDIRECT_HDR = 4, /* RFC2461 */ ND_OPT_MTU = 5, /* RFC2461 */ + ND_OPT_NONCE = 14, /* RFC7527 */ __ND_OPT_ARRAY_MAX, ND_OPT_ROUTE_INFO = 24, /* RFC4191 */ ND_OPT_RDNSS = 25, /* RFC5006 */ @@ -121,6 +122,7 @@ struct ndisc_options { #define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] #define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] #define nd_opts_mtu nd_opt_array[ND_OPT_MTU] +#define nd_opts_nonce nd_opt_array[ND_OPT_NONCE] #define nd_802154_opts_src_lladdr nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR] #define nd_802154_opts_tgt_lladdr nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR] @@ -398,7 +400,8 @@ void ndisc_cleanup(void); int ndisc_rcv(struct sk_buff *skb); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, - const struct in6_addr *daddr, const struct in6_addr *saddr); + const struct in6_addr *daddr, const struct in6_addr *saddr, + u64 nonce); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 0933c7455a30..af8fe8a909dc 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -60,6 +60,7 @@ struct net { struct list_head exit_list; /* Use only net_mutex */ struct user_namespace *user_ns; /* Owning user namespace */ + struct ucounts *ucounts; spinlock_t nsid_lock; struct idr netns_ids; @@ -169,7 +170,7 @@ static inline struct net *copy_net_ns(unsigned long flags, extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); -struct net *get_net_ns_by_fd(int pid); +struct net *get_net_ns_by_fd(int fd); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); @@ -290,7 +291,7 @@ struct pernet_operations { int (*init)(struct net *net); void (*exit)(struct net *net); void (*exit_batch)(struct list_head *net_exit_list); - int *id; + unsigned int *id; size_t size; }; diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index e8d1448425a7..0b0c35c37125 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -15,6 +15,12 @@ static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) void nf_bridge_update_protocol(struct sk_buff *skb); +int br_nf_hook_thresh(unsigned int hook, struct net *net, struct sock *sk, + struct sk_buff *skb, struct net_device *indev, + struct net_device *outdev, + int (*okfn)(struct net *, struct sock *, + struct sk_buff *)); + static inline struct nf_bridge_info * nf_bridge_info_get(const struct sk_buff *skb) { diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h index 981c327374da..919e4e8af327 100644 --- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h +++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h @@ -15,6 +15,15 @@ extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp; +#ifdef CONFIG_NF_CT_PROTO_DCCP +extern struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4; +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP +extern struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4; +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE +extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4; +#endif int nf_conntrack_ipv4_compat_init(void); void nf_conntrack_ipv4_compat_fini(void); diff --git a/include/net/netfilter/ipv4/nf_defrag_ipv4.h b/include/net/netfilter/ipv4/nf_defrag_ipv4.h index f01ef208dff6..db405f70e538 100644 --- a/include/net/netfilter/ipv4/nf_defrag_ipv4.h +++ b/include/net/netfilter/ipv4/nf_defrag_ipv4.h @@ -1,6 +1,7 @@ #ifndef _NF_DEFRAG_IPV4_H #define _NF_DEFRAG_IPV4_H -void nf_defrag_ipv4_enable(void); +struct net; +int nf_defrag_ipv4_enable(struct net *); #endif /* _NF_DEFRAG_IPV4_H */ diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h index a4c993685795..eaea968f8657 100644 --- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h +++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h @@ -6,6 +6,15 @@ extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6; +#ifdef CONFIG_NF_CT_PROTO_DCCP +extern struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6; +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP +extern struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6; +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE +extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6; +#endif #include <linux/sysctl.h> extern struct ctl_table nf_ct_ipv6_sysctl_table[]; diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index ddf162f7966f..7664efe37974 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -1,7 +1,8 @@ #ifndef _NF_DEFRAG_IPV6_H #define _NF_DEFRAG_IPV6_H -void nf_defrag_ipv6_enable(void); +struct net; +int nf_defrag_ipv6_enable(struct net *); int nf_ct_frag6_init(void); void nf_ct_frag6_cleanup(void); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 445b019c2078..5916aa9ab3f0 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -42,7 +42,6 @@ union nf_conntrack_expect_proto { #include <linux/types.h> #include <linux/skbuff.h> -#include <linux/timer.h> #ifdef CONFIG_NETFILTER_DEBUG #define NF_CT_ASSERT(x) WARN_ON(!(x)) @@ -73,7 +72,7 @@ struct nf_conn_help { #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> struct nf_conn { - /* Usage count in here is 1 for hash table/destruct timer, 1 per skb, + /* Usage count in here is 1 for hash table, 1 per skb, * plus 1 for any connection(s) we are `master' for * * Hint, SKB address this struct and refcnt via skb->nfct and @@ -96,11 +95,14 @@ struct nf_conn { /* Have we seen traffic both ways yet? (bitset) */ unsigned long status; - /* Timer function; drops refcnt when it goes off. */ - struct timer_list timeout; + /* jiffies32 when this ct is considered dead */ + u32 timeout; possible_net_t ct_net; +#if IS_ENABLED(CONFIG_NF_NAT) + struct rhlist_head nat_bysource; +#endif /* all members below initialized via memset */ u8 __nfct_init_offset[0]; @@ -118,9 +120,6 @@ struct nf_conn { /* Extensions */ struct nf_ct_ext *ext; -#if IS_ENABLED(CONFIG_NF_NAT) - struct rhash_head nat_bysource; -#endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; }; @@ -182,6 +181,10 @@ static inline void nf_ct_put(struct nf_conn *ct) int nf_ct_l3proto_try_module_get(unsigned short l3proto); void nf_ct_l3proto_module_put(unsigned short l3proto); +/* load module; enable/disable conntrack in this namespace */ +int nf_ct_netns_get(struct net *net, u8 nfproto); +void nf_ct_netns_put(struct net *net, u8 nfproto); + /* * Allocate a hashtable of hlist_head (if nulls == 0), * or hlist_nulls_head (if nulls == 1) @@ -220,21 +223,14 @@ static inline void nf_ct_refresh(struct nf_conn *ct, __nf_ct_refresh_acct(ct, 0, skb, extra_jiffies, 0); } -bool __nf_ct_kill_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo, - const struct sk_buff *skb, int do_acct); - /* kill conntrack and do accounting */ -static inline bool nf_ct_kill_acct(struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - const struct sk_buff *skb) -{ - return __nf_ct_kill_acct(ct, ctinfo, skb, 1); -} +bool nf_ct_kill_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo, + const struct sk_buff *skb); /* kill conntrack without accounting */ static inline bool nf_ct_kill(struct nf_conn *ct) { - return __nf_ct_kill_acct(ct, 0, NULL, 0); + return nf_ct_delete(ct, 0, 0); } /* These are for NAT. Icky. */ @@ -291,21 +287,55 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb) return skb->dev && skb->skb_iif && skb->dev->flags & IFF_LOOPBACK; } +#define nfct_time_stamp ((u32)(jiffies)) + /* jiffies until ct expires, 0 if already expired */ static inline unsigned long nf_ct_expires(const struct nf_conn *ct) { - long timeout = (long)ct->timeout.expires - (long)jiffies; + s32 timeout = ct->timeout - nfct_time_stamp; return timeout > 0 ? timeout : 0; } +static inline bool nf_ct_is_expired(const struct nf_conn *ct) +{ + return (__s32)(ct->timeout - nfct_time_stamp) <= 0; +} + +/* use after obtaining a reference count */ +static inline bool nf_ct_should_gc(const struct nf_conn *ct) +{ + return nf_ct_is_expired(ct) && nf_ct_is_confirmed(ct) && + !nf_ct_is_dying(ct); +} + struct kernel_param; int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); int nf_conntrack_hash_resize(unsigned int hashsize); + +extern struct hlist_nulls_head *nf_conntrack_hash; extern unsigned int nf_conntrack_htable_size; +extern seqcount_t nf_conntrack_generation; extern unsigned int nf_conntrack_max; +/* must be called with rcu read lock held */ +static inline void +nf_conntrack_get_ht(struct hlist_nulls_head **hash, unsigned int *hsize) +{ + struct hlist_nulls_head *hptr; + unsigned int sequence, hsz; + + do { + sequence = read_seqcount_begin(&nf_conntrack_generation); + hsz = nf_conntrack_htable_size; + hptr = nf_conntrack_hash; + } while (read_seqcount_retry(&nf_conntrack_generation, sequence)); + + *hash = hptr; + *hsize = hsz; +} + struct nf_conn *nf_ct_tmpl_alloc(struct net *net, const struct nf_conntrack_zone *zone, gfp_t flags); diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 79d7ac5c9740..62e17d1319ff 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -51,8 +51,6 @@ bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto); -void nf_conntrack_get_ht(struct hlist_nulls_head **hash, unsigned int *hsize); - /* Find a connection corresponding to a tuple. */ struct nf_conntrack_tuple_hash * nf_conntrack_find_get(struct net *net, @@ -83,7 +81,6 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, #define CONNTRACK_LOCKS 1024 -extern struct hlist_nulls_head *nf_conntrack_hash; extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; void nf_conntrack_lock(spinlock_t *lock); diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index fa36447371c6..12d967b58726 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -12,12 +12,19 @@ #include <linux/netfilter/nf_conntrack_tuple_common.h> #include <net/netfilter/nf_conntrack_extend.h> +enum nf_ct_ecache_state { + NFCT_ECACHE_UNKNOWN, /* destroy event not sent */ + NFCT_ECACHE_DESTROY_FAIL, /* tried but failed to send destroy event */ + NFCT_ECACHE_DESTROY_SENT, /* sent destroy event after failure */ +}; + struct nf_conntrack_ecache { - unsigned long cache; /* bitops want long */ - unsigned long missed; /* missed events */ - u16 ctmask; /* bitmask of ct events to be delivered */ - u16 expmask; /* bitmask of expect events to be delivered */ - u32 portid; /* netlink portid of destroyer */ + unsigned long cache; /* bitops want long */ + unsigned long missed; /* missed events */ + u16 ctmask; /* bitmask of ct events to be delivered */ + u16 expmask; /* bitmask of expect events to be delivered */ + u32 portid; /* netlink portid of destroyer */ + enum nf_ct_ecache_state state; /* ecache state */ }; static inline struct nf_conntrack_ecache * diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index cdc920b4c4c2..e01559b4d781 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -52,6 +52,10 @@ struct nf_conntrack_l3proto { int (*tuple_to_nlattr)(struct sk_buff *skb, const struct nf_conntrack_tuple *t); + /* Called when netns wants to use connection tracking */ + int (*net_ns_get)(struct net *); + void (*net_ns_put)(struct net *); + /* * Calculate size of tuple nlattr */ @@ -63,22 +67,24 @@ struct nf_conntrack_l3proto { size_t nla_size; -#ifdef CONFIG_SYSCTL - const char *ctl_table_path; -#endif /* CONFIG_SYSCTL */ - - /* Init l3proto pernet data */ - int (*init_net)(struct net *net); - /* Module (if any) which this is connected to. */ struct module *me; }; extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX]; +#ifdef CONFIG_SYSCTL /* Protocol pernet registration. */ int nf_ct_l3proto_pernet_register(struct net *net, struct nf_conntrack_l3proto *proto); +#else +static inline int nf_ct_l3proto_pernet_register(struct net *n, + struct nf_conntrack_l3proto *p) +{ + return 0; +} +#endif + void nf_ct_l3proto_pernet_unregister(struct net *net, struct nf_conntrack_l3proto *proto); diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 1a5fb36f165f..e7b836590f0b 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -98,7 +98,7 @@ struct nf_conntrack_l4proto { const struct nla_policy *nla_policy; } ctnl_timeout; #endif - int *net_id; + unsigned int *net_id; /* Init l4proto pernet data */ int (*init_net)(struct net *net, u_int16_t proto); @@ -125,22 +125,24 @@ struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u_int16_t l3proto, void nf_ct_l4proto_put(struct nf_conntrack_l4proto *p); /* Protocol pernet registration. */ +int nf_ct_l4proto_pernet_register_one(struct net *net, + struct nf_conntrack_l4proto *proto); +void nf_ct_l4proto_pernet_unregister_one(struct net *net, + struct nf_conntrack_l4proto *proto); int nf_ct_l4proto_pernet_register(struct net *net, - struct nf_conntrack_l4proto *proto); + struct nf_conntrack_l4proto *proto[], + unsigned int num_proto); void nf_ct_l4proto_pernet_unregister(struct net *net, - struct nf_conntrack_l4proto *proto); + struct nf_conntrack_l4proto *proto[], + unsigned int num_proto); /* Protocol global registration. */ -int nf_ct_l4proto_register(struct nf_conntrack_l4proto *proto); -void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *proto); - -static inline void nf_ct_kfree_compat_sysctl_table(struct nf_proto_net *pn) -{ -#if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) - kfree(pn->ctl_compat_table); - pn->ctl_compat_table = NULL; -#endif -} +int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *proto); +void nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *proto); +int nf_ct_l4proto_register(struct nf_conntrack_l4proto *proto[], + unsigned int num_proto); +void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *proto[], + unsigned int num_proto); /* Generic netlink helpers */ int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index 498814626e28..1723a67c0b0a 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -30,8 +30,7 @@ static inline struct nf_conn_labels *nf_ct_labels_ext_add(struct nf_conn *ct) if (net->ct.labels_used == 0) return NULL; - return nf_ct_ext_add_length(ct, NF_CT_EXT_LABELS, - sizeof(struct nf_conn_labels), GFP_ATOMIC); + return nf_ct_ext_add(ct, NF_CT_EXT_LABELS, GFP_ATOMIC); #else return NULL; #endif diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h index e6937318546c..b0ca402c1f72 100644 --- a/include/net/netfilter/nf_conntrack_synproxy.h +++ b/include/net/netfilter/nf_conntrack_synproxy.h @@ -54,7 +54,7 @@ struct synproxy_net { struct synproxy_stats __percpu *stats; }; -extern int synproxy_net_id; +extern unsigned int synproxy_net_id; static inline struct synproxy_net *synproxy_pernet(struct net *net) { return net_generic(net, synproxy_net_id); diff --git a/include/net/netfilter/nf_dup_netdev.h b/include/net/netfilter/nf_dup_netdev.h index 397dcae349f9..3e919356bedf 100644 --- a/include/net/netfilter/nf_dup_netdev.h +++ b/include/net/netfilter/nf_dup_netdev.h @@ -2,5 +2,6 @@ #define _NF_DUP_NETDEV_H_ void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif); +void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif); #endif diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index 83d855ba6af1..450f87f95415 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -2,15 +2,10 @@ #define _NF_LOG_H #include <linux/netfilter.h> +#include <linux/netfilter/nf_log.h> -/* those NF_LOG_* defines and struct nf_loginfo are legacy definitios that will - * disappear once iptables is replaced with pkttables. Please DO NOT use them - * for any new code! */ -#define NF_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ -#define NF_LOG_TCPOPT 0x02 /* Log TCP options */ -#define NF_LOG_IPOPT 0x04 /* Log IP options */ -#define NF_LOG_UID 0x08 /* Log UID owning local socket */ -#define NF_LOG_MASK 0x0f +/* Log tcp sequence, tcp options, ip options and uid owning local socket */ +#define NF_LOG_DEFAULT_MASK 0x0f /* This flag indicates that copy_len field in nf_loginfo is set */ #define NF_LOG_F_COPY_LEN 0x1 @@ -60,8 +55,7 @@ struct nf_logger { int nf_log_register(u_int8_t pf, struct nf_logger *logger); void nf_log_unregister(struct nf_logger *logger); -void nf_log_set(struct net *net, u_int8_t pf, - const struct nf_logger *logger); +int nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger); void nf_log_unset(struct net *net, const struct nf_logger *logger); int nf_log_bind_pf(struct net *net, u_int8_t pf, @@ -115,5 +109,12 @@ void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, const struct net_device *out, const struct nf_loginfo *loginfo, const char *prefix); +void nf_log_l2packet(struct net *net, u_int8_t pf, + __be16 protocol, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, const char *prefix); #endif /* _NF_LOG_H */ diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h index 12f4cc841b6e..3923150f2a1e 100644 --- a/include/net/netfilter/nf_nat_l4proto.h +++ b/include/net/netfilter/nf_nat_l4proto.h @@ -54,6 +54,15 @@ extern const struct nf_nat_l4proto nf_nat_l4proto_udp; extern const struct nf_nat_l4proto nf_nat_l4proto_icmp; extern const struct nf_nat_l4proto nf_nat_l4proto_icmpv6; extern const struct nf_nat_l4proto nf_nat_l4proto_unknown; +#ifdef CONFIG_NF_NAT_PROTO_DCCP +extern const struct nf_nat_l4proto nf_nat_l4proto_dccp; +#endif +#ifdef CONFIG_NF_NAT_PROTO_SCTP +extern const struct nf_nat_l4proto nf_nat_l4proto_sctp; +#endif +#ifdef CONFIG_NF_NAT_PROTO_UDPLITE +extern const struct nf_nat_l4proto nf_nat_l4proto_udplite; +#endif bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype, diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 0dbce55437f2..09948d10e38e 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -11,8 +11,8 @@ struct nf_queue_entry { struct sk_buff *skb; unsigned int id; - struct nf_hook_ops *elem; struct nf_hook_state state; + struct nf_hook_entry *hook; u16 size; /* sizeof(entry) + saved route keys */ /* extra space to store route keys */ @@ -22,10 +22,10 @@ struct nf_queue_entry { /* Packet queuing */ struct nf_queue_handler { - int (*outfn)(struct nf_queue_entry *entry, - unsigned int queuenum); - void (*nf_hook_drop)(struct net *net, - struct nf_hook_ops *ops); + int (*outfn)(struct nf_queue_entry *entry, + unsigned int queuenum); + void (*nf_hook_drop)(struct net *net, + const struct nf_hook_entry *hooks); }; void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh); @@ -41,23 +41,19 @@ static inline void init_hashrandom(u32 *jhash_initval) *jhash_initval = prandom_u32(); } -static inline u32 hash_v4(const struct sk_buff *skb, u32 jhash_initval) +static inline u32 hash_v4(const struct iphdr *iph, u32 initval) { - const struct iphdr *iph = ip_hdr(skb); - /* packets in either direction go into same queue */ if ((__force u32)iph->saddr < (__force u32)iph->daddr) return jhash_3words((__force u32)iph->saddr, - (__force u32)iph->daddr, iph->protocol, jhash_initval); + (__force u32)iph->daddr, iph->protocol, initval); return jhash_3words((__force u32)iph->daddr, - (__force u32)iph->saddr, iph->protocol, jhash_initval); + (__force u32)iph->saddr, iph->protocol, initval); } -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) -static inline u32 hash_v6(const struct sk_buff *skb, u32 jhash_initval) +static inline u32 hash_v6(const struct ipv6hdr *ip6h, u32 initval) { - const struct ipv6hdr *ip6h = ipv6_hdr(skb); u32 a, b, c; if ((__force u32)ip6h->saddr.s6_addr32[3] < @@ -75,20 +71,50 @@ static inline u32 hash_v6(const struct sk_buff *skb, u32 jhash_initval) else c = (__force u32) ip6h->daddr.s6_addr32[1]; - return jhash_3words(a, b, c, jhash_initval); + return jhash_3words(a, b, c, initval); +} + +static inline u32 hash_bridge(const struct sk_buff *skb, u32 initval) +{ + struct ipv6hdr *ip6h, _ip6h; + struct iphdr *iph, _iph; + + switch (eth_hdr(skb)->h_proto) { + case htons(ETH_P_IP): + iph = skb_header_pointer(skb, skb_network_offset(skb), + sizeof(*iph), &_iph); + if (iph) + return hash_v4(iph, initval); + break; + case htons(ETH_P_IPV6): + ip6h = skb_header_pointer(skb, skb_network_offset(skb), + sizeof(*ip6h), &_ip6h); + if (ip6h) + return hash_v6(ip6h, initval); + break; + } + + return 0; } -#endif static inline u32 nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family, - u32 jhash_initval) + u32 initval) { - if (family == NFPROTO_IPV4) - queue += ((u64) hash_v4(skb, jhash_initval) * queues_total) >> 32; -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) - else if (family == NFPROTO_IPV6) - queue += ((u64) hash_v6(skb, jhash_initval) * queues_total) >> 32; -#endif + switch (family) { + case NFPROTO_IPV4: + queue += reciprocal_scale(hash_v4(ip_hdr(skb), initval), + queues_total); + break; + case NFPROTO_IPV6: + queue += reciprocal_scale(hash_v6(ipv6_hdr(skb), initval), + queues_total); + break; + case NFPROTO_BRIDGE: + queue += reciprocal_scale(hash_bridge(skb, initval), + queues_total); + break; + } return queue; } diff --git a/include/net/netfilter/nf_socket.h b/include/net/netfilter/nf_socket.h new file mode 100644 index 000000000000..f2fc39c97d43 --- /dev/null +++ b/include/net/netfilter/nf_socket.h @@ -0,0 +1,27 @@ +#ifndef _NF_SOCK_H_ +#define _NF_SOCK_H_ + +struct net_device; +struct sk_buff; +struct sock; +struct net; + +static inline bool nf_sk_is_transparent(struct sock *sk) +{ + switch (sk->sk_state) { + case TCP_TIME_WAIT: + return inet_twsk(sk)->tw_transparent; + case TCP_NEW_SYN_RECV: + return inet_rsk(inet_reqsk(sk))->no_srccheck; + default: + return inet_sk(sk)->transparent; + } +} + +struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb, + const struct net_device *indev); + +struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, + const struct net_device *indev); + +#endif diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f2f13399ce44..924325c46aab 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -14,26 +14,60 @@ struct nft_pktinfo { struct sk_buff *skb; - struct net *net; - const struct net_device *in; - const struct net_device *out; - u8 pf; - u8 hook; + bool tprot_set; u8 tprot; /* for x_tables compatibility */ struct xt_action_param xt; }; +static inline struct net *nft_net(const struct nft_pktinfo *pkt) +{ + return pkt->xt.state->net; +} + +static inline unsigned int nft_hook(const struct nft_pktinfo *pkt) +{ + return pkt->xt.state->hook; +} + +static inline u8 nft_pf(const struct nft_pktinfo *pkt) +{ + return pkt->xt.state->pf; +} + +static inline const struct net_device *nft_in(const struct nft_pktinfo *pkt) +{ + return pkt->xt.state->in; +} + +static inline const struct net_device *nft_out(const struct nft_pktinfo *pkt) +{ + return pkt->xt.state->out; +} + static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, struct sk_buff *skb, const struct nf_hook_state *state) { pkt->skb = skb; - pkt->net = pkt->xt.net = state->net; - pkt->in = pkt->xt.in = state->in; - pkt->out = pkt->xt.out = state->out; - pkt->hook = pkt->xt.hooknum = state->hook; - pkt->pf = pkt->xt.family = state->pf; + pkt->xt.state = state; +} + +static inline void nft_set_pktinfo_proto_unspec(struct nft_pktinfo *pkt, + struct sk_buff *skb) +{ + pkt->tprot_set = false; + pkt->tprot = 0; + pkt->xt.thoff = 0; + pkt->xt.fragoff = 0; +} + +static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + nft_set_pktinfo(pkt, skb, state); + nft_set_pktinfo_proto_unspec(pkt, skb); } /** @@ -127,6 +161,7 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE; } +int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); unsigned int nft_parse_register(const struct nlattr *attr); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); @@ -224,7 +259,8 @@ struct nft_expr; * @lookup: look up an element within the set * @insert: insert new element into set * @activate: activate new element in the next generation - * @deactivate: deactivate element in the next generation + * @deactivate: lookup for element and deactivate it in the next generation + * @deactivate_one: deactivate element in the next generation * @remove: remove element from set * @walk: iterate over all set elemeennts * @privsize: function to return size of set private data @@ -251,13 +287,17 @@ struct nft_set_ops { int (*insert)(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem); + const struct nft_set_elem *elem, + struct nft_set_ext **ext); void (*activate)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem); void * (*deactivate)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem); + bool (*deactivate_one)(const struct net *net, + const struct nft_set *set, + void *priv); void (*remove)(const struct nft_set *set, const struct nft_set_elem *elem); void (*walk)(const struct nft_ctx *ctx, @@ -290,10 +330,11 @@ void nft_unregister_set(struct nft_set_ops *ops); * @name: name of the set * @ktype: key type (numeric type defined by userspace, not used in the kernel) * @dtype: data type (verdict or numeric type defined by userspace) + * @objtype: object type (see NFT_OBJECT_* definitions) * @size: maximum set size * @nelems: number of elements * @ndeact: number of deactivated elements queued for removal - * @timeout: default timeout value in msecs + * @timeout: default timeout value in jiffies * @gc_int: garbage collection interval in msecs * @policy: set parameterization (see enum nft_set_policies) * @udlen: user data length @@ -311,6 +352,7 @@ struct nft_set { char name[NFT_SET_MAXNAMELEN]; u32 ktype; u32 dtype; + u32 objtype; u32 size; atomic_t nelems; u32 ndeact; @@ -380,6 +422,7 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, * @NFT_SET_EXT_EXPIRATION: element expiration time * @NFT_SET_EXT_USERDATA: user data associated with the element * @NFT_SET_EXT_EXPR: expression assiociated with the element + * @NFT_SET_EXT_OBJREF: stateful object reference associated with element * @NFT_SET_EXT_NUM: number of extension types */ enum nft_set_extensions { @@ -390,6 +433,7 @@ enum nft_set_extensions { NFT_SET_EXT_EXPIRATION, NFT_SET_EXT_USERDATA, NFT_SET_EXT_EXPR, + NFT_SET_EXT_OBJREF, NFT_SET_EXT_NUM }; @@ -518,11 +562,17 @@ static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, return elem + set->ops->elemsize; } +static inline struct nft_object **nft_set_ext_obj(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_OBJREF); +} + void *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *data, u64 timeout, gfp_t gfp); -void nft_set_elem_destroy(const struct nft_set *set, void *elem); +void nft_set_elem_destroy(const struct nft_set *set, void *elem, + bool destroy_expr); /** * struct nft_set_gc_batch_head - nf_tables set garbage collection batch @@ -673,7 +723,6 @@ static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) { int err; - __module_get(src->ops->type->owner); if (src->ops->clone) { dst->ops = src->ops; err = src->ops->clone(dst, src); @@ -682,6 +731,8 @@ static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) } else { memcpy(dst, src, src->ops->size); } + + __module_get(src->ops->type->owner); return 0; } @@ -837,6 +888,7 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); * @list: used internally * @chains: chains in the table * @sets: sets in the table + * @objects: stateful objects in the table * @hgenerator: handle generator state * @use: number of chain references to this table * @flags: table flag (see enum nft_table_flags) @@ -847,6 +899,7 @@ struct nft_table { struct list_head list; struct list_head chains; struct list_head sets; + struct list_head objects; u64 hgenerator; u32 use; u16 flags:14, @@ -897,6 +950,80 @@ int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v); /** + * struct nft_object - nf_tables stateful object + * + * @list: table stateful object list node + * @table: table this object belongs to + * @type: pointer to object type + * @data: pointer to object data + * @name: name of this stateful object + * @genmask: generation mask + * @use: number of references to this stateful object + * @data: object data, layout depends on type + */ +struct nft_object { + struct list_head list; + char name[NFT_OBJ_MAXNAMELEN]; + struct nft_table *table; + u32 genmask:2, + use:30; + /* runtime data below here */ + const struct nft_object_type *type ____cacheline_aligned; + unsigned char data[] + __attribute__((aligned(__alignof__(u64)))); +}; + +static inline void *nft_obj_data(const struct nft_object *obj) +{ + return (void *)obj->data; +} + +#define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr)) + +struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, + const struct nlattr *nla, u32 objtype, + u8 genmask); + +int nft_obj_notify(struct net *net, struct nft_table *table, + struct nft_object *obj, u32 portid, u32 seq, + int event, int family, int report, gfp_t gfp); + +/** + * struct nft_object_type - stateful object type + * + * @eval: stateful object evaluation function + * @list: list node in list of object types + * @type: stateful object numeric type + * @size: stateful object size + * @owner: module owner + * @maxattr: maximum netlink attribute + * @policy: netlink attribute policy + * @init: initialize object from netlink attributes + * @destroy: release existing stateful object + * @dump: netlink dump stateful object + */ +struct nft_object_type { + void (*eval)(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt); + struct list_head list; + u32 type; + unsigned int size; + unsigned int maxattr; + struct module *owner; + const struct nla_policy *policy; + int (*init)(const struct nlattr * const tb[], + struct nft_object *obj); + void (*destroy)(struct nft_object *obj); + int (*dump)(struct sk_buff *skb, + struct nft_object *obj, + bool reset); +}; + +int nft_register_obj(struct nft_object_type *obj_type); +void nft_unregister_obj(struct nft_object_type *obj_type); + +/** * struct nft_traceinfo - nft tracing information and state * * @pkt: pktinfo currently processed @@ -943,6 +1070,9 @@ void nft_trace_notify(struct nft_traceinfo *info); #define MODULE_ALIAS_NFT_SET() \ MODULE_ALIAS("nft-set") +#define MODULE_ALIAS_NFT_OBJ(type) \ + MODULE_ALIAS("nft-obj-" __stringify(type)) + /* * The gencursor defines two generations, the currently active and the * next one. Objects contain a bitmask of 2 bits specifying the generations @@ -1119,4 +1249,11 @@ struct nft_trans_elem { #define nft_trans_elem(trans) \ (((struct nft_trans_elem *)trans->data)->elem) +struct nft_trans_obj { + struct nft_object *obj; +}; + +#define nft_trans_obj(trans) \ + (((struct nft_trans_obj *)trans->data)->obj) + #endif /* _NET_NF_TABLES_H */ diff --git a/include/net/netfilter/nf_tables_bridge.h b/include/net/netfilter/nf_tables_bridge.h deleted file mode 100644 index 511fb79f6dad..000000000000 --- a/include/net/netfilter/nf_tables_bridge.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef _NET_NF_TABLES_BRIDGE_H -#define _NET_NF_TABLES_BRIDGE_H - -int nft_bridge_iphdr_validate(struct sk_buff *skb); -int nft_bridge_ip6hdr_validate(struct sk_buff *skb); - -#endif /* _NET_NF_TABLES_BRIDGE_H */ diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index a9060dd99db7..8f690effec37 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -1,12 +1,18 @@ #ifndef _NET_NF_TABLES_CORE_H #define _NET_NF_TABLES_CORE_H +extern struct nft_expr_type nft_imm_type; +extern struct nft_expr_type nft_cmp_type; +extern struct nft_expr_type nft_lookup_type; +extern struct nft_expr_type nft_bitwise_type; +extern struct nft_expr_type nft_byteorder_type; +extern struct nft_expr_type nft_payload_type; +extern struct nft_expr_type nft_dynset_type; +extern struct nft_expr_type nft_range_type; + int nf_tables_core_module_init(void); void nf_tables_core_module_exit(void); -int nft_immediate_module_init(void); -void nft_immediate_module_exit(void); - struct nft_cmp_fast_expr { u32 data; enum nft_registers sreg:8; @@ -25,21 +31,6 @@ static inline u32 nft_cmp_fast_mask(unsigned int len) extern const struct nft_expr_ops nft_cmp_fast_ops; -int nft_cmp_module_init(void); -void nft_cmp_module_exit(void); - -int nft_lookup_module_init(void); -void nft_lookup_module_exit(void); - -int nft_dynset_module_init(void); -void nft_dynset_module_exit(void); - -int nft_bitwise_module_init(void); -void nft_bitwise_module_exit(void); - -int nft_byteorder_module_init(void); -void nft_byteorder_module_exit(void); - struct nft_payload { enum nft_payload_bases base:8; u8 offset; @@ -54,12 +45,10 @@ struct nft_payload_set { enum nft_registers sreg:8; u8 csum_type; u8 csum_offset; + u8 csum_flags; }; extern const struct nft_expr_ops nft_payload_fast_ops; extern struct static_key_false nft_trace_enabled; -int nft_payload_module_init(void); -void nft_payload_module_exit(void); - #endif /* _NET_NF_TABLES_CORE_H */ diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index ca6ef6bf775e..25e33aee91e7 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -14,11 +14,53 @@ nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, nft_set_pktinfo(pkt, skb, state); ip = ip_hdr(pkt->skb); + pkt->tprot_set = true; pkt->tprot = ip->protocol; pkt->xt.thoff = ip_hdrlen(pkt->skb); pkt->xt.fragoff = ntohs(ip->frag_off) & IP_OFFSET; } +static inline int +__nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct iphdr *iph, _iph; + u32 len, thoff; + + iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), + &_iph); + if (!iph) + return -1; + + if (iph->ihl < 5 || iph->version != 4) + return -1; + + len = ntohs(iph->tot_len); + thoff = iph->ihl * 4; + if (skb->len < len) + return -1; + else if (len < thoff) + return -1; + + pkt->tprot_set = true; + pkt->tprot = iph->protocol; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; + + return 0; +} + +static inline void +nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + nft_set_pktinfo(pkt, skb, state); + if (__nft_set_pktinfo_ipv4_validate(pkt, skb, state) < 0) + nft_set_pktinfo_proto_unspec(pkt, skb); +} + extern struct nft_af_info nft_af_ipv4; #endif diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 8ad39a6a5fe1..d150b5066201 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -4,7 +4,7 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/ipv6.h> -static inline int +static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, struct sk_buff *skb, const struct nf_hook_state *state) @@ -15,15 +15,64 @@ nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, nft_set_pktinfo(pkt, skb, state); protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); - /* If malformed, drop it */ + if (protohdr < 0) { + nft_set_pktinfo_proto_unspec(pkt, skb); + return; + } + + pkt->tprot_set = true; + pkt->tprot = protohdr; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = frag_off; +} + +static inline int +__nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ +#if IS_ENABLED(CONFIG_IPV6) + struct ipv6hdr *ip6h, _ip6h; + unsigned int thoff = 0; + unsigned short frag_off; + int protohdr; + u32 pkt_len; + + ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h), + &_ip6h); + if (!ip6h) + return -1; + + if (ip6h->version != 6) + return -1; + + pkt_len = ntohs(ip6h->payload_len); + if (pkt_len + sizeof(*ip6h) > skb->len) + return -1; + + protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); if (protohdr < 0) return -1; + pkt->tprot_set = true; pkt->tprot = protohdr; pkt->xt.thoff = thoff; pkt->xt.fragoff = frag_off; return 0; +#else + return -1; +#endif +} + +static inline void +nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + nft_set_pktinfo(pkt, skb, state); + if (__nft_set_pktinfo_ipv6_validate(pkt, skb, state) < 0) + nft_set_pktinfo_proto_unspec(pkt, skb); } extern struct nft_af_info nft_af_ipv6; diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h new file mode 100644 index 000000000000..cbedda077db2 --- /dev/null +++ b/include/net/netfilter/nft_fib.h @@ -0,0 +1,31 @@ +#ifndef _NFT_FIB_H_ +#define _NFT_FIB_H_ + +struct nft_fib { + enum nft_registers dreg:8; + u8 result; + u32 flags; +}; + +extern const struct nla_policy nft_fib_policy[]; + +int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr); +int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]); +int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nft_data **data); + + +void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); +void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); + +void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); +void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); + +void nft_fib_store_result(void *reg, enum nft_fib_result r, + const struct nft_pktinfo *pkt, int index); +#endif diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h index 79f45e19f31e..130e58361f99 100644 --- a/include/net/netfilter/xt_rateest.h +++ b/include/net/netfilter/xt_rateest.h @@ -1,19 +1,23 @@ #ifndef _XT_RATEEST_H #define _XT_RATEEST_H +#include <net/gen_stats.h> + struct xt_rateest { /* keep lock and bstats on same cache line to speedup xt_rateest_tg() */ struct gnet_stats_basic_packed bstats; spinlock_t lock; - /* keep rstats and lock on same cache line to speedup xt_rateest_mt() */ - struct gnet_stats_rate_est64 rstats; + /* following fields not accessed in hot path */ + unsigned int refcnt; struct hlist_node list; char name[IFNAMSIZ]; - unsigned int refcnt; struct gnet_estimator params; struct rcu_head rcu; + + /* keep this field far away to speedup xt_rateest_mt() */ + struct net_rate_estimator __rcu *rate_est; }; struct xt_rateest *xt_rateest_lookup(const char *name); diff --git a/include/net/netlink.h b/include/net/netlink.h index 254a0fc01800..d3938f11ae52 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -713,7 +713,7 @@ static inline int nla_ok(const struct nlattr *nla, int remaining) */ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining) { - int totlen = NLA_ALIGN(nla->nla_len); + unsigned int totlen = NLA_ALIGN(nla->nla_len); *remaining -= totlen; return (struct nlattr *) ((char *) nla + totlen); @@ -1191,6 +1191,16 @@ static inline struct in6_addr nla_get_in6_addr(const struct nlattr *nla) } /** + * nla_memdup - duplicate attribute memory (kmemdup) + * @src: netlink attribute to duplicate from + * @gfp: GFP mask + */ +static inline void *nla_memdup(const struct nlattr *src, gfp_t gfp) +{ + return kmemdup(nla_data(src), nla_len(src), gfp); +} + +/** * nla_nest_start - Start a new level of nested attributes * @skb: socket buffer to add attributes to * @attrtype: attribute type of container diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 38b1a80517f0..cf799fc3fdec 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -6,6 +6,12 @@ #include <linux/atomic.h> #include <linux/workqueue.h> #include <linux/netfilter/nf_conntrack_tcp.h> +#ifdef CONFIG_NF_CT_PROTO_DCCP +#include <linux/netfilter/nf_conntrack_dccp.h> +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP +#include <linux/netfilter/nf_conntrack_sctp.h> +#endif #include <linux/seqlock.h> struct ctl_table_header; @@ -15,10 +21,6 @@ struct nf_proto_net { #ifdef CONFIG_SYSCTL struct ctl_table_header *ctl_table_header; struct ctl_table *ctl_table; -#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT - struct ctl_table_header *ctl_compat_header; - struct ctl_table *ctl_compat_table; -#endif #endif unsigned int users; }; @@ -52,15 +54,48 @@ struct nf_icmp_net { unsigned int timeout; }; +#ifdef CONFIG_NF_CT_PROTO_DCCP +struct nf_dccp_net { + struct nf_proto_net pn; + int dccp_loose; + unsigned int dccp_timeout[CT_DCCP_MAX + 1]; +}; +#endif + +#ifdef CONFIG_NF_CT_PROTO_SCTP +struct nf_sctp_net { + struct nf_proto_net pn; + unsigned int timeouts[SCTP_CONNTRACK_MAX]; +}; +#endif + +#ifdef CONFIG_NF_CT_PROTO_UDPLITE +enum udplite_conntrack { + UDPLITE_CT_UNREPLIED, + UDPLITE_CT_REPLIED, + UDPLITE_CT_MAX +}; + +struct nf_udplite_net { + struct nf_proto_net pn; + unsigned int timeouts[UDPLITE_CT_MAX]; +}; +#endif + struct nf_ip_net { struct nf_generic_net generic; struct nf_tcp_net tcp; struct nf_udp_net udp; struct nf_icmp_net icmp; struct nf_icmp_net icmpv6; -#if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) - struct ctl_table_header *ctl_table_header; - struct ctl_table *ctl_table; +#ifdef CONFIG_NF_CT_PROTO_DCCP + struct nf_dccp_net dccp; +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + struct nf_sctp_net sctp; +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE + struct nf_udplite_net udplite; #endif }; @@ -99,7 +134,6 @@ struct netns_ct { struct nf_ip_net nf_ct_proto; #if defined(CONFIG_NF_CONNTRACK_LABELS) unsigned int labels_used; - u8 label_words; #endif }; #endif diff --git a/include/net/netns/generic.h b/include/net/netns/generic.h index 70e158551704..f15daaa89385 100644 --- a/include/net/netns/generic.h +++ b/include/net/netns/generic.h @@ -25,20 +25,24 @@ */ struct net_generic { - unsigned int len; - struct rcu_head rcu; - - void *ptr[0]; + union { + struct { + unsigned int len; + struct rcu_head rcu; + } s; + + void *ptr[0]; + }; }; -static inline void *net_generic(const struct net *net, int id) +static inline void *net_generic(const struct net *net, unsigned int id) { struct net_generic *ng; void *ptr; rcu_read_lock(); ng = rcu_dereference(net->gen); - ptr = ng->ptr[id - 1]; + ptr = ng->ptr[id]; rcu_read_unlock(); return ptr; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d061ffeb1e71..0378e88f6fd3 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -40,7 +40,6 @@ struct netns_ipv4 { #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rules_ops *rules_ops; bool fib_has_custom_rules; - struct fib_table __rcu *fib_local; struct fib_table __rcu *fib_main; struct fib_table __rcu *fib_default; #endif @@ -111,6 +110,7 @@ struct netns_ipv4 { int sysctl_tcp_orphan_retries; int sysctl_tcp_fin_timeout; unsigned int sysctl_tcp_notsent_lowat; + int sysctl_tcp_tw_reuse; int sysctl_igmp_max_memberships; int sysctl_igmp_max_msf; @@ -136,6 +136,9 @@ struct netns_ipv4 { #ifdef CONFIG_IP_ROUTE_MULTIPATH int sysctl_fib_multipath_use_neigh; #endif + + unsigned int fib_seq; /* protected by rtnl_mutex */ + atomic_t rt_genid; }; #endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 10d0848f5b8a..de7745e2edcc 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -85,6 +85,7 @@ struct netns_ipv6 { #endif atomic_t dev_addr_genid; atomic_t fib6_sernum; + struct seg6_pernet_data *seg6_data; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 36d723579af2..cea396b53a60 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -16,6 +16,12 @@ struct netns_nf { #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; #endif - struct list_head hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; + struct nf_hook_entry __rcu *hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) + bool defrag_ipv4; +#endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + bool defrag_ipv6; +#endif }; #endif diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 24cd3949a9a4..27bb9633c69d 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -11,7 +11,7 @@ struct ctl_table_header; struct xfrm_policy_hash { - struct hlist_head *table; + struct hlist_head __rcu *table; unsigned int hmask; u8 dbits4; u8 sbits4; @@ -38,14 +38,12 @@ struct netns_xfrm { * mode. Also, it can be used by ah/esp icmp error handler to find * offending SA. */ - struct hlist_head *state_bydst; - struct hlist_head *state_bysrc; - struct hlist_head *state_byspi; + struct hlist_head __rcu *state_bydst; + struct hlist_head __rcu *state_bysrc; + struct hlist_head __rcu *state_byspi; unsigned int state_hmask; unsigned int state_num; struct work_struct state_hash_work; - struct hlist_head state_gc_list; - struct work_struct state_gc_work; struct list_head policy_all; struct hlist_head *policy_byidx; @@ -73,7 +71,7 @@ struct netns_xfrm { struct dst_ops xfrm6_dst_ops; #endif spinlock_t xfrm_state_lock; - rwlock_t xfrm_policy_lock; + spinlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; /* flow cache part */ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index c99508d426cc..f0a051480c6c 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -69,17 +69,19 @@ struct tcf_exts { int police; }; -static inline void tcf_exts_init(struct tcf_exts *exts, int action, int police) +static inline int tcf_exts_init(struct tcf_exts *exts, int action, int police) { #ifdef CONFIG_NET_CLS_ACT exts->type = 0; exts->nr_actions = 0; exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *), GFP_KERNEL); - WARN_ON(!exts->actions); /* TODO: propagate the error to callers */ + if (!exts->actions) + return -ENOMEM; #endif exts->action = action; exts->police = police; + return 0; } /** @@ -121,7 +123,7 @@ static inline void tcf_exts_to_list(const struct tcf_exts *exts, for (i = 0; i < exts->nr_actions; i++) { struct tc_action *a = exts->actions[i]; - list_add(&a->list, actions); + list_add_tail(&a->list, actions); } #endif } @@ -169,6 +171,8 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, struct tcf_exts *src); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); +int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, + struct net_device **hw_dev); /** * struct tcf_pkt_info - packet information @@ -423,16 +427,14 @@ struct tc_cls_u32_offload { }; }; -static inline bool tc_should_offload(const struct net_device *dev, - const struct tcf_proto *tp, u32 flags) +static inline bool tc_can_offload(const struct net_device *dev, + const struct tcf_proto *tp) { const struct Qdisc *sch = tp->q; const struct Qdisc_class_ops *cops = sch->ops->cl_ops; if (!(dev->features & NETIF_F_HW_TC)) return false; - if (flags & TCA_CLS_FLAGS_SKIP_HW) - return false; if (!dev->netdev_ops->ndo_setup_tc) return false; if (cops && cops->tcf_cl_offload) @@ -441,6 +443,19 @@ static inline bool tc_should_offload(const struct net_device *dev, return true; } +static inline bool tc_skip_hw(u32 flags) +{ + return (flags & TCA_CLS_FLAGS_SKIP_HW) ? true : false; +} + +static inline bool tc_should_offload(const struct net_device *dev, + const struct tcf_proto *tp, u32 flags) +{ + if (tc_skip_hw(flags)) + return false; + return tc_can_offload(dev, tp); +} + static inline bool tc_skip_sw(u32 flags) { return (flags & TCA_CLS_FLAGS_SKIP_SW) ? true : false; @@ -484,4 +499,20 @@ struct tc_cls_matchall_offload { unsigned long cookie; }; +enum tc_clsbpf_command { + TC_CLSBPF_ADD, + TC_CLSBPF_REPLACE, + TC_CLSBPF_DESTROY, + TC_CLSBPF_STATS, +}; + +struct tc_cls_bpf_offload { + enum tc_clsbpf_command command; + struct tcf_exts *exts; + struct bpf_prog *prog; + const char *name; + bool exts_integrated; + u32 gen_flags; +}; + #endif diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 7caa99b482c6..f1b76b8e6d2d 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -6,6 +6,8 @@ #include <linux/if_vlan.h> #include <net/sch_generic.h> +#define DEFAULT_TX_QUEUE_LEN 1000 + struct qdisc_walker { int stop; int skip; @@ -90,8 +92,8 @@ int unregister_qdisc(struct Qdisc_ops *qops); void qdisc_get_default(char *id, size_t len); int qdisc_set_default(const char *id); -void qdisc_list_add(struct Qdisc *q); -void qdisc_list_del(struct Qdisc *q); +void qdisc_hash_add(struct Qdisc *q); +void qdisc_hash_del(struct Qdisc *q); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle); struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, diff --git a/include/net/pptp.h b/include/net/pptp.h new file mode 100644 index 000000000000..92e9f1fe2628 --- /dev/null +++ b/include/net/pptp.h @@ -0,0 +1,23 @@ +#ifndef _NET_PPTP_H +#define _NET_PPTP_H + +#define PPP_LCP_ECHOREQ 0x09 +#define PPP_LCP_ECHOREP 0x0A +#define SC_RCV_BITS (SC_RCV_B7_1|SC_RCV_B7_0|SC_RCV_ODDP|SC_RCV_EVNP) + +#define MISSING_WINDOW 20 +#define WRAPPED(curseq, lastseq)\ + ((((curseq) & 0xffffff00) == 0) &&\ + (((lastseq) & 0xffffff00) == 0xffffff00)) + +#define PPTP_HEADER_OVERHEAD (2+sizeof(struct pptp_gre_header)) +struct pptp_gre_header { + struct gre_base_hdr gre_hd; + __be16 payload_len; + __be16 call_id; + __be32 seq; + __be32 ack; +} __packed; + + +#endif diff --git a/include/net/raw.h b/include/net/raw.h index 3e789008394d..57c33dd22ec4 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -23,6 +23,12 @@ extern struct proto raw_prot; +extern struct raw_hashinfo raw_v4_hashinfo; +struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, + unsigned short num, __be32 raddr, + __be32 laddr, int dif); + +int raw_abort(struct sock *sk, int err); void raw_icmp_error(struct sk_buff *, int, u32); int raw_local_deliver(struct sk_buff *, int); diff --git a/include/net/rawv6.h b/include/net/rawv6.h index 87783dea0791..cbe4e9de1894 100644 --- a/include/net/rawv6.h +++ b/include/net/rawv6.h @@ -3,6 +3,13 @@ #include <net/protocol.h> +extern struct raw_hashinfo raw_v6_hashinfo; +struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, + unsigned short num, const struct in6_addr *loc_addr, + const struct in6_addr *rmt_addr, int dif); + +int raw_abort(struct sock *sk, int err); + void raw6_icmp_error(struct sk_buff *, int nexthdr, u8 type, u8 code, int inner_offset, __be32); bool raw6_local_deliver(struct sk_buff *, int); diff --git a/include/net/red.h b/include/net/red.h index 76e0b5f922c6..208e718e16b9 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -207,7 +207,7 @@ static inline void red_set_parms(struct red_parms *p, static inline int red_is_idling(const struct red_vars *v) { - return v->qidlestart.tv64 != 0; + return v->qidlestart != 0; } static inline void red_start_of_idle_period(struct red_vars *v) @@ -217,7 +217,7 @@ static inline void red_start_of_idle_period(struct red_vars *v) static inline void red_end_of_idle_period(struct red_vars *v) { - v->qidlestart.tv64 = 0; + v->qidlestart = 0; } static inline void red_restart(struct red_vars *v) diff --git a/include/net/route.h b/include/net/route.h index ad777d79af94..c0874c87c173 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -29,7 +29,6 @@ #include <net/flow.h> #include <net/inet_sock.h> #include <net/ip_fib.h> -#include <net/l3mdev.h> #include <linux/in_route.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> @@ -154,7 +153,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos, RT_SCOPE_UNIVERSE, proto, sk ? inet_sk_flowi_flags(sk) : 0, - daddr, saddr, dport, sport); + daddr, saddr, dport, sport, sock_net_uid(net, sk)); if (sk) security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); return ip_route_output_flow(net, fl4, sk); @@ -270,7 +269,8 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 flow_flags |= FLOWI_FLAG_ANYSRC; flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, - protocol, flow_flags, dst, src, dport, sport); + protocol, flow_flags, dst, src, dport, sport, + sk->sk_uid); } static inline struct rtable *ip_route_connect(struct flowi4 *fl4, @@ -285,15 +285,6 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, ip_route_connect_init(fl4, dst, src, tos, oif, protocol, sport, dport, sk); - if (!src && oif) { - int rc; - - rc = l3mdev_get_saddr(net, oif, fl4); - if (rc < 0) - return ERR_PTR(rc); - - src = fl4->saddr; - } if (!dst || !src) { rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 909aff2db2b3..498f81b229a4 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -36,6 +36,14 @@ struct qdisc_size_table { u16 data[]; }; +/* similar to sk_buff_head, but skb->prev pointer is undefined. */ +struct qdisc_skb_head { + struct sk_buff *head; + struct sk_buff *tail; + __u32 qlen; + spinlock_t lock; +}; + struct Qdisc { int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, @@ -61,14 +69,14 @@ struct Qdisc { u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; - struct list_head list; + struct hlist_node hash; u32 handle; u32 parent; void *u32_node; struct netdev_queue *dev_queue; - struct gnet_stats_rate_est64 rate_est; + struct net_rate_estimator __rcu *rate_est; struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; @@ -76,7 +84,7 @@ struct Qdisc { * For performance sake on SMP, we put highly modified fields at the end */ struct sk_buff *gso_skb ____cacheline_aligned_in_smp; - struct sk_buff_head q; + struct qdisc_skb_head q; struct gnet_stats_basic_packed bstats; seqcount_t running; struct gnet_stats_queue qstats; @@ -592,7 +600,7 @@ static inline void qdisc_qstats_drop(struct Qdisc *sch) static inline void qdisc_qstats_cpu_drop(struct Qdisc *sch) { - qstats_drop_inc(this_cpu_ptr(sch->cpu_qstats)); + this_cpu_inc(sch->cpu_qstats->drops); } static inline void qdisc_qstats_overlimit(struct Qdisc *sch) @@ -600,10 +608,27 @@ static inline void qdisc_qstats_overlimit(struct Qdisc *sch) sch->qstats.overlimits++; } +static inline void qdisc_skb_head_init(struct qdisc_skb_head *qh) +{ + qh->head = NULL; + qh->tail = NULL; + qh->qlen = 0; +} + static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff_head *list) + struct qdisc_skb_head *qh) { - __skb_queue_tail(list, skb); + struct sk_buff *last = qh->tail; + + if (last) { + skb->next = NULL; + last->next = skb; + qh->tail = skb; + } else { + qh->tail = skb; + qh->head = skb; + } + qh->qlen++; qdisc_qstats_backlog_inc(sch, skb); return NET_XMIT_SUCCESS; @@ -614,14 +639,16 @@ static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) return __qdisc_enqueue_tail(skb, sch, &sch->q); } -static inline struct sk_buff *__qdisc_dequeue_head(struct Qdisc *sch, - struct sk_buff_head *list) +static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) { - struct sk_buff *skb = __skb_dequeue(list); + struct sk_buff *skb = qh->head; if (likely(skb != NULL)) { - qdisc_qstats_backlog_dec(sch, skb); - qdisc_bstats_update(sch, skb); + qh->head = skb->next; + qh->qlen--; + if (qh->head == NULL) + qh->tail = NULL; + skb->next = NULL; } return skb; @@ -629,7 +656,14 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct Qdisc *sch, static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) { - return __qdisc_dequeue_head(sch, &sch->q); + struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + + if (likely(skb != NULL)) { + qdisc_qstats_backlog_dec(sch, skb); + qdisc_bstats_update(sch, skb); + } + + return skb; } /* Instead of calling kfree_skb() while root qdisc lock is held, @@ -642,10 +676,10 @@ static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free) } static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, - struct sk_buff_head *list, + struct qdisc_skb_head *qh, struct sk_buff **to_free) { - struct sk_buff *skb = __skb_dequeue(list); + struct sk_buff *skb = __qdisc_dequeue_head(qh); if (likely(skb != NULL)) { unsigned int len = qdisc_pkt_len(skb); @@ -666,7 +700,9 @@ static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch, static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) { - return skb_peek(&sch->q); + const struct qdisc_skb_head *qh = &sch->q; + + return qh->head; } /* generic pseudo peek method for non-work-conserving qdisc */ @@ -701,15 +737,19 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch) return skb; } -static inline void __qdisc_reset_queue(struct sk_buff_head *list) +static inline void __qdisc_reset_queue(struct qdisc_skb_head *qh) { /* * We do not know the backlog in bytes of this list, it * is up to the caller to correct it */ - if (!skb_queue_empty(list)) { - rtnl_kfree_skbs(list->next, list->prev); - __skb_queue_head_init(list); + ASSERT_RTNL(); + if (qh->qlen) { + rtnl_kfree_skbs(qh->head, qh->tail); + + qh->head = NULL; + qh->tail = NULL; + qh->qlen = 0; } } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 632e205ca54b..d8833a86cd7e 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -69,7 +69,7 @@ #include <net/ip6_route.h> #endif -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/page.h> #include <net/sock.h> #include <net/snmp.h> @@ -83,9 +83,9 @@ #endif /* Round an int up to the next multiple of 4. */ -#define WORD_ROUND(s) (((s)+3)&~3) +#define SCTP_PAD4(s) (((s)+3)&~3) /* Truncate to the previous multiple of 4. */ -#define WORD_TRUNC(s) ((s)&~3) +#define SCTP_TRUNC4(s) ((s)&~3) /* * Function declarations. @@ -152,7 +152,7 @@ void sctp_unhash_endpoint(struct sctp_endpoint *); struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *, struct sctphdr *, struct sctp_association **, struct sctp_transport **); -void sctp_err_finish(struct sock *, struct sctp_association *); +void sctp_err_finish(struct sock *, struct sctp_transport *); void sctp_icmp_frag_needed(struct sock *, struct sctp_association *, struct sctp_transport *t, __u32 pmtu); void sctp_icmp_redirect(struct sock *, struct sctp_transport *, @@ -164,7 +164,7 @@ void sctp_backlog_migrate(struct sctp_association *assoc, struct sock *oldsk, struct sock *newsk); int sctp_transport_hashtable_init(void); void sctp_transport_hashtable_destroy(void); -void sctp_hash_transport(struct sctp_transport *t); +int sctp_hash_transport(struct sctp_transport *t); void sctp_unhash_transport(struct sctp_transport *t); struct sctp_transport *sctp_addrs_lookup_transport( struct net *net, @@ -433,7 +433,7 @@ static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu) if (asoc->user_frag) frag = min_t(int, frag, asoc->user_frag); - frag = WORD_TRUNC(min_t(int, frag, SCTP_MAX_CHUNK_LEN)); + frag = SCTP_TRUNC4(min_t(int, frag, SCTP_MAX_CHUNK_LEN)); return frag; } @@ -462,7 +462,7 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member) for (pos.v = chunk->member;\ pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\ ntohs(pos.p->length) >= sizeof(sctp_paramhdr_t);\ - pos.v += WORD_ROUND(ntohs(pos.p->length))) + pos.v += SCTP_PAD4(ntohs(pos.p->length))) #define sctp_walk_errors(err, chunk_hdr)\ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length)) @@ -472,7 +472,7 @@ for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \ sizeof(sctp_chunkhdr_t));\ (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\ ntohs(err->length) >= sizeof(sctp_errhdr_t); \ - err = (sctp_errhdr_t *)((void *)err + WORD_ROUND(ntohs(err->length)))) + err = (sctp_errhdr_t *)((void *)err + SCTP_PAD4(ntohs(err->length)))) #define sctp_walk_fwdtsn(pos, chunk)\ _sctp_walk_fwdtsn((pos), (chunk), ntohs((chunk)->chunk_hdr->length) - sizeof(struct sctp_fwdtsn_chunk)) diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index bafe2a0ab908..ca6c971dd74a 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -307,85 +307,27 @@ static inline __u16 sctp_data_size(struct sctp_chunk *chunk) } /* Compare two TSNs */ +#define TSN_lt(a,b) \ + (typecheck(__u32, a) && \ + typecheck(__u32, b) && \ + ((__s32)((a) - (b)) < 0)) -/* RFC 1982 - Serial Number Arithmetic - * - * 2. Comparison - * Then, s1 is said to be equal to s2 if and only if i1 is equal to i2, - * in all other cases, s1 is not equal to s2. - * - * s1 is said to be less than s2 if, and only if, s1 is not equal to s2, - * and - * - * (i1 < i2 and i2 - i1 < 2^(SERIAL_BITS - 1)) or - * (i1 > i2 and i1 - i2 > 2^(SERIAL_BITS - 1)) - * - * s1 is said to be greater than s2 if, and only if, s1 is not equal to - * s2, and - * - * (i1 < i2 and i2 - i1 > 2^(SERIAL_BITS - 1)) or - * (i1 > i2 and i1 - i2 < 2^(SERIAL_BITS - 1)) - */ - -/* - * RFC 2960 - * 1.6 Serial Number Arithmetic - * - * Comparisons and arithmetic on TSNs in this document SHOULD use Serial - * Number Arithmetic as defined in [RFC1982] where SERIAL_BITS = 32. - */ - -enum { - TSN_SIGN_BIT = (1<<31) -}; - -static inline int TSN_lt(__u32 s, __u32 t) -{ - return ((s) - (t)) & TSN_SIGN_BIT; -} - -static inline int TSN_lte(__u32 s, __u32 t) -{ - return ((s) == (t)) || (((s) - (t)) & TSN_SIGN_BIT); -} +#define TSN_lte(a,b) \ + (typecheck(__u32, a) && \ + typecheck(__u32, b) && \ + ((__s32)((a) - (b)) <= 0)) /* Compare two SSNs */ - -/* - * RFC 2960 - * 1.6 Serial Number Arithmetic - * - * Comparisons and arithmetic on Stream Sequence Numbers in this document - * SHOULD use Serial Number Arithmetic as defined in [RFC1982] where - * SERIAL_BITS = 16. - */ -enum { - SSN_SIGN_BIT = (1<<15) -}; - -static inline int SSN_lt(__u16 s, __u16 t) -{ - return ((s) - (t)) & SSN_SIGN_BIT; -} - -static inline int SSN_lte(__u16 s, __u16 t) -{ - return ((s) == (t)) || (((s) - (t)) & SSN_SIGN_BIT); -} - -/* - * ADDIP 3.1.1 - * The valid range of Serial Number is from 0 to 4294967295 (2**32 - 1). Serial - * Numbers wrap back to 0 after reaching 4294967295. - */ -enum { - ADDIP_SERIAL_SIGN_BIT = (1<<31) -}; - -static inline int ADDIP_SERIAL_gte(__u32 s, __u32 t) -{ - return ((s) == (t)) || (((t) - (s)) & ADDIP_SERIAL_SIGN_BIT); -} +#define SSN_lt(a,b) \ + (typecheck(__u16, a) && \ + typecheck(__u16, b) && \ + ((__s16)((a) - (b)) < 0)) + +/* ADDIP 3.1.1 */ +#define ADDIP_SERIAL_gte(a,b) \ + (typecheck(__u32, a) && \ + typecheck(__u32, b) && \ + ((__s32)((b) - (a)) <= 0)) /* Check VTAG of the packet matches the sender's own tag. */ static inline int diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index ced0df374e60..92daabdc007d 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -124,7 +124,7 @@ extern struct sctp_globals { /* This is the sctp port control hash. */ struct sctp_bind_hashbucket *port_hashtable; /* This is the hash of all transports. */ - struct rhashtable transport_hashtable; + struct rhltable transport_hashtable; /* Sizes of above hashtables. */ int ep_hashsize; @@ -530,13 +530,13 @@ struct sctp_datamsg { /* Did the messenge fail to send? */ int send_error; u8 send_failed:1, - can_abandon:1, /* can chunks from this message can be abandoned. */ can_delay; /* should this message be Nagle delayed */ }; struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *, struct sctp_sndrcvinfo *, struct iov_iter *); +void sctp_datamsg_free(struct sctp_datamsg *); void sctp_datamsg_put(struct sctp_datamsg *); void sctp_chunk_fail(struct sctp_chunk *, int error); int sctp_chunk_abandoned(struct sctp_chunk *); @@ -640,7 +640,6 @@ struct sctp_chunk { #define SCTP_NEED_FRTX 0x1 #define SCTP_DONT_FRTX 0x2 __u16 rtt_in_progress:1, /* This chunk used for RTT calc? */ - resent:1, /* Has this chunk ever been resent. */ has_tsn:1, /* Does this chunk have a TSN yet? */ has_ssn:1, /* Does this chunk have a SSN yet? */ singleton:1, /* Only chunk in the packet? */ @@ -655,6 +654,7 @@ struct sctp_chunk { fast_retransmit:2; /* Is this chunk fast retransmitted? */ }; +#define sctp_chunk_retransmitted(chunk) (chunk->sent_count > 1) void sctp_chunk_hold(struct sctp_chunk *); void sctp_chunk_put(struct sctp_chunk *); int sctp_user_addto_chunk(struct sctp_chunk *chunk, int len, @@ -761,7 +761,7 @@ static inline int sctp_packet_empty(struct sctp_packet *packet) struct sctp_transport { /* A list of transports. */ struct list_head transports; - struct rhash_head node; + struct rhlist_head node; /* Reference counting. */ atomic_t refcnt; @@ -1069,7 +1069,7 @@ struct sctp_outq { void sctp_outq_init(struct sctp_association *, struct sctp_outq *); void sctp_outq_teardown(struct sctp_outq *); void sctp_outq_free(struct sctp_outq*); -int sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk, gfp_t); +void sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk, gfp_t); int sctp_outq_sack(struct sctp_outq *, struct sctp_chunk *); int sctp_outq_is_empty(const struct sctp_outq *); void sctp_outq_restart(struct sctp_outq *); @@ -1077,7 +1077,7 @@ void sctp_outq_restart(struct sctp_outq *); void sctp_retransmit(struct sctp_outq *, struct sctp_transport *, sctp_retransmit_reason_t); void sctp_retransmit_mark(struct sctp_outq *, struct sctp_transport *, __u8); -int sctp_outq_uncork(struct sctp_outq *, gfp_t gfp); +void sctp_outq_uncork(struct sctp_outq *, gfp_t gfp); void sctp_prsctp_prune(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len); /* Uncork and flush an outqueue. */ diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index 3f36d45b714a..0caee631a836 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -6,10 +6,10 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); -__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport); -__u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport); +u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport, u32 *tsoff); +u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport, u32 *tsoff); u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, diff --git a/include/net/seg6.h b/include/net/seg6.h new file mode 100644 index 000000000000..4e0357517d79 --- /dev/null +++ b/include/net/seg6.h @@ -0,0 +1,62 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun <david.lebrun@uclouvain.be> + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _NET_SEG6_H +#define _NET_SEG6_H + +#include <linux/net.h> +#include <linux/ipv6.h> +#include <net/lwtunnel.h> +#include <linux/seg6.h> +#include <linux/rhashtable.h> + +static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, + __be32 to) +{ + __be32 diff[] = { ~from, to }; + + skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); +} + +static inline void update_csum_diff16(struct sk_buff *skb, __be32 *from, + __be32 *to) +{ + __be32 diff[] = { + ~from[0], ~from[1], ~from[2], ~from[3], + to[0], to[1], to[2], to[3], + }; + + skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); +} + +struct seg6_pernet_data { + struct mutex lock; + struct in6_addr __rcu *tun_src; +#ifdef CONFIG_IPV6_SEG6_HMAC + struct rhashtable hmac_infos; +#endif +}; + +static inline struct seg6_pernet_data *seg6_pernet(struct net *net) +{ + return net->ipv6.seg6_data; +} + +extern int seg6_init(void); +extern void seg6_exit(void); +extern int seg6_iptunnel_init(void); +extern void seg6_iptunnel_exit(void); + +extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len); + +#endif diff --git a/include/net/seg6_hmac.h b/include/net/seg6_hmac.h new file mode 100644 index 000000000000..69c3a106056b --- /dev/null +++ b/include/net/seg6_hmac.h @@ -0,0 +1,62 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun <david.lebrun@uclouvain.be> + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _NET_SEG6_HMAC_H +#define _NET_SEG6_HMAC_H + +#include <net/flow.h> +#include <net/ip6_fib.h> +#include <net/sock.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/route.h> +#include <net/seg6.h> +#include <linux/seg6_hmac.h> +#include <linux/rhashtable.h> + +#define SEG6_HMAC_MAX_DIGESTSIZE 160 +#define SEG6_HMAC_RING_SIZE 256 + +struct seg6_hmac_info { + struct rhash_head node; + struct rcu_head rcu; + + u32 hmackeyid; + char secret[SEG6_HMAC_SECRET_LEN]; + u8 slen; + u8 alg_id; +}; + +struct seg6_hmac_algo { + u8 alg_id; + char name[64]; + struct crypto_shash * __percpu *tfms; + struct shash_desc * __percpu *shashs; +}; + +extern int seg6_hmac_compute(struct seg6_hmac_info *hinfo, + struct ipv6_sr_hdr *hdr, struct in6_addr *saddr, + u8 *output); +extern struct seg6_hmac_info *seg6_hmac_info_lookup(struct net *net, u32 key); +extern int seg6_hmac_info_add(struct net *net, u32 key, + struct seg6_hmac_info *hinfo); +extern int seg6_hmac_info_del(struct net *net, u32 key); +extern int seg6_push_hmac(struct net *net, struct in6_addr *saddr, + struct ipv6_sr_hdr *srh); +extern bool seg6_hmac_validate_skb(struct sk_buff *skb); +extern int seg6_hmac_init(void); +extern void seg6_hmac_exit(void); +extern int seg6_hmac_net_init(struct net *net); +extern void seg6_hmac_net_exit(struct net *net); + +#endif diff --git a/include/net/sock.h b/include/net/sock.h index 8741988e6880..f0e867f58722 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -252,6 +252,7 @@ struct sock_common { * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes + * @sk_padding: unused element for alignment * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) @@ -302,7 +303,8 @@ struct sock_common { * @sk_backlog_rcv: callback to process the backlog * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container - */ + * @sk_rcu: used during RCU grace period + */ struct sock { /* * Now struct inet_timewait_sock also uses sock_common, so please just @@ -341,6 +343,9 @@ struct sock { #define sk_rxhash __sk_common.skc_rxhash socket_lock_t sk_lock; + atomic_t sk_drops; + int sk_rcvlowat; + struct sk_buff_head sk_error_queue; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with @@ -357,14 +362,13 @@ struct sock { struct sk_buff *tail; } sk_backlog; #define sk_rmem_alloc sk_backlog.rmem_alloc - int sk_forward_alloc; - __u32 sk_txhash; + int sk_forward_alloc; #ifdef CONFIG_NET_RX_BUSY_POLL - unsigned int sk_napi_id; unsigned int sk_ll_usec; + /* ===== mostly read cache line ===== */ + unsigned int sk_napi_id; #endif - atomic_t sk_drops; int sk_rcvbuf; struct sk_filter __rcu *sk_filter; @@ -377,16 +381,50 @@ struct sock { #endif struct dst_entry *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; - /* Note: 32bit hole on 64bit arches */ - atomic_t sk_wmem_alloc; atomic_t sk_omem_alloc; int sk_sndbuf; + + /* ===== cache line for TX ===== */ + int sk_wmem_queued; + atomic_t sk_wmem_alloc; + unsigned long sk_tsq_flags; + struct sk_buff *sk_send_head; struct sk_buff_head sk_write_queue; + __s32 sk_peek_off; + int sk_write_pending; + long sk_sndtimeo; + struct timer_list sk_timer; + __u32 sk_priority; + __u32 sk_mark; + u32 sk_pacing_rate; /* bytes per second */ + u32 sk_max_pacing_rate; + struct page_frag sk_frag; + netdev_features_t sk_route_caps; + netdev_features_t sk_route_nocaps; + int sk_gso_type; + unsigned int sk_gso_max_size; + gfp_t sk_allocation; + __u32 sk_txhash; /* * Because of non atomicity rules, all * changes are protected by socket lock. */ + unsigned int __sk_flags_offset[0]; +#ifdef __BIG_ENDIAN_BITFIELD +#define SK_FL_PROTO_SHIFT 16 +#define SK_FL_PROTO_MASK 0x00ff0000 + +#define SK_FL_TYPE_SHIFT 0 +#define SK_FL_TYPE_MASK 0x0000ffff +#else +#define SK_FL_PROTO_SHIFT 8 +#define SK_FL_PROTO_MASK 0x0000ff00 + +#define SK_FL_TYPE_SHIFT 16 +#define SK_FL_TYPE_MASK 0xffff0000 +#endif + kmemcheck_bitfield_begin(flags); unsigned int sk_padding : 2, sk_no_check_tx : 1, @@ -397,41 +435,24 @@ struct sock { #define SK_PROTOCOL_MAX U8_MAX kmemcheck_bitfield_end(flags); - int sk_wmem_queued; - gfp_t sk_allocation; - u32 sk_pacing_rate; /* bytes per second */ - u32 sk_max_pacing_rate; - netdev_features_t sk_route_caps; - netdev_features_t sk_route_nocaps; - int sk_gso_type; - unsigned int sk_gso_max_size; u16 sk_gso_max_segs; - int sk_rcvlowat; unsigned long sk_lingertime; - struct sk_buff_head sk_error_queue; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; int sk_err, sk_err_soft; u32 sk_ack_backlog; u32 sk_max_ack_backlog; - __u32 sk_priority; - __u32 sk_mark; + kuid_t sk_uid; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; - long sk_sndtimeo; - struct timer_list sk_timer; ktime_t sk_stamp; u16 sk_tsflags; u8 sk_shutdown; u32 sk_tskey; struct socket *sk_socket; void *sk_user_data; - struct page_frag sk_frag; - struct sk_buff *sk_send_head; - __s32 sk_peek_off; - int sk_write_pending; #ifdef CONFIG_SECURITY void *sk_security; #endif @@ -892,7 +913,20 @@ static inline void sock_rps_record_flow_hash(__u32 hash) static inline void sock_rps_record_flow(const struct sock *sk) { #ifdef CONFIG_RPS - sock_rps_record_flow_hash(sk->sk_rxhash); + if (static_key_false(&rfs_needed)) { + /* Reading sk->sk_rxhash might incur an expensive cache line + * miss. + * + * TCP_ESTABLISHED does cover almost all states where RFS + * might be useful, and is cheaper [1] than testing : + * IPv4: inet_sk(sk)->inet_daddr + * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) + * OR an additional socket flag + * [1] : sk_state and sk_prot are in the same cache line. + */ + if (sk->sk_state == TCP_ESTABLISHED) + sock_rps_record_flow_hash(sk->sk_rxhash); + } #endif } @@ -912,14 +946,16 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) #endif } -#define sk_wait_event(__sk, __timeo, __condition) \ +#define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ - *(__timeo) = schedule_timeout(*(__timeo)); \ + *(__timeo) = wait_woken(__wait, \ + TASK_INTERRUPTIBLE, \ + *(__timeo)); \ } \ - sched_annotate_sleep(); \ + sched_annotate_sleep(); \ lock_sock(__sk); \ __rc = __condition; \ __rc; \ @@ -1020,7 +1056,6 @@ struct proto { void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); - void (*clear_sk)(struct sock *sk, int size); /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS @@ -1114,6 +1149,16 @@ static inline bool sk_stream_is_writeable(const struct sock *sk) sk_stream_memory_free(sk); } +static inline int sk_under_cgroup_hierarchy(struct sock *sk, + struct cgroup *ancestor) +{ +#ifdef CONFIG_SOCK_CGROUP_DATA + return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), + ancestor); +#else + return -ENOTSUPP; +#endif +} static inline bool sk_has_memory_pressure(const struct sock *sk) { @@ -1151,11 +1196,6 @@ static inline void sk_enter_memory_pressure(struct sock *sk) sk->sk_prot->enter_memory_pressure(sk); } -static inline long sk_prot_mem_limits(const struct sock *sk, int index) -{ - return sk->sk_prot->sysctl_mem[index]; -} - static inline long sk_memory_allocated(const struct sock *sk) { @@ -1232,8 +1272,6 @@ static inline int __sk_prot_rehash(struct sock *sk) return sk->sk_prot->hash(sk); } -void sk_prot_clear_portaddr_nulls(struct sock *sk, int size); - /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) @@ -1267,14 +1305,32 @@ static inline struct inode *SOCK_INODE(struct socket *socket) /* * Functions for memory accounting */ +int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind); int __sk_mem_schedule(struct sock *sk, int size, int kind); +void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); -#define SK_MEM_QUANTUM ((int)PAGE_SIZE) +/* We used to have PAGE_SIZE here, but systems with 64KB pages + * do not necessarily have 16x time more memory than 4KB ones. + */ +#define SK_MEM_QUANTUM 4096 #define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 +/* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ +static inline long sk_prot_mem_limits(const struct sock *sk, int index) +{ + long val = sk->sk_prot->sysctl_mem[index]; + +#if PAGE_SIZE > SK_MEM_QUANTUM + val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; +#elif PAGE_SIZE < SK_MEM_QUANTUM + val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT; +#endif + return val; +} + static inline int sk_mem_pages(int amt) { return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT; @@ -1587,11 +1643,11 @@ static inline void sock_put(struct sock *sk) void sock_gen_put(struct sock *sk); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, - unsigned int trim_cap); + unsigned int trim_cap, bool refcounted); static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) { - return __sk_receive_skb(sk, skb, nested, 1); + return __sk_receive_skb(sk, skb, nested, 1, true); } static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) @@ -1642,6 +1698,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) sk->sk_wq = parent->wq; parent->sk = sk; sk_set_socket(sk, parent); + sk->sk_uid = SOCK_INODE(parent)->i_uid; security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } @@ -1649,6 +1706,11 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) kuid_t sock_i_uid(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); +static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) +{ + return sk ? sk->sk_uid : make_kuid(net->user_ns, 0); +} + static inline u32 net_tx_rndhash(void) { u32 v = prandom_u32(); @@ -1774,13 +1836,13 @@ static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, { if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; - if (csum_and_copy_from_iter(to, copy, &csum, from) != copy) + if (!csum_and_copy_from_iter_full(to, copy, &csum, from)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, offset); } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { - if (copy_from_iter_nocache(to, copy, from) != copy) + if (!copy_from_iter_full_nocache(to, copy, from)) return -EFAULT; - } else if (copy_from_iter(to, copy, from) != copy) + } else if (!copy_from_iter_full(to, copy, from)) return -EFAULT; return 0; @@ -1943,6 +2005,8 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer, void sk_stop_timer(struct sock *sk, struct timer_list *timer); +int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, + unsigned int flags); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); @@ -2099,7 +2163,8 @@ struct sock_skb_cb { static inline void sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) { - SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops); + SOCK_SKB_CB(skb)->dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ? + atomic_read(&sk->sk_drops) : 0; } static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb) @@ -2128,8 +2193,8 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) */ if (sock_flag(sk, SOCK_RCVTSTAMP) || (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || - (kt.tv64 && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) || - (hwtstamps->hwtstamp.tv64 && + (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) || + (hwtstamps->hwtstamp && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else diff --git a/include/net/strparser.h b/include/net/strparser.h new file mode 100644 index 000000000000..0c28ad97c52f --- /dev/null +++ b/include/net/strparser.h @@ -0,0 +1,142 @@ +/* + * Stream Parser + * + * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#ifndef __NET_STRPARSER_H_ +#define __NET_STRPARSER_H_ + +#include <linux/skbuff.h> +#include <net/sock.h> + +#define STRP_STATS_ADD(stat, count) ((stat) += (count)) +#define STRP_STATS_INCR(stat) ((stat)++) + +struct strp_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned int rx_mem_fail; + unsigned int rx_need_more_hdr; + unsigned int rx_msg_too_big; + unsigned int rx_msg_timeouts; + unsigned int rx_bad_hdr_len; +}; + +struct strp_aggr_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned int rx_mem_fail; + unsigned int rx_need_more_hdr; + unsigned int rx_msg_too_big; + unsigned int rx_msg_timeouts; + unsigned int rx_bad_hdr_len; + unsigned int rx_aborts; + unsigned int rx_interrupted; + unsigned int rx_unrecov_intr; +}; + +struct strparser; + +/* Callbacks are called with lock held for the attached socket */ +struct strp_callbacks { + int (*parse_msg)(struct strparser *strp, struct sk_buff *skb); + void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb); + int (*read_sock_done)(struct strparser *strp, int err); + void (*abort_parser)(struct strparser *strp, int err); +}; + +struct strp_rx_msg { + int full_len; + int offset; +}; + +static inline struct strp_rx_msg *strp_rx_msg(struct sk_buff *skb) +{ + return (struct strp_rx_msg *)((void *)skb->cb + + offsetof(struct qdisc_skb_cb, data)); +} + +/* Structure for an attached lower socket */ +struct strparser { + struct sock *sk; + + u32 rx_stopped : 1; + u32 rx_paused : 1; + u32 rx_aborted : 1; + u32 rx_interrupted : 1; + u32 rx_unrecov_intr : 1; + + struct sk_buff **rx_skb_nextp; + struct timer_list rx_msg_timer; + struct sk_buff *rx_skb_head; + unsigned int rx_need_bytes; + struct delayed_work rx_delayed_work; + struct work_struct rx_work; + struct strp_stats stats; + struct strp_callbacks cb; +}; + +/* Must be called with lock held for attached socket */ +static inline void strp_pause(struct strparser *strp) +{ + strp->rx_paused = 1; +} + +/* May be called without holding lock for attached socket */ +void strp_unpause(struct strparser *strp); + +static inline void save_strp_stats(struct strparser *strp, + struct strp_aggr_stats *agg_stats) +{ + /* Save psock statistics in the mux when psock is being unattached. */ + +#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += \ + strp->stats._stat) + SAVE_PSOCK_STATS(rx_msgs); + SAVE_PSOCK_STATS(rx_bytes); + SAVE_PSOCK_STATS(rx_mem_fail); + SAVE_PSOCK_STATS(rx_need_more_hdr); + SAVE_PSOCK_STATS(rx_msg_too_big); + SAVE_PSOCK_STATS(rx_msg_timeouts); + SAVE_PSOCK_STATS(rx_bad_hdr_len); +#undef SAVE_PSOCK_STATS + + if (strp->rx_aborted) + agg_stats->rx_aborts++; + if (strp->rx_interrupted) + agg_stats->rx_interrupted++; + if (strp->rx_unrecov_intr) + agg_stats->rx_unrecov_intr++; +} + +static inline void aggregate_strp_stats(struct strp_aggr_stats *stats, + struct strp_aggr_stats *agg_stats) +{ +#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat) + SAVE_PSOCK_STATS(rx_msgs); + SAVE_PSOCK_STATS(rx_bytes); + SAVE_PSOCK_STATS(rx_mem_fail); + SAVE_PSOCK_STATS(rx_need_more_hdr); + SAVE_PSOCK_STATS(rx_msg_too_big); + SAVE_PSOCK_STATS(rx_msg_timeouts); + SAVE_PSOCK_STATS(rx_bad_hdr_len); + SAVE_PSOCK_STATS(rx_aborts); + SAVE_PSOCK_STATS(rx_interrupted); + SAVE_PSOCK_STATS(rx_unrecov_intr); +#undef SAVE_PSOCK_STATS + +} + +void strp_done(struct strparser *strp); +void strp_stop(struct strparser *strp); +void strp_check_rcv(struct strparser *strp); +int strp_init(struct strparser *strp, struct sock *csk, + struct strp_callbacks *cb); +void strp_data_ready(struct strparser *strp); + +#endif /* __NET_STRPARSER_H_ */ diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 62f6a967a1b7..eba80c4fc56f 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -68,7 +68,6 @@ struct switchdev_attr { enum switchdev_obj_id { SWITCHDEV_OBJ_ID_UNDEFINED, SWITCHDEV_OBJ_ID_PORT_VLAN, - SWITCHDEV_OBJ_ID_IPV4_FIB, SWITCHDEV_OBJ_ID_PORT_FDB, SWITCHDEV_OBJ_ID_PORT_MDB, }; @@ -92,21 +91,6 @@ struct switchdev_obj_port_vlan { #define SWITCHDEV_OBJ_PORT_VLAN(obj) \ container_of(obj, struct switchdev_obj_port_vlan, obj) -/* SWITCHDEV_OBJ_ID_IPV4_FIB */ -struct switchdev_obj_ipv4_fib { - struct switchdev_obj obj; - u32 dst; - int dst_len; - struct fib_info *fi; - u8 tos; - u8 type; - u32 nlflags; - u32 tb_id; -}; - -#define SWITCHDEV_OBJ_IPV4_FIB(obj) \ - container_of(obj, struct switchdev_obj_ipv4_fib, obj) - /* SWITCHDEV_OBJ_ID_PORT_FDB */ struct switchdev_obj_port_fdb { struct switchdev_obj obj; @@ -209,11 +193,6 @@ int switchdev_port_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); int switchdev_port_bridge_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); -int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 nlflags, u32 tb_id); -int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id); -void switchdev_fib_ipv4_abort(struct fib_info *fi); int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlm_flags); @@ -222,7 +201,7 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], u16 vid); int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, - struct net_device *filter_dev, int idx); + struct net_device *filter_dev, int *idx); void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); @@ -304,25 +283,6 @@ static inline int switchdev_port_bridge_dellink(struct net_device *dev, return -EOPNOTSUPP; } -static inline int switchdev_fib_ipv4_add(u32 dst, int dst_len, - struct fib_info *fi, - u8 tos, u8 type, - u32 nlflags, u32 tb_id) -{ - return 0; -} - -static inline int switchdev_fib_ipv4_del(u32 dst, int dst_len, - struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) -{ - return 0; -} - -static inline void switchdev_fib_ipv4_abort(struct fib_info *fi) -{ -} - static inline int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, @@ -342,15 +302,9 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, - int idx) -{ - return idx; -} - -static inline void switchdev_port_fwd_mark_set(struct net_device *dev, - struct net_device *group_dev, - bool joining) + int *idx) { + return *idx; } static inline bool switchdev_port_same_parent_id(struct net_device *a, diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index 5164bd7a38fb..9fd2bea0a6e0 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -50,9 +50,11 @@ int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp); int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp); int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi); +int ife_check_meta_u16(u16 metaval, struct tcf_meta_info *mi); int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi); int ife_validate_meta_u32(void *val, int len); int ife_validate_meta_u16(void *val, int len); +int ife_encode_meta_u16(u16 metaval, void *skbdata, struct tcf_meta_info *mi); void ife_release_meta_gen(struct tcf_meta_info *mi); int register_ife_op(struct tcf_meta_ops *mops); int unregister_ife_op(struct tcf_meta_ops *mops); diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 62770add15bd..604bc31e23ab 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -8,13 +8,13 @@ struct tcf_mirred { struct tc_action common; int tcfm_eaction; int tcfm_ifindex; - int tcfm_ok_push; + bool tcfm_mac_header_xmit; struct net_device __rcu *tcfm_dev; struct list_head tcfm_list; }; #define to_mirred(a) ((struct tcf_mirred *)a) -static inline bool is_tcf_mirred_redirect(const struct tc_action *a) +static inline bool is_tcf_mirred_egress_redirect(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->type == TCA_ACT_MIRRED) @@ -23,7 +23,7 @@ static inline bool is_tcf_mirred_redirect(const struct tc_action *a) return false; } -static inline bool is_tcf_mirred_mirror(const struct tc_action *a) +static inline bool is_tcf_mirred_egress_mirror(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->type == TCA_ACT_MIRRED) diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 5767e9dbcf92..19cd3d345804 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -27,6 +27,7 @@ struct tcf_skbedit { u32 flags; u32 priority; u32 mark; + u32 mask; u16 queue_mapping; u16 ptype; }; diff --git a/include/net/tc_act/tc_skbmod.h b/include/net/tc_act/tc_skbmod.h new file mode 100644 index 000000000000..644a2116b47b --- /dev/null +++ b/include/net/tc_act/tc_skbmod.h @@ -0,0 +1,30 @@ +/* + * Copyright (c) 2016, Jamal Hadi Salim + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. +*/ + +#ifndef __NET_TC_SKBMOD_H +#define __NET_TC_SKBMOD_H + +#include <net/act_api.h> +#include <linux/tc_act/tc_skbmod.h> + +struct tcf_skbmod_params { + struct rcu_head rcu; + u64 flags; /*up to 64 types of operations; extend if needed */ + u8 eth_dst[ETH_ALEN]; + u16 eth_type; + u8 eth_src[ETH_ALEN]; +}; + +struct tcf_skbmod { + struct tc_action common; + struct tcf_skbmod_params __rcu *skbmod_p; +}; +#define to_skbmod(a) ((struct tcf_skbmod *)a) + +#endif /* __NET_TC_SKBMOD_H */ diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h new file mode 100644 index 000000000000..efef0b4b1b2b --- /dev/null +++ b/include/net/tc_act/tc_tunnel_key.h @@ -0,0 +1,67 @@ +/* + * Copyright (c) 2016, Amir Vadai <amir@vadai.me> + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __NET_TC_TUNNEL_KEY_H +#define __NET_TC_TUNNEL_KEY_H + +#include <net/act_api.h> +#include <linux/tc_act/tc_tunnel_key.h> +#include <net/dst_metadata.h> + +struct tcf_tunnel_key_params { + struct rcu_head rcu; + int tcft_action; + int action; + struct metadata_dst *tcft_enc_metadata; +}; + +struct tcf_tunnel_key { + struct tc_action common; + struct tcf_tunnel_key_params __rcu *params; +}; + +#define to_tunnel_key(a) ((struct tcf_tunnel_key *)a) + +static inline bool is_tcf_tunnel_set(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + struct tcf_tunnel_key *t = to_tunnel_key(a); + struct tcf_tunnel_key_params *params = rtnl_dereference(t->params); + + if (a->ops && a->ops->type == TCA_ACT_TUNNEL_KEY) + return params->tcft_action == TCA_TUNNEL_KEY_ACT_SET; +#endif + return false; +} + +static inline bool is_tcf_tunnel_release(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + struct tcf_tunnel_key *t = to_tunnel_key(a); + struct tcf_tunnel_key_params *params = rtnl_dereference(t->params); + + if (a->ops && a->ops->type == TCA_ACT_TUNNEL_KEY) + return params->tcft_action == TCA_TUNNEL_KEY_ACT_RELEASE; +#endif + return false; +} + +static inline struct ip_tunnel_info *tcf_tunnel_info(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + struct tcf_tunnel_key *t = to_tunnel_key(a); + struct tcf_tunnel_key_params *params = rtnl_dereference(t->params); + + return ¶ms->tcft_enc_metadata->u.tun_info; +#else + return NULL; +#endif +} +#endif /* __NET_TC_TUNNEL_KEY_H */ diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index e29f52e8bdf1..48cca321ee6c 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -11,6 +11,7 @@ #define __NET_TC_VLAN_H #include <net/act_api.h> +#include <linux/tc_act/tc_vlan.h> #define VLAN_F_POP 0x1 #define VLAN_F_PUSH 0x2 @@ -20,7 +21,32 @@ struct tcf_vlan { int tcfv_action; u16 tcfv_push_vid; __be16 tcfv_push_proto; + u8 tcfv_push_prio; }; #define to_vlan(a) ((struct tcf_vlan *)a) +static inline bool is_tcf_vlan(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->type == TCA_ACT_VLAN) + return true; +#endif + return false; +} + +static inline u32 tcf_vlan_action(const struct tc_action *a) +{ + return to_vlan(a)->tcfv_action; +} + +static inline u16 tcf_vlan_push_vid(const struct tc_action *a) +{ + return to_vlan(a)->tcfv_push_vid; +} + +static inline __be16 tcf_vlan_push_proto(const struct tc_action *a) +{ + return to_vlan(a)->tcfv_push_proto; +} + #endif /* __NET_TC_VLAN_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 7717302cab91..6061963cca98 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -227,10 +227,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TFO_SERVER_COOKIE_NOT_REQD 0x200 /* Force enable TFO on all listeners, i.e., not requiring the - * TCP_FASTOPEN socket option. SOCKOPT1/2 determine how to set max_qlen. + * TCP_FASTOPEN socket option. */ #define TFO_SERVER_WO_SOCKOPT1 0x400 -#define TFO_SERVER_WO_SOCKOPT2 0x800 extern struct inet_timewait_death_row tcp_death_row; @@ -253,7 +252,6 @@ extern int sysctl_tcp_wmem[3]; extern int sysctl_tcp_rmem[3]; extern int sysctl_tcp_app_win; extern int sysctl_tcp_adv_win_scale; -extern int sysctl_tcp_tw_reuse; extern int sysctl_tcp_frto; extern int sysctl_tcp_low_latency; extern int sysctl_tcp_nometrics_save; @@ -534,6 +532,8 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ +u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, + int min_tso_segs); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); bool tcp_may_send_now(struct sock *sk); @@ -604,8 +604,6 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ -typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, - unsigned int, size_t); int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); @@ -643,7 +641,7 @@ static inline void tcp_fast_path_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - if (skb_queue_empty(&tp->out_of_order_queue) && + if (RB_EMPTY_ROOT(&tp->out_of_order_queue) && tp->rcv_wnd && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && !tp->urg_data) @@ -674,7 +672,7 @@ static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) /* Minimum RTT in usec. ~0 means not available. */ static inline u32 tcp_min_rtt(const struct tcp_sock *tp) { - return tp->rtt_min[0].rtt; + return minmax_get(&tp->rtt_min); } /* Compute the actual receive window we are currently advertising. @@ -766,8 +764,16 @@ struct tcp_skb_cb { __u32 ack_seq; /* Sequence number ACK'd */ union { struct { - /* There is space for up to 20 bytes */ - __u32 in_flight;/* Bytes in flight when packet sent */ + /* There is space for up to 24 bytes */ + __u32 in_flight:30,/* Bytes in flight at transmit */ + is_app_limited:1, /* cwnd not fully used? */ + unused:1; + /* pkts S/ACKed so far upon tx of skb, incl retrans: */ + __u32 delivered; + /* start of send pipeline phase */ + struct skb_mstamp first_tx_mstamp; + /* when we reached the "delivered" count */ + struct skb_mstamp delivered_mstamp; } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; @@ -787,12 +793,23 @@ struct tcp_skb_cb { */ static inline int tcp_v6_iif(const struct sk_buff *skb) { - bool l3_slave = skb_l3mdev_slave(TCP_SKB_CB(skb)->header.h6.flags); + bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; } #endif +/* TCP_SKB_CB reference means this can not be used from early demux */ +static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (!net->ipv4.sysctl_tcp_l3mdev_accept && + skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags)) + return true; +#endif + return false; +} + /* Due to TSO, an SKB can be composed of multiple actual * packets. To keep these tracked properly, we use this. */ @@ -863,6 +880,27 @@ struct ack_sample { u32 in_flight; }; +/* A rate sample measures the number of (original/retransmitted) data + * packets delivered "delivered" over an interval of time "interval_us". + * The tcp_rate.c code fills in the rate sample, and congestion + * control modules that define a cong_control function to run at the end + * of ACK processing can optionally chose to consult this sample when + * setting cwnd and pacing rate. + * A sample is invalid if "delivered" or "interval_us" is negative. + */ +struct rate_sample { + struct skb_mstamp prior_mstamp; /* starting timestamp for interval */ + u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ + s32 delivered; /* number of packets delivered over interval */ + long interval_us; /* time for tp->delivered to incr "delivered" */ + long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ + int losses; /* number of packets marked lost upon ACK */ + u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ + u32 prior_in_flight; /* in flight before this ACK */ + bool is_app_limited; /* is sample from packet with bubble in pipe? */ + bool is_retrans; /* is sample from retransmission? */ +}; + struct tcp_congestion_ops { struct list_head list; u32 key; @@ -887,6 +925,14 @@ struct tcp_congestion_ops { u32 (*undo_cwnd)(struct sock *sk); /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); + /* suggest number of segments for each skb to transmit (optional) */ + u32 (*tso_segs_goal)(struct sock *sk); + /* returns the multiplier used in tcp_sndbuf_expand (optional) */ + u32 (*sndbuf_expand)(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, const struct rate_sample *rs); /* get info for inet_diag (optional) */ size_t (*get_info)(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info); @@ -911,6 +957,7 @@ u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); u32 tcp_reno_ssthresh(struct sock *sk); +u32 tcp_reno_undo_cwnd(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); extern struct tcp_congestion_ops tcp_reno; @@ -949,6 +996,14 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) icsk->icsk_ca_ops->cwnd_event(sk, event); } +/* From tcp_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, + struct skb_mstamp *now, struct rate_sample *rs); +void tcp_rate_check_app_limited(struct sock *sk); + /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. @@ -1164,6 +1219,8 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp) } bool tcp_prequeue(struct sock *sk, struct sk_buff *skb); +bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); +int tcp_filter(struct sock *sk, struct sk_buff *skb); #undef STATE_TRACE @@ -1458,11 +1515,26 @@ struct tcp_fastopen_context { struct rcu_head rcu; }; +/* Latencies incurred by various limits for a sender. They are + * chronograph-like stats that are mutually exclusive. + */ +enum tcp_chrono { + TCP_CHRONO_UNSPEC, + TCP_CHRONO_BUSY, /* Actively sending data (non-empty write queue) */ + TCP_CHRONO_RWND_LIMITED, /* Stalled by insufficient receive window */ + TCP_CHRONO_SNDBUF_LIMITED, /* Stalled by insufficient send buffer */ + __TCP_CHRONO_MAX, +}; + +void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type); +void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type); + /* write queue abstraction */ static inline void tcp_write_queue_purge(struct sock *sk) { struct sk_buff *skb; + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) sk_wmem_free_skb(sk, skb); sk_mem_reclaim(sk); @@ -1521,8 +1593,10 @@ static inline void tcp_advance_send_head(struct sock *sk, const struct sk_buff * static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked) { - if (sk->sk_send_head == skb_unlinked) + if (sk->sk_send_head == skb_unlinked) { sk->sk_send_head = NULL; + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); + } if (tcp_sk(sk)->highest_sack == skb_unlinked) tcp_sk(sk)->highest_sack = NULL; } @@ -1544,6 +1618,7 @@ static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb /* Queue it, remembering where we must start sending. */ if (sk->sk_send_head == NULL) { sk->sk_send_head = skb; + tcp_chrono_start(sk, TCP_CHRONO_BUSY); if (tcp_sk(sk)->highest_sack == NULL) tcp_sk(sk)->highest_sack = skb; @@ -1751,7 +1826,7 @@ struct tcp_request_sock_ops { struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, const struct request_sock *req, bool *strict); - __u32 (*init_seq)(const struct sk_buff *skb); + __u32 (*init_seq)(const struct sk_buff *skb, u32 *tsoff); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, @@ -1853,6 +1928,8 @@ static inline int tcp_inq(struct sock *sk) return answ; } +int tcp_peek_len(struct socket *sock); + static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) { u16 segs_in; diff --git a/include/net/udp.h b/include/net/udp.h index 8894d7144189..1661791e8ca1 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -246,17 +246,39 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, } /* net/ipv4/udp.c */ +void udp_destruct_sock(struct sock *sk); +void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); +int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); +void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); +static inline struct sk_buff * +__skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *peeked, + int *off, int *err) +{ + return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), + udp_skb_destructor, peeked, off, err); +} +static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, + int noblock, int *err) +{ + int peeked, off = 0; + + return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err); +} + void udp_v4_early_demux(struct sk_buff *skb); int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, const struct sock *)); void udp_err(struct sk_buff *, u32); +int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); int udp_rcv(struct sk_buff *skb); int udp_ioctl(struct sock *sk, int cmd, unsigned long arg); +int udp_init_sock(struct sock *sk); +int __udp_disconnect(struct sock *sk, int flags); int udp_disconnect(struct sock *sk, int flags); unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait); struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, diff --git a/include/net/udplite.h b/include/net/udplite.h index 80761938b9a7..ea340524f99b 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -20,13 +20,14 @@ static __inline__ int udplite_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct msghdr *msg = from; - return copy_from_iter(to, len, &msg->msg_iter) != len ? -EFAULT : 0; + return copy_from_iter_full(to, len, &msg->msg_iter) ? 0 : -EFAULT; } /* Designate sk as UDP-Lite socket */ static inline int udplite_sk_init(struct sock *sk) { udp_sk(sk)->pcflag = UDPLITE_BIT; + sk->sk_destruct = udp_destruct_sock; return 0; } diff --git a/include/net/vxlan.h b/include/net/vxlan.h index b96d0360c095..49a59202f85e 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -225,9 +225,9 @@ struct vxlan_config { struct vxlan_dev { struct hlist_node hlist; /* vni hash table */ struct list_head next; /* vxlan's per namespace list */ - struct vxlan_sock *vn4_sock; /* listening socket for IPv4 */ + struct vxlan_sock __rcu *vn4_sock; /* listening socket for IPv4 */ #if IS_ENABLED(CONFIG_IPV6) - struct vxlan_sock *vn6_sock; /* listening socket for IPv6 */ + struct vxlan_sock __rcu *vn6_sock; /* listening socket for IPv6 */ #endif struct net_device *dev; struct net *net; /* netns for packet i/o */ @@ -281,16 +281,6 @@ struct vxlan_dev { struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf); -static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan, - unsigned short family) -{ -#if IS_ENABLED(CONFIG_IPV6) - if (family == AF_INET6) - return inet_sk(vxlan->vn6_sock->sock->sk)->inet_sport; -#endif - return inet_sk(vxlan->vn4_sock->sock->sk)->inet_sport; -} - static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, netdev_features_t features) { @@ -350,24 +340,6 @@ static inline __be32 vxlan_vni_field(__be32 vni) #endif } -static inline __be32 vxlan_tun_id_to_vni(__be64 tun_id) -{ -#if defined(__BIG_ENDIAN) - return (__force __be32)tun_id; -#else - return (__force __be32)((__force u64)tun_id >> 32); -#endif -} - -static inline __be64 vxlan_vni_to_tun_id(__be32 vni) -{ -#if defined(__BIG_ENDIAN) - return (__force __be64)vni; -#else - return (__force __be64)((u64)(__force u32)vni << 32); -#endif -} - static inline size_t vxlan_rco_start(__be32 vni_field) { return be32_to_cpu(vni_field & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 17934312eecb..31947b9c21d6 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -187,7 +187,7 @@ struct xfrm_state { struct xfrm_replay_state_esn *preplay_esn; /* The functions for replay detection. */ - struct xfrm_replay *repl; + const struct xfrm_replay *repl; /* internal flag that only holds state for delayed aevent at the * moment |