From 03dd4cb26d967f9588437b0fc9cc0e8353322bb7 Mon Sep 17 00:00:00 2001 From: André Fabian Silva Delgado Date: Fri, 25 Mar 2016 03:53:42 -0300 Subject: Linux-libre 4.5-gnu --- include/net/6lowpan.h | 10 +- include/net/addrconf.h | 3 +- include/net/bluetooth/bluetooth.h | 25 ++-- include/net/bluetooth/hci.h | 4 +- include/net/bluetooth/hci_core.h | 62 ++++++--- include/net/bluetooth/hci_mon.h | 2 + include/net/bluetooth/hci_sock.h | 1 + include/net/bluetooth/l2cap.h | 6 + include/net/bluetooth/mgmt.h | 15 +++ include/net/bonding.h | 39 +++++- include/net/busy_poll.h | 45 +------ include/net/cfg80211.h | 10 +- include/net/checksum.h | 3 +- include/net/cls_cgroup.h | 11 +- include/net/dsa.h | 20 ++- include/net/genetlink.h | 2 + include/net/geneve.h | 8 ++ include/net/ieee802154_netdev.h | 2 +- include/net/ila.h | 18 +++ include/net/inet_frag.h | 1 - include/net/inet_sock.h | 14 ++ include/net/ip6_tunnel.h | 19 +-- include/net/ip_fib.h | 3 +- include/net/ip_tunnels.h | 29 ++-- include/net/ipv6.h | 15 +++ include/net/iw_handler.h | 6 + include/net/l3mdev.h | 23 ++++ include/net/mac80211.h | 56 ++++++++ include/net/net_namespace.h | 3 + include/net/netfilter/ipv6/nf_defrag_ipv6.h | 3 +- include/net/netfilter/nf_conntrack_core.h | 8 +- include/net/netfilter/nf_conntrack_timeout.h | 2 +- include/net/netfilter/nf_dup_netdev.h | 6 + include/net/netfilter/nf_tables.h | 45 ++++++- include/net/netfilter/nf_tables_core.h | 10 ++ include/net/netfilter/nft_meta.h | 3 + include/net/netns/ipv4.h | 7 + include/net/netns/sctp.h | 7 + include/net/netprio_cgroup.h | 16 ++- include/net/nfc/nfc.h | 1 + include/net/protocol.h | 2 +- include/net/request_sock.h | 2 +- include/net/sch_generic.h | 9 ++ include/net/sctp/sctp.h | 32 ++--- include/net/sctp/structs.h | 15 +-- include/net/sock.h | 194 +++++---------------------- include/net/sock_reuseport.h | 28 ++++ include/net/switchdev.h | 15 +++ include/net/tcp.h | 36 +++-- include/net/tcp_memcontrol.h | 7 - include/net/udp.h | 7 +- include/net/udp_tunnel.h | 8 +- include/net/vxlan.h | 2 +- 53 files changed, 559 insertions(+), 361 deletions(-) create mode 100644 include/net/ila.h create mode 100644 include/net/netfilter/nf_dup_netdev.h create mode 100644 include/net/sock_reuseport.h delete mode 100644 include/net/tcp_memcontrol.h (limited to 'include/net') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index cf3bc564a..2f6a3f223 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -53,6 +53,8 @@ #ifndef __6LOWPAN_H__ #define __6LOWPAN_H__ +#include + #include #include @@ -98,6 +100,7 @@ enum lowpan_lltypes { struct lowpan_priv { enum lowpan_lltypes lltype; + struct dentry *iface_debugfs; /* must be last */ u8 priv[0] __aligned(sizeof(void *)); @@ -185,7 +188,12 @@ static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, *hc_ptr += len; } -void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype); +int lowpan_register_netdevice(struct net_device *dev, + enum lowpan_lltypes lltype); +int lowpan_register_netdev(struct net_device *dev, + enum lowpan_lltypes lltype); +void lowpan_unregister_netdevice(struct net_device *dev); +void lowpan_unregister_netdev(struct net_device *dev); /** * lowpan_header_decompress - replace 6LoWPAN header with IPv6 header diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 78003dfb8..47f52d3cd 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -87,7 +87,8 @@ int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, u32 banned_flags); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags); -int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2); +int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, + bool match_wildcard); void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr); diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 42844d7b1..bfd159082 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -29,6 +29,8 @@ #include #include +#define BT_SUBSYS_VERSION "2.21" + #ifndef AF_BLUETOOTH #define AF_BLUETOOTH 31 #define PF_BLUETOOTH AF_BLUETOOTH @@ -296,12 +298,17 @@ typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); typedef void (*hci_req_complete_skb_t)(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb); +#define HCI_REQ_START BIT(0) +#define HCI_REQ_SKB BIT(1) + struct hci_ctrl { __u16 opcode; - bool req_start; + u8 req_flags; u8 req_event; - hci_req_complete_t req_complete; - hci_req_complete_skb_t req_complete_skb; + union { + hci_req_complete_t req_complete; + hci_req_complete_skb_t req_complete_skb; + }; }; struct bt_skb_cb { @@ -316,15 +323,17 @@ struct bt_skb_cb { }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) +#define hci_skb_pkt_type(skb) bt_cb((skb))->pkt_type +#define hci_skb_expect(skb) bt_cb((skb))->expect +#define hci_skb_opcode(skb) bt_cb((skb))->hci.opcode + static inline struct sk_buff *bt_skb_alloc(unsigned int len, gfp_t how) { struct sk_buff *skb; skb = alloc_skb(len + BT_SKB_RESERVE, how); - if (skb) { + if (skb) skb_reserve(skb, BT_SKB_RESERVE); - bt_cb(skb)->incoming = 0; - } return skb; } @@ -334,10 +343,8 @@ static inline struct sk_buff *bt_skb_send_alloc(struct sock *sk, struct sk_buff *skb; skb = sock_alloc_send_skb(sk, len + BT_SKB_RESERVE, nb, err); - if (skb) { + if (skb) skb_reserve(skb, BT_SKB_RESERVE); - bt_cb(skb)->incoming = 0; - } if (!skb && *err) return NULL; diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 0205b80cc..339ea57be 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -239,7 +239,6 @@ enum { HCI_LE_ENABLED, HCI_ADVERTISING, HCI_ADVERTISING_CONNECTABLE, - HCI_ADVERTISING_INSTANCE, HCI_CONNECTABLE, HCI_DISCOVERABLE, HCI_LIMITED_DISCOVERABLE, @@ -452,7 +451,8 @@ enum { #define HCI_ERROR_REMOTE_POWER_OFF 0x15 #define HCI_ERROR_LOCAL_HOST_TERM 0x16 #define HCI_ERROR_PAIRING_NOT_ALLOWED 0x18 -#define HCI_ERROR_INVALID_LL_PARAMS 0x1E +#define HCI_ERROR_INVALID_LL_PARAMS 0x1e +#define HCI_ERROR_UNSPECIFIED 0x1f #define HCI_ERROR_ADVERTISING_TIMEOUT 0x3c /* Flow control modes */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 1878d0a96..d4f82edb5 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -77,6 +77,7 @@ struct discovery_state { u8 last_adv_data_len; bool report_invalid_rssi; bool result_filtering; + bool limited; s8 rssi; u16 uuid_count; u8 (*uuids)[16]; @@ -327,6 +328,14 @@ struct hci_dev { struct work_struct cmd_work; struct work_struct tx_work; + struct work_struct discov_update; + struct work_struct bg_scan_update; + struct work_struct scan_update; + struct work_struct connectable_update; + struct work_struct discoverable_update; + struct delayed_work le_scan_disable; + struct delayed_work le_scan_restart; + struct sk_buff_head rx_q; struct sk_buff_head raw_q; struct sk_buff_head cmd_q; @@ -370,9 +379,6 @@ struct hci_dev { DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); - struct delayed_work le_scan_disable; - struct delayed_work le_scan_restart; - __s8 adv_tx_power; __u8 adv_data[HCI_MAX_AD_LENGTH]; __u8 adv_data_len; @@ -875,7 +881,7 @@ struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle); struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, - u16 conn_timeout, u8 role); + u16 conn_timeout); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, u16 conn_timeout, u8 role); @@ -1036,7 +1042,6 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); -void hci_conn_params_clear_all(struct hci_dev *hdev); void hci_conn_params_clear_disabled(struct hci_dev *hdev); struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, @@ -1279,31 +1284,41 @@ static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, mutex_unlock(&hci_cb_list_lock); } -static inline bool eir_has_data_type(u8 *data, size_t data_len, u8 type) +static inline void *eir_get_data(u8 *eir, size_t eir_len, u8 type, + size_t *data_len) { size_t parsed = 0; - if (data_len < 2) - return false; + if (eir_len < 2) + return NULL; - while (parsed < data_len - 1) { - u8 field_len = data[0]; + while (parsed < eir_len - 1) { + u8 field_len = eir[0]; if (field_len == 0) break; parsed += field_len + 1; - if (parsed > data_len) + if (parsed > eir_len) break; - if (data[1] == type) - return true; + if (eir[1] != type) { + eir += field_len + 1; + continue; + } + + /* Zero length data */ + if (field_len == 1) + return NULL; - data += field_len + 1; + if (data_len) + *data_len = field_len - 1; + + return &eir[2]; } - return false; + return NULL; } static inline bool hci_bdaddr_is_rpa(bdaddr_t *bdaddr, u8 addr_type) @@ -1431,10 +1446,8 @@ int mgmt_new_settings(struct hci_dev *hdev); void mgmt_index_added(struct hci_dev *hdev); void mgmt_index_removed(struct hci_dev *hdev); void mgmt_set_powered_failed(struct hci_dev *hdev, int err); -int mgmt_powered(struct hci_dev *hdev, u8 powered); -int mgmt_update_adv_data(struct hci_dev *hdev); -void mgmt_discoverable_timeout(struct hci_dev *hdev); -void mgmt_adv_timeout_expired(struct hci_dev *hdev); +void mgmt_power_on(struct hci_dev *hdev, int err); +void __mgmt_power_off(struct hci_dev *hdev); void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent); void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, @@ -1473,6 +1486,8 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status); void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, u8 status); void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status); +void mgmt_start_discovery_complete(struct hci_dev *hdev, u8 status); +void mgmt_stop_discovery_complete(struct hci_dev *hdev, u8 status); void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len); @@ -1487,8 +1502,15 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 store_hint, u16 min_interval, u16 max_interval, u16 latency, u16 timeout); -void mgmt_reenable_advertising(struct hci_dev *hdev); void mgmt_smp_complete(struct hci_conn *conn, bool complete); +bool mgmt_get_connectable(struct hci_dev *hdev); +void mgmt_set_connectable_complete(struct hci_dev *hdev, u8 status); +void mgmt_set_discoverable_complete(struct hci_dev *hdev, u8 status); +u8 mgmt_get_adv_discov_flags(struct hci_dev *hdev); +void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, + u8 instance); +void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev, + u8 instance); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index 2b67567cf..587d0131b 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -43,6 +43,8 @@ struct hci_mon_hdr { #define HCI_MON_CLOSE_INDEX 9 #define HCI_MON_INDEX_INFO 10 #define HCI_MON_VENDOR_DIAG 11 +#define HCI_MON_SYSTEM_NOTE 12 +#define HCI_MON_USER_LOGGING 13 struct hci_mon_new_index { __u8 type; diff --git a/include/net/bluetooth/hci_sock.h b/include/net/bluetooth/hci_sock.h index 9a46d665c..8e9138acd 100644 --- a/include/net/bluetooth/hci_sock.h +++ b/include/net/bluetooth/hci_sock.h @@ -45,6 +45,7 @@ struct sockaddr_hci { #define HCI_CHANNEL_USER 1 #define HCI_CHANNEL_MONITOR 2 #define HCI_CHANNEL_CONTROL 3 +#define HCI_CHANNEL_LOGGING 4 struct hci_filter { unsigned long type_mask; diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 52899291f..5ee3c689c 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -252,6 +252,12 @@ struct l2cap_conn_rsp { #define L2CAP_PSM_3DSP 0x0021 #define L2CAP_PSM_IPSP 0x0023 /* 6LoWPAN */ +#define L2CAP_PSM_DYN_START 0x1001 +#define L2CAP_PSM_DYN_END 0xffff +#define L2CAP_PSM_AUTO_END 0x10ff +#define L2CAP_PSM_LE_DYN_START 0x0080 +#define L2CAP_PSM_LE_DYN_END 0x00ff + /* channel identifier */ #define L2CAP_CID_SIGNALING 0x0001 #define L2CAP_CID_CONN_LESS 0x0002 diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index b831242d4..ea73e0826 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -571,6 +571,21 @@ struct mgmt_rp_remove_advertising { __u8 instance; } __packed; +#define MGMT_OP_GET_ADV_SIZE_INFO 0x0040 +struct mgmt_cp_get_adv_size_info { + __u8 instance; + __le32 flags; +} __packed; +#define MGMT_GET_ADV_SIZE_INFO_SIZE 5 +struct mgmt_rp_get_adv_size_info { + __u8 instance; + __le32 flags; + __u8 max_adv_data_len; + __u8 max_scan_rsp_len; +} __packed; + +#define MGMT_OP_START_LIMITED_DISCOVERY 0x0041 + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; diff --git a/include/net/bonding.h b/include/net/bonding.h index c1740a279..ee6c52053 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -165,7 +165,8 @@ struct slave { u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ inactive:1, /* indicates inactive slave */ - should_notify:1; /* indicateds whether the state changed */ + should_notify:1, /* indicates whether the state changed */ + should_notify_link:1; /* indicates whether the link changed */ u8 duplex; u32 original_mtu; u32 link_failure_count; @@ -246,6 +247,7 @@ struct bonding { ((struct slave *) rtnl_dereference(dev->rx_handler_data)) void bond_queue_slave_event(struct slave *slave); +void bond_lower_state_changed(struct slave *slave); struct bond_vlan_tag { __be16 vlan_proto; @@ -327,6 +329,7 @@ static inline void bond_set_active_slave(struct slave *slave) if (slave->backup) { slave->backup = 0; bond_queue_slave_event(slave); + bond_lower_state_changed(slave); rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); } } @@ -336,6 +339,7 @@ static inline void bond_set_backup_slave(struct slave *slave) if (!slave->backup) { slave->backup = 1; bond_queue_slave_event(slave); + bond_lower_state_changed(slave); rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); } } @@ -348,6 +352,7 @@ static inline void bond_set_slave_state(struct slave *slave, slave->backup = slave_state; if (notify) { + bond_lower_state_changed(slave); rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); bond_queue_slave_event(slave); slave->should_notify = 0; @@ -379,6 +384,7 @@ static inline void bond_slave_state_notify(struct bonding *bond) bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify) { + bond_lower_state_changed(tmp); rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC); tmp->should_notify = 0; } @@ -504,10 +510,37 @@ static inline bool bond_is_slave_inactive(struct slave *slave) return slave->inactive; } -static inline void bond_set_slave_link_state(struct slave *slave, int state) +static inline void bond_set_slave_link_state(struct slave *slave, int state, + bool notify) { + if (slave->link == state) + return; + slave->link = state; - bond_queue_slave_event(slave); + if (notify) { + bond_queue_slave_event(slave); + bond_lower_state_changed(slave); + slave->should_notify_link = 0; + } else { + if (slave->should_notify_link) + slave->should_notify_link = 0; + else + slave->should_notify_link = 1; + } +} + +static inline void bond_slave_link_notify(struct bonding *bond) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) { + if (tmp->should_notify_link) { + bond_queue_slave_event(tmp); + bond_lower_state_changed(tmp); + tmp->should_notify_link = 0; + } + } } static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local) diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 1d67fb6b2..2fbeb1313 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -72,50 +72,7 @@ static inline bool busy_loop_timeout(unsigned long end_time) return time_after(now, end_time); } -/* when used in sock_poll() nonblock is known at compile time to be true - * so the loop and end_time will be optimized out - */ -static inline bool sk_busy_loop(struct sock *sk, int nonblock) -{ - unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0; - const struct net_device_ops *ops; - struct napi_struct *napi; - int rc = false; - - /* - * rcu read lock for napi hash - * bh so we don't race with net_rx_action - */ - rcu_read_lock_bh(); - - napi = napi_by_id(sk->sk_napi_id); - if (!napi) - goto out; - - ops = napi->dev->netdev_ops; - if (!ops->ndo_busy_poll) - goto out; - - do { - rc = ops->ndo_busy_poll(napi); - - if (rc == LL_FLUSH_FAILED) - break; /* permanent failure */ - - if (rc > 0) - /* local bh are disabled so it is ok to use _BH */ - NET_ADD_STATS_BH(sock_net(sk), - LINUX_MIB_BUSYPOLLRXPACKETS, rc); - cpu_relax(); - - } while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) && - !need_resched() && !busy_loop_timeout(end_time)); - - rc = !skb_queue_empty(&sk->sk_receive_queue); -out: - rcu_read_unlock_bh(); - return rc; -} +bool sk_busy_loop(struct sock *sk, int nonblock); /* used in the NIC receive handler to mark the skb */ static inline void skb_mark_napi_id(struct sk_buff *skb, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 2c7bdb81d..9bcaaf7cd 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2321,6 +2321,8 @@ struct cfg80211_qos_map { * the driver, and will be valid until passed to cfg80211_scan_done(). * For scan results, call cfg80211_inform_bss(); you can call this outside * the scan/scan_done bracket too. + * @abort_scan: Tell the driver to abort an ongoing scan. The driver shall + * indicate the status of the scan through cfg80211_scan_done(). * * @auth: Request to authenticate with the specified peer * (invoked with the wireless_dev mutex held) @@ -2593,6 +2595,7 @@ struct cfg80211_ops { int (*scan)(struct wiphy *wiphy, struct cfg80211_scan_request *request); + void (*abort_scan)(struct wiphy *wiphy, struct wireless_dev *wdev); int (*auth)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_auth_request *req); @@ -5173,8 +5176,11 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, * buffer starts, which may be @ielen if the entire (remainder) * of the buffer should be used. */ -size_t ieee80211_ie_split(const u8 *ies, size_t ielen, - const u8 *ids, int n_ids, size_t offset); +static inline size_t ieee80211_ie_split(const u8 *ies, size_t ielen, + const u8 *ids, int n_ids, size_t offset) +{ + return ieee80211_ie_split_ric(ies, ielen, ids, n_ids, NULL, 0, offset); +} /** * cfg80211_report_wowlan_wakeup - report wakeup from WoWLAN diff --git a/include/net/checksum.h b/include/net/checksum.h index 9fcaedf99..10a16b5bd 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -165,7 +165,8 @@ static inline __wsum remcsum_adjust(void *ptr, __wsum csum, csum = csum_sub(csum, csum_partial(ptr, start, 0)); /* Set derived checksum in packet */ - delta = csum_sub(csum_fold(csum), *psum); + delta = csum_sub((__force __wsum)csum_fold(csum), + (__force __wsum)*psum); *psum = csum_fold(csum); return delta; diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index ccd6d8bff..c0a92e2c2 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -41,13 +41,12 @@ static inline u32 task_cls_classid(struct task_struct *p) return classid; } -static inline void sock_update_classid(struct sock *sk) +static inline void sock_update_classid(struct sock_cgroup_data *skcd) { u32 classid; classid = task_cls_classid(current); - if (classid != sk->sk_classid) - sk->sk_classid = classid; + sock_cgroup_set_classid(skcd, classid); } static inline u32 task_get_classid(const struct sk_buff *skb) @@ -64,17 +63,17 @@ static inline u32 task_get_classid(const struct sk_buff *skb) * softirqs always disables bh. */ if (in_serving_softirq()) { - /* If there is an sk_classid we'll use that. */ + /* If there is an sock_cgroup_classid we'll use that. */ if (!skb->sk) return 0; - classid = skb->sk->sk_classid; + classid = sock_cgroup_classid(&skb->sk->sk_cgrp_data); } return classid; } #else /* !CONFIG_CGROUP_NET_CLASSID */ -static inline void sock_update_classid(struct sock *sk) +static inline void sock_update_classid(struct sock_cgroup_data *skcd) { } diff --git a/include/net/dsa.h b/include/net/dsa.h index 82a4c6011..26a0e86e6 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -64,6 +65,13 @@ struct dsa_chip_data { * NULL if there is only one switch chip. */ s8 *rtable; + + /* + * A switch may have a GPIO line tied to its reset pin. Parse + * this from the device tree, and use it before performing + * switch soft reset. + */ + struct gpio_desc *reset; }; struct dsa_platform_data { @@ -108,13 +116,6 @@ struct dsa_switch_tree { s8 cpu_switch; s8 cpu_port; - /* - * Link state polling. - */ - int link_poll_needed; - struct work_struct link_poll_work; - struct timer_list link_poll_timer; - /* * Data for the individual switch chips. */ @@ -223,11 +224,6 @@ struct dsa_switch_driver { int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); - /* - * Link state polling and IRQ handling. - */ - void (*poll_link)(struct dsa_switch *ds); - /* * Link state adjustment (called from libphy) */ diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 1b6b6dcb0..43c0e771f 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -114,6 +114,7 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) * @flags: flags * @policy: attribute validation policy * @doit: standard command callback + * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps * @ops_list: operations list @@ -122,6 +123,7 @@ struct genl_ops { const struct nla_policy *policy; int (*doit)(struct sk_buff *skb, struct genl_info *info); + int (*start)(struct netlink_callback *cb); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); diff --git a/include/net/geneve.h b/include/net/geneve.h index 3106ed6ea..e6c23dc76 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -62,6 +62,14 @@ struct genevehdr { struct geneve_opt options[]; }; +#if IS_ENABLED(CONFIG_GENEVE) +void geneve_get_rx_port(struct net_device *netdev); +#else +static inline void geneve_get_rx_port(struct net_device *netdev) +{ +} +#endif + #ifdef CONFIG_INET struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port); diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index a62a051a3..c4b31601c 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -337,7 +337,7 @@ struct ieee802154_mlme_ops { void (*get_mac_params)(struct net_device *dev, struct ieee802154_mac_params *params); - struct ieee802154_llsec_ops *llsec; + const struct ieee802154_llsec_ops *llsec; }; static inline struct ieee802154_mlme_ops * diff --git a/include/net/ila.h b/include/net/ila.h new file mode 100644 index 000000000..9f4f43e94 --- /dev/null +++ b/include/net/ila.h @@ -0,0 +1,18 @@ +/* + * ILA kernel interface + * + * Copyright (c) 2015 Tom Herbert + * + * 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_ILA_H +#define _NET_ILA_H + +int ila_xlat_outgoing(struct sk_buff *skb); +int ila_xlat_incoming(struct sk_buff *skb); + +#endif /* _NET_ILA_H */ diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index ac42bbb37..12aac0fd6 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -99,7 +99,6 @@ struct inet_frags { void (*constructor)(struct inet_frag_queue *q, const void *arg); void (*destructor)(struct inet_frag_queue *); - void (*skb_free)(struct sk_buff *); void (*frag_expire)(unsigned long data); struct kmem_cache *frags_cachep; const char *frags_cache_name; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 625bdf95d..012b1f91f 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -28,6 +28,7 @@ #include #include #include +#include /** struct ip_options - IP Options * @@ -113,6 +114,19 @@ static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) return sk->sk_mark; } +static inline int inet_request_bound_dev_if(const struct sock *sk, + struct sk_buff *skb) +{ +#ifdef CONFIG_NET_L3_MASTER_DEV + struct net *net = sock_net(sk); + + if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) + return l3mdev_master_ifindex_by_index(net, skb->skb_iif); +#endif + + return sk->sk_bound_dev_if; +} + struct inet_cork { unsigned int flags; __be32 addr; diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index ff788b665..0d0ce0b2d 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -5,6 +5,7 @@ #include #include #include +#include #define IP6TUNNEL_ERR_TIMEO (30*HZ) @@ -80,25 +81,17 @@ __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, struct net *ip6_tnl_get_link_net(const struct net_device *dev); int ip6_tnl_get_iflink(const struct net_device *dev); +#ifdef CONFIG_INET static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, struct net_device *dev) { - struct net_device_stats *stats = &dev->stats; int pkt_len, err; pkt_len = skb->len - skb_inner_network_offset(skb); err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); - - if (net_xmit_eval(err) == 0) { - struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += pkt_len; - tstats->tx_packets++; - u64_stats_update_end(&tstats->syncp); - put_cpu_ptr(tstats); - } else { - stats->tx_errors++; - stats->tx_aborted_errors++; - } + if (unlikely(net_xmit_eval(err))) + pkt_len = -1; + iptunnel_xmit_stats(dev, pkt_len); } #endif +#endif diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 3f9823338..4079fc18f 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -326,7 +326,8 @@ extern u32 fib_multipath_secret __read_mostly; static inline int fib_multipath_hash(__be32 saddr, __be32 daddr) { - return jhash_2words(saddr, daddr, fib_multipath_secret) >> 1; + return jhash_2words((__force u32)saddr, (__force u32)daddr, + fib_multipath_secret) >> 1; } void fib_select_multipath(struct fib_result *res, int hash); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 62a750a6a..dda9abf6b 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -230,6 +230,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t, u8 *protocol, struct flowi4 *fl4); +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); struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, @@ -273,32 +274,34 @@ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, } int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto); -int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, - __be32 src, __be32 dst, u8 proto, - u8 tos, u8 ttl, __be16 df, bool xnet); +void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, + __be32 src, __be32 dst, u8 proto, + u8 tos, u8 ttl, __be16 df, bool xnet); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags); struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum, int gso_type_mask); -static inline void iptunnel_xmit_stats(int err, - struct net_device_stats *err_stats, - struct pcpu_sw_netstats __percpu *stats) +static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) { - if (err > 0) { - struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats); + if (pkt_len > 0) { + struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += err; + tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); put_cpu_ptr(tstats); - } else if (err < 0) { - err_stats->tx_errors++; - err_stats->tx_aborted_errors++; } else { - err_stats->tx_dropped++; + struct net_device_stats *err_stats = &dev->stats; + + if (pkt_len < 0) { + err_stats->tx_errors++; + err_stats->tx_aborted_errors++; + } else { + err_stats->tx_dropped++; + } } } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 9a5c9f013..6570f379a 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -401,6 +401,21 @@ static inline void ipv6_addr_prefix(struct in6_addr *pfx, pfx->s6_addr[o] = addr->s6_addr[o] & (0xff00 >> b); } +static inline void ipv6_addr_prefix_copy(struct in6_addr *addr, + const struct in6_addr *pfx, + int plen) +{ + /* caller must guarantee 0 <= plen <= 128 */ + int o = plen >> 3, + b = plen & 0x7; + + memcpy(addr->s6_addr, pfx, o); + if (b != 0) { + addr->s6_addr[o] &= ~(0xff00 >> b); + addr->s6_addr[o] |= (pfx->s6_addr[o] & (0xff00 >> b)); + } +} + static inline void __ipv6_addr_set_half(__be32 *addr, __be32 wh, __be32 wl) { diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index 8f81bbbc3..e0f4109e6 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -439,6 +439,12 @@ int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length); /* Send a single event to user space */ void wireless_send_event(struct net_device *dev, unsigned int cmd, union iwreq_data *wrqu, const char *extra); +#ifdef CONFIG_WEXT_CORE +/* flush all previous wext events - if work is done from netdev notifiers */ +void wireless_nlevent_flush(void); +#else +static inline void wireless_nlevent_flush(void) {} +#endif /* We may need a function to send a stream of events to user space. * More on that later... */ diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 5689a0c74..5567d46b3 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -51,6 +51,24 @@ static inline int l3mdev_master_ifindex(struct net_device *dev) return ifindex; } +static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) +{ + struct net_device *dev; + int rc = 0; + + if (likely(ifindex)) { + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); + if (dev) + rc = l3mdev_master_ifindex_rcu(dev); + + rcu_read_unlock(); + } + + return rc; +} + /* 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 @@ -170,6 +188,11 @@ static inline int l3mdev_master_ifindex(struct net_device *dev) return 0; } +static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) +{ + return 0; +} + static inline int l3mdev_fib_oif_rcu(struct net_device *dev) { return dev ? dev->ifindex : 0; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 760bc4d5a..7c30faff2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1321,11 +1321,15 @@ struct ieee80211_channel_switch { * interface. This flag should be set during interface addition, * but may be set/cleared as late as authentication to an AP. It is * only valid for managed/station mode interfaces. + * @IEEE80211_VIF_GET_NOA_UPDATE: request to handle NOA attributes + * and send P2P_PS notification to the driver if NOA changed, even + * this is not pure P2P vif. */ enum ieee80211_vif_flags { IEEE80211_VIF_BEACON_FILTER = BIT(0), IEEE80211_VIF_SUPPORTS_CQM_RSSI = BIT(1), IEEE80211_VIF_SUPPORTS_UAPSD = BIT(2), + IEEE80211_VIF_GET_NOA_UPDATE = BIT(3), }; /** @@ -1901,6 +1905,11 @@ struct ieee80211_txq { * @IEEE80211_HW_BEACON_TX_STATUS: The device/driver provides TX status * for sent beacons. * + * @IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR: Hardware (or driver) requires that each + * station has a unique address, i.e. each station entry can be identified + * by just its MAC address; this prevents, for example, the same station + * from connecting to two virtual AP interfaces at the same time. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -1936,6 +1945,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_TDLS_WIDER_BW, IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU, IEEE80211_HW_BEACON_TX_STATUS, + IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -4862,6 +4872,28 @@ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, */ void ieee80211_sta_eosp(struct ieee80211_sta *pubsta); +/** + * ieee80211_send_eosp_nullfunc - ask mac80211 to send NDP with EOSP + * @pubsta: the station + * @tid: the tid of the NDP + * + * Sometimes the device understands that it needs to close + * the Service Period unexpectedly. This can happen when + * sending frames that are filling holes in the BA window. + * In this case, the device can ask mac80211 to send a + * Nullfunc frame with EOSP set. When that happens, the + * driver must have called ieee80211_sta_set_buffered() to + * let mac80211 know that there are no buffered frames any + * more, otherwise mac80211 will get the more_data bit wrong. + * The low level driver must have made sure that the frame + * will be sent despite the station being in power-save. + * Mac80211 won't call allow_buffered_frames(). + * Note that calling this function, doesn't exempt the driver + * from closing the EOSP properly, it will still have to call + * ieee80211_sta_eosp when the NDP is sent. + */ +void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid); + /** * ieee80211_iter_keys - iterate keys programmed into the device * @hw: pointer obtained from ieee80211_alloc_hw() @@ -4889,6 +4921,30 @@ void ieee80211_iter_keys(struct ieee80211_hw *hw, void *data), void *iter_data); +/** + * ieee80211_iter_keys_rcu - iterate keys programmed into the device + * @hw: pointer obtained from ieee80211_alloc_hw() + * @vif: virtual interface to iterate, may be %NULL for all + * @iter: iterator function that will be called for each key + * @iter_data: custom data to pass to the iterator function + * + * This function can be used to iterate all the keys known to + * mac80211, even those that weren't previously programmed into + * the device. Note that due to locking reasons, keys of station + * in removal process will be skipped. + * + * This function requires being called in an RCU critical section, + * and thus iter must be atomic. + */ +void ieee80211_iter_keys_rcu(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + void (*iter)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key, + void *data), + void *iter_data); + /** * ieee80211_iter_chan_contexts_atomic - iterate channel contexts * @hw: pointre obtained from ieee80211_alloc_hw(). diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 2dcea635e..4089abc6e 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -121,6 +121,9 @@ struct net { #if IS_ENABLED(CONFIG_NETFILTER_NETLINK_ACCT) struct list_head nfnl_acct_list; #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + struct list_head nfct_timeout_list; +#endif #endif #ifdef CONFIG_WEXT_CORE struct sk_buff_head wext_nlevents; diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index fb7da5bb7..ddf162f79 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -5,8 +5,7 @@ void nf_defrag_ipv6_enable(void); int nf_ct_frag6_init(void); void nf_ct_frag6_cleanup(void); -struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user); -void nf_ct_frag6_consume_orig(struct sk_buff *skb); +int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user); struct inet_frags_ctl; diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 788ef58a6..62e17d131 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -79,12 +79,10 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *proto); -#ifdef CONFIG_LOCKDEP -# define CONNTRACK_LOCKS 8 -#else -# define CONNTRACK_LOCKS 1024 -#endif +#define CONNTRACK_LOCKS 1024 + extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; +void nf_conntrack_lock(spinlock_t *lock); extern spinlock_t nf_conntrack_expect_lock; diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index f72be3886..5cc5e9e61 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -104,7 +104,7 @@ static inline void nf_conntrack_timeout_fini(void) #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_NF_CONNTRACK_TIMEOUT -extern struct ctnl_timeout *(*nf_ct_timeout_find_get_hook)(const char *name); +extern struct ctnl_timeout *(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name); extern void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout); #endif diff --git a/include/net/netfilter/nf_dup_netdev.h b/include/net/netfilter/nf_dup_netdev.h new file mode 100644 index 000000000..397dcae34 --- /dev/null +++ b/include/net/netfilter/nf_dup_netdev.h @@ -0,0 +1,6 @@ +#ifndef _NF_DUP_NETDEV_H_ +#define _NF_DUP_NETDEV_H_ + +void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif); + +#endif diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 4bd7508be..f6b1daf2e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -19,8 +19,6 @@ struct nft_pktinfo { const struct net_device *out; u8 pf; u8 hook; - u8 nhoff; - u8 thoff; u8 tprot; /* for x_tables compatibility */ struct xt_action_param xt; @@ -293,6 +291,8 @@ void nft_unregister_set(struct nft_set_ops *ops); * @timeout: default timeout value in msecs * @gc_int: garbage collection interval in msecs * @policy: set parameterization (see enum nft_set_policies) + * @udlen: user data length + * @udata: user data * @ops: set ops * @pnet: network namespace * @flags: set flags @@ -312,6 +312,8 @@ struct nft_set { u64 timeout; u32 gc_int; u16 policy; + u16 udlen; + unsigned char *udata; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; possible_net_t pnet; @@ -823,10 +825,7 @@ static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chai return container_of(chain, struct nft_base_chain, chain); } -int nft_register_basechain(struct nft_base_chain *basechain, - unsigned int hook_nops); -void nft_unregister_basechain(struct nft_base_chain *basechain, - unsigned int hook_nops); +int __nft_release_basechain(struct nft_ctx *ctx); unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); @@ -882,7 +881,7 @@ struct nft_af_info { }; int nft_register_afinfo(struct net *, struct nft_af_info *); -void nft_unregister_afinfo(struct nft_af_info *); +void nft_unregister_afinfo(struct net *, struct nft_af_info *); int nft_register_chain_type(const struct nf_chain_type *); void nft_unregister_chain_type(const struct nf_chain_type *); @@ -890,6 +889,38 @@ void nft_unregister_chain_type(const struct nf_chain_type *); int nft_register_expr(struct nft_expr_type *); void nft_unregister_expr(struct nft_expr_type *); +int nft_verdict_dump(struct sk_buff *skb, int type, + const struct nft_verdict *v); + +/** + * struct nft_traceinfo - nft tracing information and state + * + * @pkt: pktinfo currently processed + * @basechain: base chain currently processed + * @chain: chain currently processed + * @rule: rule that was evaluated + * @verdict: verdict given by rule + * @type: event type (enum nft_trace_types) + * @packet_dumped: packet headers sent in a previous traceinfo message + * @trace: other struct members are initialised + */ +struct nft_traceinfo { + const struct nft_pktinfo *pkt; + const struct nft_base_chain *basechain; + const struct nft_chain *chain; + const struct nft_rule *rule; + const struct nft_verdict *verdict; + enum nft_trace_types type; + bool packet_dumped; + bool trace; +}; + +void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, + const struct nft_verdict *verdict, + const struct nft_chain *basechain); + +void nft_trace_notify(struct nft_traceinfo *info); + #define nft_dereference(p) \ nfnl_dereference(p, NFNL_SUBSYS_NFTABLES) diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index c6f400cfa..a9060dd99 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -47,7 +47,17 @@ struct nft_payload { enum nft_registers dreg:8; }; +struct nft_payload_set { + enum nft_payload_bases base:8; + u8 offset; + u8 len; + enum nft_registers sreg:8; + u8 csum_type; + u8 csum_offset; +}; + 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); diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index 711887a09..d27588c8d 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -33,4 +33,7 @@ void nft_meta_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_meta_set_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr); + #endif diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index c68926b48..2b7907a35 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -86,11 +86,18 @@ struct netns_ipv4 { int sysctl_fwmark_reflect; int sysctl_tcp_fwmark_accept; +#ifdef CONFIG_NET_L3_MASTER_DEV + int sysctl_tcp_l3mdev_accept; +#endif int sysctl_tcp_mtu_probing; int sysctl_tcp_base_mss; int sysctl_tcp_probe_threshold; u32 sysctl_tcp_probe_interval; + int sysctl_tcp_keepalive_time; + int sysctl_tcp_keepalive_probes; + int sysctl_tcp_keepalive_intvl; + struct ping_group_range ping_group_range; atomic_t dev_addr_genid; diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 8ba379f9e..c501d6717 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -88,6 +88,13 @@ struct netns_sctp { */ int pf_retrans; + /* + * Disable Potentially-Failed feature, the feature is enabled by default + * pf_enable - 0 : disable pf + * - >0 : enable pf + */ + int pf_enable; + /* * Policy for preforming sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_sndbuf diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h index f2a9597ff..604190596 100644 --- a/include/net/netprio_cgroup.h +++ b/include/net/netprio_cgroup.h @@ -25,8 +25,6 @@ struct netprio_map { u32 priomap[]; }; -void sock_update_netprioidx(struct sock *sk); - static inline u32 task_netprioidx(struct task_struct *p) { struct cgroup_subsys_state *css; @@ -38,13 +36,25 @@ static inline u32 task_netprioidx(struct task_struct *p) rcu_read_unlock(); return idx; } + +static inline void sock_update_netprioidx(struct sock_cgroup_data *skcd) +{ + if (in_interrupt()) + return; + + sock_cgroup_set_prioidx(skcd, task_netprioidx(current)); +} + #else /* !CONFIG_CGROUP_NET_PRIO */ + static inline u32 task_netprioidx(struct task_struct *p) { return 0; } -#define sock_update_netprioidx(sk) +static inline void sock_update_netprioidx(struct sock_cgroup_data *skcd) +{ +} #endif /* CONFIG_CGROUP_NET_PRIO */ #endif /* _NET_CLS_CGROUP_H */ diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index dcfcfc9c0..1a3de8b34 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -299,6 +299,7 @@ void nfc_driver_failure(struct nfc_dev *dev, int err); int nfc_se_transaction(struct nfc_dev *dev, u8 se_idx, struct nfc_evt_transaction *evt_transaction); +int nfc_se_connectivity(struct nfc_dev *dev, u8 se_idx); int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type); int nfc_remove_se(struct nfc_dev *dev, u32 se_idx); struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx); diff --git a/include/net/protocol.h b/include/net/protocol.h index d6fcc1fcd..da689f543 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -107,7 +107,7 @@ int inet_del_offload(const struct net_offload *prot, unsigned char num); void inet_register_protosw(struct inet_protosw *p); void inet_unregister_protosw(struct inet_protosw *p); -int udp_add_offload(struct udp_offload *prot); +int udp_add_offload(struct net *net, struct udp_offload *prot); void udp_del_offload(struct udp_offload *prot); #if IS_ENABLED(CONFIG_IPV6) diff --git a/include/net/request_sock.h b/include/net/request_sock.h index a0dde04eb..f49759dec 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -68,7 +68,7 @@ struct request_sock { u32 peer_secid; }; -static inline struct request_sock *inet_reqsk(struct sock *sk) +static inline struct request_sock *inet_reqsk(const struct sock *sk) { return (struct request_sock *)sk; } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index b2a8e6338..636a362a0 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -407,6 +407,15 @@ bool tcf_destroy(struct tcf_proto *tp, bool force); void tcf_destroy_chain(struct tcf_proto __rcu **fl); int skb_do_redirect(struct sk_buff *); +static inline bool skb_at_tc_ingress(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_CLS_ACT + return G_TC_AT(skb->tc_verd) & AT_INGRESS; +#else + return false; +#endif +} + /* Reset all TX qdiscs greater then index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index ce13cf20f..835aa2ed9 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -126,8 +126,6 @@ int sctp_primitive_ASCONF(struct net *, struct sctp_association *, void *arg); */ int sctp_rcv(struct sk_buff *skb); void sctp_v4_err(struct sk_buff *skb, u32 info); -void sctp_hash_established(struct sctp_association *); -void sctp_unhash_established(struct sctp_association *); void sctp_hash_endpoint(struct sctp_endpoint *); void sctp_unhash_endpoint(struct sctp_endpoint *); struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *, @@ -143,6 +141,17 @@ void sctp_icmp_proto_unreachable(struct sock *sk, struct sctp_transport *t); 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); +void sctp_unhash_transport(struct sctp_transport *t); +struct sctp_transport *sctp_addrs_lookup_transport( + struct net *net, + const union sctp_addr *laddr, + const union sctp_addr *paddr); +struct sctp_transport *sctp_epaddr_lookup_transport( + const struct sctp_endpoint *ep, + const union sctp_addr *paddr); /* * sctp/proc.c @@ -519,25 +528,6 @@ static inline int sctp_ep_hashfn(struct net *net, __u16 lport) return (net_hash_mix(net) + lport) & (sctp_ep_hashsize - 1); } -/* This is the hash function for the association hash table. */ -static inline int sctp_assoc_hashfn(struct net *net, __u16 lport, __u16 rport) -{ - int h = (lport << 16) + rport + net_hash_mix(net); - h ^= h>>8; - return h & (sctp_assoc_hashsize - 1); -} - -/* This is the hash function for the association hash table. This is - * not used yet, but could be used as a better hash function when - * we have a vtag. - */ -static inline int sctp_vtag_hashfn(__u16 lport, __u16 rport, __u32 vtag) -{ - int h = (lport << 16) + rport; - h ^= vtag; - return h & (sctp_assoc_hashsize - 1); -} - #define sctp_for_each_hentry(epb, head) \ hlist_for_each_entry(epb, head, node) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index eea9bdeec..205630bb5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -48,6 +48,7 @@ #define __sctp_structs_h__ #include +#include #include /* linux/in.h needs this!! */ #include /* We get struct sockaddr_in. */ #include /* We get struct in6_addr */ @@ -119,14 +120,13 @@ extern struct sctp_globals { /* This is the hash of all endpoints. */ struct sctp_hashbucket *ep_hashtable; - /* This is the hash of all associations. */ - struct sctp_hashbucket *assoc_hashtable; /* This is the sctp port control hash. */ struct sctp_bind_hashbucket *port_hashtable; + /* This is the hash of all transports. */ + struct rhashtable transport_hashtable; /* Sizes of above hashtables. */ int ep_hashsize; - int assoc_hashsize; int port_hashsize; /* Default initialization values to be applied to new associations. */ @@ -143,10 +143,9 @@ extern struct sctp_globals { #define sctp_address_families (sctp_globals.address_families) #define sctp_ep_hashsize (sctp_globals.ep_hashsize) #define sctp_ep_hashtable (sctp_globals.ep_hashtable) -#define sctp_assoc_hashsize (sctp_globals.assoc_hashsize) -#define sctp_assoc_hashtable (sctp_globals.assoc_hashtable) #define sctp_port_hashsize (sctp_globals.port_hashsize) #define sctp_port_hashtable (sctp_globals.port_hashtable) +#define sctp_transport_hashtable (sctp_globals.transport_hashtable) #define sctp_checksum_disable (sctp_globals.checksum_disable) /* SCTP Socket type: UDP or TCP style. */ @@ -753,10 +752,10 @@ 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; /* Reference counting. */ atomic_t refcnt; - __u32 dead:1, /* RTO-Pending : A flag used to track if one of the DATA * chunks sent to this address is currently being * used to compute a RTT. If this flag is 0, @@ -766,7 +765,7 @@ struct sctp_transport { * calculation completes (i.e. the DATA chunk * is SACK'd) clear this flag. */ - rto_pending:1, + __u32 rto_pending:1, /* * hb_sent : a flag that signals that we have a pending @@ -955,7 +954,7 @@ void sctp_transport_route(struct sctp_transport *, union sctp_addr *, void sctp_transport_pmtu(struct sctp_transport *, struct sock *sk); void sctp_transport_free(struct sctp_transport *); void sctp_transport_reset_timers(struct sctp_transport *); -void sctp_transport_hold(struct sctp_transport *); +int sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); void sctp_transport_raise_cwnd(struct sctp_transport *, __u32, __u32); diff --git a/include/net/sock.h b/include/net/sock.h index 14d3c0734..f5ea14885 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -58,6 +58,8 @@ #include #include #include +#include +#include #include #include @@ -69,22 +71,6 @@ #include #include -struct cgroup; -struct cgroup_subsys; -#ifdef CONFIG_NET -int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss); -void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg); -#else -static inline -int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) -{ - return 0; -} -static inline -void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) -{ -} -#endif /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of @@ -243,7 +229,6 @@ struct sock_common { /* public: */ }; -struct cg_proto; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock @@ -287,7 +272,6 @@ struct cg_proto; * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_priority: %SO_PRIORITY setting - * @sk_cgrp_prioidx: socket group's priority map index * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family * @sk_peer_pid: &struct pid for this socket's peer @@ -308,8 +292,8 @@ struct cg_proto; * @sk_send_head: front of stuff to transmit * @sk_security: used by security modules * @sk_mark: generic packet mark - * @sk_classid: this socket's cgroup classid - * @sk_cgrp: this socket's cgroup-specific proto data + * @sk_cgrp_data: cgroup data for this cgroup + * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed @@ -317,6 +301,7 @@ struct cg_proto; * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @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 */ struct sock { /* @@ -425,9 +410,7 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; __u32 sk_priority; -#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) - __u32 sk_cgrp_prioidx; -#endif + __u32 sk_mark; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; @@ -445,11 +428,8 @@ struct sock { #ifdef CONFIG_SECURITY void *sk_security; #endif - __u32 sk_mark; -#ifdef CONFIG_CGROUP_NET_CLASSID - u32 sk_classid; -#endif - struct cg_proto *sk_cgrp; + struct sock_cgroup_data sk_cgrp_data; + struct mem_cgroup *sk_memcg; void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk); void (*sk_write_space)(struct sock *sk); @@ -457,6 +437,7 @@ struct sock { int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb); void (*sk_destruct)(struct sock *sk); + struct sock_reuseport __rcu *sk_reuseport_cb; }; #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) @@ -778,9 +759,9 @@ static inline int sk_memalloc_socks(void) #endif -static inline gfp_t sk_gfp_atomic(const struct sock *sk, gfp_t gfp_mask) +static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask) { - return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC); + return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC); } static inline void sk_acceptq_removed(struct sock *sk) @@ -1055,18 +1036,7 @@ struct proto { #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif -#ifdef CONFIG_MEMCG_KMEM - /* - * cgroup specific init/deinit functions. Called once for all - * protocols that implement it, from cgroups populate function. - * This function has to setup any files the protocol want to - * appear in the kmem cgroup filesystem. - */ - int (*init_cgroup)(struct mem_cgroup *memcg, - struct cgroup_subsys *ss); - void (*destroy_cgroup)(struct mem_cgroup *memcg); - struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg); -#endif + int (*diag_destroy)(struct sock *sk, int err); }; int proto_register(struct proto *prot, int alloc_slab); @@ -1097,23 +1067,6 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_NET) -extern struct static_key memcg_socket_limit_enabled; -static inline struct cg_proto *parent_cg_proto(struct proto *proto, - struct cg_proto *cg_proto) -{ - return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg)); -} -#define mem_cgroup_sockets_enabled static_key_false(&memcg_socket_limit_enabled) -#else -#define mem_cgroup_sockets_enabled 0 -static inline struct cg_proto *parent_cg_proto(struct proto *proto, - struct cg_proto *cg_proto) -{ - return NULL; -} -#endif - static inline bool sk_stream_memory_free(const struct sock *sk) { if (sk->sk_wmem_queued >= sk->sk_sndbuf) @@ -1140,8 +1093,9 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) if (!sk->sk_prot->memory_pressure) return false; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return !!sk->sk_cgrp->memory_pressure; + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) + return true; return !!*sk->sk_prot->memory_pressure; } @@ -1155,15 +1109,6 @@ static inline void sk_leave_memory_pressure(struct sock *sk) if (*memory_pressure) *memory_pressure = 0; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct cg_proto *cg_proto = sk->sk_cgrp; - struct proto *prot = sk->sk_prot; - - for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - cg_proto->memory_pressure = 0; - } - } static inline void sk_enter_memory_pressure(struct sock *sk) @@ -1171,116 +1116,46 @@ static inline void sk_enter_memory_pressure(struct sock *sk) if (!sk->sk_prot->enter_memory_pressure) return; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct cg_proto *cg_proto = sk->sk_cgrp; - struct proto *prot = sk->sk_prot; - - for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - cg_proto->memory_pressure = 1; - } - sk->sk_prot->enter_memory_pressure(sk); } static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long *prot = sk->sk_prot->sysctl_mem; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - prot = sk->sk_cgrp->sysctl_mem; - return prot[index]; -} - -static inline void memcg_memory_allocated_add(struct cg_proto *prot, - unsigned long amt, - int *parent_status) -{ - page_counter_charge(&prot->memory_allocated, amt); - - if (page_counter_read(&prot->memory_allocated) > - prot->memory_allocated.limit) - *parent_status = OVER_LIMIT; -} - -static inline void memcg_memory_allocated_sub(struct cg_proto *prot, - unsigned long amt) -{ - page_counter_uncharge(&prot->memory_allocated, amt); + return sk->sk_prot->sysctl_mem[index]; } static inline long sk_memory_allocated(const struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return page_counter_read(&sk->sk_cgrp->memory_allocated); - - return atomic_long_read(prot->memory_allocated); + return atomic_long_read(sk->sk_prot->memory_allocated); } static inline long -sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status) +sk_memory_allocated_add(struct sock *sk, int amt) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status); - /* update the root cgroup regardless */ - atomic_long_add_return(amt, prot->memory_allocated); - return page_counter_read(&sk->sk_cgrp->memory_allocated); - } - - return atomic_long_add_return(amt, prot->memory_allocated); + return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - memcg_memory_allocated_sub(sk->sk_cgrp, amt); - - atomic_long_sub(amt, prot->memory_allocated); + atomic_long_sub(amt, sk->sk_prot->memory_allocated); } static inline void sk_sockets_allocated_dec(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct cg_proto *cg_proto = sk->sk_cgrp; - - for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - percpu_counter_dec(&cg_proto->sockets_allocated); - } - - percpu_counter_dec(prot->sockets_allocated); + percpu_counter_dec(sk->sk_prot->sockets_allocated); } static inline void sk_sockets_allocated_inc(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct cg_proto *cg_proto = sk->sk_cgrp; - - for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - percpu_counter_inc(&cg_proto->sockets_allocated); - } - - percpu_counter_inc(prot->sockets_allocated); + percpu_counter_inc(sk->sk_prot->sockets_allocated); } static inline int sk_sockets_allocated_read_positive(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return percpu_counter_read_positive(&sk->sk_cgrp->sockets_allocated); - - return percpu_counter_read_positive(prot->sockets_allocated); + return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); } static inline int @@ -1798,6 +1673,15 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) sk->sk_route_caps &= ~flags; } +static inline bool sk_check_csum_caps(struct sock *sk) +{ + return (sk->sk_route_caps & NETIF_F_HW_CSUM) || + (sk->sk_family == PF_INET && + (sk->sk_route_caps & NETIF_F_IP_CSUM)) || + (sk->sk_family == PF_INET6 && + (sk->sk_route_caps & NETIF_F_IPV6_CSUM)); +} + static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) @@ -1883,12 +1767,12 @@ static inline bool sk_has_allocations(const struct sock *sk) } /** - * wq_has_sleeper - check if there are any waiting processes + * skwq_has_sleeper - check if there are any waiting processes * @wq: struct socket_wq * * Returns true if socket_wq has waiting processes * - * The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory + * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. * * Consider following tcp code paths: @@ -1914,15 +1798,9 @@ static inline bool sk_has_allocations(const struct sock *sk) * data on the socket. * */ -static inline bool wq_has_sleeper(struct socket_wq *wq) +static inline bool skwq_has_sleeper(struct socket_wq *wq) { - /* We need to be sure we are in sync with the - * add_wait_queue modifications to the wait queue. - * - * This memory barrier is paired in the sock_poll_wait. - */ - smp_mb(); - return wq && waitqueue_active(&wq->wait); + return wq && wq_has_sleeper(&wq->wait); } /** diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h new file mode 100644 index 000000000..aecd30308 --- /dev/null +++ b/include/net/sock_reuseport.h @@ -0,0 +1,28 @@ +#ifndef _SOCK_REUSEPORT_H +#define _SOCK_REUSEPORT_H + +#include +#include +#include +#include + +struct sock_reuseport { + struct rcu_head rcu; + + u16 max_socks; /* length of socks */ + u16 num_socks; /* elements in socks */ + struct bpf_prog __rcu *prog; /* optional BPF sock selector */ + struct sock *socks[0]; /* array of sock pointers */ +}; + +extern int reuseport_alloc(struct sock *sk); +extern int reuseport_add_sock(struct sock *sk, struct sock *sk2); +extern void reuseport_detach_sock(struct sock *sk); +extern struct sock *reuseport_select_sock(struct sock *sk, + u32 hash, + struct sk_buff *skb, + int hdr_len); +extern struct bpf_prog *reuseport_attach_prog(struct sock *sk, + struct bpf_prog *prog); + +#endif /* _SOCK_REUSEPORT_H */ diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 1d22ce9f3..d451122e8 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -47,9 +47,11 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_PORT_STP_STATE, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, + SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, }; struct switchdev_attr { + struct net_device *orig_dev; enum switchdev_attr_id id; u32 flags; union { @@ -57,6 +59,7 @@ struct switchdev_attr { u8 stp_state; /* PORT_STP_STATE */ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ u32 ageing_time; /* BRIDGE_AGEING_TIME */ + bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ } u; }; @@ -65,9 +68,11 @@ enum switchdev_obj_id { SWITCHDEV_OBJ_ID_PORT_VLAN, SWITCHDEV_OBJ_ID_IPV4_FIB, SWITCHDEV_OBJ_ID_PORT_FDB, + SWITCHDEV_OBJ_ID_PORT_MDB, }; struct switchdev_obj { + struct net_device *orig_dev; enum switchdev_obj_id id; u32 flags; }; @@ -109,6 +114,16 @@ struct switchdev_obj_port_fdb { #define SWITCHDEV_OBJ_PORT_FDB(obj) \ container_of(obj, struct switchdev_obj_port_fdb, obj) +/* SWITCHDEV_OBJ_ID_PORT_MDB */ +struct switchdev_obj_port_mdb { + struct switchdev_obj obj; + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +#define SWITCHDEV_OBJ_PORT_MDB(obj) \ + container_of(obj, struct switchdev_obj_port_mdb, obj) + void switchdev_trans_item_enqueue(struct switchdev_trans *trans, void *data, void (*destructor)(void const *), struct switchdev_trans_item *tritem); diff --git a/include/net/tcp.h b/include/net/tcp.h index 47e0ed9f6..7b9c0ffe0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -216,7 +216,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ -/* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */ +/* TCP initial congestion window as per rfc6928 */ #define TCP_INIT_CWND 10 /* Bit Flags for sysctl_tcp_fastopen */ @@ -240,9 +240,6 @@ extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_sack; extern int sysctl_tcp_fin_timeout; -extern int sysctl_tcp_keepalive_time; -extern int sysctl_tcp_keepalive_probes; -extern int sysctl_tcp_keepalive_intvl; extern int sysctl_tcp_syn_retries; extern int sysctl_tcp_synack_retries; extern int sysctl_tcp_retries1; @@ -292,8 +289,9 @@ extern int tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) { - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return !!sk->sk_cgrp->memory_pressure; + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) + return true; return tcp_memory_pressure; } @@ -1176,6 +1174,8 @@ void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); +int tcp_abort(struct sock *sk, int err); + static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) { rx_opt->dsack = 0; @@ -1229,17 +1229,23 @@ void tcp_enter_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { - return tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl; + struct net *net = sock_net((struct sock *)tp); + + return tp->keepalive_intvl ? : net->ipv4.sysctl_tcp_keepalive_intvl; } static inline int keepalive_time_when(const struct tcp_sock *tp) { - return tp->keepalive_time ? : sysctl_tcp_keepalive_time; + struct net *net = sock_net((struct sock *)tp); + + return tp->keepalive_time ? : net->ipv4.sysctl_tcp_keepalive_time; } static inline int keepalive_probes(const struct tcp_sock *tp) { - return tp->keepalive_probes ? : sysctl_tcp_keepalive_probes; + struct net *net = sock_net((struct sock *)tp); + + return tp->keepalive_probes ? : net->ipv4.sysctl_tcp_keepalive_probes; } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) @@ -1624,6 +1630,18 @@ static inline void tcp_highest_sack_combine(struct sock *sk, tcp_sk(sk)->highest_sack = new; } +/* This helper checks if socket has IP_TRANSPARENT set */ +static inline bool inet_sk_transparent(const 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; + } + return inet_sk(sk)->transparent; +} + /* Determines whether this is a thin stream (which may suffer from * increased latency). Used to trigger latency-reducing mechanisms. */ diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h deleted file mode 100644 index 05b94d945..000000000 --- a/include/net/tcp_memcontrol.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef _TCP_MEMCG_H -#define _TCP_MEMCG_H - -struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg); -int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss); -void tcp_destroy_cgroup(struct mem_cgroup *memcg); -#endif /* _TCP_MEMCG_H */ diff --git a/include/net/udp.h b/include/net/udp.h index 6d4ed18e1..2842541e2 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -191,7 +191,7 @@ static inline void udp_lib_close(struct sock *sk, long timeout) } int udp_lib_get_port(struct sock *sk, unsigned short snum, - int (*)(const struct sock *, const struct sock *), + int (*)(const struct sock *, const struct sock *, bool), unsigned int hash2_nulladdr); u32 udp_flow_hashrnd(void); @@ -258,7 +258,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, - struct udp_table *tbl); + struct udp_table *tbl, struct sk_buff *skb); struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, @@ -266,7 +266,8 @@ struct sock *udp6_lib_lookup(struct net *net, struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, - int dif, struct udp_table *tbl); + int dif, struct udp_table *tbl, + struct sk_buff *skb); /* * SNMP statistics for UDP and UDP-Lite diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index cb2f89f20..cca2ad308 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -78,10 +78,10 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); /* Transmit the skb using UDP encapsulation. */ -int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, - __be32 src, __be32 dst, __u8 tos, __u8 ttl, - __be16 df, __be16 src_port, __be16 dst_port, - bool xnet, bool nocheck); +void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, + __be32 src, __be32 dst, __u8 tos, __u8 ttl, + __be16 df, __be16 src_port, __be16 dst_port, + bool xnet, bool nocheck); #if IS_ENABLED(CONFIG_IPV6) int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, diff --git a/include/net/vxlan.h b/include/net/vxlan.h index e289ada6a..0fb864425 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -232,7 +232,7 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, skb->inner_protocol != htons(ETH_P_TEB) || (skb_inner_mac_header(skb) - skb_transport_header(skb) != sizeof(struct udphdr) + sizeof(struct vxlanhdr)))) - return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); return features; } -- cgit v1.2.3-54-g00ecf