diff options
Diffstat (limited to 'include/net')
40 files changed, 709 insertions, 160 deletions
diff --git a/include/net/addrconf.h b/include/net/addrconf.h index ec51e673b4b..d13573bb879 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -202,7 +202,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); void ipv6_sock_ac_close(struct sock *sk); -int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr); +int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr); int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr); void ipv6_ac_destroy_dev(struct inet6_dev *idev); bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, diff --git a/include/net/ah.h b/include/net/ah.h index ca95b98969d..4e2dfa474a7 100644 --- a/include/net/ah.h +++ b/include/net/ah.h @@ -3,9 +3,6 @@ #include <linux/skbuff.h> -/* This is the maximum truncated ICV length that we know of. */ -#define MAX_AH_AUTH_LEN 64 - struct crypto_ahash; struct ah_data { diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 6f884e6c731..206b92bfeeb 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -302,7 +302,7 @@ struct hci_dev { __u32 req_status; __u32 req_result; - struct crypto_blkcipher *tfm_aes; + void *smp_data; struct discovery_state discovery; struct hci_conn_hash conn_hash; @@ -539,7 +539,6 @@ enum { HCI_CONN_RSWITCH_PEND, HCI_CONN_MODE_CHANGE_PEND, HCI_CONN_SCO_SETUP_PEND, - HCI_CONN_LE_SMP_PEND, HCI_CONN_MGMT_CONNECTED, HCI_CONN_SSP_ENABLED, HCI_CONN_SC_ENABLED, @@ -553,6 +552,7 @@ enum { HCI_CONN_FIPS, HCI_CONN_STK_ENCRYPT, HCI_CONN_AUTH_INITIATOR, + HCI_CONN_DROP, }; static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) @@ -702,7 +702,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev, return NULL; } -void hci_disconnect(struct hci_conn *conn, __u8 reason); +int hci_disconnect(struct hci_conn *conn, __u8 reason); bool hci_setup_sync(struct hci_conn *conn, __u16 handle); void hci_sco_setup(struct hci_conn *conn, __u8 status); @@ -756,9 +756,10 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status); * _get()/_drop() in it, but require the caller to have a valid ref (FIXME). */ -static inline void hci_conn_get(struct hci_conn *conn) +static inline struct hci_conn *hci_conn_get(struct hci_conn *conn) { get_device(&conn->dev); + return conn; } static inline void hci_conn_put(struct hci_conn *conn) @@ -790,7 +791,7 @@ static inline void hci_conn_drop(struct hci_conn *conn) if (!conn->out) timeo *= 2; } else { - timeo = msecs_to_jiffies(10); + timeo = 0; } break; @@ -799,7 +800,7 @@ static inline void hci_conn_drop(struct hci_conn *conn) break; default: - timeo = msecs_to_jiffies(10); + timeo = 0; break; } @@ -970,6 +971,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define lmp_host_le_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE)) #define lmp_host_le_br_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE_BREDR)) +#define hdev_is_powered(hdev) (test_bit(HCI_UP, &hdev->flags) && \ + !test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 @@ -1258,6 +1262,8 @@ bool hci_req_pending(struct hci_dev *hdev); void hci_req_add_le_scan_disable(struct hci_request *req); void hci_req_add_le_passive_scan(struct hci_request *req); +void hci_update_page_scan(struct hci_dev *hdev, struct hci_request *req); + struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param, u32 timeout); struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, @@ -1336,8 +1342,7 @@ int mgmt_user_passkey_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u32 passkey, u8 entered); -void mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, - u8 addr_type, u8 status); +void mgmt_auth_failed(struct hci_conn *conn, u8 status); void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status); void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status); void mgmt_sc_enable_complete(struct hci_dev *hdev, u8 enable, u8 status); @@ -1353,6 +1358,7 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, s8 rssi, u8 *name, u8 name_len); void mgmt_discovering(struct hci_dev *hdev, u8 discovering); +bool mgmt_powering_down(struct hci_dev *hdev); void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent); void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk); void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 8df15ad0d43..ead99f032f7 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -633,10 +633,11 @@ struct l2cap_conn { struct sk_buff_head pending_rx; struct work_struct pending_rx_work; + struct work_struct id_addr_update_work; + __u8 disc_reason; - struct delayed_work security_timer; - struct smp_chan *smp_chan; + struct l2cap_chan *smp; struct list_head chan_l; struct mutex chan_lock; @@ -708,6 +709,8 @@ enum { FLAG_EFS_ENABLE, FLAG_DEFER_SETUP, FLAG_LE_CONN_REQ_SENT, + FLAG_PENDING_SECURITY, + FLAG_HOLD_HCI_CONN, }; enum { @@ -837,18 +840,43 @@ static inline struct l2cap_chan *l2cap_chan_no_new_connection(struct l2cap_chan return NULL; } +static inline int l2cap_chan_no_recv(struct l2cap_chan *chan, struct sk_buff *skb) +{ + return -ENOSYS; +} + +static inline struct sk_buff *l2cap_chan_no_alloc_skb(struct l2cap_chan *chan, + unsigned long hdr_len, + unsigned long len, int nb) +{ + return ERR_PTR(-ENOSYS); +} + static inline void l2cap_chan_no_teardown(struct l2cap_chan *chan, int err) { } +static inline void l2cap_chan_no_close(struct l2cap_chan *chan) +{ +} + static inline void l2cap_chan_no_ready(struct l2cap_chan *chan) { } +static inline void l2cap_chan_no_state_change(struct l2cap_chan *chan, + int state, int err) +{ +} + static inline void l2cap_chan_no_defer(struct l2cap_chan *chan) { } +static inline void l2cap_chan_no_suspend(struct l2cap_chan *chan) +{ +} + static inline void l2cap_chan_no_resume(struct l2cap_chan *chan) { } @@ -911,14 +939,13 @@ int l2cap_ertm_init(struct l2cap_chan *chan); void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan); void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan); void l2cap_chan_del(struct l2cap_chan *chan, int err); -void l2cap_conn_update_id_addr(struct hci_conn *hcon); void l2cap_send_conn_req(struct l2cap_chan *chan); void l2cap_move_start(struct l2cap_chan *chan); void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan, u8 status); void __l2cap_physical_cfm(struct l2cap_chan *chan, int result); -void l2cap_conn_get(struct l2cap_conn *conn); +struct l2cap_conn *l2cap_conn_get(struct l2cap_conn *conn); void l2cap_conn_put(struct l2cap_conn *conn); int l2cap_register_user(struct l2cap_conn *conn, struct l2cap_user *user); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0a080c4de27..a2ddcf2398f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4,6 +4,7 @@ * 802.11 device and configuration interface * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> + * Copyright 2013-2014 Intel Mobile Communications 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 @@ -663,6 +664,7 @@ struct cfg80211_acl_data { * @crypto: crypto settings * @privacy: the BSS uses privacy * @auth_type: Authentication type (algorithm) + * @smps_mode: SMPS mode * @inactivity_timeout: time in seconds to determine station's inactivity. * @p2p_ctwindow: P2P CT Window * @p2p_opp_ps: P2P opportunistic PS @@ -681,6 +683,7 @@ struct cfg80211_ap_settings { struct cfg80211_crypto_settings crypto; bool privacy; enum nl80211_auth_type auth_type; + enum nl80211_smps_mode smps_mode; int inactivity_timeout; u8 p2p_ctwindow; bool p2p_opp_ps; @@ -1503,12 +1506,14 @@ enum cfg80211_signal_type { * @tsf: TSF contained in the frame that carried these IEs * @rcu_head: internal use, for freeing * @len: length of the IEs + * @from_beacon: these IEs are known to come from a beacon * @data: IE data */ struct cfg80211_bss_ies { u64 tsf; struct rcu_head rcu_head; int len; + bool from_beacon; u8 data[]; }; @@ -1605,10 +1610,12 @@ struct cfg80211_auth_request { * * @ASSOC_REQ_DISABLE_HT: Disable HT (802.11n) * @ASSOC_REQ_DISABLE_VHT: Disable VHT + * @ASSOC_REQ_USE_RRM: Declare RRM capability in this association */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), ASSOC_REQ_DISABLE_VHT = BIT(1), + ASSOC_REQ_USE_RRM = BIT(2), }; /** @@ -1800,6 +1807,7 @@ struct cfg80211_connect_params { * @WIPHY_PARAM_FRAG_THRESHOLD: wiphy->frag_threshold has changed * @WIPHY_PARAM_RTS_THRESHOLD: wiphy->rts_threshold has changed * @WIPHY_PARAM_COVERAGE_CLASS: coverage class changed + * @WIPHY_PARAM_DYN_ACK: dynack has been enabled */ enum wiphy_params_flags { WIPHY_PARAM_RETRY_SHORT = 1 << 0, @@ -1807,6 +1815,7 @@ enum wiphy_params_flags { WIPHY_PARAM_FRAG_THRESHOLD = 1 << 2, WIPHY_PARAM_RTS_THRESHOLD = 1 << 3, WIPHY_PARAM_COVERAGE_CLASS = 1 << 4, + WIPHY_PARAM_DYN_ACK = 1 << 5, }; /* @@ -1973,14 +1982,12 @@ struct cfg80211_wowlan_wakeup { /** * struct cfg80211_gtk_rekey_data - rekey data - * @kek: key encryption key - * @kck: key confirmation key - * @replay_ctr: replay counter + * @kek: key encryption key (NL80211_KEK_LEN bytes) + * @kck: key confirmation key (NL80211_KCK_LEN bytes) + * @replay_ctr: replay counter (NL80211_REPLAY_CTR_LEN bytes) */ struct cfg80211_gtk_rekey_data { - u8 kek[NL80211_KEK_LEN]; - u8 kck[NL80211_KCK_LEN]; - u8 replay_ctr[NL80211_REPLAY_CTR_LEN]; + const u8 *kek, *kck, *replay_ctr; }; /** @@ -2313,6 +2320,17 @@ struct cfg80211_qos_map { * @set_ap_chanwidth: Set the AP (including P2P GO) mode channel width for the * given interface This is used e.g. for dynamic HT 20/40 MHz channel width * changes during the lifetime of the BSS. + * + * @add_tx_ts: validate (if admitted_time is 0) or add a TX TS to the device + * with the given parameters; action frame exchange has been handled by + * userspace so this just has to modify the TX path to take the TS into + * account. + * If the admitted time is 0 just validate the parameters to make sure + * the session can be created at all; it is valid to just always return + * success for that but that may result in inefficient behaviour (handshake + * with the peer followed by immediate teardown when the addition is later + * rejected) + * @del_tx_ts: remove an existing TX TS */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -2553,6 +2571,12 @@ struct cfg80211_ops { int (*set_ap_chanwidth)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef); + + int (*add_tx_ts)(struct wiphy *wiphy, struct net_device *dev, + u8 tsid, const u8 *peer, u8 user_prio, + u16 admitted_time); + int (*del_tx_ts)(struct wiphy *wiphy, struct net_device *dev, + u8 tsid, const u8 *peer); }; /* @@ -2599,9 +2623,13 @@ 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_SUPPORTS_WMM_ADMISSION: the device supports setting up WMM + * TSPEC sessions (TID aka TSID 0-7) with the NL80211_CMD_ADD_TX_TS + * command. Standard IEEE 802.11 TSPEC setup is not yet supported, it + * needs to be able to handle Block-Ack agreements and other things. */ enum wiphy_flags { - /* use hole at 0 */ + WIPHY_FLAG_SUPPORTS_WMM_ADMISSION = BIT(0), /* use hole at 1 */ /* use hole at 2 */ WIPHY_FLAG_NETNS_OK = BIT(3), @@ -3765,11 +3793,25 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy, } /** - * cfg80211_inform_bss - inform cfg80211 of a new BSS + * enum cfg80211_bss_frame_type - frame type that the BSS data came from + * @CFG80211_BSS_FTYPE_UNKNOWN: driver doesn't know whether the data is + * from a beacon or probe response + * @CFG80211_BSS_FTYPE_BEACON: data comes from a beacon + * @CFG80211_BSS_FTYPE_PRESP: data comes from a probe response + */ +enum cfg80211_bss_frame_type { + CFG80211_BSS_FTYPE_UNKNOWN, + CFG80211_BSS_FTYPE_BEACON, + CFG80211_BSS_FTYPE_PRESP, +}; + +/** + * cfg80211_inform_bss_width - inform cfg80211 of a new BSS * * @wiphy: the wiphy reporting the BSS * @rx_channel: The channel the frame was received on * @scan_width: width of the control channel + * @ftype: frame type (if known) * @bssid: the BSSID of the BSS * @tsf: the TSF sent by the peer in the beacon/probe response (or 0) * @capability: the capability field sent by the peer @@ -3789,6 +3831,7 @@ struct cfg80211_bss * __must_check cfg80211_inform_bss_width(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, + enum cfg80211_bss_frame_type ftype, const u8 *bssid, u64 tsf, u16 capability, u16 beacon_interval, const u8 *ie, size_t ielen, s32 signal, gfp_t gfp); @@ -3796,12 +3839,13 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, static inline struct cfg80211_bss * __must_check cfg80211_inform_bss(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, + enum cfg80211_bss_frame_type ftype, const u8 *bssid, u64 tsf, u16 capability, u16 beacon_interval, const u8 *ie, size_t ielen, s32 signal, gfp_t gfp) { return cfg80211_inform_bss_width(wiphy, rx_channel, - NL80211_BSS_CHAN_WIDTH_20, + NL80211_BSS_CHAN_WIDTH_20, ftype, bssid, tsf, capability, beacon_interval, ie, ielen, signal, gfp); @@ -3902,6 +3946,7 @@ 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. * * After being asked to associate via cfg80211_ops::assoc() the driver must * call either this function or cfg80211_auth_timeout(). @@ -3910,7 +3955,8 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr); */ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss, - const u8 *buf, size_t len); + const u8 *buf, size_t len, + int uapsd_queues); /** * cfg80211_assoc_timeout - notification of timed out association @@ -4412,7 +4458,6 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr, * @buf: Management frame (header + body) * @len: length of the frame data * @flags: flags, as defined in enum nl80211_rxmgmt_flags - * @gfp: context flags * * This function is called whenever an Action frame is received for a station * mode interface, but is not processed in kernel. @@ -4423,7 +4468,7 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr, * driver is responsible for rejecting the frame. */ bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_dbm, - const u8 *buf, size_t len, u32 flags, gfp_t gfp); + const u8 *buf, size_t len, u32 flags); /** * cfg80211_mgmt_tx_status - notification of TX status for management frame diff --git a/include/net/checksum.h b/include/net/checksum.h index 87cb1903640..6465bae80a4 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -122,9 +122,7 @@ static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum) static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) { - __be32 diff[] = { ~from, to }; - - *sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum))); + *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), from), to)); } /* Implements RFC 1624 (Incremental Internet Checksum) diff --git a/include/net/codel.h b/include/net/codel.h index fe0eab32ce7..aeee2808124 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -66,7 +66,7 @@ typedef s32 codel_tdiff_t; static inline codel_time_t codel_get_time(void) { - u64 ns = ktime_to_ns(ktime_get()); + u64 ns = ktime_get_ns(); return ns >> CODEL_SHIFT; } diff --git a/include/net/dsa.h b/include/net/dsa.h index 6efce384451..58ad8c6492d 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -15,6 +15,17 @@ #include <linux/list.h> #include <linux/timer.h> #include <linux/workqueue.h> +#include <linux/of.h> +#include <linux/phy.h> +#include <linux/phy_fixed.h> + +enum dsa_tag_protocol { + DSA_TAG_PROTO_NONE = 0, + DSA_TAG_PROTO_DSA, + DSA_TAG_PROTO_TRAILER, + DSA_TAG_PROTO_EDSA, + DSA_TAG_PROTO_BRCM, +}; #define DSA_MAX_SWITCHES 4 #define DSA_MAX_PORTS 12 @@ -23,9 +34,15 @@ struct dsa_chip_data { /* * How to access the switch configuration registers. */ - struct device *mii_bus; + struct device *host_dev; int sw_addr; + /* Device tree node pointer for this specific switch chip + * used during switch setup in case additional properties + * and resources needs to be used + */ + struct device_node *of_node; + /* * The names of the switch's ports. Use "cpu" to * designate the switch port that the cpu is connected to, @@ -34,6 +51,7 @@ struct dsa_chip_data { * or any other string to indicate this is a physical port. */ char *port_names[DSA_MAX_PORTS]; + struct device_node *port_dn[DSA_MAX_PORTS]; /* * An array (with nr_chips elements) of which element [a] @@ -59,6 +77,8 @@ struct dsa_platform_data { struct dsa_chip_data *chip; }; +struct packet_type; + struct dsa_switch_tree { /* * Configuration data for the platform device that owns @@ -71,7 +91,11 @@ struct dsa_switch_tree { * protocol to use. */ struct net_device *master_netdev; - __be16 tag_protocol; + int (*rcv)(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev); + enum dsa_tag_protocol tag_protocol; /* * The switch and port to which the CPU is attached. @@ -110,15 +134,16 @@ struct dsa_switch { struct dsa_switch_driver *drv; /* - * Reference to mii bus to use. + * Reference to host device to use. */ - struct mii_bus *master_mii_bus; + struct device *master_dev; /* * Slave mii_bus and devices for the individual ports. */ u32 dsa_port_mask; u32 phys_port_mask; + u32 phys_mii_mask; struct mii_bus *slave_mii_bus; struct net_device *ports[DSA_MAX_PORTS]; }; @@ -147,15 +172,16 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) struct dsa_switch_driver { struct list_head list; - __be16 tag_protocol; + enum dsa_tag_protocol tag_protocol; int priv_size; /* * Probing and setup. */ - char *(*probe)(struct mii_bus *bus, int sw_addr); + char *(*probe)(struct device *host_dev, int sw_addr); 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); /* * Access to the switch's PHY registers. @@ -170,37 +196,64 @@ struct dsa_switch_driver { void (*poll_link)(struct dsa_switch *ds); /* + * Link state adjustment (called from libphy) + */ + void (*adjust_link)(struct dsa_switch *ds, int port, + struct phy_device *phydev); + void (*fixed_link_update)(struct dsa_switch *ds, int port, + struct fixed_phy_status *st); + + /* * ethtool hardware statistics. */ void (*get_strings)(struct dsa_switch *ds, int port, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds); + + /* + * ethtool Wake-on-LAN + */ + void (*get_wol)(struct dsa_switch *ds, int port, + struct ethtool_wolinfo *w); + int (*set_wol)(struct dsa_switch *ds, int port, + struct ethtool_wolinfo *w); + + /* + * Suspend and resume + */ + int (*suspend)(struct dsa_switch *ds); + int (*resume)(struct dsa_switch *ds); + + /* + * Port enable/disable + */ + int (*port_enable)(struct dsa_switch *ds, int port, + struct phy_device *phy); + void (*port_disable)(struct dsa_switch *ds, int port, + struct phy_device *phy); + + /* + * EEE setttings + */ + int (*set_eee)(struct dsa_switch *ds, int port, + struct phy_device *phydev, + struct ethtool_eee *e); + int (*get_eee)(struct dsa_switch *ds, int port, + struct ethtool_eee *e); }; void register_switch_driver(struct dsa_switch_driver *type); void unregister_switch_driver(struct dsa_switch_driver *type); +struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev); static inline void *ds_to_priv(struct dsa_switch *ds) { return (void *)(ds + 1); } -/* - * The original DSA tag format and some other tag formats have no - * ethertype, which means that we need to add a little hack to the - * networking receive path to make sure that received frames get - * the right ->protocol assigned to them when one of those tag - * formats is in use. - */ -static inline bool dsa_uses_dsa_tags(struct dsa_switch_tree *dst) -{ - return !!(dst->tag_protocol == htons(ETH_P_DSA)); -} - -static inline bool dsa_uses_trailer_tags(struct dsa_switch_tree *dst) +static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) { - return !!(dst->tag_protocol == htons(ETH_P_TRAILER)); + return dst->rcv != NULL; } - #endif diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h index 6667a054763..7ee2df08354 100644 --- a/include/net/flow_keys.h +++ b/include/net/flow_keys.h @@ -27,7 +27,19 @@ struct flow_keys { u8 ip_proto; }; -bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow); -__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto); +bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, + void *data, __be16 proto, int nhoff, int hlen); +static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow) +{ + return __skb_flow_dissect(skb, flow, NULL, 0, 0, 0); +} +__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, + void *data, int hlen_proto); +static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto) +{ + return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); +} u32 flow_hash_from_keys(struct flow_keys *keys); +unsigned int flow_get_hlen(const unsigned char *data, unsigned int max_len, + __be16 protocol); #endif diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index ea4271dceff..cbafa3768d4 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -6,6 +6,11 @@ #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> +struct gnet_stats_basic_cpu { + struct gnet_stats_basic_packed bstats; + struct u64_stats_sync syncp; +}; + struct gnet_dump { spinlock_t * lock; struct sk_buff * skb; @@ -27,21 +32,29 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d); int gnet_stats_copy_basic(struct gnet_dump *d, + struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); +void __gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats, + 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); -int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q); +int gnet_stats_copy_queue(struct gnet_dump *d, + struct gnet_stats_queue __percpu *cpu_q, + struct gnet_stats_queue *q, __u32 qlen); int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len); 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, spinlock_t *stats_lock, struct nlattr *opt); void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est64 *rate_est); 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, spinlock_t *stats_lock, struct nlattr *opt); bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 5fbe6568c3c..848e85cb5c6 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -242,6 +242,15 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, #endif } +static inline unsigned long +inet_csk_rto_backoff(const struct inet_connection_sock *icsk, + unsigned long max_when) +{ + u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff; + + return (unsigned long)min_t(u64, when, max_when); +} + struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); struct request_sock *inet_csk_search_req(const struct sock *sk, diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 01d590ee5e7..80479abddf7 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -61,7 +61,6 @@ struct inet_peer { struct inet_peer_base { struct inet_peer __rcu *root; seqlock_t lock; - u32 flush_seq; int total; }; diff --git a/include/net/ip.h b/include/net/ip.h index db4a771b9ef..0bb62070292 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -180,8 +180,10 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0; } -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, - __be32 saddr, const struct ip_reply_arg *arg, +void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, + const struct ip_options *sopt, + __be32 daddr, __be32 saddr, + const struct ip_reply_arg *arg, unsigned int len); #define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field) @@ -229,8 +231,6 @@ static inline int inet_is_local_reserved_port(struct net *net, int port) } #endif -extern int sysctl_ip_nonlocal_bind; - /* From inetpeer.c */ extern int inet_peer_threshold; extern int inet_peer_minttl; @@ -364,6 +364,14 @@ static inline void inet_set_txhash(struct sock *sk) sk->sk_txhash = flow_hash_from_keys(&keys); } +static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto) +{ + const struct iphdr *iph = skb_gro_network_header(skb); + + return csum_tcpudp_nofold(iph->saddr, iph->daddr, + skb_gro_len(skb), proto, 0); +} + /* * Map a multicast IP onto multicast MAC for type ethernet. */ @@ -505,7 +513,14 @@ int ip_forward(struct sk_buff *skb); void ip_options_build(struct sk_buff *skb, struct ip_options *opt, __be32 daddr, struct rtable *rt, int is_frag); -int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb); + +int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb, + const struct ip_options *sopt); +static inline int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb) +{ + return __ip_options_echo(dopt, skb, &IPCB(skb)->opt); +} + void ip_options_fragment(struct sk_buff *skb); int ip_options_compile(struct net *net, struct ip_options *opt, struct sk_buff *skb); @@ -542,6 +557,10 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, u32 info); +bool icmp_global_allow(void); +extern int sysctl_icmp_msgs_per_sec; +extern int sysctl_icmp_msgs_burst; + #ifdef CONFIG_PROC_FS int ip_misc_proc_init(void); #endif diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h index 55236cb7117..1a49b73f7f6 100644 --- a/include/net/ip6_checksum.h +++ b/include/net/ip6_checksum.h @@ -48,6 +48,14 @@ static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto) skb->len, proto, 0)); } +static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + + return ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, + skb_gro_len(skb), proto, 0)); +} + static __inline__ __sum16 tcp_v6_check(int len, const struct in6_addr *saddr, const struct in6_addr *daddr, diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 9922093f575..dc9d2a27c31 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -65,7 +65,8 @@ struct fnhe_hash_bucket { struct fib_nh_exception __rcu *chain; }; -#define FNHE_HASH_SIZE 2048 +#define FNHE_HASH_SHIFT 11 +#define FNHE_HASH_SIZE (1 << FNHE_HASH_SHIFT) #define FNHE_RECLAIM_DEPTH 5 struct fib_nh { @@ -87,7 +88,7 @@ struct fib_nh { int nh_saddr_genid; struct rtable __rcu * __percpu *nh_pcpu_rth_output; struct rtable __rcu *nh_rth_input; - struct fnhe_hash_bucket *nh_exceptions; + struct fnhe_hash_bucket __rcu *nh_exceptions; }; /* diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 8dd8cab88b8..7f538ba6e26 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -10,6 +10,7 @@ #include <net/gro_cells.h> #include <net/inet_ecn.h> #include <net/ip.h> +#include <net/netns/generic.h> #include <net/rtnetlink.h> #if IS_ENABLED(CONFIG_IPV6) @@ -31,6 +32,13 @@ struct ip_tunnel_6rd_parm { }; #endif +struct ip_tunnel_encap { + __u16 type; + __u16 flags; + __be16 sport; + __be16 dport; +}; + struct ip_tunnel_prl_entry { struct ip_tunnel_prl_entry __rcu *next; __be32 addr; @@ -56,13 +64,18 @@ struct ip_tunnel { /* These four fields used only by GRE */ __u32 i_seqno; /* The last seen seqno */ __u32 o_seqno; /* The last output seqno */ - int hlen; /* Precalculated header length */ + int tun_hlen; /* Precalculated header length */ int mlink; struct ip_tunnel_dst __percpu *dst_cache; struct ip_tunnel_parm parms; + int encap_hlen; /* Encap header length (FOU,GUE) */ + struct ip_tunnel_encap encap; + + int hlen; /* tun_hlen + encap_hlen */ + /* for SIT */ #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd_parm ip6rd; @@ -114,6 +127,8 @@ 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); 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); struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, @@ -131,6 +146,8 @@ 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_dst_reset_all(struct ip_tunnel *t); +int ip_tunnel_encap_setup(struct ip_tunnel *t, + struct ip_tunnel_encap *ipencap); /* Extract dsfield from inner protocol */ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 624a8a54806..576d7f0bed5 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -535,6 +535,7 @@ struct ip_vs_conn { union nf_inet_addr daddr; /* destination address */ volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ + __u16 daf; /* Address family of the dest */ #ifdef CONFIG_NET_NS struct net *net; /* Name space */ #endif @@ -648,6 +649,9 @@ struct ip_vs_dest_user_kern { /* thresholds for active connections */ u32 u_threshold; /* upper threshold */ u32 l_threshold; /* lower threshold */ + + /* Address family of addr */ + u16 af; }; @@ -986,6 +990,10 @@ struct netns_ipvs { char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; /* net name space ptr */ struct net *net; /* Needed by timer routines */ + /* Number of heterogeneous destinations, needed because + * heterogeneous are not supported when synchronization is + * enabled */ + unsigned int mixed_address_family_dests; }; #define DEFAULT_SYNC_THRESHOLD 3 @@ -1210,7 +1218,7 @@ static inline void __ip_vs_conn_put(struct ip_vs_conn *cp) void ip_vs_conn_put(struct ip_vs_conn *cp); void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport); -struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, +struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, const union nf_inet_addr *daddr, __be16 dport, unsigned int flags, struct ip_vs_dest *dest, __u32 fwmark); @@ -1396,8 +1404,9 @@ void ip_vs_unregister_nl_ioctl(void); int ip_vs_control_init(void); void ip_vs_control_cleanup(void); struct ip_vs_dest * -ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, - __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, +ip_vs_find_dest(struct net *net, int svc_af, int dest_af, + const union nf_inet_addr *daddr, __be16 dport, + const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol, __u32 fwmark, __u32 flags); void ip_vs_try_bind_dest(struct ip_vs_conn *cp); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index a2db816e846..97f47201243 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -121,6 +121,7 @@ struct frag_hdr { /* sysctls */ extern int sysctl_mld_max_msf; +extern int sysctl_mld_qrv; #define _DEVINC(net, statname, modifier, idev, field) \ ({ \ @@ -287,7 +288,8 @@ struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt); -bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb); +bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, + const struct inet6_skb_parm *opt); static inline bool ipv6_accept_ra(struct inet6_dev *idev) { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index dae2e24616e..0ad1f47d2dc 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -4,6 +4,7 @@ * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> + * Copyright 2013-2014 Intel Mobile Communications 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 @@ -1226,7 +1227,8 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); * * @IEEE80211_KEY_FLAG_GENERATE_IV: This flag should be set by the * driver to indicate that it requires IV generation for this - * particular key. + * particular key. Setting this flag does not necessarily mean that SKBs + * will have sufficient tailroom for ICV or MIC. * @IEEE80211_KEY_FLAG_GENERATE_MMIC: This flag should be set by * the driver for a TKIP key if it requires Michael MIC * generation in software. @@ -1238,7 +1240,9 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); * @IEEE80211_KEY_FLAG_PUT_IV_SPACE: This flag should be set by the driver * if space should be prepared for the IV, but the IV * itself should not be generated. Do not set together with - * @IEEE80211_KEY_FLAG_GENERATE_IV on the same key. + * @IEEE80211_KEY_FLAG_GENERATE_IV on the same key. Setting this flag does + * not necessarily mean that SKBs will have sufficient tailroom for ICV or + * MIC. * @IEEE80211_KEY_FLAG_RX_MGMT: This key will be used to decrypt received * management frames. The flag can help drivers that have a hardware * crypto implementation that doesn't deal with management frames @@ -1405,7 +1409,7 @@ 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 - * @wme: indicates whether the STA supports WME. Only valid during AP-mode. + * @wme: indicates whether the STA supports QoS/WME. * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *), size is determined in hw information. * @uapsd_queues: bitmap of queues configured for uapsd. Only valid @@ -1533,16 +1537,6 @@ struct ieee80211_tx_control { * @IEEE80211_HW_MFP_CAPABLE: * Hardware supports management frame protection (MFP, IEEE 802.11w). * - * @IEEE80211_HW_SUPPORTS_STATIC_SMPS: - * Hardware supports static spatial multiplexing powersave, - * ie. can turn off all but one chain even on HT connections - * that should be using more chains. - * - * @IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS: - * Hardware supports dynamic spatial multiplexing powersave, - * ie. can turn off all but one chain and then wake the rest - * up as required after, for example, rts/cts handshake. - * * @IEEE80211_HW_SUPPORTS_UAPSD: * Hardware supports Unscheduled Automatic Power Save Delivery * (U-APSD) in managed mode. The mode is configured with @@ -1606,6 +1600,9 @@ struct ieee80211_tx_control { * is not enabled the default action is to disconnect when getting the * CSA frame. * + * @IEEE80211_HW_SUPPORTS_CLONED_SKBS: The driver will never modify the payload + * or tailroom of TX skbs without copying them first. + * * @IEEE80211_SINGLE_HW_SCAN_ON_ALL_BANDS: The HW supports scanning on all bands * in one command, mac80211 doesn't have to run separate scans per band. */ @@ -1625,8 +1622,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_DYNAMIC_PS = 1<<12, IEEE80211_HW_MFP_CAPABLE = 1<<13, IEEE80211_HW_WANT_MONITOR_VIF = 1<<14, - IEEE80211_HW_SUPPORTS_STATIC_SMPS = 1<<15, - IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS = 1<<16, + /* free slots */ IEEE80211_HW_SUPPORTS_UAPSD = 1<<17, IEEE80211_HW_REPORTS_TX_ACK_STATUS = 1<<18, IEEE80211_HW_CONNECTION_MONITOR = 1<<19, @@ -1639,7 +1635,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_TIMING_BEACON_ONLY = 1<<26, IEEE80211_HW_SUPPORTS_HT_CCK_RATES = 1<<27, IEEE80211_HW_CHANCTX_STA_CSA = 1<<28, - /* bit 29 unused */ + IEEE80211_HW_SUPPORTS_CLONED_SKBS = 1<<29, IEEE80211_SINGLE_HW_SCAN_ON_ALL_BANDS = 1<<30, }; @@ -2666,7 +2662,9 @@ enum ieee80211_roc_type { * * @set_coverage_class: Set slot time for given coverage class as specified * in IEEE 802.11-2007 section 17.3.8.6 and modify ACK timeout - * accordingly. This callback is not required and may sleep. + * accordingly; coverage class equals to -1 to enable ACK timeout + * estimation algorithm (dynack). To disable dynack set valid value for + * coverage class. This callback is not required and may sleep. * * @testmode_cmd: Implement a cfg80211 test mode command. The passed @vif may * be %NULL. The callback can sleep. @@ -2950,7 +2948,7 @@ struct ieee80211_ops { int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); - void (*set_coverage_class)(struct ieee80211_hw *hw, u8 coverage_class); + void (*set_coverage_class)(struct ieee80211_hw *hw, s16 coverage_class); #ifdef CONFIG_NL80211_TESTMODE int (*testmode_cmd)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void *data, int len); diff --git a/include/net/mld.h b/include/net/mld.h index faa1d161bf2..01d75130349 100644 --- a/include/net/mld.h +++ b/include/net/mld.h @@ -88,12 +88,15 @@ struct mld2_query { #define MLDV2_QQIC_EXP(value) (((value) >> 4) & 0x07) #define MLDV2_QQIC_MAN(value) ((value) & 0x0f) +#define MLD_EXP_MIN_LIMIT 32768UL +#define MLDV1_MRD_MAX_COMPAT (MLD_EXP_MIN_LIMIT - 1) + static inline unsigned long mldv2_mrc(const struct mld2_query *mlh2) { /* RFC3810, 5.1.3. Maximum Response Code */ unsigned long ret, mc_mrc = ntohs(mlh2->mld2q_mrc); - if (mc_mrc < 32768) { + if (mc_mrc < MLD_EXP_MIN_LIMIT) { ret = mc_mrc; } else { unsigned long mc_man, mc_exp; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 47f425464f8..f60558d0254 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -373,7 +373,7 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) return 0; } -#ifdef CONFIG_BRIDGE_NETFILTER +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) { unsigned int seq, hh_alen; diff --git a/include/net/netfilter/ipv4/nf_nat_masquerade.h b/include/net/netfilter/ipv4/nf_nat_masquerade.h new file mode 100644 index 00000000000..a9c001c646d --- /dev/null +++ b/include/net/netfilter/ipv4/nf_nat_masquerade.h @@ -0,0 +1,14 @@ +#ifndef _NF_NAT_MASQUERADE_IPV4_H_ +#define _NF_NAT_MASQUERADE_IPV4_H_ + +#include <net/netfilter/nf_nat.h> + +unsigned int +nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, + const struct nf_nat_range *range, + const struct net_device *out); + +void nf_nat_masquerade_ipv4_register_notifier(void); +void nf_nat_masquerade_ipv4_unregister_notifier(void); + +#endif /*_NF_NAT_MASQUERADE_IPV4_H_ */ diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h index 931fbf81217..f713b5a31d6 100644 --- a/include/net/netfilter/ipv4/nf_reject.h +++ b/include/net/netfilter/ipv4/nf_reject.h @@ -98,7 +98,7 @@ static void nf_send_reset(struct sk_buff *oldskb, int hook) nf_ct_attach(nskb, oldskb); -#ifdef CONFIG_BRIDGE_NETFILTER +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip_local_out for bridged traffic, the MAC source on * the RST will be ours, instead of the destination's. This confuses * some routers/firewalls, and they drop the packet. So we need to diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h new file mode 100644 index 00000000000..0a13396cd39 --- /dev/null +++ b/include/net/netfilter/ipv6/nf_nat_masquerade.h @@ -0,0 +1,10 @@ +#ifndef _NF_NAT_MASQUERADE_IPV6_H_ +#define _NF_NAT_MASQUERADE_IPV6_H_ + +unsigned int +nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, + const struct net_device *out); +void nf_nat_masquerade_ipv6_register_notifier(void); +void nf_nat_masquerade_ipv6_unregister_notifier(void); + +#endif /* _NF_NAT_MASQUERADE_IPV6_H_ */ diff --git a/include/net/netfilter/ipv6/nf_reject.h b/include/net/netfilter/ipv6/nf_reject.h index 710d17ed70b..7a10cfcd8e3 100644 --- a/include/net/netfilter/ipv6/nf_reject.h +++ b/include/net/netfilter/ipv6/nf_reject.h @@ -147,7 +147,7 @@ static void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) nf_ct_attach(nskb, oldskb); -#ifdef CONFIG_BRIDGE_NETFILTER +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip6_local_out for bridged traffic, the MAC source on * the RST will be ours, instead of the destination's. This confuses * some routers/firewalls, and they drop the packet. So we need to diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index a71dd333ac6..344b1ab1922 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -32,10 +32,8 @@ struct nf_conn_nat { struct hlist_node bysource; struct nf_conn *ct; union nf_conntrack_nat_help help; -#if defined(CONFIG_IP_NF_TARGET_MASQUERADE) || \ - defined(CONFIG_IP_NF_TARGET_MASQUERADE_MODULE) || \ - defined(CONFIG_IP6_NF_TARGET_MASQUERADE) || \ - defined(CONFIG_IP6_NF_TARGET_MASQUERADE_MODULE) +#if IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV4) || \ + IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV6) int masq_index; #endif }; @@ -68,8 +66,8 @@ static inline bool nf_nat_oif_changed(unsigned int hooknum, struct nf_conn_nat *nat, const struct net_device *out) { -#if IS_ENABLED(CONFIG_IP_NF_TARGET_MASQUERADE) || \ - IS_ENABLED(CONFIG_IP6_NF_TARGET_MASQUERADE) +#if IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV4) || \ + IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV6) return nat->masq_index && hooknum == NF_INET_POST_ROUTING && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL && nat->masq_index != out->ifindex; diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h index 5a2919b2e09..340c013795a 100644 --- a/include/net/netfilter/nf_nat_l3proto.h +++ b/include/net/netfilter/nf_nat_l3proto.h @@ -42,8 +42,83 @@ const struct nf_nat_l3proto *__nf_nat_l3proto_find(u8 l3proto); int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum); + +unsigned int nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)); + +unsigned int nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)); + +unsigned int nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)); + +unsigned int nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)); + int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen); +unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)); + +unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)); + +unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)); + +unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + unsigned int (*do_chain)(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct)); + #endif /* _NF_NAT_L3PROTO_H */ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c4d86198d3d..3d7292392fa 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -241,6 +241,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @dtype: data type (verdict or numeric type defined by userspace) * @size: maximum set size * @nelems: number of elements + * @policy: set parameterization (see enum nft_set_policies) * @ops: set ops * @flags: set flags * @klen: key length @@ -255,6 +256,7 @@ struct nft_set { u32 dtype; u32 size; u32 nelems; + u16 policy; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; u16 flags; diff --git a/include/net/netfilter/nft_masq.h b/include/net/netfilter/nft_masq.h new file mode 100644 index 00000000000..c72729f954f --- /dev/null +++ b/include/net/netfilter/nft_masq.h @@ -0,0 +1,16 @@ +#ifndef _NFT_MASQ_H_ +#define _NFT_MASQ_H_ + +struct nft_masq { + u32 flags; +}; + +extern const struct nla_policy nft_masq_policy[]; + +int nft_masq_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]); + +int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr); + +#endif /* _NFT_MASQ_H_ */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index aec5e12f9f1..24945cefc4f 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -76,6 +76,7 @@ struct netns_ipv4 { int sysctl_tcp_ecn; int sysctl_ip_no_pmtu_disc; int sysctl_ip_fwd_use_pmtu; + int sysctl_ip_nonlocal_bind; int sysctl_fwmark_reflect; int sysctl_tcp_fwmark_accept; diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 3492434baf8..9da798256f0 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -13,6 +13,19 @@ struct ctl_table_header; struct xfrm_policy_hash { struct hlist_head *table; unsigned int hmask; + u8 dbits4; + u8 sbits4; + u8 dbits6; + u8 sbits6; +}; + +struct xfrm_policy_hthresh { + struct work_struct work; + seqlock_t lock; + u8 lbits4; + u8 rbits4; + u8 lbits6; + u8 rbits6; }; struct netns_xfrm { @@ -41,6 +54,7 @@ struct netns_xfrm { struct xfrm_policy_hash policy_bydst[XFRM_POLICY_MAX * 2]; unsigned int policy_count[XFRM_POLICY_MAX * 2]; struct work_struct policy_hash_work; + struct xfrm_policy_hthresh policy_hthresh; struct sock *nlsk; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 6da46dcf104..ef44ad9a642 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -20,11 +20,7 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); static inline unsigned long __cls_set_class(unsigned long *clp, unsigned long cl) { - unsigned long old_cl; - - old_cl = *clp; - *clp = cl; - return old_cl; + return xchg(clp, cl); } static inline unsigned long @@ -137,7 +133,7 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr); -void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts); +void tcf_exts_destroy(struct tcf_exts *exts); 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); diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index ec030cd7661..8bbe626e9ec 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -50,7 +50,7 @@ typedef long psched_tdiff_t; static inline psched_time_t psched_get_time(void) { - return PSCHED_NS2TICKS(ktime_to_ns(ktime_get())); + return PSCHED_NS2TICKS(ktime_get_ns()); } static inline psched_tdiff_t diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 620e086c0cb..f12669819d1 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -6,6 +6,7 @@ #include <linux/rcupdate.h> #include <linux/pkt_sched.h> #include <linux/pkt_cls.h> +#include <linux/percpu.h> #include <net/gen_stats.h> #include <net/rtnetlink.h> @@ -58,6 +59,7 @@ struct Qdisc { * multiqueue device. */ #define TCQ_F_WARN_NONWC (1 << 16) +#define TCQ_F_CPUSTATS 0x20 /* run using percpu statistics */ u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; @@ -83,9 +85,15 @@ struct Qdisc { */ unsigned long state; struct sk_buff_head q; - struct gnet_stats_basic_packed bstats; + union { + struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_cpu __percpu *cpu_bstats; + } __packed; unsigned int __state; - struct gnet_stats_queue qstats; + union { + struct gnet_stats_queue qstats; + struct gnet_stats_queue __percpu *cpu_qstats; + } __packed; struct rcu_head rcu_head; int padded; atomic_t refcnt; @@ -143,7 +151,7 @@ struct Qdisc_class_ops { void (*walk)(struct Qdisc *, struct qdisc_walker * arg); /* Filter manipulation */ - struct tcf_proto ** (*tcf_chain)(struct Qdisc *, unsigned long); + struct tcf_proto __rcu ** (*tcf_chain)(struct Qdisc *, unsigned long); unsigned long (*bind_tcf)(struct Qdisc *, unsigned long, u32 classid); void (*unbind_tcf)(struct Qdisc *, unsigned long); @@ -212,8 +220,8 @@ struct tcf_proto_ops { struct tcf_proto { /* Fast access part */ - struct tcf_proto *next; - void *root; + struct tcf_proto __rcu *next; + void __rcu *root; int (*classify)(struct sk_buff *, const struct tcf_proto *, struct tcf_result *); @@ -225,6 +233,7 @@ struct tcf_proto { struct Qdisc *q; void *data; const struct tcf_proto_ops *ops; + struct rcu_head rcu; }; struct qdisc_skb_cb { @@ -260,7 +269,9 @@ static inline spinlock_t *qdisc_lock(struct Qdisc *qdisc) static inline struct Qdisc *qdisc_root(const struct Qdisc *qdisc) { - return qdisc->dev_queue->qdisc; + struct Qdisc *q = rcu_dereference_rtnl(qdisc->dev_queue->qdisc); + + return q; } static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) @@ -377,7 +388,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); void tcf_destroy(struct tcf_proto *tp); -void tcf_destroy_chain(struct tcf_proto **fl); +void tcf_destroy_chain(struct tcf_proto __rcu **fl); /* 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) @@ -385,7 +396,7 @@ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) struct Qdisc *qdisc; for (; i < dev->num_tx_queues; i++) { - qdisc = netdev_get_tx_queue(dev, i)->qdisc; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); if (qdisc) { spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); @@ -403,13 +414,18 @@ static inline void qdisc_reset_all_tx(struct net_device *dev) static inline bool qdisc_all_tx_empty(const struct net_device *dev) { unsigned int i; + + rcu_read_lock(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - const struct Qdisc *q = txq->qdisc; + const struct Qdisc *q = rcu_dereference(txq->qdisc); - if (q->q.qlen) + if (q->q.qlen) { + rcu_read_unlock(); return false; + } } + rcu_read_unlock(); return true; } @@ -417,9 +433,10 @@ static inline bool qdisc_all_tx_empty(const struct net_device *dev) static inline bool qdisc_tx_changing(const struct net_device *dev) { unsigned int i; + for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (txq->qdisc != txq->qdisc_sleeping) + if (rcu_access_pointer(txq->qdisc) != txq->qdisc_sleeping) return true; } return false; @@ -429,9 +446,10 @@ static inline bool qdisc_tx_changing(const struct net_device *dev) static inline bool qdisc_tx_is_noop(const struct net_device *dev) { unsigned int i; + for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (txq->qdisc != &noop_qdisc) + if (rcu_access_pointer(txq->qdisc) != &noop_qdisc) return false; } return true; @@ -477,6 +495,10 @@ static inline int qdisc_enqueue_root(struct sk_buff *skb, struct Qdisc *sch) return qdisc_enqueue(skb, sch) & NET_XMIT_MASK; } +static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) +{ + return q->flags & TCQ_F_CPUSTATS; +} static inline void bstats_update(struct gnet_stats_basic_packed *bstats, const struct sk_buff *skb) @@ -485,17 +507,62 @@ static inline void bstats_update(struct gnet_stats_basic_packed *bstats, bstats->packets += skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1; } +static inline void qdisc_bstats_update_cpu(struct Qdisc *sch, + const struct sk_buff *skb) +{ + struct gnet_stats_basic_cpu *bstats = + this_cpu_ptr(sch->cpu_bstats); + + u64_stats_update_begin(&bstats->syncp); + bstats_update(&bstats->bstats, skb); + u64_stats_update_end(&bstats->syncp); +} + static inline void qdisc_bstats_update(struct Qdisc *sch, const struct sk_buff *skb) { bstats_update(&sch->bstats, skb); } +static inline void qdisc_qstats_backlog_dec(struct Qdisc *sch, + const struct sk_buff *skb) +{ + sch->qstats.backlog -= qdisc_pkt_len(skb); +} + +static inline void qdisc_qstats_backlog_inc(struct Qdisc *sch, + const struct sk_buff *skb) +{ + sch->qstats.backlog += qdisc_pkt_len(skb); +} + +static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count) +{ + sch->qstats.drops += count; +} + +static inline void qdisc_qstats_drop(struct Qdisc *sch) +{ + sch->qstats.drops++; +} + +static inline void qdisc_qstats_drop_cpu(struct Qdisc *sch) +{ + struct gnet_stats_queue *qstats = this_cpu_ptr(sch->cpu_qstats); + + qstats->drops++; +} + +static inline void qdisc_qstats_overlimit(struct Qdisc *sch) +{ + sch->qstats.overlimits++; +} + static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff_head *list) { __skb_queue_tail(list, skb); - sch->qstats.backlog += qdisc_pkt_len(skb); + qdisc_qstats_backlog_inc(sch, skb); return NET_XMIT_SUCCESS; } @@ -511,7 +578,7 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct Qdisc *sch, struct sk_buff *skb = __skb_dequeue(list); if (likely(skb != NULL)) { - sch->qstats.backlog -= qdisc_pkt_len(skb); + qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); } @@ -530,7 +597,7 @@ static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, if (likely(skb != NULL)) { unsigned int len = qdisc_pkt_len(skb); - sch->qstats.backlog -= len; + qdisc_qstats_backlog_dec(sch, skb); kfree_skb(skb); return len; } @@ -549,7 +616,7 @@ static inline struct sk_buff *__qdisc_dequeue_tail(struct Qdisc *sch, struct sk_buff *skb = __skb_dequeue_tail(list); if (likely(skb != NULL)) - sch->qstats.backlog -= qdisc_pkt_len(skb); + qdisc_qstats_backlog_dec(sch, skb); return skb; } @@ -631,14 +698,14 @@ static inline unsigned int qdisc_queue_drop(struct Qdisc *sch) static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) { kfree_skb(skb); - sch->qstats.drops++; + qdisc_qstats_drop(sch); return NET_XMIT_DROP; } static inline int qdisc_reshape_fail(struct sk_buff *skb, struct Qdisc *sch) { - sch->qstats.drops++; + qdisc_qstats_drop(sch); #ifdef CONFIG_NET_CLS_ACT if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch)) diff --git a/include/net/snmp.h b/include/net/snmp.h index f1f27fdbb0d..8fd2f498782 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -146,19 +146,15 @@ struct linux_xfrm_mib { #define SNMP_ADD_STATS(mib, field, addend) \ this_cpu_add(mib->mibs[field], addend) -/* - * Use "__typeof__(*mib) *ptr" instead of "__typeof__(mib) ptr" - * to make @ptr a non-percpu pointer. - */ #define SNMP_UPD_PO_STATS(mib, basefield, addend) \ do { \ - __typeof__(*mib->mibs) *ptr = mib->mibs; \ + __typeof__((mib->mibs) + 0) ptr = mib->mibs; \ this_cpu_inc(ptr[basefield##PKTS]); \ this_cpu_add(ptr[basefield##OCTETS], addend); \ } while (0) #define SNMP_UPD_PO_STATS_BH(mib, basefield, addend) \ do { \ - __typeof__(*mib->mibs) *ptr = mib->mibs; \ + __typeof__((mib->mibs) + 0) ptr = mib->mibs; \ __this_cpu_inc(ptr[basefield##PKTS]); \ __this_cpu_add(ptr[basefield##OCTETS], addend); \ } while (0) diff --git a/include/net/sock.h b/include/net/sock.h index b9a5bd0ed9f..515a4d01e93 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1574,7 +1574,12 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, void sock_wfree(struct sk_buff *skb); void skb_orphan_partial(struct sk_buff *skb); void sock_rfree(struct sk_buff *skb); +void sock_efree(struct sk_buff *skb); +#ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); +#else +#define sock_edemux(skb) sock_efree(skb) +#endif int sock_setsockopt(struct socket *sock, int level, int op, char __user *optval, unsigned int optlen); @@ -2041,6 +2046,7 @@ void sk_stop_timer(struct sock *sk, struct timer_list *timer); int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); +struct sk_buff *sock_dequeue_err_skb(struct sock *sk); /* * Recover an error report and clear atomically @@ -2193,6 +2199,8 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, sk->sk_stamp = skb->tstamp; } +void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags); + /** * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet @@ -2200,7 +2208,13 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, * * Note : callers should take care of initial *tx_flags value (usually 0) */ -void sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags); +static inline void sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags) +{ + if (unlikely(sk->sk_tsflags)) + __sock_tx_timestamp(sk, tx_flags); + if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) + *tx_flags |= SKBTX_WIFI_STATUS; +} /** * sk_eat_skb - Release a skb if it is no longer needed diff --git a/include/net/tcp.h b/include/net/tcp.h index 590e01a476a..ba2f9d03076 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -672,6 +672,12 @@ void tcp_send_window_probe(struct sock *sk); */ #define tcp_time_stamp ((__u32)(jiffies)) +static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) +{ + return skb->skb_mstamp.stamp_jiffies; +} + + #define tcp_flag_byte(th) (((u_int8_t *)th)[13]) #define TCPHDR_FIN 0x01 @@ -690,15 +696,18 @@ void tcp_send_window_probe(struct sock *sk); * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately. */ struct tcp_skb_cb { - union { - struct inet_skb_parm h4; -#if IS_ENABLED(CONFIG_IPV6) - struct inet6_skb_parm h6; -#endif - } header; /* For incoming frames */ __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ - __u32 when; /* used to compute rtt's */ + union { + /* Note : tcp_tw_isn is used in input path only + * (isn chosen by tcp_timewait_state_process()) + * + * tcp_gso_segs is used in write queue only, + * cf tcp_skb_pcount() + */ + __u32 tcp_tw_isn; + __u32 tcp_gso_segs; + }; __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ __u8 sacked; /* State flags for SACK/FACK. */ @@ -714,33 +723,32 @@ struct tcp_skb_cb { __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ /* 1 byte hole */ __u32 ack_seq; /* Sequence number ACK'd */ + union { + struct inet_skb_parm h4; +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_skb_parm h6; +#endif + } header; /* For incoming frames */ }; #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) -/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set - * - * If we receive a SYN packet with these bits set, it means a network is - * playing bad games with TOS bits. In order to avoid possible false congestion - * notifications, we disable TCP ECN negociation. +/* Due to TSO, an SKB can be composed of multiple actual + * packets. To keep these tracked properly, we use this. */ -static inline void -TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb, - struct net *net) +static inline int tcp_skb_pcount(const struct sk_buff *skb) { - const struct tcphdr *th = tcp_hdr(skb); + return TCP_SKB_CB(skb)->tcp_gso_segs; +} - if (net->ipv4.sysctl_tcp_ecn && th->ece && th->cwr && - INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield)) - inet_rsk(req)->ecn_ok = 1; +static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs) +{ + TCP_SKB_CB(skb)->tcp_gso_segs = segs; } -/* Due to TSO, an SKB can be composed of multiple actual - * packets. To keep these tracked properly, we use this. - */ -static inline int tcp_skb_pcount(const struct sk_buff *skb) +static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs) { - return skb_shinfo(skb)->gso_segs; + TCP_SKB_CB(skb)->tcp_gso_segs += segs; } /* This is valid iff tcp_skb_pcount() > 1. */ @@ -755,8 +763,17 @@ enum tcp_ca_event { CA_EVENT_CWND_RESTART, /* congestion window restart */ CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */ CA_EVENT_LOSS, /* loss timeout */ - CA_EVENT_FAST_ACK, /* in sequence ack */ - CA_EVENT_SLOW_ACK, /* other ack */ + CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */ + CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */ + CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */ + CA_EVENT_NON_DELAYED_ACK, +}; + +/* Information about inbound ACK, passed to cong_ops->in_ack_event() */ +enum tcp_ca_ack_event_flags { + CA_ACK_SLOWPATH = (1 << 0), /* In slow path processing */ + CA_ACK_WIN_UPDATE = (1 << 1), /* ACK updated window */ + CA_ACK_ECE = (1 << 2), /* ECE bit is set on ack */ }; /* @@ -766,7 +783,10 @@ enum tcp_ca_event { #define TCP_CA_MAX 128 #define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX) +/* Algorithm can be set on socket without CAP_NET_ADMIN privileges */ #define TCP_CONG_NON_RESTRICTED 0x1 +/* Requires ECN/ECT set on all packets */ +#define TCP_CONG_NEEDS_ECN 0x2 struct tcp_congestion_ops { struct list_head list; @@ -785,6 +805,8 @@ struct tcp_congestion_ops { void (*set_state)(struct sock *sk, u8 new_state); /* call when cwnd event occurs (optional) */ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); + /* call when ack arrives (optional) */ + void (*in_ack_event)(struct sock *sk, u32 flags); /* new value of cwnd after loss (optional) */ u32 (*undo_cwnd)(struct sock *sk); /* hook for packet ack accounting (optional) */ @@ -799,6 +821,7 @@ struct tcp_congestion_ops { int tcp_register_congestion_control(struct tcp_congestion_ops *type); void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); +void tcp_assign_congestion_control(struct sock *sk); void tcp_init_congestion_control(struct sock *sk); void tcp_cleanup_congestion_control(struct sock *sk); int tcp_set_default_congestion_control(const char *name); @@ -807,14 +830,20 @@ void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name); -int tcp_slow_start(struct tcp_sock *tp, u32 acked); +void tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w); -extern struct tcp_congestion_ops tcp_init_congestion_ops; u32 tcp_reno_ssthresh(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); extern struct tcp_congestion_ops tcp_reno; +static inline bool tcp_ca_needs_ecn(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; +} + static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/include/net/udp.h b/include/net/udp.h index 70f941368ac..07f9b70962f 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -158,6 +158,24 @@ static inline __sum16 udp_v4_check(int len, __be32 saddr, void udp_set_csum(bool nocheck, struct sk_buff *skb, __be32 saddr, __be32 daddr, int len); +struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, + struct udphdr *uh); +int udp_gro_complete(struct sk_buff *skb, int nhoff); + +static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) +{ + struct udphdr *uh; + unsigned int hlen, off; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*uh); + uh = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) + uh = skb_gro_header_slow(skb, hlen, off); + + return uh; +} + /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ static inline void udp_lib_hash(struct sock *sk) { @@ -221,7 +239,8 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg); 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, - netdev_features_t features); + netdev_features_t features, + bool is_ipv6); int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int udp_lib_setsockopt(struct sock *sk, int level, int optname, diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index ffd69cbded3..a47790bcaa3 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -1,6 +1,14 @@ #ifndef __NET_UDP_TUNNEL_H #define __NET_UDP_TUNNEL_H +#include <net/ip_tunnels.h> +#include <net/udp.h> + +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6.h> +#include <net/addrconf.h> +#endif + struct udp_port_cfg { u8 family; @@ -26,7 +34,80 @@ struct udp_port_cfg { use_udp6_rx_checksums:1; }; -int udp_sock_create(struct net *net, struct udp_port_cfg *cfg, - struct socket **sockp); +int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, + struct socket **sockp); + +#if IS_ENABLED(CONFIG_IPV6) +int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, + struct socket **sockp); +#else +static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, + struct socket **sockp) +{ + return 0; +} +#endif + +static inline int udp_sock_create(struct net *net, + struct udp_port_cfg *cfg, + struct socket **sockp) +{ + if (cfg->family == AF_INET) + return udp_sock_create4(net, cfg, sockp); + + if (cfg->family == AF_INET6) + return udp_sock_create6(net, cfg, sockp); + + return -EPFNOSUPPORT; +} + +typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); +typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); + +struct udp_tunnel_sock_cfg { + void *sk_user_data; /* user data used by encap_rcv call back */ + /* Used for setting up udp_sock fields, see udp.h for details */ + __u8 encap_type; + udp_tunnel_encap_rcv_t encap_rcv; + udp_tunnel_encap_destroy_t encap_destroy; +}; + +/* Setup the given (UDP) sock to receive UDP encapsulated packets */ +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 socket *sock, struct rtable *rt, + struct sk_buff *skb, __be32 src, __be32 dst, + __u8 tos, __u8 ttl, __be16 df, __be16 src_port, + __be16 dst_port, bool xnet); + +#if IS_ENABLED(CONFIG_IPV6) +int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst, + struct sk_buff *skb, struct net_device *dev, + struct in6_addr *saddr, struct in6_addr *daddr, + __u8 prio, __u8 ttl, __be16 src_port, + __be16 dst_port); +#endif + +void udp_tunnel_sock_release(struct socket *sock); + +static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb, + bool udp_csum) +{ + int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; + + return iptunnel_handle_offloads(skb, udp_csum, type); +} + +static inline void udp_tunnel_encap_enable(struct socket *sock) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (sock->sk->sk_family == PF_INET6) + ipv6_stub->udpv6_encap_enable(); + else +#endif + udp_encap_enable(); +} #endif diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 721e9c3b11b..dc4865e90fe 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1591,6 +1591,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir, u32 id, int delete, int *err); int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); +void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); int verify_spi_info(u8 proto, u32 min, u32 max); int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); |