diff options
Diffstat (limited to 'include/net')
51 files changed, 717 insertions, 242 deletions
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index b1c717286993..ab207677e0a8 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -135,6 +135,14 @@ struct vsock_transport { bool (*stream_is_active)(struct vsock_sock *); bool (*stream_allow)(u32 cid, u32 port); + /* SEQ_PACKET. */ + ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, + int flags); + int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg, + size_t len); + bool (*seqpacket_allow)(u32 remote_cid); + u32 (*seqpacket_has_data)(struct vsock_sock *vsk); + /* Notification. */ int (*notify_poll_in)(struct vsock_sock *, size_t, bool *); int (*notify_poll_out)(struct vsock_sock *, size_t, bool *); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index ea4ae551c426..b80415011dcd 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -36,7 +36,7 @@ #define HCI_MAX_AMP_ASSOC_SIZE 672 -#define HCI_MAX_CSB_DATA_SIZE 252 +#define HCI_MAX_CPB_DATA_SIZE 252 /* HCI dev events */ #define HCI_DEV_REG 1 @@ -339,6 +339,7 @@ enum { #define HCI_PAIRING_TIMEOUT msecs_to_jiffies(60000) /* 60 seconds */ #define HCI_INIT_TIMEOUT msecs_to_jiffies(10000) /* 10 seconds */ #define HCI_CMD_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ +#define HCI_NCMD_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ #define HCI_ACL_TX_TIMEOUT msecs_to_jiffies(45000) /* 45 seconds */ #define HCI_AUTO_OFF_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ #define HCI_POWER_OFF_TIMEOUT msecs_to_jiffies(5000) /* 5 seconds */ @@ -471,10 +472,10 @@ enum { #define LMP_EXTFEATURES 0x80 /* Extended LMP features */ -#define LMP_CSB_MASTER 0x01 -#define LMP_CSB_SLAVE 0x02 -#define LMP_SYNC_TRAIN 0x04 -#define LMP_SYNC_SCAN 0x08 +#define LMP_CPB_CENTRAL 0x01 +#define LMP_CPB_PERIPHERAL 0x02 +#define LMP_SYNC_TRAIN 0x04 +#define LMP_SYNC_SCAN 0x08 #define LMP_SC 0x01 #define LMP_PING 0x02 @@ -488,7 +489,7 @@ enum { /* LE features */ #define HCI_LE_ENCRYPTION 0x01 #define HCI_LE_CONN_PARAM_REQ_PROC 0x02 -#define HCI_LE_SLAVE_FEATURES 0x08 +#define HCI_LE_PERIPHERAL_FEATURES 0x08 #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 #define HCI_LE_LL_PRIVACY 0x40 @@ -497,8 +498,8 @@ enum { #define HCI_LE_PHY_CODED 0x08 #define HCI_LE_EXT_ADV 0x10 #define HCI_LE_CHAN_SEL_ALG2 0x40 -#define HCI_LE_CIS_MASTER 0x10 -#define HCI_LE_CIS_SLAVE 0x20 +#define HCI_LE_CIS_CENTRAL 0x10 +#define HCI_LE_CIS_PERIPHERAL 0x20 /* Connection modes */ #define HCI_CM_ACTIVE 0x0000 @@ -876,17 +877,17 @@ struct hci_rp_logical_link_cancel { __u8 flow_spec_id; } __packed; -#define HCI_OP_SET_CSB 0x0441 -struct hci_cp_set_csb { +#define HCI_OP_SET_CPB 0x0441 +struct hci_cp_set_cpb { __u8 enable; __u8 lt_addr; __u8 lpo_allowed; __le16 packet_type; __le16 interval_min; __le16 interval_max; - __le16 csb_sv_tout; + __le16 cpb_sv_tout; } __packed; -struct hci_rp_set_csb { +struct hci_rp_set_cpb { __u8 status; __u8 lt_addr; __le16 interval; @@ -1183,14 +1184,14 @@ struct hci_rp_delete_reserved_lt_addr { __u8 lt_addr; } __packed; -#define HCI_OP_SET_CSB_DATA 0x0c76 -struct hci_cp_set_csb_data { +#define HCI_OP_SET_CPB_DATA 0x0c76 +struct hci_cp_set_cpb_data { __u8 lt_addr; __u8 fragment; __u8 data_length; - __u8 data[HCI_MAX_CSB_DATA_SIZE]; + __u8 data[HCI_MAX_CPB_DATA_SIZE]; } __packed; -struct hci_rp_set_csb_data { +struct hci_rp_set_cpb_data { __u8 status; __u8 lt_addr; } __packed; @@ -1504,7 +1505,7 @@ struct hci_cp_le_set_scan_enable { } __packed; #define HCI_LE_USE_PEER_ADDR 0x00 -#define HCI_LE_USE_WHITELIST 0x01 +#define HCI_LE_USE_ACCEPT_LIST 0x01 #define HCI_OP_LE_CREATE_CONN 0x200d struct hci_cp_le_create_conn { @@ -1524,22 +1525,22 @@ struct hci_cp_le_create_conn { #define HCI_OP_LE_CREATE_CONN_CANCEL 0x200e -#define HCI_OP_LE_READ_WHITE_LIST_SIZE 0x200f -struct hci_rp_le_read_white_list_size { +#define HCI_OP_LE_READ_ACCEPT_LIST_SIZE 0x200f +struct hci_rp_le_read_accept_list_size { __u8 status; __u8 size; } __packed; -#define HCI_OP_LE_CLEAR_WHITE_LIST 0x2010 +#define HCI_OP_LE_CLEAR_ACCEPT_LIST 0x2010 -#define HCI_OP_LE_ADD_TO_WHITE_LIST 0x2011 -struct hci_cp_le_add_to_white_list { +#define HCI_OP_LE_ADD_TO_ACCEPT_LIST 0x2011 +struct hci_cp_le_add_to_accept_list { __u8 bdaddr_type; bdaddr_t bdaddr; } __packed; -#define HCI_OP_LE_DEL_FROM_WHITE_LIST 0x2012 -struct hci_cp_le_del_from_white_list { +#define HCI_OP_LE_DEL_FROM_ACCEPT_LIST 0x2012 +struct hci_cp_le_del_from_accept_list { __u8 bdaddr_type; bdaddr_t bdaddr; } __packed; @@ -1774,13 +1775,15 @@ struct hci_cp_ext_adv_set { __u8 max_events; } __packed; +#define HCI_MAX_EXT_AD_LENGTH 251 + #define HCI_OP_LE_SET_EXT_ADV_DATA 0x2037 struct hci_cp_le_set_ext_adv_data { __u8 handle; __u8 operation; __u8 frag_pref; __u8 length; - __u8 data[HCI_MAX_AD_LENGTH]; + __u8 data[]; } __packed; #define HCI_OP_LE_SET_EXT_SCAN_RSP_DATA 0x2038 @@ -1789,7 +1792,7 @@ struct hci_cp_le_set_ext_scan_rsp_data { __u8 operation; __u8 frag_pref; __u8 length; - __u8 data[HCI_MAX_AD_LENGTH]; + __u8 data[]; } __packed; #define LE_SET_ADV_DATA_OP_COMPLETE 0x03 @@ -1838,23 +1841,23 @@ struct hci_rp_le_read_iso_tx_sync { #define HCI_OP_LE_SET_CIG_PARAMS 0x2062 struct hci_cis_params { __u8 cis_id; - __le16 m_sdu; - __le16 s_sdu; - __u8 m_phy; - __u8 s_phy; - __u8 m_rtn; - __u8 s_rtn; + __le16 c_sdu; + __le16 p_pdu; + __u8 c_phy; + __u8 p_phy; + __u8 c_rtn; + __u8 p_rtn; } __packed; struct hci_cp_le_set_cig_params { __u8 cig_id; - __u8 m_interval[3]; - __u8 s_interval[3]; - __u8 sca; + __u8 c_interval[3]; + __u8 p_interval[3]; + __u8 wc_sca; __u8 packing; __u8 framing; - __le16 m_latency; - __le16 s_latency; + __le16 c_latency; + __le16 p_latency; __u8 num_cis; struct hci_cis_params cis[]; } __packed; @@ -2259,7 +2262,7 @@ struct hci_ev_sync_train_complete { __u8 status; } __packed; -#define HCI_EV_SLAVE_PAGE_RESP_TIMEOUT 0x54 +#define HCI_EV_PERIPHERAL_PAGE_RESP_TIMEOUT 0x54 #define HCI_EV_LE_CONN_COMPLETE 0x01 struct hci_ev_le_conn_complete { @@ -2417,17 +2420,17 @@ struct hci_evt_le_cis_established { __le16 handle; __u8 cig_sync_delay[3]; __u8 cis_sync_delay[3]; - __u8 m_latency[3]; - __u8 s_latency[3]; - __u8 m_phy; - __u8 s_phy; + __u8 c_latency[3]; + __u8 p_latency[3]; + __u8 c_phy; + __u8 p_phy; __u8 nse; - __u8 m_bn; - __u8 s_bn; - __u8 m_ft; - __u8 s_ft; - __le16 m_mtu; - __le16 s_mtu; + __u8 c_bn; + __u8 p_bn; + __u8 c_ft; + __u8 p_ft; + __le16 c_mtu; + __le16 p_mtu; __le16 interval; } __packed; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index c73ac52af186..a53e94459ecd 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -122,7 +122,7 @@ struct hci_conn_hash { unsigned int amp_num; unsigned int sco_num; unsigned int le_num; - unsigned int le_num_slave; + unsigned int le_num_peripheral; }; struct bdaddr_list { @@ -228,9 +228,9 @@ struct adv_info { __u16 remaining_time; __u16 duration; __u16 adv_data_len; - __u8 adv_data[HCI_MAX_AD_LENGTH]; + __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; __u16 scan_rsp_len; - __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; + __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH]; __s8 tx_power; __u32 min_interval; __u32 max_interval; @@ -327,7 +327,7 @@ struct hci_dev { __u8 max_page; __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[8]; - __u8 le_white_list_size; + __u8 le_accept_list_size; __u8 le_resolv_list_size; __u8 le_num_of_adv_sets; __u8 le_states[8]; @@ -470,6 +470,7 @@ struct hci_dev { struct delayed_work service_cache; struct delayed_work cmd_timer; + struct delayed_work ncmd_timer; struct work_struct rx_work; struct work_struct cmd_work; @@ -521,14 +522,14 @@ struct hci_dev { struct hci_conn_hash conn_hash; struct list_head mgmt_pending; - struct list_head blacklist; - struct list_head whitelist; + struct list_head reject_list; + struct list_head accept_list; struct list_head uuids; struct list_head link_keys; struct list_head long_term_keys; struct list_head identity_resolving_keys; struct list_head remote_oob_data; - struct list_head le_white_list; + struct list_head le_accept_list; struct list_head le_resolv_list; struct list_head le_conn_params; struct list_head pend_le_conns; @@ -550,9 +551,9 @@ struct hci_dev { DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); __s8 adv_tx_power; - __u8 adv_data[HCI_MAX_AD_LENGTH]; + __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 adv_data_len; - __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; + __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH]; __u8 scan_rsp_data_len; struct list_head adv_instances; @@ -893,7 +894,7 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) case LE_LINK: h->le_num++; if (c->role == HCI_ROLE_SLAVE) - h->le_num_slave++; + h->le_num_peripheral++; break; case SCO_LINK: case ESCO_LINK: @@ -919,7 +920,7 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) case LE_LINK: h->le_num--; if (c->role == HCI_ROLE_SLAVE) - h->le_num_slave--; + h->le_num_peripheral--; break; case SCO_LINK: case ESCO_LINK: @@ -1393,8 +1394,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define lmp_edr_5slot_capable(dev) ((dev)->features[0][5] & LMP_EDR_5SLOT) /* ----- Extended LMP capabilities ----- */ -#define lmp_csb_master_capable(dev) ((dev)->features[2][0] & LMP_CSB_MASTER) -#define lmp_csb_slave_capable(dev) ((dev)->features[2][0] & LMP_CSB_SLAVE) +#define lmp_cpb_central_capable(dev) ((dev)->features[2][0] & LMP_CPB_CENTRAL) +#define lmp_cpb_peripheral_capable(dev) ((dev)->features[2][0] & LMP_CPB_PERIPHERAL) #define lmp_sync_train_capable(dev) ((dev)->features[2][0] & LMP_SYNC_TRAIN) #define lmp_sync_scan_capable(dev) ((dev)->features[2][0] & LMP_SYNC_SCAN) #define lmp_sc_capable(dev) ((dev)->features[2][1] & LMP_SC) @@ -1768,7 +1769,7 @@ 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, - u32 flags, u8 *name, u8 name_len); + u8 *name, u8 name_len); void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 reason, bool mgmt_connected); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index a7cffb069565..23a0524061b7 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -202,7 +202,7 @@ struct mgmt_cp_load_link_keys { struct mgmt_ltk_info { struct mgmt_addr_info addr; __u8 type; - __u8 master; + __u8 initiator; __u8 enc_size; __le16 ediv; __le64 rand; @@ -939,6 +939,7 @@ struct mgmt_ev_auth_failed { #define MGMT_DEV_FOUND_CONFIRM_NAME 0x01 #define MGMT_DEV_FOUND_LEGACY_PAIRING 0x02 #define MGMT_DEV_FOUND_NOT_CONNECTABLE 0x04 +#define MGMT_DEV_FOUND_INITIATED_CONN 0x08 #define MGMT_EV_DEVICE_FOUND 0x0012 struct mgmt_ev_device_found { diff --git a/include/net/bonding.h b/include/net/bonding.h index 019e998d944a..15335732e166 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -232,7 +232,7 @@ struct bonding { char proc_file_name[IFNAMSIZ]; #endif /* CONFIG_PROC_FS */ struct list_head bond_list; - u32 rr_tx_counter; + u32 __percpu *rr_tx_counter; struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 58c2cd417e89..161cdf7df1a0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7,7 +7,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/ethtool.h> @@ -22,6 +22,7 @@ #include <linux/if_ether.h> #include <linux/ieee80211.h> #include <linux/net.h> +#include <linux/rfkill.h> #include <net/regulatory.h> /** @@ -370,11 +371,18 @@ struct ieee80211_sta_he_cap { * @he_cap: holds the HE capabilities * @he_6ghz_capa: HE 6 GHz capabilities, must be filled in for a * 6 GHz band channel (and 0 may be valid value). + * @vendor_elems: vendor element(s) to advertise + * @vendor_elems.data: vendor element(s) data + * @vendor_elems.len: vendor element(s) length */ struct ieee80211_sband_iftype_data { u16 types_mask; struct ieee80211_sta_he_cap he_cap; struct ieee80211_he_6ghz_capa he_6ghz_capa; + struct { + const u8 *data; + unsigned int len; + } vendor_elems; }; /** @@ -534,18 +542,6 @@ ieee80211_get_he_iftype_cap(const struct ieee80211_supported_band *sband, } /** - * ieee80211_get_he_sta_cap - return HE capabilities for an sband's STA - * @sband: the sband to search for the STA on - * - * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found - */ -static inline const struct ieee80211_sta_he_cap * -ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) -{ - return ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_STATION); -} - -/** * ieee80211_get_he_6ghz_capa - return HE 6 GHz capabilities * @sband: the sband to search for the STA on * @iftype: the iftype to search for @@ -906,6 +902,17 @@ ieee80211_chandef_max_power(struct cfg80211_chan_def *chandef) } /** + * cfg80211_any_usable_channels - check for usable channels + * @wiphy: the wiphy to check for + * @band_mask: which bands to check on + * @prohibited_flags: which channels to not consider usable, + * %IEEE80211_CHAN_DISABLED is always taken into account + */ +bool cfg80211_any_usable_channels(struct wiphy *wiphy, + unsigned long band_mask, + u32 prohibited_flags); + +/** * enum survey_info_flags - survey information flags * * @SURVEY_INFO_NOISE_DBM: noise (in dBm) was filled in @@ -1245,8 +1252,6 @@ struct cfg80211_csa_settings { u8 count; }; -#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 - /** * struct iface_combination_params - input parameters for interface combinations * @@ -3522,7 +3527,10 @@ struct cfg80211_pmsr_result { * If neither @trigger_based nor @non_trigger_based is set, * EDCA based ranging will be used. * @lmr_feedback: negotiate for I2R LMR feedback. Only valid if either - * @trigger_based or @non_trigger_based is set. + * @trigger_based or @non_trigger_based is set. + * @bss_color: the bss color of the responder. Optional. Set to zero to + * indicate the driver should set the BSS color. Only valid if + * @non_trigger_based or @trigger_based is set. * * See also nl80211 for the respective attribute documentation. */ @@ -3540,6 +3548,7 @@ struct cfg80211_pmsr_ftm_request_peer { u8 burst_duration; u8 ftms_per_burst; u8 ftmr_retries; + u8 bss_color; }; /** @@ -4945,6 +4954,7 @@ struct wiphy_iftype_akm_suites { * configuration through the %NL80211_TID_CONFIG_ATTR_RETRY_SHORT and * %NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes * @sar_capa: SAR control capabilities + * @rfkill: a pointer to the rfkill structure */ struct wiphy { struct mutex mtx; @@ -5087,6 +5097,8 @@ struct wiphy { const struct cfg80211_sar_capa *sar_capa; + struct rfkill *rfkill; + char priv[] __aligned(NETDEV_ALIGN); }; @@ -6661,7 +6673,10 @@ void wiphy_rfkill_start_polling(struct wiphy *wiphy); * wiphy_rfkill_stop_polling - stop polling rfkill * @wiphy: the wiphy */ -void wiphy_rfkill_stop_polling(struct wiphy *wiphy); +static inline void wiphy_rfkill_stop_polling(struct wiphy *wiphy) +{ + rfkill_pause_polling(wiphy->rfkill); +} /** * DOC: Vendor commands @@ -8154,6 +8169,8 @@ bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, dev_notice(&(wiphy)->dev, format, ##args) #define wiphy_info(wiphy, format, args...) \ dev_info(&(wiphy)->dev, format, ##args) +#define wiphy_info_once(wiphy, format, args...) \ + dev_info_once(&(wiphy)->dev, format, ##args) #define wiphy_err_ratelimited(wiphy, format, args...) \ dev_err_ratelimited(&(wiphy)->dev, format, ##args) diff --git a/include/net/devlink.h b/include/net/devlink.h index 7c984cadfec4..57b738b78073 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -34,6 +34,7 @@ struct devlink_ops; struct devlink { struct list_head list; struct list_head port_list; + struct list_head rate_list; struct list_head sb_list; struct list_head dpipe_table_list; struct list_head resource_list; @@ -133,6 +134,24 @@ struct devlink_port_attrs { }; }; +struct devlink_rate { + struct list_head list; + enum devlink_rate_type type; + struct devlink *devlink; + void *priv; + u64 tx_share; + u64 tx_max; + + struct devlink_rate *parent; + union { + struct devlink_port *devlink_port; + struct { + char *name; + refcount_t refcnt; + }; + }; +}; + struct devlink_port { struct list_head list; struct list_head param_list; @@ -152,6 +171,8 @@ struct devlink_port { struct delayed_work type_warn_dw; struct list_head reporter_list; struct mutex reporters_lock; /* Protects reporter_list */ + + struct devlink_rate *devlink_rate; }; struct devlink_port_new_attrs { @@ -1327,6 +1348,16 @@ struct devlink_ops { enum devlink_trap_action action, struct netlink_ext_ack *extack); /** + * @trap_drop_counter_get: Trap drop counter get function. + * + * Should be used by device drivers to report number of packets + * that have been dropped, and cannot be passed to the devlink + * subsystem by the underlying device. + */ + int (*trap_drop_counter_get)(struct devlink *devlink, + const struct devlink_trap *trap, + u64 *p_drops); + /** * @trap_policer_init: Trap policer initialization function. * * Should be used by device drivers to initialize the trap policer in @@ -1453,6 +1484,30 @@ struct devlink_ops { struct devlink_port *port, enum devlink_port_fn_state state, struct netlink_ext_ack *extack); + + /** + * Rate control callbacks. + */ + int (*rate_leaf_tx_share_set)(struct devlink_rate *devlink_rate, void *priv, + u64 tx_share, struct netlink_ext_ack *extack); + int (*rate_leaf_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, + u64 tx_max, struct netlink_ext_ack *extack); + int (*rate_node_tx_share_set)(struct devlink_rate *devlink_rate, void *priv, + u64 tx_share, struct netlink_ext_ack *extack); + int (*rate_node_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, + u64 tx_max, struct netlink_ext_ack *extack); + int (*rate_node_new)(struct devlink_rate *rate_node, void **priv, + struct netlink_ext_ack *extack); + int (*rate_node_del)(struct devlink_rate *rate_node, void *priv, + struct netlink_ext_ack *extack); + int (*rate_leaf_parent_set)(struct devlink_rate *child, + struct devlink_rate *parent, + void *priv_child, void *priv_parent, + struct netlink_ext_ack *extack); + int (*rate_node_parent_set)(struct devlink_rate *child, + struct devlink_rate *parent, + void *priv_child, void *priv_parent, + struct netlink_ext_ack *extack); }; static inline void *devlink_priv(struct devlink *devlink) @@ -1512,6 +1567,9 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u32 sf, bool external); +int devlink_rate_leaf_create(struct devlink_port *port, void *priv); +void devlink_rate_leaf_destroy(struct devlink_port *devlink_port); +void devlink_rate_nodes_destroy(struct devlink *devlink); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/net/dsa.h b/include/net/dsa.h index e1a2610a0e06..33f40c1ec379 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -50,6 +50,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 +#define DSA_TAG_PROTO_SJA1110_VALUE 23 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -75,6 +76,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, + DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, }; struct packet_type; @@ -91,7 +93,8 @@ struct dsa_device_ops { * as regular on the master net device. */ bool (*filter)(const struct sk_buff *skb, struct net_device *dev); - unsigned int overhead; + unsigned int needed_headroom; + unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC @@ -100,7 +103,6 @@ struct dsa_device_ops { * its RX filter. */ bool promisc_on_master; - bool tail_tag; }; /* This structure defines the control interfaces that are overlayed by the @@ -283,6 +285,12 @@ struct dsa_port { */ const struct dsa_netdevice_ops *netdev_ops; + /* List of MAC addresses that must be forwarded on this port. + * These are only valid on CPU ports and DSA links. + */ + struct list_head fdbs; + struct list_head mdbs; + bool setup; }; @@ -297,6 +305,13 @@ struct dsa_link { struct list_head list; }; +struct dsa_mac_addr { + unsigned char addr[ETH_ALEN]; + u16 vid; + refcount_t refcount; + struct list_head list; +}; + struct dsa_switch { bool setup; @@ -407,6 +422,21 @@ static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) return NULL; } +static inline bool dsa_port_is_dsa(struct dsa_port *port) +{ + return port->type == DSA_PORT_TYPE_DSA; +} + +static inline bool dsa_port_is_cpu(struct dsa_port *port) +{ + return port->type == DSA_PORT_TYPE_CPU; +} + +static inline bool dsa_port_is_user(struct dsa_port *dp) +{ + return dp->type == DSA_PORT_TYPE_USER; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; @@ -474,6 +504,32 @@ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } +/* Return true if this is the local port used to reach the CPU port */ +static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) +{ + if (dsa_is_unused_port(ds, port)) + return false; + + return port == dsa_upstream_port(ds, port); +} + +/* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning + * that the routing port from @downstream_ds to @upstream_ds is also the port + * which @downstream_ds uses to reach its dedicated CPU. + */ +static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, + struct dsa_switch *downstream_ds) +{ + int routing_port; + + if (upstream_ds == downstream_ds) + return true; + + routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); + + return dsa_is_upstream_port(downstream_ds, routing_port); +} + static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; @@ -926,7 +982,7 @@ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; - int tag_len = ops->overhead; + int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index dc5c1e69cd9f..69c9eabf8325 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -319,12 +319,14 @@ flow_action_mixed_hw_stats_check(const struct flow_action *action, if (flow_offload_has_one_action(action)) return true; - flow_action_for_each(i, action_entry, action) { - if (i && action_entry->hw_stats != last_hw_stats) { - NL_SET_ERR_MSG_MOD(extack, "Mixing HW stats types for actions is not supported"); - return false; + if (action) { + flow_action_for_each(i, action_entry, action) { + if (i && action_entry->hw_stats != last_hw_stats) { + NL_SET_ERR_MSG_MOD(extack, "Mixing HW stats types for actions is not supported"); + return false; + } + last_hw_stats = action_entry->hw_stats; } - last_hw_stats = action_entry->hw_stats; } return true; } diff --git a/include/net/icmp.h b/include/net/icmp.h index fd84adc47963..caddf4a59ad1 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -57,5 +57,6 @@ int icmp_rcv(struct sk_buff *skb); int icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); void icmp_out_count(struct net *net, unsigned char type); +bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr); #endif /* _ICMP_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3c8c59471bc1..b06c2d02ec84 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -135,7 +135,7 @@ struct inet_connection_sock { u32 icsk_user_timeout; u64 icsk_ca_priv[104 / sizeof(u64)]; -#define ICSK_CA_PRIV_SIZE (13 * sizeof(u64)) +#define ICSK_CA_PRIV_SIZE sizeof_field(struct inet_connection_sock, icsk_ca_priv) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ diff --git a/include/net/ip.h b/include/net/ip.h index e20874059f82..d9683bef8684 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -31,6 +31,7 @@ #include <net/flow.h> #include <net/flow_dissector.h> #include <net/netns/hash.h> +#include <net/lwtunnel.h> #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ #define IPV4_MIN_MTU 68 /* RFC 791 */ @@ -445,22 +446,25 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, /* 'forwarding = true' case should always honour route mtu */ mtu = dst_metric_raw(dst, RTAX_MTU); - if (mtu) - return mtu; + if (!mtu) + mtu = min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); - return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); + return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } static inline unsigned int ip_skb_dst_mtu(struct sock *sk, const struct sk_buff *skb) { + unsigned int mtu; + if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) { bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding); } - return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU); + mtu = min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU); + return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu); } struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f51a118bfce8..f14149df5a65 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -265,11 +265,18 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, static inline int ip6_skb_dst_mtu(struct sk_buff *skb) { + int mtu; + struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; - return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ? - skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); + if (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) { + mtu = READ_ONCE(skb_dst(skb)->dev->mtu); + mtu -= lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu); + } else + mtu = dst_mtu(skb_dst(skb)); + + return mtu; } static inline bool ip6_sk_accept_pmtu(const struct sock *sk) @@ -317,7 +324,7 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) if (dst_metric_locked(dst, RTAX_MTU)) { mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; } mtu = IPV6_MIN_MTU; @@ -327,7 +334,8 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) mtu = idev->cnf.mtu6; rcu_read_unlock(); - return mtu; +out: + return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } u32 ip6_mtu_from_fib6(const struct fib6_result *res, diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index a914f33f3ed5..3ab2563b1a23 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -466,6 +466,49 @@ int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); +/* Fields used for sysctl_fib_multipath_hash_fields. + * Common to IPv4 and IPv6. + * + * Add new fields at the end. This is user API. + */ +#define FIB_MULTIPATH_HASH_FIELD_SRC_IP BIT(0) +#define FIB_MULTIPATH_HASH_FIELD_DST_IP BIT(1) +#define FIB_MULTIPATH_HASH_FIELD_IP_PROTO BIT(2) +#define FIB_MULTIPATH_HASH_FIELD_FLOWLABEL BIT(3) +#define FIB_MULTIPATH_HASH_FIELD_SRC_PORT BIT(4) +#define FIB_MULTIPATH_HASH_FIELD_DST_PORT BIT(5) +#define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP BIT(6) +#define FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP BIT(7) +#define FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO BIT(8) +#define FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL BIT(9) +#define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT BIT(10) +#define FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT BIT(11) + +#define FIB_MULTIPATH_HASH_FIELD_OUTER_MASK \ + (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ + FIB_MULTIPATH_HASH_FIELD_DST_IP | \ + FIB_MULTIPATH_HASH_FIELD_IP_PROTO | \ + FIB_MULTIPATH_HASH_FIELD_FLOWLABEL | \ + FIB_MULTIPATH_HASH_FIELD_SRC_PORT | \ + FIB_MULTIPATH_HASH_FIELD_DST_PORT) + +#define FIB_MULTIPATH_HASH_FIELD_INNER_MASK \ + (FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP | \ + FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP | \ + FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO | \ + FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL | \ + FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT | \ + FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) + +#define FIB_MULTIPATH_HASH_FIELD_ALL_MASK \ + (FIB_MULTIPATH_HASH_FIELD_OUTER_MASK | \ + FIB_MULTIPATH_HASH_FIELD_INNER_MASK) + +#define FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK \ + (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ + FIB_MULTIPATH_HASH_FIELD_DST_IP | \ + FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 448bf2b34759..f2d0ecc257bb 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -926,11 +926,19 @@ static inline int ip6_multipath_hash_policy(const struct net *net) { return net->ipv6.sysctl.multipath_hash_policy; } +static inline u32 ip6_multipath_hash_fields(const struct net *net) +{ + return net->ipv6.sysctl.multipath_hash_fields; +} #else static inline int ip6_multipath_hash_policy(const struct net *net) { return 0; } +static inline u32 ip6_multipath_hash_fields(const struct net *net) +{ + return 0; +} #endif /* diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e89530d0d9c6..d8a1d09a2141 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -7,7 +7,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2020 Intel Corporation + * Copyright (C) 2018 - 2021 Intel Corporation */ #ifndef MAC80211_H @@ -526,6 +526,7 @@ struct ieee80211_fils_discovery { * @twt_responder: does this BSS support TWT requester (relevant for managed * mode only, set if the AP advertises TWT responder role) * @twt_protected: does this BSS support protected TWT frames + * @twt_broadcast: does this BSS support broadcast TWT * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS * or not @@ -642,6 +643,7 @@ struct ieee80211_bss_conf { bool twt_requester; bool twt_responder; bool twt_protected; + bool twt_broadcast; /* association related data */ bool assoc, ibss_joined; bool ibss_creator; @@ -3345,6 +3347,21 @@ enum ieee80211_reconfig_type { }; /** + * struct ieee80211_prep_tx_info - prepare TX information + * @duration: if non-zero, hint about the required duration, + * only used with the mgd_prepare_tx() method. + * @subtype: frame subtype (auth, (re)assoc, deauth, disassoc) + * @success: whether the frame exchange was successful, only + * used with the mgd_complete_tx() method, and then only + * valid for auth and (re)assoc. + */ +struct ieee80211_prep_tx_info { + u16 duration; + u16 subtype; + u8 success:1; +}; + +/** * struct ieee80211_ops - callbacks from mac80211 to the driver * * This structure contains various callbacks that the driver may @@ -3756,9 +3773,13 @@ enum ieee80211_reconfig_type { * frame in case that no beacon was heard from the AP/P2P GO. * The callback will be called before each transmission and upon return * mac80211 will transmit the frame right away. - * If duration is greater than zero, mac80211 hints to the driver the - * duration for which the operation is requested. + * Additional information is passed in the &struct ieee80211_prep_tx_info + * data. If duration there is greater than zero, mac80211 hints to the + * driver the duration for which the operation is requested. * The callback is optional and can (should!) sleep. + * @mgd_complete_tx: Notify the driver that the response frame for a previously + * transmitted frame announced with @mgd_prepare_tx was received, the data + * is filled similarly to @mgd_prepare_tx though the duration is not used. * * @mgd_protect_tdls_discover: Protect a TDLS discovery session. After sending * a TDLS discovery-request, we expect a reply to arrive on the AP's @@ -4109,7 +4130,10 @@ struct ieee80211_ops { void (*mgd_prepare_tx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - u16 duration); + struct ieee80211_prep_tx_info *info); + void (*mgd_complete_tx)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_prep_tx_info *info); void (*mgd_protect_tdls_discover)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); @@ -6184,6 +6208,11 @@ enum rate_control_capabilities { * otherwise the NSS difference doesn't bother us. */ RATE_CTRL_CAPA_VHT_EXT_NSS_BW = BIT(0), + /** + * @RATE_CTRL_CAPA_AMPDU_TRIGGER: + * mac80211 should start A-MPDU sessions on tx + */ + RATE_CTRL_CAPA_AMPDU_TRIGGER = BIT(1), }; struct rate_control_ops { @@ -6576,9 +6605,6 @@ static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) { } -void __ieee80211_schedule_txq(struct ieee80211_hw *hw, - struct ieee80211_txq *txq, bool force); - /** * ieee80211_schedule_txq - schedule a TXQ for transmission * @@ -6591,11 +6617,7 @@ void __ieee80211_schedule_txq(struct ieee80211_hw *hw, * The driver may call this function if it has buffered packets for * this TXQ internally. */ -static inline void -ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) -{ - __ieee80211_schedule_txq(hw, txq, true); -} +void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq); /** * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() @@ -6607,12 +6629,8 @@ ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) * The driver may set force=true if it has buffered packets for this TXQ * internally. */ -static inline void -ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, - bool force) -{ - __ieee80211_schedule_txq(hw, txq, force); -} +void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, + bool force); /** * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit @@ -6752,4 +6770,22 @@ struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw, struct sk_buff * ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, struct ieee80211_vif *vif); + +/** + * ieee80211_is_tx_data - check if frame is a data frame + * + * The function is used to check if a frame is a data frame. Frames with + * hardware encapsulation enabled are data frames. + * + * @skb: the frame to be transmitted. + */ +static inline bool ieee80211_is_tx_data(struct sk_buff *skb) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr = (void *) skb->data; + + return info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP || + ieee80211_is_data(hdr->frame_control); +} + #endif /* MAC80211_H */ diff --git a/include/net/macsec.h b/include/net/macsec.h index 52874cdfe226..d6fa6b97f6ef 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -241,7 +241,7 @@ struct macsec_context { struct macsec_rx_sc *rx_sc; struct { unsigned char assoc_num; - u8 key[MACSEC_KEYID_LEN]; + u8 key[MACSEC_MAX_KEY_LEN]; union { struct macsec_rx_sa *rx_sa; struct macsec_tx_sa *tx_sa; diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 83f23774b908..cb580b06152f 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -23,6 +23,7 @@ struct mptcp_ext { u64 data_seq; u32 subflow_seq; u16 data_len; + __sum16 csum; u8 use_map:1, dsn64:1, data_fin:1, @@ -31,7 +32,8 @@ struct mptcp_ext { mpc_map:1, frozen:1, reset_transient:1; - u8 reset_reason:4; + u8 reset_reason:4, + csum_reqd:1; }; #define MPTCP_RM_IDS_MAX 8 @@ -63,8 +65,10 @@ struct mptcp_out_options { struct mptcp_rm_list rm_list; u8 join_id; u8 backup; - u8 reset_reason:4; - u8 reset_transient:1; + u8 reset_reason:4, + reset_transient:1, + csum_reqd:1, + allow_join_id0:1; u32 nonce; u64 thmac; u32 token; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index bdc0459a595e..12cf6d7ea62c 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -32,6 +32,7 @@ #include <net/netns/mpls.h> #include <net/netns/can.h> #include <net/netns/xdp.h> +#include <net/netns/smc.h> #include <net/netns/bpf.h> #include <linux/ns_common.h> #include <linux/idr.h> @@ -170,6 +171,9 @@ struct net { struct sock *crypto_nlsk; #endif struct sock *diag_nlsk; +#if IS_ENABLED(CONFIG_SMC) + struct netns_smc smc; +#endif } __randomize_layout; #include <linux/seq_file_net.h> diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 06dc6db70d18..cc663c68ddc4 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -346,6 +346,13 @@ nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info) skb_set_nfct(skb, (unsigned long)ct | info); } +extern unsigned int nf_conntrack_net_id; + +static inline struct nf_conntrack_net *nf_ct_pernet(const struct net *net) +{ + return net_generic(net, nf_conntrack_net_id); +} + #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v)) diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 96f9cf81f46b..1f47bef51722 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -159,22 +159,26 @@ unsigned int nf_ct_port_nlattr_tuple_size(void); extern const struct nla_policy nf_ct_port_nla_policy[]; #ifdef CONFIG_SYSCTL -__printf(3, 4) __cold +__printf(4, 5) __cold void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, + const struct nf_hook_state *state, const char *fmt, ...); -__printf(5, 6) __cold +__printf(4, 5) __cold void nf_l4proto_log_invalid(const struct sk_buff *skb, - struct net *net, - u16 pf, u8 protonum, + const struct nf_hook_state *state, + u8 protonum, const char *fmt, ...); #else -static inline __printf(5, 6) __cold -void nf_l4proto_log_invalid(const struct sk_buff *skb, struct net *net, - u16 pf, u8 protonum, const char *fmt, ...) {} -static inline __printf(3, 4) __cold +static inline __printf(4, 5) __cold +void nf_l4proto_log_invalid(const struct sk_buff *skb, + const struct nf_hook_state *state, + u8 protonum, + const char *fmt, ...) {} +static inline __printf(4, 5) __cold void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, + const struct nf_hook_state *state, const char *fmt, ...) { } #endif /* CONFIG_SYSCTL */ diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 48ef7460ff30..a3647fadf1cc 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -177,6 +177,8 @@ struct flow_offload { #define NF_FLOW_TIMEOUT (30 * HZ) #define nf_flowtable_time_stamp (u32)jiffies +unsigned long flow_offload_get_timeout(struct flow_offload *flow); + static inline __s32 nf_flow_timeout_delta(unsigned int timeout) { return (__s32)(timeout - nf_flowtable_time_stamp); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 0a5655e300b5..148f5d8ee5ab 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -23,35 +23,46 @@ struct module; struct nft_pktinfo { struct sk_buff *skb; + const struct nf_hook_state *state; bool tprot_set; u8 tprot; - /* for x_tables compatibility */ - struct xt_action_param xt; + u16 fragoff; + unsigned int thoff; }; +static inline struct sock *nft_sk(const struct nft_pktinfo *pkt) +{ + return pkt->state->sk; +} + +static inline unsigned int nft_thoff(const struct nft_pktinfo *pkt) +{ + return pkt->thoff; +} + static inline struct net *nft_net(const struct nft_pktinfo *pkt) { - return pkt->xt.state->net; + return pkt->state->net; } static inline unsigned int nft_hook(const struct nft_pktinfo *pkt) { - return pkt->xt.state->hook; + return pkt->state->hook; } static inline u8 nft_pf(const struct nft_pktinfo *pkt) { - return pkt->xt.state->pf; + return pkt->state->pf; } static inline const struct net_device *nft_in(const struct nft_pktinfo *pkt) { - return pkt->xt.state->in; + return pkt->state->in; } static inline const struct net_device *nft_out(const struct nft_pktinfo *pkt) { - return pkt->xt.state->out; + return pkt->state->out; } static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, @@ -59,16 +70,15 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_state *state) { pkt->skb = skb; - pkt->xt.state = state; + pkt->state = state; } -static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt) { pkt->tprot_set = false; pkt->tprot = 0; - pkt->xt.thoff = 0; - pkt->xt.fragoff = 0; + pkt->thoff = 0; + pkt->fragoff = 0; } /** diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index fd10a7862fdc..0fa5a6d98a00 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -3,6 +3,7 @@ #define _NET_NF_TABLES_CORE_H #include <net/netfilter/nf_tables.h> +#include <linux/indirect_call_wrapper.h> extern struct nft_expr_type nft_imm_type; extern struct nft_expr_type nft_cmp_type; @@ -15,6 +16,7 @@ extern struct nft_expr_type nft_range_type; extern struct nft_expr_type nft_meta_type; extern struct nft_expr_type nft_rt_type; extern struct nft_expr_type nft_exthdr_type; +extern struct nft_expr_type nft_last_type; #ifdef CONFIG_NETWORK_SECMARK extern struct nft_object_type nft_secmark_obj_type; @@ -88,6 +90,36 @@ extern const struct nft_set_type nft_set_bitmap_type; extern const struct nft_set_type nft_set_pipapo_type; extern const struct nft_set_type nft_set_pipapo_avx2_type; +#ifdef CONFIG_RETPOLINE +bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +bool nft_hash_lookup_fast(const struct net *net, + const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +bool nft_hash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +bool nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +#else +static inline bool +nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) +{ + return set->ops->lookup(net, set, key, ext); +} +#endif + +/* called from nft_pipapo_avx2.c */ +bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +/* called from nft_set_pipapo.c */ +bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); + struct nft_expr; struct nft_regs; struct nft_pktinfo; diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 1f7bea39ad1b..eb4c094cd54d 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -5,26 +5,24 @@ #include <net/netfilter/nf_tables.h> #include <net/ip.h> -static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt) { struct iphdr *ip; ip = ip_hdr(pkt->skb); pkt->tprot_set = true; pkt->tprot = ip->protocol; - pkt->xt.thoff = ip_hdrlen(pkt->skb); - pkt->xt.fragoff = ntohs(ip->frag_off) & IP_OFFSET; + pkt->thoff = ip_hdrlen(pkt->skb); + pkt->fragoff = ntohs(ip->frag_off) & IP_OFFSET; } -static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) { struct iphdr *iph, _iph; u32 len, thoff; - iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), - &_iph); + iph = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), + sizeof(*iph), &_iph); if (!iph) return -1; @@ -33,42 +31,40 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, len = ntohs(iph->tot_len); thoff = iph->ihl * 4; - if (skb->len < len) + if (pkt->skb->len < len) return -1; else if (len < thoff) return -1; pkt->tprot_set = true; pkt->tprot = iph->protocol; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; + pkt->thoff = thoff; + pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; return 0; } -static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) { - if (__nft_set_pktinfo_ipv4_validate(pkt, skb) < 0) - nft_set_pktinfo_unspec(pkt, skb); + if (__nft_set_pktinfo_ipv4_validate(pkt) < 0) + nft_set_pktinfo_unspec(pkt); } -static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt) { struct iphdr *iph; u32 len, thoff; - if (!pskb_may_pull(skb, sizeof(*iph))) + if (!pskb_may_pull(pkt->skb, sizeof(*iph))) return -1; - iph = ip_hdr(skb); + iph = ip_hdr(pkt->skb); if (iph->ihl < 5 || iph->version != 4) goto inhdr_error; len = ntohs(iph->tot_len); thoff = iph->ihl * 4; - if (skb->len < len) { + if (pkt->skb->len < len) { __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS); return -1; } else if (len < thoff) { @@ -77,8 +73,8 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt, pkt->tprot_set = true; pkt->tprot = iph->protocol; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; + pkt->thoff = thoff; + pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; return 0; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 867de29f3f7a..7595e02b00ba 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -6,8 +6,7 @@ #include <net/ipv6.h> #include <net/netfilter/nf_tables.h> -static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt) { unsigned int flags = IP6_FH_F_AUTH; int protohdr, thoff = 0; @@ -15,18 +14,17 @@ static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); if (protohdr < 0) { - nft_set_pktinfo_unspec(pkt, skb); + nft_set_pktinfo_unspec(pkt); return; } pkt->tprot_set = true; pkt->tprot = protohdr; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = frag_off; + pkt->thoff = thoff; + pkt->fragoff = frag_off; } -static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) { #if IS_ENABLED(CONFIG_IPV6) unsigned int flags = IP6_FH_F_AUTH; @@ -36,8 +34,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, int protohdr; u32 pkt_len; - ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h), - &_ip6h); + ip6h = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), + sizeof(*ip6h), &_ip6h); if (!ip6h) return -1; @@ -45,7 +43,7 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, return -1; pkt_len = ntohs(ip6h->payload_len); - if (pkt_len + sizeof(*ip6h) > skb->len) + if (pkt_len + sizeof(*ip6h) > pkt->skb->len) return -1; protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); @@ -54,8 +52,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, pkt->tprot_set = true; pkt->tprot = protohdr; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = frag_off; + pkt->thoff = thoff; + pkt->fragoff = frag_off; return 0; #else @@ -63,15 +61,13 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, #endif } -static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) { - if (__nft_set_pktinfo_ipv6_validate(pkt, skb) < 0) - nft_set_pktinfo_unspec(pkt, skb); + if (__nft_set_pktinfo_ipv6_validate(pkt) < 0) + nft_set_pktinfo_unspec(pkt); } -static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt) { #if IS_ENABLED(CONFIG_IPV6) unsigned int flags = IP6_FH_F_AUTH; @@ -82,15 +78,15 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt, int protohdr; u32 pkt_len; - if (!pskb_may_pull(skb, sizeof(*ip6h))) + if (!pskb_may_pull(pkt->skb, sizeof(*ip6h))) return -1; - ip6h = ipv6_hdr(skb); + ip6h = ipv6_hdr(pkt->skb); if (ip6h->version != 6) goto inhdr_error; pkt_len = ntohs(ip6h->payload_len); - if (pkt_len + sizeof(*ip6h) > skb->len) { + if (pkt_len + sizeof(*ip6h) > pkt->skb->len) { idev = __in6_dev_get(nft_in(pkt)); __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INTRUNCATEDPKTS); return -1; @@ -102,8 +98,8 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt, pkt->tprot_set = true; pkt->tprot = protohdr; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = frag_off; + pkt->thoff = thoff; + pkt->fragoff = frag_off; return 0; diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index ad0a95c2335e..c3094b83a525 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -27,6 +27,10 @@ struct nf_tcp_net { u8 tcp_loose; u8 tcp_be_liberal; u8 tcp_max_retrans; +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + unsigned int offload_timeout; + unsigned int offload_pickup; +#endif }; enum udp_conntrack { @@ -37,6 +41,10 @@ enum udp_conntrack { struct nf_udp_net { unsigned int timeouts[UDP_CT_MAX]; +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + unsigned int offload_timeout; + unsigned int offload_pickup; +#endif }; struct nf_icmp_net { diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index f6af8d96d3c6..b8620519eace 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -126,6 +126,7 @@ struct netns_ipv4 { u8 sysctl_tcp_syn_retries; u8 sysctl_tcp_synack_retries; u8 sysctl_tcp_syncookies; + u8 sysctl_tcp_migrate_req; int sysctl_tcp_reordering; u8 sysctl_tcp_retries1; u8 sysctl_tcp_retries2; @@ -210,6 +211,7 @@ struct netns_ipv4 { #endif #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH + u32 sysctl_fib_multipath_hash_fields; u8 sysctl_fib_multipath_use_neigh; u8 sysctl_fib_multipath_hash_policy; #endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 6153c8067009..bde0b7adb4a3 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -28,8 +28,9 @@ struct netns_sysctl_ipv6 { int ip6_rt_gc_elasticity; int ip6_rt_mtu_expires; int ip6_rt_min_advmss; - u8 bindv6only; + u32 multipath_hash_fields; u8 multipath_hash_policy; + u8 bindv6only; u8 flowlabel_consistency; u8 auto_flowlabels; int icmpv6_time; diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index a0f315effa94..40240722cdca 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -84,6 +84,9 @@ struct netns_sctp { /* HB.interval - 30 seconds */ unsigned int hb_interval; + /* The interval for PLPMTUD probe timer */ + unsigned int probe_interval; + /* Association.Max.Retrans - 10 attempts * Path.Max.Retrans - 5 attempts (per destination address) * Max.Init.Retransmits - 8 attempts diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h new file mode 100644 index 000000000000..ea8a9cf2619b --- /dev/null +++ b/include/net/netns/smc.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NETNS_SMC_H__ +#define __NETNS_SMC_H__ +#include <linux/mutex.h> +#include <linux/percpu.h> + +struct smc_stats_rsn; +struct smc_stats; +struct netns_smc { + /* per cpu counters for SMC */ + struct smc_stats __percpu *smc_stats; + /* protect fback_rsn */ + struct mutex mutex_fback_rsn; + struct smc_stats_rsn *fback_rsn; +}; +#endif diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index e816b6a3ef2b..e946366e8ba5 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -42,6 +42,7 @@ struct netns_xfrm { struct hlist_head __rcu *state_bydst; struct hlist_head __rcu *state_bysrc; struct hlist_head __rcu *state_byspi; + struct hlist_head __rcu *state_byseq; unsigned int state_hmask; unsigned int state_num; struct work_struct state_hash_work; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b4b6de909c93..3dd62dd73027 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -146,6 +146,8 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) return pool->p.dma_dir; } +bool page_pool_return_skb_page(struct page *page); + struct page_pool *page_pool_create(const struct page_pool_params *params); #ifdef CONFIG_PAGE_POOL @@ -251,4 +253,11 @@ static inline void page_pool_ring_unlock(struct page_pool *pool) spin_unlock_bh(&pool->ring.producer_lock); } +/* Store mem_info on struct page and use it while recycling skb frags */ +static inline +void page_pool_store_mem_info(struct page *page, struct page_pool *pp) +{ + page->pp = pp; +} + #endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/protocol.h b/include/net/protocol.h index 2b778e1d2d8f..f51c06ae365f 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -43,7 +43,6 @@ struct net_protocol { int (*err_handler)(struct sk_buff *skb, u32 info); unsigned int no_policy:1, - netns_ok:1, /* does the protocol do more stringent * icmp tag validation than simple * socket lookup? diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 479f60ef54c0..384e800665f2 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -37,6 +37,9 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters + * @alloc: netdev allocation function, can be %NULL and is then used + * in place of alloc_netdev_mqs(), in this case @priv_size + * and @setup are unused. Returns a netdev or ERR_PTR(). * @priv_size: sizeof net_device private space * @setup: net_device setup function * @newlink: Function for configuring and registering a new device @@ -63,6 +66,11 @@ struct rtnl_link_ops { const char *kind; size_t priv_size; + struct net_device *(*alloc)(struct nlattr *tb[], + const char *ifname, + unsigned char name_assign_type, + unsigned int num_tx_queues, + unsigned int num_rx_queues); void (*setup)(struct net_device *dev); bool netns_refund; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 1e625519ae96..9ed33e6840bd 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -37,8 +37,15 @@ enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, __QDISC_STATE_MISSED, + __QDISC_STATE_DRAINING, }; +#define QDISC_STATE_MISSED BIT(__QDISC_STATE_MISSED) +#define QDISC_STATE_DRAINING BIT(__QDISC_STATE_DRAINING) + +#define QDISC_STATE_NON_EMPTY (QDISC_STATE_MISSED | \ + QDISC_STATE_DRAINING) + struct qdisc_size_table { struct rcu_head rcu; struct list_head list; @@ -110,8 +117,6 @@ struct Qdisc { spinlock_t busylock ____cacheline_aligned_in_smp; spinlock_t seqlock; - /* for NOLOCK qdisc, true if there are no enqueued skbs */ - bool empty; struct rcu_head rcu; /* private data */ @@ -145,6 +150,11 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc) return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; } +static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc) +{ + return !(READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY); +} + static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) { return q->flags & TCQ_F_CPUSTATS; @@ -153,7 +163,7 @@ static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) static inline bool qdisc_is_empty(const struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) - return READ_ONCE(qdisc->empty); + return nolock_qdisc_is_empty(qdisc); return !READ_ONCE(qdisc->q.qlen); } @@ -161,7 +171,13 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { if (spin_trylock(&qdisc->seqlock)) - goto nolock_empty; + return true; + + /* Paired with smp_mb__after_atomic() to make sure + * STATE_MISSED checking is synchronized with clearing + * in pfifo_fast_dequeue(). + */ + smp_mb__before_atomic(); /* If the MISSED flag is set, it means other thread has * set the MISSED flag before second spin_trylock(), so @@ -180,14 +196,16 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) */ set_bit(__QDISC_STATE_MISSED, &qdisc->state); + /* spin_trylock() only has load-acquire semantic, so use + * smp_mb__after_atomic() to ensure STATE_MISSED is set + * before doing the second spin_trylock(). + */ + smp_mb__after_atomic(); + /* Retry again in case other CPU may not see the new flag * after it releases the lock at the end of qdisc_run_end(). */ - if (!spin_trylock(&qdisc->seqlock)) - return false; - -nolock_empty: - WRITE_ONCE(qdisc->empty, false); + return spin_trylock(&qdisc->seqlock); } else if (qdisc_is_running(qdisc)) { return false; } @@ -201,15 +219,14 @@ nolock_empty: static inline void qdisc_run_end(struct Qdisc *qdisc) { - write_seqcount_end(&qdisc->running); if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); if (unlikely(test_bit(__QDISC_STATE_MISSED, - &qdisc->state))) { - clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + &qdisc->state))) __netif_schedule(qdisc); - } + } else { + write_seqcount_end(&qdisc->running); } } diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index 5e848884ff61..2058fabffbf6 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -59,6 +59,7 @@ enum sctp_verb { SCTP_CMD_HB_TIMERS_START, /* Start the heartbeat timers. */ SCTP_CMD_HB_TIMER_UPDATE, /* Update a heartbeat timers. */ SCTP_CMD_HB_TIMERS_STOP, /* Stop the heartbeat timers. */ + SCTP_CMD_PROBE_TIMER_UPDATE, /* Update a probe timer. */ SCTP_CMD_TRANSPORT_HB_SENT, /* Reset the status of a transport. */ SCTP_CMD_TRANSPORT_IDLE, /* Do manipulations on idle transport */ SCTP_CMD_TRANSPORT_ON, /* Mark the transport as active. */ diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 14a0d22c9113..265fffa33dad 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -77,6 +77,7 @@ enum sctp_event_timeout { SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD, SCTP_EVENT_TIMEOUT_HEARTBEAT, SCTP_EVENT_TIMEOUT_RECONF, + SCTP_EVENT_TIMEOUT_PROBE, SCTP_EVENT_TIMEOUT_SACK, SCTP_EVENT_TIMEOUT_AUTOCLOSE, }; @@ -200,6 +201,23 @@ enum sctp_sock_state { SCTP_SS_CLOSING = TCP_CLOSE_WAIT, }; +enum sctp_plpmtud_state { + SCTP_PL_DISABLED, + SCTP_PL_BASE, + SCTP_PL_SEARCH, + SCTP_PL_COMPLETE, + SCTP_PL_ERROR, +}; + +#define SCTP_BASE_PLPMTU 1200 +#define SCTP_MAX_PLPMTU 9000 +#define SCTP_MIN_PLPMTU 512 + +#define SCTP_MAX_PROBES 3 + +#define SCTP_PL_BIG_STEP 32 +#define SCTP_PL_MIN_STEP 4 + /* These functions map various type to printable names. */ const char *sctp_cname(const union sctp_subtype id); /* chunk types */ const char *sctp_oname(const union sctp_subtype id); /* other events */ @@ -424,4 +442,6 @@ enum { */ #define SCTP_AUTH_RANDOM_LENGTH 32 +#define SCTP_PROBE_TIMER_MIN 5000 + #endif /* __sctp_constants_h__ */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 86f74f2fe6de..69bab88ad66b 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -145,6 +145,8 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *, struct sctphdr *, struct sctp_association **, struct sctp_transport **); void sctp_err_finish(struct sock *, struct sctp_transport *); +int sctp_udp_v4_err(struct sock *sk, struct sk_buff *skb); +int sctp_udp_v6_err(struct sock *sk, struct sk_buff *skb); void sctp_icmp_frag_needed(struct sock *, struct sctp_association *, struct sctp_transport *t, __u32 pmtu); void sctp_icmp_redirect(struct sock *, struct sctp_transport *, @@ -573,14 +575,15 @@ static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport * /* Calculate max payload size given a MTU, or the total overhead if * given MTU is zero */ -static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp, - __u32 mtu, __u32 extra) +static inline __u32 __sctp_mtu_payload(const struct sctp_sock *sp, + const struct sctp_transport *t, + __u32 mtu, __u32 extra) { __u32 overhead = sizeof(struct sctphdr) + extra; if (sp) { overhead += sp->pf->af->net_header_len; - if (sp->udp_port) + if (sp->udp_port && (!t || t->encap_port)) overhead += sizeof(struct udphdr); } else { overhead += sizeof(struct ipv6hdr); @@ -592,6 +595,12 @@ static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp, return mtu ? mtu - overhead : overhead; } +static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp, + __u32 mtu, __u32 extra) +{ + return __sctp_mtu_payload(sp, NULL, mtu, extra); +} + static inline __u32 sctp_dst_mtu(const struct dst_entry *dst) { return SCTP_TRUNC4(max_t(__u32, dst_mtu(dst), @@ -615,6 +624,48 @@ static inline __u32 sctp_min_frag_point(struct sctp_sock *sp, __u16 datasize) return sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT, datasize); } +static inline int sctp_transport_pl_hlen(struct sctp_transport *t) +{ + return __sctp_mtu_payload(sctp_sk(t->asoc->base.sk), t, 0, 0); +} + +static inline void sctp_transport_pl_reset(struct sctp_transport *t) +{ + if (t->probe_interval && (t->param_flags & SPP_PMTUD_ENABLE) && + (t->state == SCTP_ACTIVE || t->state == SCTP_UNKNOWN)) { + if (t->pl.state == SCTP_PL_DISABLED) { + t->pl.state = SCTP_PL_BASE; + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pl.probe_size = SCTP_BASE_PLPMTU; + sctp_transport_reset_probe_timer(t); + } + } else { + if (t->pl.state != SCTP_PL_DISABLED) { + if (del_timer(&t->probe_timer)) + sctp_transport_put(t); + t->pl.state = SCTP_PL_DISABLED; + } + } +} + +static inline void sctp_transport_pl_update(struct sctp_transport *t) +{ + if (t->pl.state == SCTP_PL_DISABLED) + return; + + if (del_timer(&t->probe_timer)) + sctp_transport_put(t); + + t->pl.state = SCTP_PL_BASE; + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pl.probe_size = SCTP_BASE_PLPMTU; +} + +static inline bool sctp_transport_pl_enabled(struct sctp_transport *t) +{ + return t->pl.state != SCTP_PL_DISABLED; +} + static inline bool sctp_newsk_ready(const struct sock *sk) { return sock_flag(sk, SOCK_DEAD) || sk->sk_socket; diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index fd223c94589a..2eb6d7c2c931 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -151,6 +151,7 @@ sctp_state_fn_t sctp_sf_cookie_wait_icmp_abort; /* Prototypes for timeout event state functions. */ sctp_state_fn_t sctp_sf_do_6_3_3_rtx; sctp_state_fn_t sctp_sf_send_reconf; +sctp_state_fn_t sctp_sf_send_probe; sctp_state_fn_t sctp_sf_do_6_2_sack; sctp_state_fn_t sctp_sf_autoclose_timer_expire; @@ -225,11 +226,13 @@ struct sctp_chunk *sctp_make_new_encap_port( const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, - const struct sctp_transport *transport); + const struct sctp_transport *transport, + __u32 probe_size); struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const void *payload, const size_t paylen); +struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len); struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, @@ -310,6 +313,7 @@ int sctp_do_sm(struct net *net, enum sctp_event_type event_type, void sctp_generate_t3_rtx_event(struct timer_list *t); void sctp_generate_heartbeat_event(struct timer_list *t); void sctp_generate_reconf_event(struct timer_list *t); +void sctp_generate_probe_event(struct timer_list *t); void sctp_generate_proto_unreach_event(struct timer_list *t); void sctp_ootb_pkt_free(struct sctp_packet *packet); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 1aa585216f34..32fc4a309df5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -177,6 +177,7 @@ struct sctp_sock { * will be inherited by all new associations. */ __u32 hbinterval; + __u32 probe_interval; __be16 udp_port; __be16 encap_port; @@ -385,6 +386,7 @@ struct sctp_sender_hb_info { union sctp_addr daddr; unsigned long sent_at; __u64 hb_nonce; + __u32 probe_size; }; int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, @@ -461,7 +463,7 @@ struct sctp_af { int saddr); void (*from_sk) (union sctp_addr *, struct sock *sk); - void (*from_addr_param) (union sctp_addr *, + bool (*from_addr_param) (union sctp_addr *, union sctp_addr_param *, __be16 port, int iif); int (*to_addr_param) (const union sctp_addr *, @@ -656,6 +658,7 @@ struct sctp_chunk { data_accepted:1, /* At least 1 chunk accepted */ auth:1, /* IN: was auth'ed | OUT: needs auth */ has_asconf:1, /* IN: have seen an asconf before */ + pmtu_probe:1, /* Used by PLPMTUD, can be set in s HB chunk */ tsn_missing_report:2, /* Data chunk missing counter. */ fast_retransmit:2; /* Is this chunk fast retransmitted? */ }; @@ -858,6 +861,7 @@ struct sctp_transport { * the destination address every heartbeat interval. */ unsigned long hbinterval; + unsigned long probe_interval; /* SACK delay timeout */ unsigned long sackdelay; @@ -934,6 +938,9 @@ struct sctp_transport { /* Timer to handler reconf chunk rtx */ struct timer_list reconf_timer; + /* Timer to send a probe HB packet for PLPMTUD */ + struct timer_list probe_timer; + /* Since we're using per-destination retransmission timers * (see above), we're also using per-destination "transmitted" * queues. This probably ought to be a private struct @@ -976,6 +983,15 @@ struct sctp_transport { char cacc_saw_newack; } cacc; + struct { + __u16 pmtu; + __u16 probe_size; + __u16 probe_high; + __u8 probe_count:3; + __u8 raise_count:5; + __u8 state; + } pl; /* plpmtud related */ + /* 64-bit random number sent with heartbeat. */ __u64 hb_nonce; @@ -993,6 +1009,7 @@ void sctp_transport_free(struct sctp_transport *); void sctp_transport_reset_t3_rtx(struct sctp_transport *); void sctp_transport_reset_hb_timer(struct sctp_transport *); void sctp_transport_reset_reconf_timer(struct sctp_transport *transport); +void sctp_transport_reset_probe_timer(struct sctp_transport *transport); int sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); @@ -1007,6 +1024,8 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); void sctp_transport_immediate_rtx(struct sctp_transport *); void sctp_transport_dst_release(struct sctp_transport *t); void sctp_transport_dst_confirm(struct sctp_transport *t); +void sctp_transport_pl_send(struct sctp_transport *t); +void sctp_transport_pl_recv(struct sctp_transport *t); /* This is the structure we use to queue packets as they come into @@ -1795,6 +1814,7 @@ struct sctp_association { * will be inherited by all new transports. */ unsigned long hbinterval; + unsigned long probe_interval; __be16 encap_port; diff --git a/include/net/sock.h b/include/net/sock.h index 7a7058f4f265..8bdd80027ffb 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2281,6 +2281,8 @@ static inline int sock_error(struct sock *sk) return -err; } +void sk_error_report(struct sock *sk); + static inline unsigned long sock_wspace(struct sock *sk) { int amt = 0; @@ -2752,6 +2754,9 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) void sock_def_readable(struct sock *sk); int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); +void sock_set_timestamp(struct sock *sk, int optname, bool valbool); +int sock_set_timestamping(struct sock *sk, int optname, int val); + void sock_enable_timestamps(struct sock *sk); void sock_no_linger(struct sock *sk); void sock_set_keepalive(struct sock *sk); diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 505f1e18e9bf..473b0b0fa4ab 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -13,8 +13,9 @@ extern spinlock_t reuseport_lock; struct sock_reuseport { struct rcu_head rcu; - u16 max_socks; /* length of socks */ - u16 num_socks; /* elements in socks */ + u16 max_socks; /* length of socks */ + u16 num_socks; /* elements in socks */ + u16 num_closed_socks; /* closed elements in socks */ /* The last synq overflow event timestamp of this * reuse->socks[] group. */ @@ -31,10 +32,14 @@ extern int reuseport_alloc(struct sock *sk, bool bind_inany); extern int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany); extern void reuseport_detach_sock(struct sock *sk); +void reuseport_stop_listen_sock(struct sock *sk); extern struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len); +struct sock *reuseport_migrate_sock(struct sock *sk, + struct sock *migrating_sk, + struct sk_buff *skb); extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index f1a5a9a3634d..e4cac9218ce1 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -202,6 +202,7 @@ enum switchdev_notifier_type { struct switchdev_notifier_info { struct net_device *dev; struct netlink_ext_ack *extack; + const void *ctx; }; struct switchdev_notifier_fdb_info { @@ -268,19 +269,19 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*add_cb)(struct net_device *dev, + int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)); int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*del_cb)(struct net_device *dev, + int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)); int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), - int (*set_cb)(struct net_device *dev, + int (*set_cb)(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack)); #else @@ -352,7 +353,7 @@ static inline int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*add_cb)(struct net_device *dev, + int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)) { @@ -363,7 +364,7 @@ static inline int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*del_cb)(struct net_device *dev, + int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)) { return 0; @@ -373,7 +374,7 @@ static inline int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), - int (*set_cb)(struct net_device *dev, + int (*set_cb)(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack)) { diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index f051046ba034..f94b8bc26f9e 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -16,6 +16,7 @@ struct tcf_vlan_params { u16 tcfv_push_vid; __be16 tcfv_push_proto; u8 tcfv_push_prio; + bool tcfv_push_prio_exists; struct rcu_head rcu; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index d05193cb0d99..e668f1bf780d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -412,6 +412,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); int tcp_set_window_clamp(struct sock *sk, int val); +void tcp_update_recv_tstamps(struct sk_buff *skb, + struct scm_timestamping_internal *tss); +void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, + struct scm_timestamping_internal *tss); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, diff --git a/include/net/tls.h b/include/net/tls.h index 8341a8d1e807..be4b3e1cac46 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -79,8 +79,6 @@ __SNMP_INC_STATS((net)->mib.tls_statistics, field) #define TLS_INC_STATS(net, field) \ SNMP_INC_STATS((net)->mib.tls_statistics, field) -#define __TLS_DEC_STATS(net, field) \ - __SNMP_DEC_STATS((net)->mib.tls_statistics, field) #define TLS_DEC_STATS(net, field) \ SNMP_DEC_STATS((net)->mib.tls_statistics, field) @@ -471,7 +469,7 @@ static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) static inline void tls_err_abort(struct sock *sk, int err) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } static inline bool tls_bigint_increment(unsigned char *seq, int len) diff --git a/include/net/xdp.h b/include/net/xdp.h index a5bc214a49d9..5533f0ab2afc 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -170,6 +170,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); +struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 9c0722c6d7ac..fff069d2ed1b 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -37,7 +37,7 @@ struct xdp_umem { struct xsk_map { struct bpf_map map; spinlock_t lock; /* Synchronize map updates */ - struct xdp_sock *xsk_map[]; + struct xdp_sock __rcu *xsk_map[]; }; struct xdp_sock { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c58a6d4eb610..cbff7c2a9724 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -145,6 +145,12 @@ enum { XFRM_MODE_FLAG_TUNNEL = 1, }; +enum xfrm_replay_mode { + XFRM_REPLAY_MODE_LEGACY, + XFRM_REPLAY_MODE_BMP, + XFRM_REPLAY_MODE_ESN, +}; + /* Full description of state of transformer. */ struct xfrm_state { possible_net_t xs_net; @@ -154,6 +160,7 @@ struct xfrm_state { }; struct hlist_node bysrc; struct hlist_node byspi; + struct hlist_node byseq; refcount_t refcnt; spinlock_t lock; @@ -214,9 +221,8 @@ struct xfrm_state { struct xfrm_replay_state preplay; struct xfrm_replay_state_esn *preplay_esn; - /* The functions for replay detection. */ - const struct xfrm_replay *repl; - + /* replay detection mode */ + enum xfrm_replay_mode repl_mode; /* internal flag that only holds state for delayed aevent at the * moment */ @@ -296,18 +302,6 @@ struct km_event { struct net *net; }; -struct xfrm_replay { - void (*advance)(struct xfrm_state *x, __be32 net_seq); - int (*check)(struct xfrm_state *x, - struct sk_buff *skb, - __be32 net_seq); - int (*recheck)(struct xfrm_state *x, - struct sk_buff *skb, - __be32 net_seq); - void (*notify)(struct xfrm_state *x, int event); - int (*overflow)(struct xfrm_state *x, struct sk_buff *skb); -}; - struct xfrm_if_cb { struct xfrm_if *(*decode_session)(struct sk_buff *skb, unsigned short family); @@ -387,7 +381,6 @@ void xfrm_flush_gc(void); void xfrm_state_delete_tunnel(struct xfrm_state *x); struct xfrm_type { - char *description; struct module *owner; u8 proto; u8 flags; @@ -402,14 +395,12 @@ struct xfrm_type { int (*output)(struct xfrm_state *, struct sk_buff *pskb); int (*reject)(struct xfrm_state *, struct sk_buff *, const struct flowi *); - int (*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **); }; int xfrm_register_type(const struct xfrm_type *type, unsigned short family); void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family); struct xfrm_type_offload { - char *description; struct module *owner; u8 proto; void (*encap)(struct xfrm_state *, struct sk_buff *pskb); @@ -1024,6 +1015,7 @@ struct xfrm_offload { #define CRYPTO_INVALID_PROTOCOL 128 __u8 proto; + __u8 inner_ipproto; }; struct sec_path { @@ -1546,6 +1538,7 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x); +u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload); int xfrm_init_state(struct xfrm_state *x); @@ -1570,7 +1563,6 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm4_transport_finish(struct sk_buff *skb, int async); int xfrm4_rcv(struct sk_buff *skb); -int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq); static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) { @@ -1581,7 +1573,6 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) } int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb); -int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); @@ -1605,9 +1596,6 @@ int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family) __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr); __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr); int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb); -int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb); -int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, - u8 **prevhdr); #ifdef CONFIG_XFRM void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu); @@ -1721,6 +1709,12 @@ static inline int xfrm_policy_id2dir(u32 index) } #ifdef CONFIG_XFRM +void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq); +int xfrm_replay_check(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); +void xfrm_replay_notify(struct xfrm_state *x, int event); +int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb); +int xfrm_replay_recheck(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); + static inline int xfrm_aevent_is_on(struct net *net) { struct sock *nlsk; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index eaa8386dbc63..7a9a23e7a604 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -147,11 +147,16 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, { bool cross_pg = (addr & (PAGE_SIZE - 1)) + len > PAGE_SIZE; - if (pool->dma_pages_cnt && cross_pg) { + if (likely(!cross_pg)) + return false; + + if (pool->dma_pages_cnt) { return !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK); } - return false; + + /* skb path */ + return addr + len > pool->addrs_cnt; } static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr) |