diff options
| author | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2022-01-15 12:09:44 -0800 |
|---|---|---|
| committer | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2022-01-15 12:09:44 -0800 |
| commit | 762f99f4f3cb41a775b5157dd761217beba65873 (patch) | |
| tree | 2e93410a577dfff1202ea5b0d109460b97650e58 /include/net | |
| parent | cf73ed894ee939d6706d65e0cd186e4a64e3af6d (diff) | |
| parent | b6e43dddaea3dbfa93327f986beb3ec5e8157c4c (diff) | |
Merge branch 'next' into for-linus
Prepare input updates for 5.17 merge window.
Diffstat (limited to 'include/net')
94 files changed, 1874 insertions, 867 deletions
diff --git a/include/net/Space.h b/include/net/Space.h index 9cce0d80d37a..08ca9cef0213 100644 --- a/include/net/Space.h +++ b/include/net/Space.h @@ -8,23 +8,13 @@ struct net_device *ultra_probe(int unit); struct net_device *wd_probe(int unit); struct net_device *ne_probe(int unit); struct net_device *fmv18x_probe(int unit); -struct net_device *i82596_probe(int unit); struct net_device *ni65_probe(int unit); struct net_device *sonic_probe(int unit); struct net_device *smc_init(int unit); -struct net_device *atarilance_probe(int unit); -struct net_device *sun3lance_probe(int unit); -struct net_device *sun3_82586_probe(int unit); -struct net_device *apne_probe(int unit); struct net_device *cs89x0_probe(int unit); -struct net_device *mvme147lance_probe(int unit); struct net_device *tc515_probe(int unit); struct net_device *lance_probe(int unit); struct net_device *cops_probe(int unit); -struct net_device *ltpc_probe(void); /* Fibre Channel adapters */ int iph5526_probe(struct net_device *dev); - -/* SBNI adapters */ -int sbni_probe(int unit); diff --git a/include/net/act_api.h b/include/net/act_api.h index 086b291e9530..f19f7f4a463c 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -58,6 +58,14 @@ struct tc_action { #define TCA_ACT_HW_STATS_ANY (TCA_ACT_HW_STATS_IMMEDIATE | \ TCA_ACT_HW_STATS_DELAYED) +/* Reserve 16 bits for user-space. See TCA_ACT_FLAGS_NO_PERCPU_STATS. */ +#define TCA_ACT_FLAGS_USER_BITS 16 +#define TCA_ACT_FLAGS_USER_MASK 0xffff +#define TCA_ACT_FLAGS_POLICE (1U << TCA_ACT_FLAGS_USER_BITS) +#define TCA_ACT_FLAGS_BIND (1U << (TCA_ACT_FLAGS_USER_BITS + 1)) +#define TCA_ACT_FLAGS_REPLACE (1U << (TCA_ACT_FLAGS_USER_BITS + 2)) +#define TCA_ACT_FLAGS_NO_RTNL (1U << (TCA_ACT_FLAGS_USER_BITS + 3)) + /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. */ @@ -99,8 +107,8 @@ struct tc_action_ops { void (*cleanup)(struct tc_action *); int (*lookup)(struct net *net, struct tc_action **a, u32 index); int (*init)(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **act, int ovr, - int bind, bool rtnl_held, struct tcf_proto *tp, + struct nlattr *est, struct tc_action **act, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack); int (*walk)(struct net *, struct sk_buff *, struct netlink_callback *, int, @@ -179,18 +187,16 @@ int tcf_action_destroy(struct tc_action *actions[], int bind); int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, - struct nlattr *est, char *name, int ovr, int bind, + struct nlattr *est, struct tc_action *actions[], int init_res[], size_t *attr_size, - bool rtnl_held, struct netlink_ext_ack *extack); -struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, + u32 flags, struct netlink_ext_ack *extack); +struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police, bool rtnl_held, struct netlink_ext_ack *extack); struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind, struct tc_action_ops *a_o, int *init_res, - bool rtnl_held, - struct netlink_ext_ack *extack); + u32 flags, struct netlink_ext_ack *extack); int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, int ref, bool terse); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); diff --git a/include/net/af_unix.h b/include/net/af_unix.h index f42fdddecd41..7d142e8a0550 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -70,6 +70,9 @@ struct unix_sock { struct socket_wq peer_wq; wait_queue_entry_t peer_wake; struct scm_stat scm_stat; +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + struct sk_buff *oob_skb; +#endif }; static inline struct unix_sock *unix_sk(const struct sock *sk) @@ -82,6 +85,10 @@ static inline struct unix_sock *unix_sk(const struct sock *sk) long unix_inq_len(struct sock *sk); long unix_outq_len(struct sock *sk); +int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, + int flags); +int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, + int flags); #ifdef CONFIG_SYSCTL int unix_sysctl_register(struct net *net); void unix_sysctl_unregister(struct net *net); @@ -89,4 +96,16 @@ void unix_sysctl_unregister(struct net *net); static inline int unix_sysctl_register(struct net *net) { return 0; } static inline void unix_sysctl_unregister(struct net *net) {} #endif + +#ifdef CONFIG_BPF_SYSCALL +extern struct proto unix_dgram_proto; +extern struct proto unix_stream_proto; + +int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); +int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); +void __init unix_bpf_build_proto(void); +#else +static inline void __init unix_bpf_build_proto(void) +{} +#endif #endif 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/ax88796.h b/include/net/ax88796.h index aa52b2e8ff7b..2ed23a368602 100644 --- a/include/net/ax88796.h +++ b/include/net/ax88796.h @@ -38,4 +38,7 @@ struct ax_plat_data { int (*check_irq)(struct platform_device *pdev); }; +/* exported from ax88796.c for xsurf100.c */ +extern void ax_NS8390_reinit(struct net_device *dev); + #endif /* __NET_AX88796_PLAT_H */ 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..a7360c8c72f8 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 { @@ -221,6 +221,7 @@ struct oob_data { struct adv_info { struct list_head list; + bool enabled; bool pending; __u8 instance; __u32 flags; @@ -228,9 +229,9 @@ 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 +328,7 @@ 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 +471,7 @@ 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 +523,14 @@ 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 +552,9 @@ 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; @@ -627,6 +629,7 @@ struct hci_conn { __u8 init_addr_type; bdaddr_t resp_addr; __u8 resp_addr_type; + __u8 adv_instance; __u16 handle; __u16 state; __u8 mode; @@ -893,7 +896,7 @@ 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 +922,7 @@ 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: @@ -1222,13 +1225,25 @@ static inline void hci_set_drvdata(struct hci_dev *hdev, void *data) dev_set_drvdata(&hdev->dev, data); } +static inline void *hci_get_priv(struct hci_dev *hdev) +{ + return (char *)hdev + sizeof(*hdev); +} + struct hci_dev *hci_dev_get(int index); struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, u8 src_type); -struct hci_dev *hci_alloc_dev(void); +struct hci_dev *hci_alloc_dev_priv(int sizeof_priv); + +static inline struct hci_dev *hci_alloc_dev(void) +{ + return hci_alloc_dev_priv(0); +} + void hci_free_dev(struct hci_dev *hdev); int hci_register_dev(struct hci_dev *hdev); void hci_unregister_dev(struct hci_dev *hdev); +void hci_release_dev(struct hci_dev *hdev); int hci_suspend_dev(struct hci_dev *hdev); int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); @@ -1393,8 +1408,8 @@ 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) @@ -1410,6 +1425,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); !hci_dev_test_flag(dev, HCI_AUTO_OFF)) #define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ hci_dev_test_flag(dev, HCI_SC_ENABLED)) +#define rpa_valid(dev) (bacmp(&dev->rpa, BDADDR_ANY) && \ + !hci_dev_test_flag(dev, HCI_RPA_EXPIRED)) +#define adv_rpa_valid(adv) (bacmp(&adv->random_addr, BDADDR_ANY) && \ + !adv->rpa_expired) #define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M)) @@ -1768,7 +1787,7 @@ 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/bond_3ad.h b/include/net/bond_3ad.h index c8696a230b7d..38785d48baff 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -303,6 +303,7 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond, int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); int bond_3ad_set_carrier(struct bonding *bond); +void bond_3ad_update_lacp_active(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); void bond_3ad_update_ad_actor_settings(struct bonding *bond); int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats); diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 9d382f2f0bc5..e64833a674eb 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -64,6 +64,7 @@ enum { BOND_OPT_AD_USER_PORT_KEY, BOND_OPT_NUM_PEER_NOTIF_ALIAS, BOND_OPT_PEER_NOTIF_DELAY, + BOND_OPT_LACP_ACTIVE, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index 019e998d944a..15e083e18f75 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -129,6 +129,7 @@ struct bond_params { int updelay; int downdelay; int peer_notif_delay; + int lacp_active; int lacp_fast; unsigned int min_links; int ad_select; @@ -149,11 +150,6 @@ struct bond_params { u8 ad_actor_system[ETH_ALEN + 2]; }; -struct bond_parm_tbl { - char *modename; - int mode; -}; - struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ @@ -201,6 +197,11 @@ struct bond_up_slave { */ #define BOND_LINK_NOCHANGE -1 +struct bond_ipsec { + struct list_head list; + struct xfrm_state *xs; +}; + /* * Here are the locking policies for the two bonding locks: * Get rcu_read_lock when reading or RTNL when writing slave list. @@ -232,7 +233,7 @@ 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; @@ -249,8 +250,11 @@ struct bonding { #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; #ifdef CONFIG_XFRM_OFFLOAD - struct xfrm_state *xs; + struct list_head ipsec_list; + /* protecting ipsec_list */ + spinlock_t ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ + struct bpf_prog *xdp_prog; }; #define bond_slave_get_rcu(dev) \ @@ -746,13 +750,6 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) /* exported from bond_main.c */ extern unsigned int bond_net_id; -extern const struct bond_parm_tbl bond_lacp_tbl[]; -extern const struct bond_parm_tbl xmit_hashtype_tbl[]; -extern const struct bond_parm_tbl arp_validate_tbl[]; -extern const struct bond_parm_tbl arp_all_targets_tbl[]; -extern const struct bond_parm_tbl fail_over_mac_tbl[]; -extern const struct bond_parm_tbl pri_reselect_tbl[]; -extern struct bond_parm_tbl ad_select_tbl[]; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 73af4a64a599..40296ed976a9 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -38,7 +38,7 @@ static inline bool net_busy_loop_on(void) static inline bool sk_can_busy_loop(const struct sock *sk) { - return sk->sk_ll_usec && !signal_pending(current); + return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current); } bool sk_busy_loop_end(void *p, unsigned long start_time); diff --git a/include/net/caif/caif_hsi.h b/include/net/caif/caif_hsi.h deleted file mode 100644 index 552cf68d28d2..000000000000 --- a/include/net/caif/caif_hsi.h +++ /dev/null @@ -1,200 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson AB 2010 - * Author: Daniel Martensson / daniel.martensson@stericsson.com - * Dmitry.Tarnyagin / dmitry.tarnyagin@stericsson.com - */ - -#ifndef CAIF_HSI_H_ -#define CAIF_HSI_H_ - -#include <net/caif/caif_layer.h> -#include <net/caif/caif_device.h> -#include <linux/atomic.h> - -/* - * Maximum number of CAIF frames that can reside in the same HSI frame. - */ -#define CFHSI_MAX_PKTS 15 - -/* - * Maximum number of bytes used for the frame that can be embedded in the - * HSI descriptor. - */ -#define CFHSI_MAX_EMB_FRM_SZ 96 - -/* - * Decides if HSI buffers should be prefilled with 0xFF pattern for easier - * debugging. Both TX and RX buffers will be filled before the transfer. - */ -#define CFHSI_DBG_PREFILL 0 - -/* Structure describing a HSI packet descriptor. */ -#pragma pack(1) /* Byte alignment. */ -struct cfhsi_desc { - u8 header; - u8 offset; - u16 cffrm_len[CFHSI_MAX_PKTS]; - u8 emb_frm[CFHSI_MAX_EMB_FRM_SZ]; -}; -#pragma pack() /* Default alignment. */ - -/* Size of the complete HSI packet descriptor. */ -#define CFHSI_DESC_SZ (sizeof(struct cfhsi_desc)) - -/* - * Size of the complete HSI packet descriptor excluding the optional embedded - * CAIF frame. - */ -#define CFHSI_DESC_SHORT_SZ (CFHSI_DESC_SZ - CFHSI_MAX_EMB_FRM_SZ) - -/* - * Maximum bytes transferred in one transfer. - */ -#define CFHSI_MAX_CAIF_FRAME_SZ 4096 - -#define CFHSI_MAX_PAYLOAD_SZ (CFHSI_MAX_PKTS * CFHSI_MAX_CAIF_FRAME_SZ) - -/* Size of the complete HSI TX buffer. */ -#define CFHSI_BUF_SZ_TX (CFHSI_DESC_SZ + CFHSI_MAX_PAYLOAD_SZ) - -/* Size of the complete HSI RX buffer. */ -#define CFHSI_BUF_SZ_RX ((2 * CFHSI_DESC_SZ) + CFHSI_MAX_PAYLOAD_SZ) - -/* Bitmasks for the HSI descriptor. */ -#define CFHSI_PIGGY_DESC (0x01 << 7) - -#define CFHSI_TX_STATE_IDLE 0 -#define CFHSI_TX_STATE_XFER 1 - -#define CFHSI_RX_STATE_DESC 0 -#define CFHSI_RX_STATE_PAYLOAD 1 - -/* Bitmasks for power management. */ -#define CFHSI_WAKE_UP 0 -#define CFHSI_WAKE_UP_ACK 1 -#define CFHSI_WAKE_DOWN_ACK 2 -#define CFHSI_AWAKE 3 -#define CFHSI_WAKELOCK_HELD 4 -#define CFHSI_SHUTDOWN 5 -#define CFHSI_FLUSH_FIFO 6 - -#ifndef CFHSI_INACTIVITY_TOUT -#define CFHSI_INACTIVITY_TOUT (1 * HZ) -#endif /* CFHSI_INACTIVITY_TOUT */ - -#ifndef CFHSI_WAKE_TOUT -#define CFHSI_WAKE_TOUT (3 * HZ) -#endif /* CFHSI_WAKE_TOUT */ - -#ifndef CFHSI_MAX_RX_RETRIES -#define CFHSI_MAX_RX_RETRIES (10 * HZ) -#endif - -/* Structure implemented by the CAIF HSI driver. */ -struct cfhsi_cb_ops { - void (*tx_done_cb) (struct cfhsi_cb_ops *drv); - void (*rx_done_cb) (struct cfhsi_cb_ops *drv); - void (*wake_up_cb) (struct cfhsi_cb_ops *drv); - void (*wake_down_cb) (struct cfhsi_cb_ops *drv); -}; - -/* Structure implemented by HSI device. */ -struct cfhsi_ops { - int (*cfhsi_up) (struct cfhsi_ops *dev); - int (*cfhsi_down) (struct cfhsi_ops *dev); - int (*cfhsi_tx) (u8 *ptr, int len, struct cfhsi_ops *dev); - int (*cfhsi_rx) (u8 *ptr, int len, struct cfhsi_ops *dev); - int (*cfhsi_wake_up) (struct cfhsi_ops *dev); - int (*cfhsi_wake_down) (struct cfhsi_ops *dev); - int (*cfhsi_get_peer_wake) (struct cfhsi_ops *dev, bool *status); - int (*cfhsi_fifo_occupancy) (struct cfhsi_ops *dev, size_t *occupancy); - int (*cfhsi_rx_cancel)(struct cfhsi_ops *dev); - struct cfhsi_cb_ops *cb_ops; -}; - -/* Structure holds status of received CAIF frames processing */ -struct cfhsi_rx_state { - int state; - int nfrms; - int pld_len; - int retries; - bool piggy_desc; -}; - -/* Priority mapping */ -enum { - CFHSI_PRIO_CTL = 0, - CFHSI_PRIO_VI, - CFHSI_PRIO_VO, - CFHSI_PRIO_BEBK, - CFHSI_PRIO_LAST, -}; - -struct cfhsi_config { - u32 inactivity_timeout; - u32 aggregation_timeout; - u32 head_align; - u32 tail_align; - u32 q_high_mark; - u32 q_low_mark; -}; - -/* Structure implemented by CAIF HSI drivers. */ -struct cfhsi { - struct caif_dev_common cfdev; - struct net_device *ndev; - struct platform_device *pdev; - struct sk_buff_head qhead[CFHSI_PRIO_LAST]; - struct cfhsi_cb_ops cb_ops; - struct cfhsi_ops *ops; - int tx_state; - struct cfhsi_rx_state rx_state; - struct cfhsi_config cfg; - int rx_len; - u8 *rx_ptr; - u8 *tx_buf; - u8 *rx_buf; - u8 *rx_flip_buf; - spinlock_t lock; - int flow_off_sent; - struct list_head list; - struct work_struct wake_up_work; - struct work_struct wake_down_work; - struct work_struct out_of_sync_work; - struct workqueue_struct *wq; - wait_queue_head_t wake_up_wait; - wait_queue_head_t wake_down_wait; - wait_queue_head_t flush_fifo_wait; - struct timer_list inactivity_timer; - struct timer_list rx_slowpath_timer; - - /* TX aggregation */ - int aggregation_len; - struct timer_list aggregation_timer; - - unsigned long bits; -}; -extern struct platform_driver cfhsi_driver; - -/** - * enum ifla_caif_hsi - CAIF HSI NetlinkRT parameters. - * @IFLA_CAIF_HSI_INACTIVITY_TOUT: Inactivity timeout before - * taking the HSI wakeline down, in milliseconds. - * When using RT Netlink to create, destroy or configure a CAIF HSI interface, - * enum ifla_caif_hsi is used to specify the configuration attributes. - */ -enum ifla_caif_hsi { - __IFLA_CAIF_HSI_UNSPEC, - __IFLA_CAIF_HSI_INACTIVITY_TOUT, - __IFLA_CAIF_HSI_AGGREGATION_TOUT, - __IFLA_CAIF_HSI_HEAD_ALIGN, - __IFLA_CAIF_HSI_TAIL_ALIGN, - __IFLA_CAIF_HSI_QHIGH_WATERMARK, - __IFLA_CAIF_HSI_QLOW_WATERMARK, - __IFLA_CAIF_HSI_MAX -}; - -struct cfhsi_ops *cfhsi_get_ops(void); - -#endif /* CAIF_HSI_H_ */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 58c2cd417e89..27336fc70467 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 @@ -1245,7 +1252,26 @@ struct cfg80211_csa_settings { u8 count; }; -#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 +/** + * struct cfg80211_color_change_settings - color change settings + * + * Used for bss color change + * + * @beacon_color_change: beacon data while performing the color countdown + * @counter_offsets_beacon: offsets of the counters within the beacon (tail) + * @counter_offsets_presp: offsets of the counters within the probe response + * @beacon_next: beacon data to be used after the color change + * @count: number of beacons until the color change + * @color: the color used after the change + */ +struct cfg80211_color_change_settings { + struct cfg80211_beacon_data beacon_color_change; + u16 counter_offset_beacon; + u16 counter_offset_presp; + struct cfg80211_beacon_data beacon_next; + u8 count; + u8 color; +}; /** * struct iface_combination_params - input parameters for interface combinations @@ -3522,7 +3548,10 @@ 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 +3569,7 @@ struct cfg80211_pmsr_ftm_request_peer { u8 burst_duration; u8 ftms_per_burst; u8 ftmr_retries; + u8 bss_color; }; /** @@ -3986,6 +4016,8 @@ struct mgmt_frame_regs { * given TIDs. This callback may sleep. * * @set_sar_specs: Update the SAR (TX power) settings. + * + * @color_change: Initiate a color change. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4313,6 +4345,9 @@ struct cfg80211_ops { const u8 *peer, u8 tids); int (*set_sar_specs)(struct wiphy *wiphy, struct cfg80211_sar_specs *sar); + int (*color_change)(struct wiphy *wiphy, + struct net_device *dev, + struct cfg80211_color_change_settings *params); }; /* @@ -4945,6 +4980,7 @@ 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 +5123,8 @@ struct wiphy { const struct cfg80211_sar_capa *sar_capa; + struct rfkill *rfkill; + char priv[] __aligned(NETDEV_ALIGN); }; @@ -5338,7 +5376,6 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * netdev and may otherwise be used by driver read-only, will be update * by cfg80211 on change_interface * @mgmt_registrations: list of registrations for management frames - * @mgmt_registrations_lock: lock for the list * @mgmt_registrations_need_update: mgmt registrations were updated, * need to propagate the update to the driver * @mtx: mutex used to lock data in this struct, may be used by drivers @@ -5385,7 +5422,6 @@ struct wireless_dev { u32 identifier; struct list_head mgmt_registrations; - spinlock_t mgmt_registrations_lock; u8 mgmt_registrations_need_update:1; struct mutex mtx; @@ -6661,7 +6697,10 @@ 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 +8193,8 @@ 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) @@ -8201,4 +8242,70 @@ void cfg80211_update_owe_info_event(struct net_device *netdev, */ void cfg80211_bss_flush(struct wiphy *wiphy); +/** + * cfg80211_bss_color_notify - notify about bss color event + * @dev: network device + * @gfp: allocation flags + * @cmd: the actual event we want to notify + * @count: the number of TBTTs until the color change happens + * @color_bitmap: representations of the colors that the local BSS is aware of + */ +int cfg80211_bss_color_notify(struct net_device *dev, gfp_t gfp, + enum nl80211_commands cmd, u8 count, + u64 color_bitmap); + +/** + * cfg80211_obss_color_collision_notify - notify about bss color collision + * @dev: network device + * @color_bitmap: representations of the colors that the local BSS is aware of + */ +static inline int cfg80211_obss_color_collision_notify(struct net_device *dev, + u64 color_bitmap) +{ + return cfg80211_bss_color_notify(dev, GFP_KERNEL, + NL80211_CMD_OBSS_COLOR_COLLISION, + 0, color_bitmap); +} + +/** + * cfg80211_color_change_started_notify - notify color change start + * @dev: the device on which the color is switched + * @count: the number of TBTTs until the color change happens + * + * Inform the userspace about the color change that has started. + */ +static inline int cfg80211_color_change_started_notify(struct net_device *dev, + u8 count) +{ + return cfg80211_bss_color_notify(dev, GFP_KERNEL, + NL80211_CMD_COLOR_CHANGE_STARTED, + count, 0); +} + +/** + * cfg80211_color_change_aborted_notify - notify color change abort + * @dev: the device on which the color is switched + * + * Inform the userspace about the color change that has aborted. + */ +static inline int cfg80211_color_change_aborted_notify(struct net_device *dev) +{ + return cfg80211_bss_color_notify(dev, GFP_KERNEL, + NL80211_CMD_COLOR_CHANGE_ABORTED, + 0, 0); +} + +/** + * cfg80211_color_change_notify - notify color change completion + * @dev: the device on which the color was switched + * + * Inform the userspace about the color change that has completed. + */ +static inline int cfg80211_color_change_notify(struct net_device *dev) +{ + return cfg80211_bss_color_notify(dev, GFP_KERNEL, + NL80211_CMD_COLOR_CHANGE_COMPLETED, + 0, 0); +} + #endif /* __NET_CFG80211_H */ diff --git a/include/net/checksum.h b/include/net/checksum.h index 0d05b9e8690b..5b96d5bd6e54 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -80,16 +80,18 @@ static inline __sum16 csum16_sub(__sum16 csum, __be16 addend) return csum16_add(csum, ~addend); } -static inline __wsum -csum_block_add(__wsum csum, __wsum csum2, int offset) +static inline __wsum csum_shift(__wsum sum, int offset) { - u32 sum = (__force u32)csum2; - /* rotate sum to align it with a 16b boundary */ if (offset & 1) - sum = ror32(sum, 8); + return (__force __wsum)ror32((__force u32)sum, 8); + return sum; +} - return csum_add(csum, (__force __wsum)sum); +static inline __wsum +csum_block_add(__wsum csum, __wsum csum2, int offset) +{ + return csum_add(csum, csum_shift(csum2, offset)); } static inline __wsum diff --git a/include/net/compat.h b/include/net/compat.h index 84805bdc4435..595fee069b82 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -71,13 +71,26 @@ struct compat_group_source_req { } __packed; struct compat_group_filter { - __u32 gf_interface; - struct __kernel_sockaddr_storage gf_group - __aligned(4); - __u32 gf_fmode; - __u32 gf_numsrc; - struct __kernel_sockaddr_storage gf_slist[1] - __aligned(4); + union { + struct { + __u32 gf_interface_aux; + struct __kernel_sockaddr_storage gf_group_aux + __aligned(4); + __u32 gf_fmode_aux; + __u32 gf_numsrc_aux; + struct __kernel_sockaddr_storage gf_slist[1] + __aligned(4); + } __packed; + struct { + __u32 gf_interface; + struct __kernel_sockaddr_storage gf_group + __aligned(4); + __u32 gf_fmode; + __u32 gf_numsrc; + struct __kernel_sockaddr_storage gf_slist_flex[] + __aligned(4); + } __packed; + }; } __packed; #endif /* NET_COMPAT_H */ diff --git a/include/net/devlink.h b/include/net/devlink.h index 7c984cadfec4..154cf0dbca37 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -32,8 +32,9 @@ struct devlink_dev_stats { struct devlink_ops; struct devlink { - struct list_head list; + u32 index; 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; @@ -54,8 +55,9 @@ struct devlink { * port, sb, dpipe, resource, params, region, traps and more. */ u8 reload_failed:1, - reload_enabled:1, - registered:1; + reload_enabled:1; + refcount_t refcount; + struct completion comp; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -133,13 +135,30 @@ 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; struct list_head region_list; struct devlink *devlink; unsigned int index; - bool registered; spinlock_t type_lock; /* Protects type and type_dev * pointer consistency. */ @@ -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 { @@ -500,6 +521,9 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE, DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -540,6 +564,15 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME "enable_remote_dev_reset" #define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL +#define DEVLINK_PARAM_GENERIC_ENABLE_ETH_NAME "enable_eth" +#define DEVLINK_PARAM_GENERIC_ENABLE_ETH_TYPE DEVLINK_PARAM_TYPE_BOOL + +#define DEVLINK_PARAM_GENERIC_ENABLE_RDMA_NAME "enable_rdma" +#define DEVLINK_PARAM_GENERIC_ENABLE_RDMA_TYPE DEVLINK_PARAM_TYPE_BOOL + +#define DEVLINK_PARAM_GENERIC_ENABLE_VNET_NAME "enable_vnet" +#define DEVLINK_PARAM_GENERIC_ENABLE_VNET_TYPE DEVLINK_PARAM_TYPE_BOOL + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ @@ -1327,6 +1360,16 @@ 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 @@ -1367,8 +1410,8 @@ struct devlink_ops { * * Note: @extack can be NULL when port notifier queries the port function. */ - int (*port_function_hw_addr_get)(struct devlink *devlink, struct devlink_port *port, - u8 *hw_addr, int *hw_addr_len, + int (*port_function_hw_addr_get)(struct devlink_port *port, u8 *hw_addr, + int *hw_addr_len, struct netlink_ext_ack *extack); /** * @port_function_hw_addr_set: Port function's hardware address set function. @@ -1377,7 +1420,7 @@ struct devlink_ops { * by the devlink port. Driver should return -EOPNOTSUPP if it doesn't support port * function handling for a particular port. */ - int (*port_function_hw_addr_set)(struct devlink *devlink, struct devlink_port *port, + int (*port_function_hw_addr_set)(struct devlink_port *port, const u8 *hw_addr, int hw_addr_len, struct netlink_ext_ack *extack); /** @@ -1433,8 +1476,7 @@ struct devlink_ops { * * Return: 0 on success, negative value otherwise. */ - int (*port_fn_state_get)(struct devlink *devlink, - struct devlink_port *port, + int (*port_fn_state_get)(struct devlink_port *port, enum devlink_port_fn_state *state, enum devlink_port_fn_opstate *opstate, struct netlink_ext_ack *extack); @@ -1449,10 +1491,33 @@ struct devlink_ops { * * Return: 0 on success, negative value otherwise. */ - int (*port_fn_state_set)(struct devlink *devlink, - struct devlink_port *port, + int (*port_fn_state_set)(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) @@ -1487,9 +1552,21 @@ static inline struct devlink *netdev_to_devlink(struct net_device *dev) struct ib_device; struct net *devlink_net(const struct devlink *devlink); -void devlink_net_set(struct devlink *devlink, struct net *net); -struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); -int devlink_register(struct devlink *devlink, struct device *dev); +/* This call is intended for software devices that can create + * devlink instances in other namespaces than init_net. + * + * Drivers that operate on real HW must use devlink_alloc() instead. + */ +struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, + size_t priv_size, struct net *net, + struct device *dev); +static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, + size_t priv_size, + struct device *dev) +{ + return devlink_alloc_ns(ops, priv_size, &init_net, dev); +} +int devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); void devlink_reload_enable(struct devlink *devlink); void devlink_reload_disable(struct devlink *devlink); @@ -1512,6 +1589,9 @@ 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, @@ -1567,8 +1647,16 @@ int devlink_params_register(struct devlink *devlink, void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *params, size_t params_count); +int devlink_param_register(struct devlink *devlink, + const struct devlink_param *param); +void devlink_param_unregister(struct devlink *devlink, + const struct devlink_param *param); void devlink_params_publish(struct devlink *devlink); void devlink_params_unpublish(struct devlink *devlink); +void devlink_param_publish(struct devlink *devlink, + const struct devlink_param *param); +void devlink_param_unpublish(struct devlink *devlink, + const struct devlink_param *param); int devlink_port_params_register(struct devlink_port *devlink_port, const struct devlink_param *params, size_t params_count); diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h index ccc6e9df178b..ddd6565957b3 100644 --- a/include/net/dn_fib.h +++ b/include/net/dn_fib.h @@ -29,7 +29,7 @@ struct dn_fib_nh { struct dn_fib_info { struct dn_fib_info *fib_next; struct dn_fib_info *fib_prev; - int fib_treeref; + refcount_t fib_treeref; refcount_t fib_clntref; int fib_dead; unsigned int fib_flags; diff --git a/include/net/dsa.h b/include/net/dsa.h index e1a2610a0e06..d784e76113b8 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, @@ -75,23 +76,18 @@ 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; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); - struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt); + struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); - /* Used to determine which traffic should match the DSA filter in - * eth_type_trans, and which, if any, should bypass it and be processed - * 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 +96,6 @@ 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 @@ -109,8 +104,8 @@ struct dsa_device_ops { * function pointers. */ struct dsa_netdevice_ops { - int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, - int cmd); + int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, + int cmd); }; #define DSA_TAG_DRIVER_ALIAS "dsa_tag-" @@ -157,6 +152,9 @@ struct dsa_switch_tree { */ struct net_device **lags; unsigned int lags_len; + + /* Track the largest switch index within a tree */ + unsigned int last_switch; }; #define dsa_lags_foreach_id(_id, _dst) \ @@ -236,9 +234,7 @@ struct dsa_port { /* Copies for faster access in master receive hot path */ struct dsa_switch_tree *dst; - struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt); - bool (*filter)(const struct sk_buff *skb, struct net_device *dev); + struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); enum { DSA_PORT_TYPE_UNUSED = 0, @@ -255,8 +251,11 @@ struct dsa_port { struct device_node *dn; unsigned int ageing_time; bool vlan_filtering; + /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ + bool learning; u8 stp_state; struct net_device *bridge_dev; + int bridge_num; struct devlink_port devlink_port; bool devlink_port_setup; struct phylink *pl; @@ -283,6 +282,12 @@ 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 +302,13 @@ 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; @@ -337,6 +349,9 @@ struct dsa_switch { unsigned int ageing_time_min; unsigned int ageing_time_max; + /* Storage for drivers using tag_8021q */ + struct dsa_8021q_context *tag_8021q_ctx; + /* devlink used to represent this switch device */ struct devlink *devlink; @@ -348,6 +363,9 @@ struct dsa_switch { */ bool vlan_filtering_is_global; + /* Keep VLAN filtering enabled on ports not offloading any upper. */ + bool needs_standalone_vlan_filtering; + /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges * that have vlan_filtering=0. All drivers should ideally set this (and * then the option would get removed), but it is unknown whether this @@ -392,6 +410,13 @@ struct dsa_switch { */ unsigned int num_lag_ids; + /* Drivers that support bridge forwarding offload should set this to + * the maximum number of bridges spanning the same switch tree (or all + * trees, in the case of cross-tree bridging support) that can be + * offloaded. + */ + unsigned int num_fwd_offloading_bridges; + size_t num_ports; }; @@ -407,6 +432,26 @@ 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_port_is_unused(struct dsa_port *dp) +{ + return dp->type == DSA_PORT_TYPE_UNUSED; +} + 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 +519,32 @@ 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; @@ -514,8 +585,16 @@ struct dsa_switch_ops { int (*change_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol proto); + /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); + + /* Per-port initialization and destruction methods. Mandatory if the + * driver registers devlink port regions, optional otherwise. + */ + int (*port_setup)(struct dsa_switch *ds, int port); + void (*port_teardown)(struct dsa_switch *ds, int port); + u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* @@ -634,6 +713,14 @@ struct dsa_switch_ops { struct net_device *bridge); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct net_device *bridge); + /* Called right after .port_bridge_join() */ + int (*port_bridge_tx_fwd_offload)(struct dsa_switch *ds, int port, + struct net_device *bridge, + int bridge_num); + /* Called right before .port_bridge_leave() */ + void (*port_bridge_tx_fwd_unoffload)(struct dsa_switch *ds, int port, + struct net_device *bridge, + int bridge_num); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); void (*port_fast_age)(struct dsa_switch *ds, int port); @@ -643,8 +730,6 @@ struct dsa_switch_ops { int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); - int (*port_set_mrouter)(struct dsa_switch *ds, int port, bool mrouter, - struct netlink_ext_ack *extack); /* * VLAN support @@ -813,6 +898,13 @@ struct dsa_switch_ops { const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); + + /* + * tag_8021q operations + */ + int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, + u16 flags); + int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ @@ -898,15 +990,6 @@ static inline bool netdev_uses_dsa(const struct net_device *dev) return false; } -static inline bool dsa_can_decode(const struct sk_buff *skb, - struct net_device *dev) -{ -#if IS_ENABLED(CONFIG_NET_DSA) - return !dev->dsa_ptr->filter || dev->dsa_ptr->filter(skb, dev); -#endif - return false; -} - /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. @@ -926,7 +1009,7 @@ 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]; @@ -947,8 +1030,8 @@ static inline int __dsa_netdevice_ops_check(struct net_device *dev) return 0; } -static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr, - int cmd) +static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, + int cmd) { const struct dsa_netdevice_ops *ops; int err; @@ -959,11 +1042,11 @@ static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr, ops = dev->dsa_ptr->netdev_ops; - return ops->ndo_do_ioctl(dev, ifr, cmd); + return ops->ndo_eth_ioctl(dev, ifr, cmd); } #else -static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr, - int cmd) +static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, + int cmd) { return -EOPNOTSUPP; } @@ -971,6 +1054,7 @@ static inline int dsa_ndo_do_ioctl(struct net_device *dev, struct ifreq *ifr, void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); +void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); diff --git a/include/net/dst.h b/include/net/dst.h index 75b1e734e9c2..a057319aabef 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -277,6 +277,7 @@ static inline void skb_dst_drop(struct sk_buff *skb) static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst) { + nskb->slow_gro |= !!refdst; nskb->_skb_refdst = refdst; if (!(nskb->_skb_refdst & SKB_DST_NOREF)) dst_clone(skb_dst(nskb)); @@ -316,6 +317,7 @@ static inline bool skb_dst_force(struct sk_buff *skb) dst = NULL; skb->_skb_refdst = (unsigned long)dst; + skb->slow_gro |= !!dst; } return skb->_skb_refdst != 0UL; diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 56cb3c38569a..14efa0ded75d 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -45,7 +45,9 @@ skb_tunnel_info(const struct sk_buff *skb) return &md_dst->u.tun_info; dst = skb_dst(skb); - if (dst && dst->lwtstate) + if (dst && dst->lwtstate && + (dst->lwtstate->type == LWTUNNEL_ENCAP_IP || + dst->lwtstate->type == LWTUNNEL_ENCAP_IP6)) return lwt_tun_info(dst->lwtstate); return NULL; diff --git a/include/net/flow.h b/include/net/flow.h index 6f5e70240071..58beb16a49b8 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -194,7 +194,7 @@ static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4) static inline struct flowi_common *flowi4_to_flowi_common(struct flowi4 *fl4) { - return &(flowi4_to_flowi(fl4)->u.__fl_common); + return &(fl4->__fl_common); } static inline struct flowi *flowi6_to_flowi(struct flowi6 *fl6) @@ -204,7 +204,7 @@ static inline struct flowi *flowi6_to_flowi(struct flowi6 *fl6) static inline struct flowi_common *flowi6_to_flowi_common(struct flowi6 *fl6) { - return &(flowi6_to_flowi(fl6)->u.__fl_common); + return &(fl6->__fl_common); } static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn) diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index dc5c1e69cd9f..3961461d9c8b 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -293,7 +293,7 @@ static inline bool flow_action_has_entries(const struct flow_action *action) } /** - * flow_action_has_one_action() - check if exactly one action is present + * flow_offload_has_one_action() - check if exactly one action is present * @action: tc filter flow offload action * * Returns true if exactly one action is present. @@ -451,6 +451,7 @@ struct flow_block_offload { struct list_head *driver_block_list; struct netlink_ext_ack *extack; struct Qdisc *sch; + struct list_head *cb_list_head; }; enum tc_setup_type; 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/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index c0854933e24f..11630351c978 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -43,6 +43,11 @@ struct ieee80211_radiotap_header { * @it_present: (first) present word */ __le32 it_present; + + /** + * @it_optional: all remaining presence bitmaps + */ + __le32 it_optional[]; } __packed; /* version is always 0 */ diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 71bb4cc4d05d..653e7d0f65cb 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -82,9 +82,6 @@ struct ip6_sf_socklist { struct in6_addr sl_addr[]; }; -#define IP6_SFLSIZE(count) (sizeof(struct ip6_sf_socklist) + \ - (count) * sizeof(struct in6_addr)) - #define IP6_SFBLOCK 10 /* allocate this many at once */ struct ipv6_mc_socklist { @@ -213,6 +210,8 @@ struct inet6_dev { unsigned long tstamp; /* ipv6InterfaceTable update timestamp */ struct rcu_head rcu; + + unsigned int ra_mtu; }; static inline void ipv6_eth_mc_map(const struct in6_addr *addr, char *buf) 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/inet_hashtables.h b/include/net/inet_hashtables.h index ca6a3ea9057e..f72ec113ae56 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -160,6 +160,12 @@ struct inet_hashinfo { ____cacheline_aligned_in_smp; }; +#define inet_lhash2_for_each_icsk_continue(__icsk) \ + hlist_for_each_entry_continue(__icsk, icsk_listen_portaddr_node) + +#define inet_lhash2_for_each_icsk(__icsk, list) \ + hlist_for_each_entry(__icsk, list, icsk_listen_portaddr_node) + #define inet_lhash2_for_each_icsk_rcu(__icsk, list) \ hlist_for_each_entry_rcu(__icsk, list, icsk_listen_portaddr_node) diff --git a/include/net/ioam6.h b/include/net/ioam6.h new file mode 100644 index 000000000000..3c2993bc48c8 --- /dev/null +++ b/include/net/ioam6.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * IPv6 IOAM implementation + * + * Author: + * Justin Iurman <justin.iurman@uliege.be> + */ + +#ifndef _NET_IOAM6_H +#define _NET_IOAM6_H + +#include <linux/net.h> +#include <linux/ipv6.h> +#include <linux/ioam6.h> +#include <linux/rhashtable-types.h> + +struct ioam6_namespace { + struct rhash_head head; + struct rcu_head rcu; + + struct ioam6_schema __rcu *schema; + + __be16 id; + __be32 data; + __be64 data_wide; +}; + +struct ioam6_schema { + struct rhash_head head; + struct rcu_head rcu; + + struct ioam6_namespace __rcu *ns; + + u32 id; + int len; + __be32 hdr; + + u8 data[0]; +}; + +struct ioam6_pernet_data { + struct mutex lock; + struct rhashtable namespaces; + struct rhashtable schemas; +}; + +static inline struct ioam6_pernet_data *ioam6_pernet(struct net *net) +{ +#if IS_ENABLED(CONFIG_IPV6) + return net->ipv6.ioam6_data; +#else + return NULL; +#endif +} + +struct ioam6_namespace *ioam6_namespace(struct net *net, __be16 id); +void ioam6_fill_trace_data(struct sk_buff *skb, + struct ioam6_namespace *ns, + struct ioam6_trace_hdr *trace); + +int ioam6_init(void); +void ioam6_exit(void); + +int ioam6_iptunnel_init(void); +void ioam6_iptunnel_exit(void); + +#endif /* _NET_IOAM6_H */ diff --git a/include/net/ip.h b/include/net/ip.h index e20874059f82..9192444f2964 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 */ @@ -435,32 +436,49 @@ static inline bool ip_sk_ignore_df(const struct sock *sk) static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { + const struct rtable *rt = container_of(dst, struct rtable, dst); struct net *net = dev_net(dst->dev); unsigned int mtu; if (net->ipv4.sysctl_ip_fwd_use_pmtu || ip_mtu_locked(dst) || - !forwarding) - return dst_mtu(dst); + !forwarding) { + mtu = rt->rt_pmtu; + if (mtu && time_before(jiffies, rt->dst.expires)) + goto out; + } /* 'forwarding = true' case should always honour route mtu */ mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; + + mtu = READ_ONCE(dst->dev->mtu); + + if (unlikely(ip_mtu_locked(dst))) { + if (rt->rt_uses_gateway && mtu > 576) + mtu = 576; + } - return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); +out: + mtu = min_t(unsigned int, 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_fib.h b/include/net/ip6_fib.h index 15b7fbe6b15c..c412dde4d67d 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -267,7 +267,7 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i) return false; } -/* Function to safely get fn->sernum for passed in rt +/* Function to safely get fn->fn_sernum for passed in rt * and store result in passed in cookie. * Return true if we can get cookie safely * Return false if not @@ -282,7 +282,7 @@ static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, if (fn) { *cookie = fn->fn_sernum; - /* pairs with smp_wmb() in fib6_update_sernum_upto_root() */ + /* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */ smp_rmb(); status = true; } diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f51a118bfce8..5efd0b71dc67 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -263,13 +263,20 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst, int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); -static inline int ip6_skb_dst_mtu(struct sk_buff *skb) +static inline unsigned int ip6_skb_dst_mtu(struct sk_buff *skb) { + unsigned 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) @@ -309,15 +316,16 @@ static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info * !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws); } -static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) +static inline unsigned int ip6_dst_mtu_maybe_forward(const struct dst_entry *dst, + bool forwarding) { struct inet6_dev *idev; unsigned int mtu; - if (dst_metric_locked(dst, RTAX_MTU)) { + if (!forwarding || 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 +335,8 @@ 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..ab5348e57db1 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -133,7 +133,7 @@ struct fib_info { struct hlist_node fib_lhash; struct list_head nh_list; struct net *fib_net; - int fib_treeref; + refcount_t fib_treeref; refcount_t fib_clntref; unsigned int fib_flags; unsigned char fib_dead; @@ -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); @@ -554,5 +597,5 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, u8 rt_family, unsigned char *flags, bool skip_oif); int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, - int nh_weight, u8 rt_family); + int nh_weight, u8 rt_family, u32 nh_tclassid); #endif /* _NET_FIB_H */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 548b65bd3973..bc3b13ec93c9 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -270,7 +270,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const u8 proto, int tunnel_hlen); int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); -int ip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); +int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); 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/ipx.h b/include/net/ipx.h deleted file mode 100644 index 9d1342807b59..000000000000 --- a/include/net/ipx.h +++ /dev/null @@ -1,171 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_INET_IPX_H_ -#define _NET_INET_IPX_H_ -/* - * The following information is in its entirety obtained from: - * - * Novell 'IPX Router Specification' Version 1.10 - * Part No. 107-000029-001 - * - * Which is available from ftp.novell.com - */ - -#include <linux/netdevice.h> -#include <net/datalink.h> -#include <linux/ipx.h> -#include <linux/list.h> -#include <linux/slab.h> -#include <linux/refcount.h> - -struct ipx_address { - __be32 net; - __u8 node[IPX_NODE_LEN]; - __be16 sock; -}; - -#define ipx_broadcast_node "\377\377\377\377\377\377" -#define ipx_this_node "\0\0\0\0\0\0" - -#define IPX_MAX_PPROP_HOPS 8 - -struct ipxhdr { - __be16 ipx_checksum __packed; -#define IPX_NO_CHECKSUM cpu_to_be16(0xFFFF) - __be16 ipx_pktsize __packed; - __u8 ipx_tctrl; - __u8 ipx_type; -#define IPX_TYPE_UNKNOWN 0x00 -#define IPX_TYPE_RIP 0x01 /* may also be 0 */ -#define IPX_TYPE_SAP 0x04 /* may also be 0 */ -#define IPX_TYPE_SPX 0x05 /* SPX protocol */ -#define IPX_TYPE_NCP 0x11 /* $lots for docs on this (SPIT) */ -#define IPX_TYPE_PPROP 0x14 /* complicated flood fill brdcast */ - struct ipx_address ipx_dest __packed; - struct ipx_address ipx_source __packed; -}; - -/* From af_ipx.c */ -extern int sysctl_ipx_pprop_broadcasting; - -struct ipx_interface { - /* IPX address */ - __be32 if_netnum; - unsigned char if_node[IPX_NODE_LEN]; - refcount_t refcnt; - - /* physical device info */ - struct net_device *if_dev; - struct datalink_proto *if_dlink; - __be16 if_dlink_type; - - /* socket support */ - unsigned short if_sknum; - struct hlist_head if_sklist; - spinlock_t if_sklist_lock; - - /* administrative overhead */ - int if_ipx_offset; - unsigned char if_internal; - unsigned char if_primary; - - struct list_head node; /* node in ipx_interfaces list */ -}; - -struct ipx_route { - __be32 ir_net; - struct ipx_interface *ir_intrfc; - unsigned char ir_routed; - unsigned char ir_router_node[IPX_NODE_LEN]; - struct list_head node; /* node in ipx_routes list */ - refcount_t refcnt; -}; - -struct ipx_cb { - u8 ipx_tctrl; - __be32 ipx_dest_net; - __be32 ipx_source_net; - struct { - __be32 netnum; - int index; - } last_hop; -}; - -#include <net/sock.h> - -struct ipx_sock { - /* struct sock has to be the first member of ipx_sock */ - struct sock sk; - struct ipx_address dest_addr; - struct ipx_interface *intrfc; - __be16 port; -#ifdef CONFIG_IPX_INTERN - unsigned char node[IPX_NODE_LEN]; -#endif - unsigned short type; - /* - * To handle special ncp connection-handling sockets for mars_nwe, - * the connection number must be stored in the socket. - */ - unsigned short ipx_ncp_conn; -}; - -static inline struct ipx_sock *ipx_sk(struct sock *sk) -{ - return (struct ipx_sock *)sk; -} - -#define IPX_SKB_CB(__skb) ((struct ipx_cb *)&((__skb)->cb[0])) - -#define IPX_MIN_EPHEMERAL_SOCKET 0x4000 -#define IPX_MAX_EPHEMERAL_SOCKET 0x7fff - -extern struct list_head ipx_routes; -extern rwlock_t ipx_routes_lock; - -extern struct list_head ipx_interfaces; -struct ipx_interface *ipx_interfaces_head(void); -extern spinlock_t ipx_interfaces_lock; - -extern struct ipx_interface *ipx_primary_net; - -int ipx_proc_init(void); -void ipx_proc_exit(void); - -const char *ipx_frame_name(__be16); -const char *ipx_device_name(struct ipx_interface *intrfc); - -static __inline__ void ipxitf_hold(struct ipx_interface *intrfc) -{ - refcount_inc(&intrfc->refcnt); -} - -void ipxitf_down(struct ipx_interface *intrfc); -struct ipx_interface *ipxitf_find_using_net(__be32 net); -int ipxitf_send(struct ipx_interface *intrfc, struct sk_buff *skb, char *node); -__be16 ipx_cksum(struct ipxhdr *packet, int length); -int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc, - unsigned char *node); -void ipxrtr_del_routes(struct ipx_interface *intrfc); -int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx, - struct msghdr *msg, size_t len, int noblock); -int ipxrtr_route_skb(struct sk_buff *skb); -struct ipx_route *ipxrtr_lookup(__be32 net); -int ipxrtr_ioctl(unsigned int cmd, void __user *arg); - -static __inline__ void ipxitf_put(struct ipx_interface *intrfc) -{ - if (refcount_dec_and_test(&intrfc->refcnt)) - ipxitf_down(intrfc); -} - -static __inline__ void ipxrtr_hold(struct ipx_route *rt) -{ - refcount_inc(&rt->refcnt); -} - -static __inline__ void ipxrtr_put(struct ipx_route *rt) -{ - if (refcount_dec_and_test(&rt->refcnt)) - kfree(rt); -} -#endif /* _NET_INET_IPX_H_ */ diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index c0f0a13ed818..49aa79c7b278 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -15,9 +15,11 @@ #include <linux/if_ether.h> /* Lengths of frame formats */ -#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ -#define LLC_PDU_LEN_S 4 -#define LLC_PDU_LEN_U 3 /* header and 1 control byte */ +#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ +#define LLC_PDU_LEN_S 4 +#define LLC_PDU_LEN_U 3 /* header and 1 control byte */ +/* header and 1 control byte and XID info */ +#define LLC_PDU_LEN_U_XID (LLC_PDU_LEN_U + sizeof(struct llc_xid_info)) /* Known SAP addresses */ #define LLC_GLOBAL_SAP 0xFF #define LLC_NULL_SAP 0x00 /* not network-layer visible */ @@ -50,9 +52,10 @@ #define LLC_PDU_TYPE_U_MASK 0x03 /* 8-bit control field */ #define LLC_PDU_TYPE_MASK 0x03 -#define LLC_PDU_TYPE_I 0 /* first bit */ -#define LLC_PDU_TYPE_S 1 /* first two bits */ -#define LLC_PDU_TYPE_U 3 /* first two bits */ +#define LLC_PDU_TYPE_I 0 /* first bit */ +#define LLC_PDU_TYPE_S 1 /* first two bits */ +#define LLC_PDU_TYPE_U 3 /* first two bits */ +#define LLC_PDU_TYPE_U_XID 4 /* private type for detecting XID commands */ #define LLC_PDU_TYPE_IS_I(pdu) \ ((!(pdu->ctrl_1 & LLC_PDU_TYPE_I_MASK)) ? 1 : 0) @@ -230,9 +233,18 @@ static inline struct llc_pdu_un *llc_pdu_un_hdr(struct sk_buff *skb) static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, u8 ssap, u8 dsap, u8 cr) { - const int hlen = type == LLC_PDU_TYPE_U ? 3 : 4; + int hlen = 4; /* default value for I and S types */ struct llc_pdu_un *pdu; + switch (type) { + case LLC_PDU_TYPE_U: + hlen = 3; + break; + case LLC_PDU_TYPE_U_XID: + hlen = 6; + break; + } + skb_push(skb, hlen); skb_reset_network_header(skb); pdu = llc_pdu_un_hdr(skb); @@ -374,7 +386,10 @@ static inline void llc_pdu_init_as_xid_cmd(struct sk_buff *skb, xid_info->fmt_id = LLC_XID_FMT_ID; /* 0x81 */ xid_info->type = svcs_supported; xid_info->rw = rx_window << 1; /* size of receive window */ - skb_put(skb, sizeof(struct llc_xid_info)); + + /* no need to push/put since llc_pdu_header_init() has already + * pushed 3 + 3 bytes + */ } /** diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 05cfd6ff6528..6f15e6fa154e 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -51,6 +51,9 @@ struct lwtunnel_encap_ops { }; #ifdef CONFIG_LWTUNNEL + +DECLARE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled); + void lwtstate_free(struct lwtunnel_state *lws); static inline struct lwtunnel_state * diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e89530d0d9c6..618d1f427cb2 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; @@ -1709,6 +1711,10 @@ enum ieee80211_offload_flags { * protected by fq->lock. * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see * &enum ieee80211_offload_flags. + * @color_change_active: marks whether a color change is ongoing. Internally it is + * write-protected by sdata_lock and local->mtx so holding either is fine + * for read access. + * @color_change_color: the bss color that will be used after the change. */ struct ieee80211_vif { enum nl80211_iftype type; @@ -1737,6 +1743,9 @@ struct ieee80211_vif { bool txqs_stopped[IEEE80211_NUM_ACS]; + bool color_change_active; + u8 color_change_color; + /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; @@ -2809,13 +2818,13 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag * when they are able to replace in-use PTK keys according to the following * requirements: - * 1) They do not hand over frames decrypted with the old key to - mac80211 once the call to set_key() with command %DISABLE_KEY has been - completed when also setting @IEEE80211_KEY_FLAG_GENERATE_IV for any key, + * 1) They do not hand over frames decrypted with the old key to mac80211 + once the call to set_key() with command %DISABLE_KEY has been completed, 2) either drop or continue to use the old key for any outgoing frames queued at the time of the key deletion (including re-transmits), 3) never send out a frame queued prior to the set_key() %SET_KEY command - encrypted with the new key and + encrypted with the new key when also needing + @IEEE80211_KEY_FLAG_GENERATE_IV and 4) never send out a frame unencrypted when it should be encrypted. Mac80211 will not queue any new frames for a deleted key to the driver. */ @@ -3345,6 +3354,21 @@ 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 +3780,13 @@ 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 @@ -3898,6 +3926,13 @@ enum ieee80211_reconfig_type { * @set_sar_specs: Update the SAR (TX power) settings. * @sta_set_decap_offload: Called to notify the driver when a station is allowed * to use rx decapsulation offload + * @add_twt_setup: Update hw with TWT agreement parameters received from the peer. + * This callback allows the hw to check if requested parameters + * are supported and if there is enough room for a new agreement. + * The hw is expected to set agreement result in the req_type field of + * twt structure. + * @twt_teardown_request: Update the hw with TWT teardown request received + * from the peer. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4109,7 +4144,10 @@ 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); @@ -4218,6 +4256,11 @@ struct ieee80211_ops { void (*sta_set_decap_offload)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool enabled); + void (*add_twt_setup)(struct ieee80211_hw *hw, + struct ieee80211_sta *sta, + struct ieee80211_twt_setup *twt); + void (*twt_teardown_request)(struct ieee80211_hw *hw, + struct ieee80211_sta *sta, u8 flowid); }; /** @@ -4984,6 +5027,16 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif); bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif); /** + * ieee80211_color_change_finish - notify mac80211 about color change + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * After a color change announcement was scheduled and the counter in this + * announcement hits 1, this function must be called by the driver to + * notify mac80211 that the color can be changed + */ +void ieee80211_color_change_finish(struct ieee80211_vif *vif); + +/** * ieee80211_proberesp_get - retrieve a Probe Response template * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. @@ -6184,6 +6237,11 @@ 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 +6634,6 @@ 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 +6646,7 @@ 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 +6658,8 @@ 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 +6799,34 @@ 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); + +/** + * ieeee80211_obss_color_collision_notify - notify userland about a BSS color + * collision. + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @color_bitmap: a 64 bit bitmap representing the colors that the local BSS is + * aware of. + */ +void +ieeee80211_obss_color_collision_notify(struct ieee80211_vif *vif, + u64 color_bitmap); + +/** + * 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/mctp.h b/include/net/mctp.h new file mode 100644 index 000000000000..ffd2c23bd76d --- /dev/null +++ b/include/net/mctp.h @@ -0,0 +1,232 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Management Component Transport Protocol (MCTP) + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#ifndef __NET_MCTP_H +#define __NET_MCTP_H + +#include <linux/bits.h> +#include <linux/mctp.h> +#include <net/net_namespace.h> +#include <net/sock.h> + +/* MCTP packet definitions */ +struct mctp_hdr { + u8 ver; + u8 dest; + u8 src; + u8 flags_seq_tag; +}; + +#define MCTP_VER_MIN 1 +#define MCTP_VER_MAX 1 + +/* Definitions for flags_seq_tag field */ +#define MCTP_HDR_FLAG_SOM BIT(7) +#define MCTP_HDR_FLAG_EOM BIT(6) +#define MCTP_HDR_FLAG_TO BIT(3) +#define MCTP_HDR_FLAGS GENMASK(5, 3) +#define MCTP_HDR_SEQ_SHIFT 4 +#define MCTP_HDR_SEQ_MASK GENMASK(1, 0) +#define MCTP_HDR_TAG_SHIFT 0 +#define MCTP_HDR_TAG_MASK GENMASK(2, 0) + +#define MCTP_HEADER_MAXLEN 4 + +#define MCTP_INITIAL_DEFAULT_NET 1 + +static inline bool mctp_address_ok(mctp_eid_t eid) +{ + return eid >= 8 && eid < 255; +} + +static inline struct mctp_hdr *mctp_hdr(struct sk_buff *skb) +{ + return (struct mctp_hdr *)skb_network_header(skb); +} + +/* socket implementation */ +struct mctp_sock { + struct sock sk; + + /* bind() params */ + unsigned int bind_net; + mctp_eid_t bind_addr; + __u8 bind_type; + + /* list of mctp_sk_key, for incoming tag lookup. updates protected + * by sk->net->keys_lock + */ + struct hlist_head keys; +}; + +/* Key for matching incoming packets to sockets or reassembly contexts. + * Packets are matched on (src,dest,tag). + * + * Lifetime requirements: + * + * - keys are free()ed via RCU + * + * - a mctp_sk_key contains a reference to a struct sock; this is valid + * for the life of the key. On sock destruction (through unhash), the key is + * removed from lists (see below), and will not be observable after a RCU + * grace period. + * + * any RX occurring within that grace period may still queue to the socket, + * but will hit the SOCK_DEAD case before the socket is freed. + * + * - these mctp_sk_keys appear on two lists: + * 1) the struct mctp_sock->keys list + * 2) the struct netns_mctp->keys list + * + * updates to either list are performed under the netns_mctp->keys + * lock. + * + * - a key may have a sk_buff attached as part of an in-progress message + * reassembly (->reasm_head). The reassembly context is protected by + * reasm_lock, which may be acquired with the keys lock (above) held, if + * necessary. Consequently, keys lock *cannot* be acquired with the + * reasm_lock held. + * + * - there are two destruction paths for a mctp_sk_key: + * + * - through socket unhash (see mctp_sk_unhash). This performs the list + * removal under keys_lock. + * + * - where a key is established to receive a reply message: after receiving + * the (complete) reply, or during reassembly errors. Here, we clean up + * the reassembly context (marking reasm_dead, to prevent another from + * starting), and remove the socket from the netns & socket lists. + */ +struct mctp_sk_key { + mctp_eid_t peer_addr; + mctp_eid_t local_addr; + __u8 tag; /* incoming tag match; invert TO for local */ + + /* we hold a ref to sk when set */ + struct sock *sk; + + /* routing lookup list */ + struct hlist_node hlist; + + /* per-socket list */ + struct hlist_node sklist; + + /* incoming fragment reassembly context */ + spinlock_t reasm_lock; + struct sk_buff *reasm_head; + struct sk_buff **reasm_tailp; + bool reasm_dead; + u8 last_seq; + + struct rcu_head rcu; +}; + +struct mctp_skb_cb { + unsigned int magic; + unsigned int net; + mctp_eid_t src; +}; + +/* skb control-block accessors with a little extra debugging for initial + * development. + * + * TODO: remove checks & mctp_skb_cb->magic; replace callers of __mctp_cb + * with mctp_cb(). + * + * __mctp_cb() is only for the initial ingress code; we should see ->magic set + * at all times after this. + */ +static inline struct mctp_skb_cb *__mctp_cb(struct sk_buff *skb) +{ + struct mctp_skb_cb *cb = (void *)skb->cb; + + cb->magic = 0x4d435450; + return cb; +} + +static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) +{ + struct mctp_skb_cb *cb = (void *)skb->cb; + + WARN_ON(cb->magic != 0x4d435450); + return (void *)(skb->cb); +} + +/* Route definition. + * + * These are held in the pernet->mctp.routes list, with RCU protection for + * removed routes. We hold a reference to the netdev; routes need to be + * dropped on NETDEV_UNREGISTER events. + * + * Updates to the route table are performed under rtnl; all reads under RCU, + * so routes cannot be referenced over a RCU grace period. Specifically: A + * caller cannot block between mctp_route_lookup and passing the route to + * mctp_do_route. + */ +struct mctp_route { + mctp_eid_t min, max; + + struct mctp_dev *dev; + unsigned int mtu; + unsigned char type; + int (*output)(struct mctp_route *route, + struct sk_buff *skb); + + struct list_head list; + refcount_t refs; + struct rcu_head rcu; +}; + +/* route interfaces */ +struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, + mctp_eid_t daddr); + +int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb); + +int mctp_local_output(struct sock *sk, struct mctp_route *rt, + struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); + +/* routing <--> device interface */ +unsigned int mctp_default_net(struct net *net); +int mctp_default_net_set(struct net *net, unsigned int index); +int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr); +int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr); +void mctp_route_remove_dev(struct mctp_dev *mdev); + +/* neighbour definitions */ +enum mctp_neigh_source { + MCTP_NEIGH_STATIC, + MCTP_NEIGH_DISCOVER, +}; + +struct mctp_neigh { + struct mctp_dev *dev; + mctp_eid_t eid; + enum mctp_neigh_source source; + + unsigned char ha[MAX_ADDR_LEN]; + + struct list_head list; + struct rcu_head rcu; +}; + +int mctp_neigh_init(void); +void mctp_neigh_exit(void); + +// ret_hwaddr may be NULL, otherwise must have space for MAX_ADDR_LEN +int mctp_neigh_lookup(struct mctp_dev *dev, mctp_eid_t eid, + void *ret_hwaddr); +void mctp_neigh_remove_dev(struct mctp_dev *mdev); + +int mctp_routes_init(void); +void mctp_routes_exit(void); + +void mctp_device_init(void); +void mctp_device_exit(void); + +#endif /* __NET_MCTP_H */ diff --git a/include/net/mctpdevice.h b/include/net/mctpdevice.h new file mode 100644 index 000000000000..71a11012fac7 --- /dev/null +++ b/include/net/mctpdevice.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Management Component Transport Protocol (MCTP) - device + * definitions. + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#ifndef __NET_MCTPDEVICE_H +#define __NET_MCTPDEVICE_H + +#include <linux/list.h> +#include <linux/types.h> +#include <linux/refcount.h> + +struct mctp_dev { + struct net_device *dev; + + unsigned int net; + + /* Only modified under RTNL. Reads have addrs_lock held */ + u8 *addrs; + size_t num_addrs; + spinlock_t addrs_lock; + + struct rcu_head rcu; +}; + +#define MCTP_INITIAL_DEFAULT_NET 1 + +struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev); +struct mctp_dev *__mctp_dev_get(const struct net_device *dev); + +#endif /* __NET_MCTPDEVICE_H */ diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 83f23774b908..3214848402ec 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 @@ -56,20 +58,37 @@ struct mptcp_addr_info { struct mptcp_out_options { #if IS_ENABLED(CONFIG_MPTCP) u16 suboptions; - u64 sndr_key; - u64 rcvr_key; - u64 ahmac; - struct mptcp_addr_info addr; struct mptcp_rm_list rm_list; u8 join_id; u8 backup; - u8 reset_reason:4; - u8 reset_transient:1; - u32 nonce; - u64 thmac; - u32 token; - u8 hmac[20]; - struct mptcp_ext ext_copy; + u8 reset_reason:4, + reset_transient:1, + csum_reqd:1, + allow_join_id0:1; + union { + struct { + u64 sndr_key; + u64 rcvr_key; + u64 data_seq; + u32 subflow_seq; + u16 data_len; + __sum16 csum; + }; + struct { + struct mptcp_addr_info addr; + u64 ahmac; + }; + struct { + struct mptcp_ext ext_copy; + u64 fail_seq; + }; + struct { + u32 nonce; + u32 token; + u64 thmac; + u8 hmac[20]; + }; + }; #endif }; @@ -101,7 +120,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts); -void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); +bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts); @@ -223,9 +242,10 @@ static inline bool mptcp_established_options(struct sock *sk, return false; } -static inline void mptcp_incoming_options(struct sock *sk, +static inline bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { + return true; } static inline void mptcp_skb_ext_move(struct sk_buff *to, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index bdc0459a595e..bb5fa5914032 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -23,7 +23,6 @@ #include <net/netns/ieee802154_6lowpan.h> #include <net/netns/sctp.h> #include <net/netns/netfilter.h> -#include <net/netns/x_tables.h> #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netns/conntrack.h> #endif @@ -32,7 +31,9 @@ #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 <net/netns/mctp.h> #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> @@ -131,7 +132,6 @@ struct net { #endif #ifdef CONFIG_NETFILTER struct netns_nf nf; - struct netns_xt xt; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct netns_ct ct; #endif @@ -166,10 +166,16 @@ struct net { #ifdef CONFIG_XDP_SOCKETS struct netns_xdp xdp; #endif +#if IS_ENABLED(CONFIG_MCTP) + struct netns_mctp mctp; +#endif #if IS_ENABLED(CONFIG_CRYPTO_USER) 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/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index 0fd8a4159662..ceadf8ba25a4 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -17,7 +17,6 @@ struct inet_frags_ctl; struct nft_ct_frag6_pernet { struct ctl_table_header *nf_frag_frags_hdr; struct fqdir *fqdir; - unsigned int users; }; #endif /* _NF_DEFRAG_IPV6_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_core.h b/include/net/netfilter/nf_conntrack_core.h index 09f2efea0b97..13807ea94cd2 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -30,7 +30,6 @@ void nf_conntrack_cleanup_net(struct net *net); void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list); void nf_conntrack_proto_pernet_init(struct net *net); -void nf_conntrack_proto_pernet_fini(struct net *net); int nf_conntrack_proto_init(void); void nf_conntrack_proto_fini(void); diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index d00ba6048e44..d932e22edcb4 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -72,14 +72,20 @@ struct nf_ct_event { int report; }; +struct nf_exp_event { + struct nf_conntrack_expect *exp; + u32 portid; + int report; +}; + struct nf_ct_event_notifier { - int (*fcn)(unsigned int events, struct nf_ct_event *item); + int (*ct_event)(unsigned int events, const struct nf_ct_event *item); + int (*exp_event)(unsigned int events, const struct nf_exp_event *item); }; -int nf_conntrack_register_notifier(struct net *net, - struct nf_ct_event_notifier *nb); -void nf_conntrack_unregister_notifier(struct net *net, - struct nf_ct_event_notifier *nb); +void nf_conntrack_register_notifier(struct net *net, + const struct nf_ct_event_notifier *nb); +void nf_conntrack_unregister_notifier(struct net *net); void nf_ct_deliver_cached_events(struct nf_conn *ct); int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, @@ -151,22 +157,6 @@ nf_conntrack_event(enum ip_conntrack_events event, struct nf_conn *ct) } #ifdef CONFIG_NF_CONNTRACK_EVENTS - -struct nf_exp_event { - struct nf_conntrack_expect *exp; - u32 portid; - int report; -}; - -struct nf_exp_event_notifier { - int (*fcn)(unsigned int events, struct nf_exp_event *item); -}; - -int nf_ct_expect_register_notifier(struct net *net, - struct nf_exp_event_notifier *nb); -void nf_ct_expect_unregister_notifier(struct net *net, - struct nf_exp_event_notifier *nb); - void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, struct nf_conntrack_expect *exp, u32 portid, int report); 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_hooks_lwtunnel.h b/include/net/netfilter/nf_hooks_lwtunnel.h new file mode 100644 index 000000000000..52e27920f829 --- /dev/null +++ b/include/net/netfilter/nf_hooks_lwtunnel.h @@ -0,0 +1,7 @@ +#include <linux/sysctl.h> +#include <linux/types.h> + +#ifdef CONFIG_SYSCTL +int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +#endif diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index e770bba00066..9eed51e920e8 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -33,8 +33,8 @@ struct nf_queue_handler { void (*nf_hook_drop)(struct net *net); }; -void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh); -void nf_unregister_queue_handler(struct net *net); +void nf_register_queue_handler(const struct nf_queue_handler *qh); +void nf_unregister_queue_handler(void); void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict); void nf_queue_entry_get_refs(struct nf_queue_entry *entry); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 0a5655e300b5..a16171c5fd9e 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; } /** @@ -1192,7 +1202,7 @@ struct nft_object *nft_obj_lookup(const struct net *net, void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, - int event, int family, int report, gfp_t gfp); + int event, u16 flags, int family, int report, gfp_t gfp); /** * struct nft_object_type - stateful object type 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/netlink.h b/include/net/netlink.h index 1ceec518ab49..7a2a9d3144ba 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -885,7 +885,7 @@ static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh, */ static inline int nlmsg_report(const struct nlmsghdr *nlh) { - return !!(nlh->nlmsg_flags & NLM_F_ECHO); + return nlh ? !!(nlh->nlmsg_flags & NLM_F_ECHO) : 0; } /** diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index ad0a95c2335e..0294f3d473af 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; + u8 tcp_ignore_invalid_rst; +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + unsigned int offload_timeout; +#endif }; enum udp_conntrack { @@ -37,6 +41,9 @@ enum udp_conntrack { struct nf_udp_net { unsigned int timeouts[UDP_CT_MAX]; +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + unsigned int offload_timeout; +#endif }; struct nf_icmp_net { @@ -106,7 +113,6 @@ struct netns_ct { struct ct_pcpu __percpu *pcpu_lists; struct ip_conntrack_stat __percpu *stat; struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; - struct nf_exp_event_notifier __rcu *nf_expect_event_cb; struct nf_ip_net nf_ct_proto; #if defined(CONFIG_NF_CONNTRACK_LABELS) unsigned int labels_used; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index f6af8d96d3c6..2f65701a43c9 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; @@ -173,7 +174,6 @@ struct netns_ipv4 { int sysctl_tcp_fastopen; const struct tcp_congestion_ops __rcu *tcp_congestion_control; struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; - spinlock_t tcp_fastopen_ctx_lock; unsigned int sysctl_tcp_fastopen_blackhole_timeout; atomic_t tfo_active_disable_times; unsigned long tfo_active_disable_stamp; @@ -210,6 +210,7 @@ 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..a4b550380316 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; @@ -50,6 +51,8 @@ struct netns_sysctl_ipv6 { int max_dst_opts_len; int max_hbh_opts_len; int seg6_flowlabel; + u32 ioam6_id; + u64 ioam6_id_wide; bool skip_notify_on_dev_down; u8 fib_notify_on_flag_change; }; @@ -109,6 +112,7 @@ struct netns_ipv6 { spinlock_t lock; u32 seq; } ip6addrlbl_table; + struct ioam6_pernet_data *ioam6_data; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) diff --git a/include/net/netns/mctp.h b/include/net/netns/mctp.h new file mode 100644 index 000000000000..acedef12a35e --- /dev/null +++ b/include/net/netns/mctp.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * MCTP per-net structures + */ + +#ifndef __NETNS_MCTP_H__ +#define __NETNS_MCTP_H__ + +#include <linux/types.h> + +struct netns_mctp { + /* Only updated under RTNL, entries freed via RCU */ + struct list_head routes; + + /* Bound sockets: list of sockets bound by type. + * This list is updated from non-atomic contexts (under bind_lock), + * and read (under rcu) in packet rx + */ + struct mutex bind_lock; + struct hlist_head binds; + + /* tag allocations. This list is read and updated from atomic contexts, + * but elements are free()ed after a RCU grace-period + */ + spinlock_t keys_lock; + struct hlist_head keys; + + /* MCTP network */ + unsigned int default_net; + + /* neighbour table */ + struct mutex neigh_lock; + struct list_head neighbours; +}; + +#endif /* __NETNS_MCTP_H__ */ diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 15e2b13fb0c0..b593f95e9991 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -12,7 +12,6 @@ struct netns_nf { #if defined CONFIG_PROC_FS struct proc_dir_entry *proc_netfilter; #endif - const struct nf_queue_handler __rcu *queue_handler; const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO]; #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; @@ -28,5 +27,11 @@ struct netns_nf { #if IS_ENABLED(CONFIG_DECNET) struct nf_hook_entries __rcu *hooks_decnet[NF_DN_NUMHOOKS]; #endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) + unsigned int defrag_ipv4_users; +#endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + unsigned int defrag_ipv6_users; +#endif }; #endif 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/x_tables.h b/include/net/netns/x_tables.h deleted file mode 100644 index d02316ec2906..000000000000 --- a/include/net/netns/x_tables.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NETNS_X_TABLES_H -#define __NETNS_X_TABLES_H - -#include <linux/list.h> -#include <linux/netfilter_defs.h> - -struct netns_xt { - bool notrack_deprecated_warning; - bool clusterip_deprecated_warning; -}; -#endif diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index e816b6a3ef2b..947733a639a6 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; @@ -64,6 +65,13 @@ struct netns_xfrm { u32 sysctl_aevent_rseqth; int sysctl_larval_drop; u32 sysctl_acq_expires; + + u8 policy_default; +#define XFRM_POL_DEFAULT_IN 1 +#define XFRM_POL_DEFAULT_OUT 2 +#define XFRM_POL_DEFAULT_FWD 4 +#define XFRM_POL_DEFAULT_MASK 7 + #ifdef CONFIG_SYSCTL struct ctl_table_header *sysctl_hdr; #endif @@ -74,6 +82,7 @@ struct netns_xfrm { #endif spinlock_t xfrm_state_lock; seqcount_spinlock_t xfrm_state_hash_generation; + seqcount_spinlock_t xfrm_policy_hash_generation; spinlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 10e1777877e6..28085b995ddc 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -325,7 +325,7 @@ int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh, struct fib_nh_common *nhc = &nhi->fib_nhc; int weight = nhg->nh_entries[i].weight; - if (fib_add_nexthop(skb, nhc, weight, rt_family) < 0) + if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0) return -EMSGSIZE; } diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h index 963db96bcbbb..bb3e8fdc0692 100644 --- a/include/net/nfc/digital.h +++ b/include/net/nfc/digital.h @@ -191,7 +191,7 @@ struct digital_poll_tech { struct nfc_digital_dev { struct nfc_dev *nfc_dev; - struct nfc_digital_ops *ops; + const struct nfc_digital_ops *ops; u32 protocols; @@ -236,7 +236,7 @@ struct nfc_digital_dev { void (*skb_add_crc)(struct sk_buff *skb); }; -struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops, +struct nfc_digital_dev *nfc_digital_allocate_device(const struct nfc_digital_ops *ops, __u32 supported_protocols, __u32 driver_capabilities, int tx_headroom, diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h index b35f37a57686..756c11084f65 100644 --- a/include/net/nfc/hci.h +++ b/include/net/nfc/hci.h @@ -118,7 +118,7 @@ struct nfc_hci_dev { struct sk_buff_head msg_rx_queue; - struct nfc_hci_ops *ops; + const struct nfc_hci_ops *ops; struct nfc_llc *llc; @@ -151,7 +151,7 @@ struct nfc_hci_dev { }; /* hci device allocation */ -struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops, +struct nfc_hci_dev *nfc_hci_allocate_device(const struct nfc_hci_ops *ops, struct nfc_hci_init_data *init_data, unsigned long quirks, u32 protocols, @@ -168,7 +168,7 @@ void nfc_hci_set_clientdata(struct nfc_hci_dev *hdev, void *clientdata); void *nfc_hci_get_clientdata(struct nfc_hci_dev *hdev); static inline int nfc_hci_set_vendor_cmds(struct nfc_hci_dev *hdev, - struct nfc_vendor_cmd *cmds, + const struct nfc_vendor_cmd *cmds, int n_cmds) { return nfc_set_vendor_cmds(hdev->ndev, cmds, n_cmds); diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 1df0f8074c9d..a964daedc17b 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -82,10 +82,10 @@ struct nci_ops { void (*hci_cmd_received)(struct nci_dev *ndev, u8 pipe, u8 cmd, struct sk_buff *skb); - struct nci_driver_ops *prop_ops; + const struct nci_driver_ops *prop_ops; size_t n_prop_ops; - struct nci_driver_ops *core_ops; + const struct nci_driver_ops *core_ops; size_t n_core_ops; }; @@ -194,7 +194,7 @@ struct nci_hci_dev { /* NCI Core structures */ struct nci_dev { struct nfc_dev *nfc_dev; - struct nci_ops *ops; + const struct nci_ops *ops; struct nci_hci_dev *hci_dev; int tx_headroom; @@ -267,7 +267,7 @@ struct nci_dev { }; /* ----- NCI Devices ----- */ -struct nci_dev *nci_allocate_device(struct nci_ops *ops, +struct nci_dev *nci_allocate_device(const struct nci_ops *ops, __u32 supported_protocols, int tx_headroom, int tx_tailroom); @@ -276,25 +276,27 @@ int nci_register_device(struct nci_dev *ndev); void nci_unregister_device(struct nci_dev *ndev); int nci_request(struct nci_dev *ndev, void (*req)(struct nci_dev *ndev, - unsigned long opt), - unsigned long opt, __u32 timeout); -int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, __u8 *payload); -int nci_core_cmd(struct nci_dev *ndev, __u16 opcode, size_t len, __u8 *payload); + const void *opt), + const void *opt, __u32 timeout); +int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, + const __u8 *payload); +int nci_core_cmd(struct nci_dev *ndev, __u16 opcode, size_t len, + const __u8 *payload); int nci_core_reset(struct nci_dev *ndev); int nci_core_init(struct nci_dev *ndev); int nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb); int nci_send_frame(struct nci_dev *ndev, struct sk_buff *skb); -int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val); +int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, const __u8 *val); int nci_nfcee_discover(struct nci_dev *ndev, u8 action); int nci_nfcee_mode_set(struct nci_dev *ndev, u8 nfcee_id, u8 nfcee_mode); int nci_core_conn_create(struct nci_dev *ndev, u8 destination_type, u8 number_destination_params, size_t params_len, - struct core_conn_create_dest_spec_params *params); + const struct core_conn_create_dest_spec_params *params); int nci_core_conn_close(struct nci_dev *ndev, u8 conn_id); -int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len, +int nci_nfcc_loopback(struct nci_dev *ndev, const void *data, size_t data_len, struct sk_buff **resp); struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev); @@ -343,7 +345,7 @@ static inline void *nci_get_drvdata(struct nci_dev *ndev) } static inline int nci_set_vendor_cmds(struct nci_dev *ndev, - struct nfc_vendor_cmd *cmds, + const struct nfc_vendor_cmd *cmds, int n_cmds) { return nfc_set_vendor_cmds(ndev->nfc_dev, cmds, n_cmds); @@ -360,7 +362,7 @@ int nci_core_rsp_packet(struct nci_dev *ndev, __u16 opcode, int nci_core_ntf_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb); void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb); -int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload); +int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, const void *payload); int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb); int nci_conn_max_data_pkt_payload_size(struct nci_dev *ndev, __u8 conn_id); void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, @@ -378,7 +380,7 @@ void nci_req_complete(struct nci_dev *ndev, int result); struct nci_conn_info *nci_get_conn_info_by_conn_id(struct nci_dev *ndev, int conn_id); int nci_get_conn_info_by_dest_type_params(struct nci_dev *ndev, u8 dest_type, - struct dest_spec_params *params); + const struct dest_spec_params *params); /* ----- NCI status code ----- */ int nci_to_errno(__u8 code); diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 2cd3a261bcbc..5dee575fbe86 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -188,17 +188,17 @@ struct nfc_dev { struct rfkill *rfkill; - struct nfc_vendor_cmd *vendor_cmds; + const struct nfc_vendor_cmd *vendor_cmds; int n_vendor_cmds; - struct nfc_ops *ops; + const struct nfc_ops *ops; struct genl_info *cur_cmd_info; }; #define to_nfc_dev(_dev) container_of(_dev, struct nfc_dev, dev) extern struct class nfc_class; -struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, +struct nfc_dev *nfc_allocate_device(const struct nfc_ops *ops, u32 supported_protocols, int tx_headroom, int tx_tailroom); @@ -245,7 +245,7 @@ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) * * @dev: The nfc device */ -static inline void *nfc_get_drvdata(struct nfc_dev *dev) +static inline void *nfc_get_drvdata(const struct nfc_dev *dev) { return dev_get_drvdata(&dev->dev); } @@ -255,7 +255,7 @@ static inline void *nfc_get_drvdata(struct nfc_dev *dev) * * @dev: The nfc device whose name to return */ -static inline const char *nfc_device_name(struct nfc_dev *dev) +static inline const char *nfc_device_name(const struct nfc_dev *dev) { return dev_name(&dev->dev); } @@ -266,7 +266,7 @@ struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk, struct sk_buff *nfc_alloc_recv_skb(unsigned int size, gfp_t gfp); int nfc_set_remote_general_bytes(struct nfc_dev *dev, - u8 *gt, u8 gt_len); + const u8 *gt, u8 gt_len); u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len); int nfc_fw_download_done(struct nfc_dev *dev, const char *firmware_name, @@ -280,7 +280,7 @@ int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, - u8 *gb, size_t gb_len); + const u8 *gb, size_t gb_len); int nfc_tm_deactivated(struct nfc_dev *dev); int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb); @@ -297,7 +297,7 @@ void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb, u8 payload_type, u8 direction); static inline int nfc_set_vendor_cmds(struct nfc_dev *dev, - struct nfc_vendor_cmd *cmds, + const struct nfc_vendor_cmd *cmds, int n_cmds) { if (dev->vendor_cmds || dev->n_vendor_cmds) diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b4b6de909c93..a4082406a003 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -45,7 +45,10 @@ * Please note DMA-sync-for-CPU is still * device driver responsibility */ -#define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV) +#define PP_FLAG_PAGE_FRAG BIT(2) /* for page frag feature */ +#define PP_FLAG_ALL (PP_FLAG_DMA_MAP |\ + PP_FLAG_DMA_SYNC_DEV |\ + PP_FLAG_PAGE_FRAG) /* * Fast allocation side cache array/stack @@ -88,6 +91,9 @@ struct page_pool { unsigned long defer_warn; u32 pages_state_hold_cnt; + unsigned int frag_offset; + struct page *frag_page; + long frag_users; /* * Data structure for allocation side @@ -137,6 +143,18 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) return page_pool_alloc_pages(pool, gfp); } +struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset, + unsigned int size, gfp_t gfp); + +static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, + unsigned int *offset, + unsigned int size) +{ + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + return page_pool_alloc_frag(pool, offset, size, gfp); +} + /* get the stored dma direction. A driver might decide to treat this locally and * avoid the extra cache line from page_pool to determine the direction */ @@ -146,6 +164,8 @@ 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 @@ -196,19 +216,48 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ + (sizeof(dma_addr_t) > sizeof(unsigned long)) + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - dma_addr_t ret = page->dma_addr[0]; - if (sizeof(dma_addr_t) > sizeof(unsigned long)) - ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16; + dma_addr_t ret = page->dma_addr; + + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; + return ret; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { - page->dma_addr[0] = addr; - if (sizeof(dma_addr_t) > sizeof(unsigned long)) - page->dma_addr[1] = upper_32_bits(addr); + page->dma_addr = addr; + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + page->dma_addr_upper = upper_32_bits(addr); +} + +static inline void page_pool_set_frag_count(struct page *page, long nr) +{ + atomic_long_set(&page->pp_frag_count, nr); +} + +static inline long page_pool_atomic_sub_frag_count_return(struct page *page, + long nr) +{ + long ret; + + /* As suggested by Alexander, atomic_long_read() may cover up the + * reference count errors, so avoid calling atomic_long_read() in + * the cases of freeing or draining the page_frags, where we would + * not expect it to match or that are slowpath anyway. + */ + if (__builtin_constant_p(nr) && + atomic_long_read(&page->pp_frag_count) == nr) + return 0; + + ret = atomic_long_sub_return(nr, &page->pp_frag_count); + WARN_ON(ret < 0); + return ret; } static inline bool is_page_pool_compiled_in(void) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index ec7823921bd2..83a6d0792180 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -76,12 +76,10 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return block->q; } -int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode); -int tcf_classify_ingress(struct sk_buff *skb, - const struct tcf_block *ingress_block, - const struct tcf_proto *tp, struct tcf_result *res, - bool compat_mode); +int tcf_classify(struct sk_buff *skb, + const struct tcf_block *block, + const struct tcf_proto *tp, struct tcf_result *res, + bool compat_mode); #else static inline bool tcf_block_shared(struct tcf_block *block) @@ -138,20 +136,14 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb, { } -static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, +static inline int tcf_classify(struct sk_buff *skb, + const struct tcf_block *block, + const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { return TC_ACT_UNSPEC; } -static inline int tcf_classify_ingress(struct sk_buff *skb, - const struct tcf_block *ingress_block, - const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode) -{ - return TC_ACT_UNSPEC; -} - #endif static inline unsigned long @@ -327,7 +319,7 @@ 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, bool rtnl_held, + struct tcf_exts *exts, u32 flags, struct netlink_ext_ack *extack); void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); @@ -337,6 +329,9 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); /** * struct tcf_pkt_info - packet information + * + * @ptr: start of the pkt data + * @nexthdr: offset of the next header */ struct tcf_pkt_info { unsigned char * ptr; @@ -355,6 +350,7 @@ struct tcf_ematch_ops; * @ops: the operations lookup table of the corresponding ematch module * @datalen: length of the ematch specific configuration data * @data: ematch specific data + * @net: the network namespace */ struct tcf_ematch { struct tcf_ematch_ops * ops; @@ -820,10 +816,9 @@ enum tc_htb_command { struct tc_htb_qopt_offload { struct netlink_ext_ack *extack; enum tc_htb_command command; - u16 classid; u32 parent_classid; + u16 classid; u16 qid; - u16 moved_qid; u64 rate; u64 ceil; }; diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 6d7b12cba015..bf79f3a890af 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -11,6 +11,7 @@ #include <uapi/linux/pkt_sched.h> #define DEFAULT_TX_QUEUE_LEN 1000 +#define STAB_SIZE_LOG_MAX 30 struct qdisc_walker { int stop; 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/psample.h b/include/net/psample.h index e328c5127757..0509d2d6be67 100644 --- a/include/net/psample.h +++ b/include/net/psample.h @@ -31,6 +31,8 @@ struct psample_group *psample_group_get(struct net *net, u32 group_num); void psample_group_take(struct psample_group *group); void psample_group_put(struct psample_group *group); +struct sk_buff; + #if IS_ENABLED(CONFIG_PSAMPLE) void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 479f60ef54c0..9f48733bfd21 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; @@ -145,7 +153,8 @@ struct rtnl_af_ops { u32 ext_filter_mask); int (*validate_link_af)(const struct net_device *dev, - const struct nlattr *attr); + const struct nlattr *attr, + struct netlink_ext_ack *extack); int (*set_link_af)(struct net_device *dev, const struct nlattr *attr, struct netlink_ext_ack *extack); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 1e625519ae96..c0069ac00e62 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); } } @@ -340,7 +357,7 @@ struct tcf_proto_ops { int (*change)(struct net *net, struct sk_buff *, struct tcf_proto*, unsigned long, u32 handle, struct nlattr **, - void **, bool, bool, + void **, u32, struct netlink_ext_ack *); int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, 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..5859e0a16a58 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 */ @@ -342,8 +360,7 @@ enum { #define SCTP_SCOPE_POLICY_MAX SCTP_SCOPE_POLICY_LINK /* Based on IPv4 scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>, - * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 198.18.0.0/24, - * 192.88.99.0/24. + * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 192.88.99.0/24. * Also, RFC 8.4, non-unicast addresses are not considered valid SCTP * addresses. */ @@ -351,7 +368,6 @@ enum { ((htonl(INADDR_BROADCAST) == a) || \ ipv4_is_multicast(a) || \ ipv4_is_zeronet(a) || \ - ipv4_is_test_198(a) || \ ipv4_is_anycast_6to4(a)) /* Flags used for the bind address copy functions. */ @@ -424,4 +440,6 @@ 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..f37c7a558d6d 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); @@ -380,11 +384,11 @@ sctp_vtag_verify(const struct sctp_chunk *chunk, * Verification Tag value does not match the receiver's own * tag value, the receiver shall silently discard the packet... */ - if (ntohl(chunk->sctp_hdr->vtag) == asoc->c.my_vtag) - return 1; + if (ntohl(chunk->sctp_hdr->vtag) != asoc->c.my_vtag) + return 0; chunk->transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; - return 0; + return 1; } /* Check VTAG of the packet matches the sender's own tag and the T bit is diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 1aa585216f34..651bba654d77 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 +983,16 @@ struct sctp_transport { char cacc_saw_newack; } cacc; + struct { + __u32 last_rtx_chunks; + __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 +1010,7 @@ 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 +1025,8 @@ 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); +bool sctp_transport_pl_send(struct sctp_transport *t); +bool sctp_transport_pl_recv(struct sctp_transport *t); /* This is the structure we use to queue packets as they come into @@ -1795,6 +1815,7 @@ 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..463f390d90b3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -68,6 +68,7 @@ #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/l3mdev.h> +#include <uapi/linux/socket.h> /* * This structure really needs to be cleaned up. @@ -306,6 +307,7 @@ struct bpf_local_storage; * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family + * @sk_peer_lock: lock protecting @sk_peer_pid and @sk_peer_cred * @sk_peer_pid: &struct pid for this socket's peer * @sk_peer_cred: %SO_PEERCRED setting * @sk_rcvlowat: %SO_RCVLOWAT setting @@ -316,7 +318,9 @@ struct bpf_local_storage; * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only - * @sk_tsflags: SO_TIMESTAMPING socket options + * @sk_tsflags: SO_TIMESTAMPING flags + * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock + * for timestamping * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals @@ -485,14 +489,17 @@ struct sock { u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; #endif + spinlock_t sk_peer_lock; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; + long sk_rcvtimeo; ktime_t sk_stamp; #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif u16 sk_tsflags; + int sk_bind_phc; u8 sk_shutdown; u32 sk_tskey; atomic_t sk_zckey; @@ -1201,7 +1208,7 @@ struct proto { #endif bool (*stream_memory_free)(const struct sock *sk, int wake); - bool (*stream_memory_read)(const struct sock *sk); + bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); @@ -1435,8 +1442,6 @@ static inline int __sk_prot_rehash(struct sock *sk) #define RCV_SHUTDOWN 1 #define SEND_SHUTDOWN 2 -#define SOCK_SNDBUF_LOCK 1 -#define SOCK_RCVBUF_LOCK 2 #define SOCK_BINDADDR_LOCK 4 #define SOCK_BINDPORT_LOCK 8 @@ -1621,7 +1626,36 @@ void release_sock(struct sock *sk); SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) -bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); + +/** + * lock_sock_fast - fast version of lock_sock + * @sk: socket + * + * This version should be used for very small section, where process wont block + * return false if fast path is taken: + * + * sk_lock.slock locked, owned = 0, BH disabled + * + * return true if slow path is taken: + * + * sk_lock.slock unlocked, owned = 1, BH enabled + */ +static inline bool lock_sock_fast(struct sock *sk) +{ + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} + +/* fast socket lock variant for caller already holding a [different] socket lock */ +static inline bool lock_sock_fast_nested(struct sock *sk) +{ + mutex_acquire(&sk->sk_lock.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} /** * unlock_sock_fast - complement of lock_sock_fast @@ -1638,6 +1672,7 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow) release_sock(sk); __release(&sk->sk_lock.slock); } else { + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); spin_unlock_bh(&sk->sk_lock.slock); } } @@ -2246,6 +2281,15 @@ static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struc return false; } +static inline void skb_prepare_for_gro(struct sk_buff *skb) +{ + if (skb->destructor != sock_wfree) { + skb_orphan(skb); + return; + } + skb->slow_gro = 1; +} + void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); @@ -2281,6 +2325,8 @@ 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; @@ -2387,6 +2433,11 @@ static inline gfp_t gfp_any(void) return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } +static inline gfp_t gfp_memcg_charge(void) +{ + return in_softirq() ? GFP_NOWAIT : GFP_KERNEL; +} + static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_rcvtimeo; @@ -2699,6 +2750,7 @@ extern int sysctl_optmem_max; extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; +#define SKB_FRAG_PAGE_ORDER get_order(32768) DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto) @@ -2752,6 +2804,10 @@ 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, + struct so_timestamping timestamping); + void sock_enable_timestamps(struct sock *sk); void sock_no_linger(struct sock *sk); void sock_set_keepalive(struct sock *sk); @@ -2764,4 +2820,10 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); +static inline bool sk_is_readable(struct sock *sk) +{ + if (sk->sk_prot->sock_is_readable) + return sk->sk_prot->sock_is_readable(sk); + return false; +} #endif /* _SOCK_H */ 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..60d806b6a5ae 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -180,6 +180,14 @@ struct switchdev_obj_in_state_mrp { typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); +struct switchdev_brport { + struct net_device *dev; + const void *ctx; + struct notifier_block *atomic_nb; + struct notifier_block *blocking_nb; + bool tx_fwd_offload; +}; + enum switchdev_notifier_type { SWITCHDEV_FDB_ADD_TO_BRIDGE = 1, SWITCHDEV_FDB_DEL_TO_BRIDGE, @@ -197,11 +205,15 @@ enum switchdev_notifier_type { SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE, SWITCHDEV_VXLAN_FDB_OFFLOADED, + + SWITCHDEV_BRPORT_OFFLOADED, + SWITCHDEV_BRPORT_UNOFFLOADED, }; struct switchdev_notifier_info { struct net_device *dev; struct netlink_ext_ack *extack; + const void *ctx; }; struct switchdev_notifier_fdb_info { @@ -225,6 +237,11 @@ struct switchdev_notifier_port_attr_info { bool handled; }; +struct switchdev_notifier_brport_info { + struct switchdev_notifier_info info; /* must be first */ + const struct switchdev_brport brport; +}; + static inline struct net_device * switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) { @@ -237,8 +254,25 @@ switchdev_notifier_info_to_extack(const struct switchdev_notifier_info *info) return info->extack; } +static inline bool +switchdev_fdb_is_dynamically_learned(const struct switchdev_notifier_fdb_info *fdb_info) +{ + return !fdb_info->added_by_user && !fdb_info->is_local; +} + #ifdef CONFIG_NET_SWITCHDEV +int switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack); +void switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb); + void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, @@ -265,26 +299,69 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); +int switchdev_handle_fdb_add_to_device(struct net_device *dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)); + +int switchdev_handle_fdb_del_to_device(struct net_device *dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)); + 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 +static inline int +switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline void +switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) +{ +} + static inline void switchdev_deferred_process(void) { } @@ -349,10 +426,42 @@ call_switchdev_blocking_notifiers(unsigned long val, } static inline int +switchdev_handle_fdb_add_to_device(struct net_device *dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)) +{ + return 0; +} + +static inline int +switchdev_handle_fdb_del_to_device(struct net_device *dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)) +{ + return 0; +} + +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 +472,7 @@ 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 +482,7 @@ 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..60c384569e9c 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, @@ -682,6 +686,10 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp) static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { + /* mptcp hooks are only on the slow path */ + if (sk_is_mptcp((struct sock *)tp)) + return; + tp->pred_flags = htonl((tp->tcp_header_len << 26) | ntohl(TCP_FLAG_ACK) | snd_wnd); @@ -1568,6 +1576,7 @@ struct tcp_md5sig_key { u8 keylen; u8 family; /* AF_INET or AF_INET6 */ u8 prefixlen; + u8 flags; union tcp_md5_addr addr; int l3index; /* set if key added with L3 scope */ u8 key[TCP_MD5SIG_MAXKEYLEN]; @@ -1613,10 +1622,10 @@ struct tcp_md5sig_pool { int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, int l3index, + int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, int l3index); + int family, u8 prefixlen, int l3index, u8 flags); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); @@ -1701,7 +1710,6 @@ struct tcp_fastopen_context { struct rcu_head rcu; }; -extern unsigned int sysctl_tcp_fastopen_blackhole_timeout; void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); @@ -1951,7 +1959,6 @@ struct tcp_iter_state { struct seq_net_private p; enum tcp_seq_states state; struct sock *syn_wait_sk; - struct tcp_seq_afinfo *bpf_seq_afinfo; int bucket, offset, sbucket, num; loff_t last_pos; }; diff --git a/include/net/tls.h b/include/net/tls.h index 8341a8d1e807..1fffb206f09f 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) @@ -360,6 +358,7 @@ int tls_sk_query(struct sock *sk, int optname, char __user *optval, int __user *optlen); int tls_sk_attach(struct sock *sk, int optname, char __user *optval, unsigned int optlen); +void tls_err_abort(struct sock *sk, int err); int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); @@ -377,7 +376,7 @@ void tls_sw_release_resources_rx(struct sock *sk); void tls_sw_free_ctx_rx(struct tls_context *tls_ctx); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); -bool tls_sw_stream_read(const struct sock *sk); +bool tls_sw_sock_is_readable(struct sock *sk); ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); @@ -468,12 +467,6 @@ static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) #endif } -static inline void tls_err_abort(struct sock *sk, int err) -{ - sk->sk_err = err; - sk->sk_error_report(sk); -} - static inline bool tls_bigint_increment(unsigned char *seq, int len) { int i; @@ -514,7 +507,7 @@ static inline void tls_advance_record_sn(struct sock *sk, struct cipher_context *ctx) { if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size)) - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); if (prot->version != TLS_1_3_VERSION && prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) diff --git a/include/net/udp.h b/include/net/udp.h index 360df454356c..909ecf447e0f 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -494,8 +494,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk, * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial * packets in udp_gro_complete_segment. As does UDP GSO, verified by * udp_send_skb. But when those packets are looped in dev_loopback_xmit - * their ip_summed is set to CHECKSUM_UNNECESSARY. Reset in this - * specific case, where PARTIAL is both correct and required. + * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY. + * Reset in this specific case, where PARTIAL is both correct and + * required. */ if (skb->pkt_type == PACKET_LOOPBACK) skb->ip_summed = CHECKSUM_PARTIAL; diff --git a/include/net/xdp.h b/include/net/xdp.h index a5bc214a49d9..ad5b02dcb6f4 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) @@ -275,6 +276,11 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp) return unlikely(xdp->data_meta > xdp->data); } +static inline bool xdp_metalen_invalid(unsigned long metalen) +{ + return (metalen & (sizeof(__u32) - 1)) || (metalen > 32); +} + struct xdp_attachment_info { struct bpf_prog *prog; u32 flags; 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..2308210793a0 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 { @@ -1083,6 +1075,22 @@ xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, un } #ifdef CONFIG_XFRM +static inline bool +xfrm_default_allow(struct net *net, int dir) +{ + u8 def = net->xfrm.policy_default; + + switch (dir) { + case XFRM_POLICY_IN: + return def & XFRM_POL_DEFAULT_IN ? false : true; + case XFRM_POLICY_OUT: + return def & XFRM_POL_DEFAULT_OUT ? false : true; + case XFRM_POLICY_FWD: + return def & XFRM_POL_DEFAULT_FWD ? false : true; + } + return false; +} + int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb, unsigned short family); @@ -1096,9 +1104,13 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, if (sk && sk->sk_policy[XFRM_POLICY_IN]) return __xfrm_policy_check(sk, ndir, skb, family); - return (!net->xfrm.policy_count[dir] && !secpath_exists(skb)) || - (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || - __xfrm_policy_check(sk, ndir, skb, family); + if (xfrm_default_allow(net, dir)) + return (!net->xfrm.policy_count[dir] && !secpath_exists(skb)) || + (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || + __xfrm_policy_check(sk, ndir, skb, family); + else + return (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || + __xfrm_policy_check(sk, ndir, skb, family); } static inline int xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) @@ -1150,9 +1162,13 @@ static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); - return !net->xfrm.policy_count[XFRM_POLICY_OUT] || - (skb_dst(skb)->flags & DST_NOXFRM) || - __xfrm_route_forward(skb, family); + if (xfrm_default_allow(net, XFRM_POLICY_FWD)) + return !net->xfrm.policy_count[XFRM_POLICY_OUT] || + (skb_dst(skb)->flags & DST_NOXFRM) || + __xfrm_route_forward(skb, family); + else + return (skb_dst(skb)->flags & DST_NOXFRM) || + __xfrm_route_forward(skb, family); } static inline int xfrm4_route_forward(struct sk_buff *skb) @@ -1546,6 +1562,7 @@ 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 +1587,6 @@ 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 +1597,6 @@ 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 +1620,6 @@ 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 +1733,12 @@ 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) |