diff options
| author | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2025-01-20 21:37:39 -0800 |
|---|---|---|
| committer | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2025-01-20 21:37:39 -0800 |
| commit | 25768de50b1f2dbb6ea44bd5148a87fe2c9c3688 (patch) | |
| tree | 91f4e0c1ea9acb1e8d477a5f4dfedd00de67ae13 /include/net | |
| parent | 3a6e5ed2372bcb2a3c554fda32419efd91ff9b0c (diff) | |
| parent | 08bd5b7c9a2401faabdaa1472d45c7de0755fd7e (diff) | |
Merge branch 'next' into for-linus
Prepare input updates for 6.14 merge window.
Diffstat (limited to 'include/net')
108 files changed, 1988 insertions, 674 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index 77ee0c657e2c..404df8557f6a 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -219,7 +219,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, 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); -int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); static inline void tcf_action_update_bstats(struct tc_action *a, struct sk_buff *skb) diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 62a407db1bf5..363dd63babe7 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -37,10 +37,14 @@ struct prefix_info { struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) __u8 onlink : 1, - autoconf : 1, - reserved : 6; + autoconf : 1, + routeraddr : 1, + preferpd : 1, + reserved : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - __u8 reserved : 6, + __u8 reserved : 4, + preferpd : 1, + routeraddr : 1, autoconf : 1, onlink : 1; #else @@ -183,10 +187,12 @@ static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) return 0; } +#define INFINITY_LIFE_TIME 0xFFFFFFFF + static inline unsigned long addrconf_timeout_fixup(u32 timeout, unsigned int unit) { - if (timeout == 0xffffffff) + if (timeout == INFINITY_LIFE_TIME) return ~0UL; /* @@ -327,7 +333,7 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) /** * __in6_dev_stats_get - get inet6_dev pointer for stats * @dev: network device - * @skb: skb for original incoming interface if neeeded + * @skb: skb for original incoming interface if needed * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 24d970f7a4fa..9e85424c8343 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -169,6 +169,9 @@ struct vsock_transport { void (*notify_buffer_size)(struct vsock_sock *, u64 *); int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val); + /* SIOCOUTQ ioctl */ + ssize_t (*unsent_bytes)(struct vsock_sock *vsk); + /* Shutdown. */ int (*shutdown)(struct vsock_sock *, int); diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 5d655e109b2c..435250c72d56 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -123,6 +123,7 @@ struct bt_voice { #define BT_VOICE_TRANSPARENT 0x0003 #define BT_VOICE_CVSD_16BIT 0x0060 +#define BT_VOICE_TRANSPARENT_16BIT 0x0063 #define BT_SNDMTU 12 #define BT_RCVMTU 13 @@ -403,6 +404,7 @@ int bt_sock_register(int proto, const struct net_proto_family *ops); void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); +bool bt_sock_linked(struct bt_sock_list *l, struct sock *s); struct sock *bt_sock_alloc(struct net *net, struct socket *sock, struct proto *prot, int proto, gfp_t prio, int kern); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, @@ -589,15 +591,6 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, return skb; } -static inline int bt_copy_from_sockptr(void *dst, size_t dst_size, - sockptr_t src, size_t src_size) -{ - if (dst_size > src_size) - return -EINVAL; - - return copy_from_sockptr(dst, src, dst_size); -} - int bt_to_errno(u16 code); __u8 bt_status(int err); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index d1d073089f38..6203bd8663b7 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1,7 +1,7 @@ /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated - Copyright 2023 NXP + Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> @@ -29,6 +29,7 @@ #define HCI_MAX_ACL_SIZE 1024 #define HCI_MAX_SCO_SIZE 255 #define HCI_MAX_ISO_SIZE 251 +#define HCI_MAX_ISO_BIS 31 #define HCI_MAX_EVENT_SIZE 260 #define HCI_MAX_FRAME_SIZE (HCI_MAX_ACL_SIZE + 4) @@ -67,6 +68,7 @@ #define HCI_I2C 8 #define HCI_SMD 9 #define HCI_VIRTIO 10 +#define HCI_IPC 11 /* HCI device quirks */ enum { @@ -300,6 +302,20 @@ enum { */ HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT, + /* + * When this quirk is set, the HCI_OP_LE_EXT_CREATE_CONN command is + * disabled. This is required for the Actions Semiconductor ATS2851 + * based controllers, which erroneously claims to support it. + */ + HCI_QUIRK_BROKEN_EXT_CREATE_CONN, + + /* + * When this quirk is set, the command WRITE_AUTH_PAYLOAD_TIMEOUT is + * skipped. This is required for the Actions Semiconductor ATS2851 + * based controllers, due to a race condition in pairing process. + */ + HCI_QUIRK_BROKEN_WRITE_AUTH_PAYLOAD_TIMEOUT, + /* When this quirk is set, MSFT extension monitor tracking by * address filter is supported. Since tracking quantity of each * pattern is limited, this feature supports tracking multiple @@ -683,6 +699,7 @@ enum { #define HCI_RSSI_INVALID 127 #define HCI_SYNC_HANDLE_INVALID 0xffff +#define HCI_SID_INVALID 0xff #define HCI_ROLE_MASTER 0x00 #define HCI_ROLE_SLAVE 0x01 @@ -2901,6 +2918,11 @@ static inline struct hci_sco_hdr *hci_sco_hdr(const struct sk_buff *skb) return (struct hci_sco_hdr *) skb->data; } +static inline struct hci_iso_hdr *hci_iso_hdr(const struct sk_buff *skb) +{ + return (struct hci_iso_hdr *)skb->data; +} + /* Command opcode pack/unpack */ #define hci_opcode_pack(ogf, ocf) ((__u16) ((ocf & 0x03ff)|(ogf << 10))) #define hci_opcode_ogf(op) (op >> 10) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index e449dba698f3..ca22ead85dbe 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -186,7 +186,6 @@ struct blocked_key { struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; - u8 link_type; u8 type; u8 val[16]; }; @@ -196,7 +195,6 @@ struct smp_ltk { struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; - u8 link_type; u8 authenticated; u8 type; u8 enc_size; @@ -211,7 +209,6 @@ struct smp_irk { bdaddr_t rpa; bdaddr_t bdaddr; u8 addr_type; - u8 link_type; u8 val[16]; }; @@ -219,8 +216,6 @@ struct link_key { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; - u8 bdaddr_type; - u8 link_type; u8 type; u8 val[HCI_LINK_KEY_SIZE]; u8 pin_len; @@ -673,6 +668,7 @@ struct hci_conn { __u8 adv_instance; __u16 handle; __u16 sync_handle; + __u8 sid; __u16 state; __u16 mtu; __u8 mode; @@ -715,6 +711,9 @@ struct hci_conn { __s8 tx_power; __s8 max_tx_power; struct bt_iso_qos iso_qos; + __u8 num_bis; + __u8 bis[HCI_MAX_ISO_BIS]; + unsigned long flags; enum conn_reasons conn_reason; @@ -805,7 +804,6 @@ struct hci_conn_params { extern struct list_head hci_dev_list; extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; -extern struct mutex hci_cb_list_lock; #define hci_dev_set_flag(hdev, nr) set_bit((nr), (hdev)->dev_flags) #define hci_dev_clear_flag(hdev, nr) clear_bit((nr), (hdev)->dev_flags) @@ -950,8 +948,10 @@ enum { HCI_CONN_PER_ADV, HCI_CONN_BIG_CREATED, HCI_CONN_CREATE_CIS, + HCI_CONN_CREATE_BIG_SYNC, HCI_CONN_BIG_SYNC, HCI_CONN_BIG_SYNC_FAILED, + HCI_CONN_CREATE_PA_SYNC, HCI_CONN_PA_SYNC, HCI_CONN_PA_SYNC_FAILED, }; @@ -1104,6 +1104,30 @@ static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, return NULL; } +static inline struct hci_conn *hci_conn_hash_lookup_sid(struct hci_dev *hdev, + __u8 sid, + bdaddr_t *dst, + __u8 dst_type) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type != ISO_LINK || bacmp(&c->dst, dst) || + c->dst_type != dst_type || c->sid != sid) + continue; + + rcu_read_unlock(); + return c; + } + + rcu_read_unlock(); + + return NULL; +} + static inline struct hci_conn * hci_conn_hash_lookup_per_adv_bis(struct hci_dev *hdev, bdaddr_t *ba, @@ -1260,7 +1284,17 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (bacmp(&c->dst, BDADDR_ANY) || c->type != ISO_LINK) + if (c->type != ISO_LINK) + continue; + + /* An ISO_LINK hcon with BDADDR_ANY as destination + * address is a Broadcast connection. A Broadcast + * slave connection is associated with a PA train, + * so the sync_handle can be used to differentiate + * from unicast. + */ + if (bacmp(&c->dst, BDADDR_ANY) && + c->sync_handle == HCI_SYNC_HANDLE_INVALID) continue; if (handle == c->iso_qos.bcast.big) { @@ -1275,6 +1309,30 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, } static inline struct hci_conn * +hci_conn_hash_lookup_big_sync_pend(struct hci_dev *hdev, + __u8 handle, __u8 num_bis) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type != ISO_LINK) + continue; + + if (handle == c->iso_qos.bcast.big && num_bis == c->num_bis) { + rcu_read_unlock(); + return c; + } + } + + rcu_read_unlock(); + + return NULL; +} + +static inline struct hci_conn * hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle, __u16 state) { struct hci_conn_hash *h = &hdev->conn_hash; @@ -1333,6 +1391,13 @@ hci_conn_hash_lookup_pa_sync_handle(struct hci_dev *hdev, __u16 sync_handle) if (c->type != ISO_LINK) continue; + /* Ignore the listen hcon, we are looking + * for the child hcon that was created as + * a result of the PA sync established event. + */ + if (c->state == BT_LISTEN) + continue; + if (c->sync_handle == sync_handle) { rcu_read_unlock(); return c; @@ -1450,6 +1515,8 @@ bool hci_setup_sync(struct hci_conn *conn, __u16 handle); void hci_sco_setup(struct hci_conn *conn, __u8 status); bool hci_iso_setup_path(struct hci_conn *conn); int hci_le_create_cis_pending(struct hci_dev *hdev); +int hci_pa_create_sync_pending(struct hci_dev *hdev); +int hci_le_big_create_sync_pending(struct hci_dev *hdev); int hci_conn_check_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, @@ -1876,8 +1943,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); !test_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &(dev)->quirks)) /* Use ext create connection if command is supported */ -#define use_ext_conn(dev) ((dev)->commands[37] & 0x80) - +#define use_ext_conn(dev) (((dev)->commands[37] & 0x80) && \ + !test_bit(HCI_QUIRK_BROKEN_EXT_CREATE_CONN, &(dev)->quirks)) /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) @@ -1890,8 +1957,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); * C24: Mandatory if the LE Controller supports Connection State and either * LE Feature (LL Privacy) or LE Feature (Extended Advertising) is supported */ -#define use_enhanced_conn_complete(dev) (ll_privacy_capable(dev) || \ - ext_adv_capable(dev)) +#define use_enhanced_conn_complete(dev) ((ll_privacy_capable(dev) || \ + ext_adv_capable(dev)) && \ + !test_bit(HCI_QUIRK_BROKEN_EXT_CREATE_CONN, \ + &(dev)->quirks)) /* Periodic advertising support */ #define per_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_PERIODIC_ADV)) @@ -1947,24 +2016,47 @@ struct hci_cb { char *name; + bool (*match) (struct hci_conn *conn); void (*connect_cfm) (struct hci_conn *conn, __u8 status); void (*disconn_cfm) (struct hci_conn *conn, __u8 status); void (*security_cfm) (struct hci_conn *conn, __u8 status, - __u8 encrypt); + __u8 encrypt); void (*key_change_cfm) (struct hci_conn *conn, __u8 status); void (*role_switch_cfm) (struct hci_conn *conn, __u8 status, __u8 role); }; +static inline void hci_cb_lookup(struct hci_conn *conn, struct list_head *list) +{ + struct hci_cb *cb, *cpy; + + rcu_read_lock(); + list_for_each_entry_rcu(cb, &hci_cb_list, list) { + if (cb->match && cb->match(conn)) { + cpy = kmalloc(sizeof(*cpy), GFP_ATOMIC); + if (!cpy) + break; + + *cpy = *cb; + INIT_LIST_HEAD(&cpy->list); + list_add_rcu(&cpy->list, list); + } + } + rcu_read_unlock(); +} + static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) { - struct hci_cb *cb; + struct list_head list; + struct hci_cb *cb, *tmp; - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { + INIT_LIST_HEAD(&list); + hci_cb_lookup(conn, &list); + + list_for_each_entry_safe(cb, tmp, &list, list) { if (cb->connect_cfm) cb->connect_cfm(conn, status); + kfree(cb); } - mutex_unlock(&hci_cb_list_lock); if (conn->connect_cfm_cb) conn->connect_cfm_cb(conn, status); @@ -1972,43 +2064,55 @@ static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) static inline void hci_disconn_cfm(struct hci_conn *conn, __u8 reason) { - struct hci_cb *cb; + struct list_head list; + struct hci_cb *cb, *tmp; + + INIT_LIST_HEAD(&list); + hci_cb_lookup(conn, &list); - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { + list_for_each_entry_safe(cb, tmp, &list, list) { if (cb->disconn_cfm) cb->disconn_cfm(conn, reason); + kfree(cb); } - mutex_unlock(&hci_cb_list_lock); if (conn->disconn_cfm_cb) conn->disconn_cfm_cb(conn, reason); } -static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) +static inline void hci_security_cfm(struct hci_conn *conn, __u8 status, + __u8 encrypt) { - struct hci_cb *cb; - __u8 encrypt; - - if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) - return; + struct list_head list; + struct hci_cb *cb, *tmp; - encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; + INIT_LIST_HEAD(&list); + hci_cb_lookup(conn, &list); - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { + list_for_each_entry_safe(cb, tmp, &list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); + kfree(cb); } - mutex_unlock(&hci_cb_list_lock); if (conn->security_cfm_cb) conn->security_cfm_cb(conn, status); } +static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) +{ + __u8 encrypt; + + if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) + return; + + encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; + + hci_security_cfm(conn, status, encrypt); +} + static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) { - struct hci_cb *cb; __u8 encrypt; if (conn->state == BT_CONFIG) { @@ -2035,40 +2139,38 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) conn->sec_level = conn->pending_sec_level; } - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { - if (cb->security_cfm) - cb->security_cfm(conn, status, encrypt); - } - mutex_unlock(&hci_cb_list_lock); - - if (conn->security_cfm_cb) - conn->security_cfm_cb(conn, status); + hci_security_cfm(conn, status, encrypt); } static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status) { - struct hci_cb *cb; + struct list_head list; + struct hci_cb *cb, *tmp; + + INIT_LIST_HEAD(&list); + hci_cb_lookup(conn, &list); - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { + list_for_each_entry_safe(cb, tmp, &list, list) { if (cb->key_change_cfm) cb->key_change_cfm(conn, status); + kfree(cb); } - mutex_unlock(&hci_cb_list_lock); } static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, __u8 role) { - struct hci_cb *cb; + struct list_head list; + struct hci_cb *cb, *tmp; + + INIT_LIST_HEAD(&list); + hci_cb_lookup(conn, &list); - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { + list_for_each_entry_safe(cb, tmp, &list, list) { if (cb->role_switch_cfm) cb->role_switch_cfm(conn, status, role); + kfree(cb); } - mutex_unlock(&hci_cb_list_lock); } static inline bool hci_bdaddr_is_rpa(bdaddr_t *bdaddr, u8 addr_type) @@ -2262,8 +2364,8 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, bool mgmt_connected); void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); -void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, - u8 addr_type, u8 status); +void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn, + u8 status); void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure); void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status); diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 75e052909b5f..f3052cb252ef 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -73,6 +73,10 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); +int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +int hci_cmd_sync_run_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); struct hci_cmd_sync_work_entry * hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 5cfdc813491a..d9c767cf773d 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -27,7 +27,7 @@ #ifndef __L2CAP_H #define __L2CAP_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/atomic.h> /* L2CAP defaults */ @@ -968,10 +968,6 @@ void l2cap_chan_list(struct l2cap_conn *conn, l2cap_chan_func_t func, void *data); void l2cap_chan_del(struct l2cap_chan *chan, int err); void l2cap_send_conn_req(struct l2cap_chan *chan); -void l2cap_move_start(struct l2cap_chan *chan); -void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan, - u8 status); -void __l2cap_physical_cfm(struct l2cap_chan *chan, int result); struct l2cap_conn *l2cap_conn_get(struct l2cap_conn *conn); void l2cap_conn_put(struct l2cap_conn *conn); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index d382679efd2b..affac861efdc 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -878,6 +878,16 @@ struct mgmt_cp_mesh_send_cancel { } __packed; #define MGMT_MESH_SEND_CANCEL_SIZE 1 +#define MGMT_OP_HCI_CMD_SYNC 0x005B +struct mgmt_cp_hci_cmd_sync { + __le16 opcode; + __u8 event; + __u8 timeout; + __le16 params_len; + __u8 params[]; +} __packed; +#define MGMT_HCI_CMD_SYNC_SIZE 6 + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 9ce5ac2bfbad..2053cd8e788a 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -231,7 +231,10 @@ typedef struct port { mux_states_t sm_mux_state; /* state machine mux state */ u16 sm_mux_timer_counter; /* state machine mux timer counter */ tx_states_t sm_tx_state; /* state machine tx state */ - u16 sm_tx_timer_counter; /* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */ + u16 sm_tx_timer_counter; /* state machine tx timer counter + * (always on - enter to transmit + * state 3 time per second) + */ u16 sm_churn_actor_timer_counter; u16 sm_churn_partner_timer_counter; u32 churn_actor_count; diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index 9dc082b2d543..e5945427f38d 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -53,7 +53,7 @@ struct slave; struct tlb_client_info { - struct slave *tx_slave; /* A pointer to slave used for transmiting + struct slave *tx_slave; /* A pointer to slave used for transmitting * packets to a Client that the Hash function * gave this entry index. */ diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 473a0147769e..18687ccf0638 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -161,5 +161,7 @@ void bond_option_arp_ip_targets_clear(struct bonding *bond); #if IS_ENABLED(CONFIG_IPV6) void bond_option_ns_ip6_targets_clear(struct bonding *bond); #endif +void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave); +void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave); #endif /* _NET_BOND_OPTIONS_H */ diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 522f1da8b747..c858270141bc 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -52,6 +52,9 @@ void napi_busy_loop_rcu(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget); +void napi_suspend_irqs(unsigned int napi_id); +void napi_resume_irqs(unsigned int napi_id); + #else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) { @@ -131,7 +134,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb, #endif } -/* used in the protocol hanlder to propagate the napi_id to the socket */ +/* used in the protocol handler to propagate the napi_id to the socket */ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h index 0f45d875905f..053e7c6a6a66 100644 --- a/include/net/caif/caif_layer.h +++ b/include/net/caif/caif_layer.h @@ -20,7 +20,7 @@ struct caif_payload_info; * @assert: expression to evaluate. * * This function will print a error message and a do WARN_ON if the - * assertion failes. Normally this will do a stack up at the current location. + * assertion fails. Normally this will do a stack up at the current location. */ #define caif_assert(assert) \ do { \ @@ -116,7 +116,7 @@ enum caif_direction { * @dn: Pointer down to the layer below. * @node: List node used when layer participate in a list. * @receive: Packet receive function. - * @transmit: Packet transmit funciton. + * @transmit: Packet transmit function. * @ctrlcmd: Used for control signalling upwards in the stack. * @modemcmd: Used for control signaling downwards in the stack. * @id: The identity of this layer diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h index 44d914a50369..acf664227d96 100644 --- a/include/net/caif/cfpkt.h +++ b/include/net/caif/cfpkt.h @@ -18,7 +18,7 @@ struct cfpkt *cfpkt_create(u16 len); /* * Destroy a CAIF Packet. - * pkt Packet to be destoyed. + * pkt Packet to be destroyed. */ void cfpkt_destroy(struct cfpkt *pkt); diff --git a/include/net/caif/cfsrvl.h b/include/net/caif/cfsrvl.h index 5ee7b322e18b..a000dc45f966 100644 --- a/include/net/caif/cfsrvl.h +++ b/include/net/caif/cfsrvl.h @@ -40,7 +40,6 @@ void cfsrvl_init(struct cfsrvl *service, struct dev_info *dev_info, bool supports_flowctrl); bool cfsrvl_ready(struct cfsrvl *service, int *err); -u8 cfsrvl_getphyid(struct cflayer *layer); static inline void cfsrvl_get(struct cflayer *layr) { diff --git a/include/net/calipso.h b/include/net/calipso.h index f8667a3fda9e..76b9e08c10c2 100644 --- a/include/net/calipso.h +++ b/include/net/calipso.h @@ -25,7 +25,7 @@ #include <net/netlabel.h> #include <net/request_sock.h> #include <linux/refcount.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* known doi values */ #define CALIPSO_DOI_UNKNOWN 0x00000000 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 192d72c8b465..27acf1292a5c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1460,7 +1460,6 @@ struct cfg80211_unsol_bcast_probe_resp { * @crypto: crypto settings * @privacy: the BSS uses privacy * @auth_type: Authentication type (algorithm) - * @smps_mode: SMPS mode * @inactivity_timeout: time in seconds to determine station's inactivity. * @p2p_ctwindow: P2P CT Window * @p2p_opp_ps: P2P opportunistic PS @@ -1498,7 +1497,6 @@ struct cfg80211_ap_settings { struct cfg80211_crypto_settings crypto; bool privacy; enum nl80211_auth_type auth_type; - enum nl80211_smps_mode smps_mode; int inactivity_timeout; u8 p2p_ctwindow; bool p2p_opp_ps; @@ -2269,6 +2267,7 @@ static inline int cfg80211_get_station(struct net_device *dev, * @MONITOR_FLAG_OTHER_BSS: disable BSSID filtering * @MONITOR_FLAG_COOK_FRAMES: report frames after processing * @MONITOR_FLAG_ACTIVE: active monitor, ACKs frames on its MAC address + * @MONITOR_FLAG_SKIP_TX: do not pass locally transmitted frames */ enum monitor_flags { MONITOR_FLAG_CHANGED = BIT(__NL80211_MNTR_FLAG_INVALID), @@ -2278,6 +2277,7 @@ enum monitor_flags { MONITOR_FLAG_OTHER_BSS = BIT(NL80211_MNTR_FLAG_OTHER_BSS), MONITOR_FLAG_COOK_FRAMES = BIT(NL80211_MNTR_FLAG_COOK_FRAMES), MONITOR_FLAG_ACTIVE = BIT(NL80211_MNTR_FLAG_ACTIVE), + MONITOR_FLAG_SKIP_TX = BIT(NL80211_MNTR_FLAG_SKIP_TX), }; /** @@ -4696,6 +4696,7 @@ struct cfg80211_ops { struct ieee80211_channel *chan); int (*set_monitor_channel)(struct wiphy *wiphy, + struct net_device *dev, struct cfg80211_chan_def *chandef); int (*scan)(struct wiphy *wiphy, @@ -4837,9 +4838,9 @@ struct cfg80211_ops { int (*start_radar_detection)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef, - u32 cac_time_ms); + u32 cac_time_ms, int link_id); void (*end_cac)(struct wiphy *wiphy, - struct net_device *dev); + struct net_device *dev, unsigned int link_id); int (*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_update_ft_ies_params *ftie); int (*crit_proto_start)(struct wiphy *wiphy, @@ -5436,6 +5437,8 @@ struct wiphy_radio_freq_range { * @iface_combinations: Valid interface combinations array, should not * list single interface types. * @n_iface_combinations: number of entries in @iface_combinations array. + * + * @antenna_mask: bitmask of antennas connected to this radio. */ struct wiphy_radio { const struct wiphy_radio_freq_range *freq_range; @@ -5443,6 +5446,8 @@ struct wiphy_radio { const struct ieee80211_iface_combination *iface_combinations; int n_iface_combinations; + + u32 antenna_mask; }; #define CFG80211_HW_TIMESTAMP_ALL_PEERS 0xffff @@ -6130,6 +6135,50 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, struct wiphy_delayed_work *dwork); /** + * wiphy_delayed_work_pending - Find out whether a wiphy delayable + * work item is currently pending. + * + * @wiphy: the wiphy, for debug purposes + * @dwork: the delayed work in question + * + * Return: true if timer is pending, false otherwise + * + * How wiphy_delayed_work_queue() works is by setting a timer which + * when it expires calls wiphy_work_queue() to queue the wiphy work. + * Because wiphy_delayed_work_queue() uses mod_timer(), if it is + * called twice and the second call happens before the first call + * deadline, the work will rescheduled for the second deadline and + * won't run before that. + * + * wiphy_delayed_work_pending() can be used to detect if calling + * wiphy_work_delayed_work_queue() would start a new work schedule + * or delayed a previous one. As seen below it cannot be used to + * detect precisely if the work has finished to execute nor if it + * is currently executing. + * + * CPU0 CPU1 + * wiphy_delayed_work_queue(wk) + * mod_timer(wk->timer) + * wiphy_delayed_work_pending(wk) -> true + * + * [...] + * expire_timers(wk->timer) + * detach_timer(wk->timer) + * wiphy_delayed_work_pending(wk) -> false + * wk->timer->function() | + * wiphy_work_queue(wk) | delayed work pending + * list_add_tail() | returns false but + * queue_work(cfg80211_wiphy_work) | wk->func() has not + * | been run yet + * [...] | + * cfg80211_wiphy_work() | + * wk->func() V + * + */ +bool wiphy_delayed_work_pending(struct wiphy *wiphy, + struct wiphy_delayed_work *dwork); + +/** * enum ieee80211_ap_reg_power - regulatory power for an Access Point * * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode @@ -6194,9 +6243,6 @@ enum ieee80211_ap_reg_power { * @address: The address for this device, valid only if @netdev is %NULL * @is_running: true if this is a non-netdev device that has been started, e.g. * the P2P Device. - * @cac_started: true if DFS channel availability check has been started - * @cac_start_time: timestamp (jiffies) when the dfs state was entered. - * @cac_time_ms: CAC time in ms * @ps: powersave mode is enabled * @ps_timeout: dynamic powersave timeout * @ap_unexpected_nlportid: (private) netlink port ID of application @@ -6220,7 +6266,13 @@ enum ieee80211_ap_reg_power { * unprotected beacon report * @links: array of %IEEE80211_MLD_MAX_NUM_LINKS elements containing @addr * @ap and @client for each link + * @links.cac_started: true if DFS channel availability check has been + * started + * @links.cac_start_time: timestamp (jiffies) when the dfs state was + * entered. + * @links.cac_time_ms: CAC time in ms * @valid_links: bitmap describing what elements of @links are valid + * @radio_mask: Bitmask of radios that this interface is allowed to operate on. */ struct wireless_dev { struct wiphy *wiphy; @@ -6261,11 +6313,6 @@ struct wireless_dev { u32 owner_nlportid; bool nl_owner_dead; - /* FIXME: need to rework radar detection for MLO */ - bool cac_started; - unsigned long cac_start_time; - unsigned int cac_time_ms; - #ifdef CONFIG_CFG80211_WEXT /* wext data */ struct { @@ -6332,8 +6379,14 @@ struct wireless_dev { struct cfg80211_internal_bss *current_bss; } client; }; + + bool cac_started; + unsigned long cac_start_time; + unsigned int cac_time_ms; } links[IEEE80211_MLD_MAX_NUM_LINKS]; u16 valid_links; + + u32 radio_mask; }; static inline const u8 *wdev_address(struct wireless_dev *wdev) @@ -6520,6 +6573,17 @@ bool cfg80211_radio_chandef_valid(const struct wiphy_radio *radio, const struct cfg80211_chan_def *chandef); /** + * cfg80211_wdev_channel_allowed - Check if the wdev may use the channel + * + * @wdev: the wireless device + * @chan: channel to check + * + * Return: whether or not the wdev may use the channel + */ +bool cfg80211_wdev_channel_allowed(struct wireless_dev *wdev, + struct ieee80211_channel *chan); + +/** * ieee80211_get_response_rate - get basic rate for a given rate * * @sband: the band to look for rates in @@ -8740,6 +8804,7 @@ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, * @chandef: chandef for the current channel * @event: type of event * @gfp: context flags + * @link_id: valid link_id for MLO operation or 0 otherwise. * * This function is called when a Channel availability check (CAC) is finished * or aborted. This must be called to notify the completion of a CAC process, @@ -8747,7 +8812,8 @@ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, */ void cfg80211_cac_event(struct net_device *netdev, const struct cfg80211_chan_def *chandef, - enum nl80211_radar_event event, gfp_t gfp); + enum nl80211_radar_event event, gfp_t gfp, + unsigned int link_id); /** * cfg80211_background_cac_abort - Channel Availability Check offchan abort event diff --git a/include/net/checksum.h b/include/net/checksum.h index 1338cb92c8e7..243f972267b8 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -151,6 +151,12 @@ static inline void csum_replace(__wsum *csum, __wsum old, __wsum new) *csum = csum_add(csum_sub(*csum, old), new); } +static inline unsigned short csum_from32to16(unsigned int sum) +{ + sum += (sum >> 16) | (sum << 16); + return (unsigned short)(sum >> 16); +} + struct sk_buff; void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr); diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index c9111bb2f59b..d6780d7903f4 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -28,7 +28,7 @@ #include <net/request_sock.h> #include <linux/atomic.h> #include <linux/refcount.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* known doi values */ #define CIPSO_V4_DOI_UNKNOWN 0x00000000 diff --git a/include/net/devlink.h b/include/net/devlink.h index db5eff6cb60f..fbb9a2668e24 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1779,12 +1779,6 @@ int devl_resource_register(struct devlink *devlink, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); -int devlink_resource_register(struct devlink *devlink, - const char *resource_name, - u64 resource_size, - u64 resource_id, - u64 parent_resource_id, - const struct devlink_resource_size_params *size_params); void devl_resources_unregister(struct devlink *devlink); void devlink_resources_unregister(struct devlink *devlink); int devl_resource_size_get(struct devlink *devlink, @@ -1797,15 +1791,8 @@ void devl_resource_occ_get_register(struct devlink *devlink, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); -void devlink_resource_occ_get_register(struct devlink *devlink, - u64 resource_id, - devlink_resource_occ_get_t *occ_get, - void *occ_get_priv); void devl_resource_occ_get_unregister(struct devlink *devlink, u64 resource_id); - -void devlink_resource_occ_get_unregister(struct devlink *devlink, - u64 resource_id); int devl_params_register(struct devlink *devlink, const struct devlink_param *params, size_t params_count); diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 9707ab54fdd5..6c5a1ea209a2 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -76,6 +76,10 @@ FN(INVALID_PROTO) \ FN(IP_INADDRERRORS) \ FN(IP_INNOROUTES) \ + FN(IP_LOCAL_SOURCE) \ + FN(IP_INVALID_SOURCE) \ + FN(IP_LOCALNET) \ + FN(IP_INVALID_DEST) \ FN(PKT_TOO_BIG) \ FN(DUP_FRAG) \ FN(FRAG_REASM_TIMEOUT) \ @@ -92,6 +96,15 @@ FN(PACKET_SOCK_ERROR) \ FN(TC_CHAIN_NOTFOUND) \ FN(TC_RECLASSIFY_LOOP) \ + FN(VXLAN_INVALID_HDR) \ + FN(VXLAN_VNI_NOT_FOUND) \ + FN(MAC_INVALID_SOURCE) \ + FN(VXLAN_ENTRY_EXISTS) \ + FN(VXLAN_NO_REMOTE) \ + FN(IP_TUNNEL_ECN) \ + FN(TUNNEL_TXINFO) \ + FN(LOCAL_MAC) \ + FN(ARP_PVLAN_DISABLE) \ FNe(MAX) /** @@ -155,8 +168,8 @@ enum skb_drop_reason { /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ SKB_DROP_REASON_SOCKET_RCVBUFF, /** - * @SKB_DROP_REASON_PROTO_MEM: proto memory limition, such as udp packet - * drop out of udp_memory_allocated. + * @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as + * udp packet drop out of udp_memory_allocated. */ SKB_DROP_REASON_PROTO_MEM, /** @@ -217,7 +230,7 @@ enum skb_drop_reason { */ SKB_DROP_REASON_TCP_ZEROWINDOW, /** - * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already + * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data received is already * received before (spurious retrans may happened), see * LINUX_MIB_DELAYEDACKLOST */ @@ -365,6 +378,21 @@ enum skb_drop_reason { * IPSTATS_MIB_INADDRERRORS */ SKB_DROP_REASON_IP_INNOROUTES, + /** @SKB_DROP_REASON_IP_LOCAL_SOURCE: the source ip is local */ + SKB_DROP_REASON_IP_LOCAL_SOURCE, + /** + * @SKB_DROP_REASON_IP_INVALID_SOURCE: the source ip is invalid: + * 1) source ip is multicast or limited broadcast + * 2) source ip is zero and not IGMP + */ + SKB_DROP_REASON_IP_INVALID_SOURCE, + /** @SKB_DROP_REASON_IP_LOCALNET: source or dest ip is local net */ + SKB_DROP_REASON_IP_LOCALNET, + /** + * @SKB_DROP_REASON_IP_INVALID_DEST: the dest ip is invalid: + * 1) dest ip is 0 + */ + SKB_DROP_REASON_IP_INVALID_DEST, /** * @SKB_DROP_REASON_PKT_TOO_BIG: packet size is too big (maybe exceed the * MTU) @@ -419,6 +447,44 @@ enum skb_drop_reason { */ SKB_DROP_REASON_TC_RECLASSIFY_LOOP, /** + * @SKB_DROP_REASON_VXLAN_INVALID_HDR: VXLAN header is invalid. E.g.: + * 1) reserved fields are not zero + * 2) "I" flag is not set + */ + SKB_DROP_REASON_VXLAN_INVALID_HDR, + /** @SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND: no VXLAN device found for VNI */ + SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND, + /** @SKB_DROP_REASON_MAC_INVALID_SOURCE: source mac is invalid */ + SKB_DROP_REASON_MAC_INVALID_SOURCE, + /** + * @SKB_DROP_REASON_VXLAN_ENTRY_EXISTS: trying to migrate a static + * entry or an entry pointing to a nexthop. + */ + SKB_DROP_REASON_VXLAN_ENTRY_EXISTS, + /** @SKB_DROP_REASON_VXLAN_NO_REMOTE: no remote found for xmit */ + SKB_DROP_REASON_VXLAN_NO_REMOTE, + /** + * @SKB_DROP_REASON_IP_TUNNEL_ECN: skb is dropped according to + * RFC 6040 4.2, see __INET_ECN_decapsulate() for detail. + */ + SKB_DROP_REASON_IP_TUNNEL_ECN, + /** + * @SKB_DROP_REASON_TUNNEL_TXINFO: packet without necessary metadata + * reached a device which is in "external" mode. + */ + SKB_DROP_REASON_TUNNEL_TXINFO, + /** + * @SKB_DROP_REASON_LOCAL_MAC: the source MAC address is equal to + * the MAC address of the local netdev. + */ + SKB_DROP_REASON_LOCAL_MAC, + /** + * @SKB_DROP_REASON_ARP_PVLAN_DISABLE: packet which is not IP is + * forwarded to the in_dev, and the proxy_arp_pvlan is not + * enabled. + */ + SKB_DROP_REASON_ARP_PVLAN_DISABLE, + /** * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which * shouldn't be used as a real 'reason' - only for tracing code gen */ diff --git a/include/net/dsa.h b/include/net/dsa.h index d7a6c2930277..72ae65e7246a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -885,21 +885,6 @@ struct dsa_switch_ops { */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); - struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds, - int port, - phy_interface_t iface); - void (*phylink_mac_config)(struct dsa_switch *ds, int port, - unsigned int mode, - const struct phylink_link_state *state); - void (*phylink_mac_link_down)(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface); - void (*phylink_mac_link_up)(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface, - struct phy_device *phydev, - int speed, int duplex, - bool tx_pause, bool rx_pause); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* diff --git a/include/net/dst.h b/include/net/dst.h index 0aa331bd2fdb..0f303cc60252 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -341,7 +341,7 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; /* - * Clear hash so that we can recalulate the hash for the + * Clear hash so that we can recalculate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h index b4a55d2d5e71..1961699598e2 100644 --- a/include/net/dst_cache.h +++ b/include/net/dst_cache.h @@ -102,7 +102,7 @@ int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp); * @dst_cache: the cache * * No synchronization is enforced: it must be called only when the cache - * is unsed. + * is unused. */ void dst_cache_destroy(struct dst_cache *dst_cache); diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 4160731dcb6e..84c15402931c 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -163,8 +163,11 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) if (!new_md) return ERR_PTR(-ENOMEM); - memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, - sizeof(struct ip_tunnel_info) + md_size); + unsafe_memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, + sizeof(struct ip_tunnel_info) + md_size, + /* metadata_dst_alloc() reserves room (md_size bytes) for + * options right after the ip_tunnel_info struct. + */); #ifdef CONFIG_DST_CACHE /* Unclone the dst cache if there is one */ if (new_md->u.tun_info.dst_cache.cache) { diff --git a/include/net/eee.h b/include/net/eee.h index 84837aba3cd9..cfab1b8bc46a 100644 --- a/include/net/eee.h +++ b/include/net/eee.h @@ -13,10 +13,7 @@ struct eee_config { static inline bool eeecfg_mac_can_tx_lpi(const struct eee_config *eeecfg) { /* eee_enabled is the master on/off */ - if (!eeecfg->eee_enabled || !eeecfg->tx_lpi_enabled) - return false; - - return true; + return eeecfg->eee_enabled && eeecfg->tx_lpi_enabled; } static inline void eeecfg_to_eee(struct ethtool_keee *eee, diff --git a/include/net/erspan.h b/include/net/erspan.h index 6cb4cbd6a48f..c6209e7b6c96 100644 --- a/include/net/erspan.h +++ b/include/net/erspan.h @@ -89,7 +89,7 @@ enum erspan_encap_type { ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ ERSPAN_ENCAP_8021Q = 0x2, /* originally 802.1Q encapsulated */ - ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ + ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag preserved in frame */ }; #define ERSPAN_V1_MDSIZE 4 @@ -192,7 +192,7 @@ static inline void erspan_build_header(struct sk_buff *skb, enc_type = ERSPAN_ENCAP_NOVLAN; /* If mirrored packet has vlan tag, extract tci and - * perserve vlan header in the mirrored frame. + * preserve vlan header in the mirrored frame. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h index 6d59221ff05a..48aad6128fea 100644 --- a/include/net/fib_notifier.h +++ b/include/net/fib_notifier.h @@ -28,7 +28,7 @@ enum fib_event_type { struct fib_notifier_ops { int family; struct list_head list; - unsigned int (*fib_seq_read)(struct net *net); + unsigned int (*fib_seq_read)(const struct net *net); int (*fib_dump)(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); struct module *owner; diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index d17855c52ef9..04383d90a1e3 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -176,7 +176,7 @@ int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table); bool fib_rule_matchall(const struct fib_rule *rule); int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, struct netlink_ext_ack *extack); -unsigned int fib_rules_seq_read(struct net *net, int family); +unsigned int fib_rules_seq_read(const struct net *net, int family); int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 292cd8f4b762..596ab9791e4d 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -685,6 +685,7 @@ struct flow_cls_common_offload { u32 chain_index; __be16 protocol; u32 prio; + bool skip_sw; struct netlink_ext_ack *extack; }; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 9ab49bfeae78..d096cc6352de 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -124,7 +124,8 @@ struct genl_family { * @genlhdr: generic netlink message header * @attrs: netlink attributes * @_net: network namespace - * @user_ptr: user pointers + * @ctx: storage space for the use by the family + * @user_ptr: user pointers (deprecated, use ctx instead) * @extack: extended ACK report struct */ struct genl_info { @@ -135,7 +136,10 @@ struct genl_info { struct genlmsghdr * genlhdr; struct nlattr ** attrs; possible_net_t _net; - void * user_ptr[2]; + union { + u8 ctx[NETLINK_CTX_SIZE]; + void * user_ptr[2]; + }; struct netlink_ext_ack *extack; }; @@ -531,13 +535,12 @@ static inline int genlmsg_multicast(const struct genl_family *family, * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array - * @flags: allocation flags * * This function must hold the RTNL or rcu_read_lock(). */ int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, - unsigned int group, gfp_t flags); + unsigned int group); /** * genlmsg_unicast - unicast a netlink message diff --git a/include/net/hwbm.h b/include/net/hwbm.h index aa495decec35..bdbe91c609ff 100644 --- a/include/net/hwbm.h +++ b/include/net/hwbm.h @@ -11,9 +11,9 @@ struct hwbm_pool { int frag_size; /* Number of buffers currently used by this pool */ int buf_num; - /* constructor called during alocation */ + /* constructor called during allocation */ int (*construct)(struct hwbm_pool *bm_pool, void *buf); - /* protect acces to the buffer counter*/ + /* protect access to the buffer counter*/ struct mutex buf_lock; /* private data */ void *priv; diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 91762faecc13..813e163ce27c 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -18,31 +18,33 @@ #define __RADIOTAP_H #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * struct ieee80211_radiotap_header - base radiotap header */ struct ieee80211_radiotap_header { - /** - * @it_version: radiotap version, always 0 - */ - uint8_t it_version; - - /** - * @it_pad: padding (or alignment) - */ - uint8_t it_pad; - - /** - * @it_len: overall radiotap header length - */ - __le16 it_len; - - /** - * @it_present: (first) present word - */ - __le32 it_present; + __struct_group(ieee80211_radiotap_header_fixed, hdr, __packed, + /** + * @it_version: radiotap version, always 0 + */ + uint8_t it_version; + + /** + * @it_pad: padding (or alignment) + */ + uint8_t it_pad; + + /** + * @it_len: overall radiotap header length + */ + __le16 it_len; + + /** + * @it_present: (first) present word + */ + __le32 it_present; + ); /** * @it_optional: all remaining presence bitmaps @@ -50,6 +52,9 @@ struct ieee80211_radiotap_header { __le32 it_optional[]; } __packed; +static_assert(offsetof(struct ieee80211_radiotap_header, it_optional) == sizeof(struct ieee80211_radiotap_header_fixed), + "struct member likely outside of __struct_group()"); + /* version is always 0 */ #define PKTHDR_RADIOTAP_VERSION 0 diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 533a7337865a..74dd90ff5f12 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -40,7 +40,7 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash, * * The sockhash lock must be held as a reader here. */ -struct sock *__inet6_lookup_established(struct net *net, +struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, @@ -56,7 +56,7 @@ inet6_ehashfn_t inet6_ehashfn; INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); -struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, @@ -64,7 +64,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, unsigned short hnum, inet6_ehashfn_t *ehashfn); -struct sock *inet6_lookup_listener(struct net *net, +struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -73,7 +73,7 @@ struct sock *inet6_lookup_listener(struct net *net, const unsigned short hnum, const int dif, const int sdif); -struct sock *inet6_lookup_run_sk_lookup(struct net *net, +struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -82,7 +82,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn); -static inline struct sock *__inet6_lookup(struct net *net, +static inline struct sock *__inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -167,7 +167,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, iif, sdif, refcounted); } -struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, +struct sock *inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, @@ -175,7 +175,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, int inet6_hash(struct sock *sk); -static inline bool inet6_match(struct net *net, const struct sock *sk, +static inline bool inet6_match(const struct net *net, const struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, const __portpair ports, diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c0deaafebfdc..3c82fad904d4 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -197,12 +197,12 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) struct inet_connection_sock *icsk = inet_csk(sk); if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { - icsk->icsk_pending = 0; + smp_store_release(&icsk->icsk_pending, 0); #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_retransmit_timer); #endif } else if (what == ICSK_TIME_DACK) { - icsk->icsk_ack.pending = 0; + smp_store_release(&icsk->icsk_ack.pending, 0); icsk->icsk_ack.retry = 0; #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_delack_timer); @@ -229,11 +229,12 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 || what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) { - icsk->icsk_pending = what; + smp_store_release(&icsk->icsk_pending, what); icsk->icsk_timeout = jiffies + when; sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); } else if (what == ICSK_TIME_DACK) { - icsk->icsk_ack.pending |= ICSK_ACK_TIMER; + smp_store_release(&icsk->icsk_ack.pending, + icsk->icsk_ack.pending | ICSK_ACK_TIMER); icsk->icsk_ack.timeout = jiffies + when; sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); } else { diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 7f1b38458743..5eea47f135a4 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -304,7 +304,7 @@ int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); -struct sock *__inet_lookup_listener(struct net *net, +struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, @@ -351,7 +351,7 @@ static inline struct sock *inet_lookup_listener(struct net *net, ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -static inline bool inet_match(struct net *net, const struct sock *sk, +static inline bool inet_match(const struct net *net, const struct sock *sk, const __addrpair cookie, const __portpair ports, int dif, int sdif) { @@ -368,7 +368,7 @@ static inline bool inet_match(struct net *net, const struct sock *sk, /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM */ -struct sock *__inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, @@ -382,13 +382,13 @@ inet_ehashfn_t inet_ehashfn; INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); -struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, inet_ehashfn_t *ehashfn); -struct sock *inet_lookup_run_sk_lookup(struct net *net, +struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index f9ddd47dc4f8..56d8bc5593d3 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -150,7 +150,8 @@ static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, return bound_dev_if == dif || bound_dev_if == sdif; } -static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if, +static inline bool inet_sk_bound_dev_eq(const struct net *net, + int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) @@ -173,6 +174,7 @@ struct inet_cork { __s16 tos; char priority; __u16 gso_size; + u32 ts_opt_id; u64 transmit_time; u32 mark; }; @@ -240,7 +242,8 @@ struct inet_sock { struct inet_cork_full cork; }; -#define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ +#define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ +#define IPCORK_TS_OPT_ID 2 /* ts_opt_id field is valid, overriding sk_tskey */ enum { INET_FLAGS_PKTINFO = 0, @@ -318,8 +321,10 @@ static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet) static inline struct sock *sk_to_full_sk(struct sock *sk) { #ifdef CONFIG_INET - if (sk && sk->sk_state == TCP_NEW_SYN_RECV) + if (sk && READ_ONCE(sk->sk_state) == TCP_NEW_SYN_RECV) sk = inet_reqsk(sk)->rsk_listener; + if (sk && READ_ONCE(sk->sk_state) == TCP_TIME_WAIT) + sk = NULL; #endif return sk; } @@ -328,8 +333,10 @@ static inline struct sock *sk_to_full_sk(struct sock *sk) static inline const struct sock *sk_const_to_full_sk(const struct sock *sk) { #ifdef CONFIG_INET - if (sk && sk->sk_state == TCP_NEW_SYN_RECV) + if (sk && READ_ONCE(sk->sk_state) == TCP_NEW_SYN_RECV) sk = ((const struct request_sock *)sk)->rsk_listener; + if (sk && READ_ONCE(sk->sk_state) == TCP_TIME_WAIT) + sk = NULL; #endif return sk; } diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index f88b68269012..62c0a7e65d6b 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -45,6 +45,8 @@ struct inet_timewait_sock { #define tw_node __tw_common.skc_nulls_node #define tw_bind_node __tw_common.skc_bind_node #define tw_refcnt __tw_common.skc_refcnt +#define tw_tx_queue_mapping __tw_common.skc_tx_queue_mapping +#define tw_rx_queue_mapping __tw_common.skc_rx_queue_mapping #define tw_hash __tw_common.skc_hash #define tw_prot __tw_common.skc_prot #define tw_net __tw_common.skc_net @@ -58,7 +60,7 @@ struct inet_timewait_sock { #define tw_dr __tw_common.skc_tw_dr __u32 tw_mark; - volatile unsigned char tw_substate; + unsigned char tw_substate; unsigned char tw_rcv_wscale; /* Socket demultiplex comparisons on incoming packets. */ diff --git a/include/net/ip.h b/include/net/ip.h index c5606cadb1a5..0e548c1f2a0e 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -33,6 +33,7 @@ #include <net/flow_dissector.h> #include <net/netns/hash.h> #include <net/lwtunnel.h> +#include <net/inet_dscp.h> #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ #define IPV4_MIN_MTU 68 /* RFC 791 */ @@ -258,7 +259,9 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet, static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet) { - return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(READ_ONCE(inet->tos)); + u8 dsfield = ipc->tos != -1 ? ipc->tos : READ_ONCE(inet->tos); + + return dsfield & INET_DSCP_MASK; } /* datagram.c */ @@ -285,7 +288,8 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0; } -void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, +void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk, + struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, @@ -421,6 +425,11 @@ int ip_decrease_ttl(struct iphdr *iph) return --iph->ttl; } +static inline dscp_t ip4h_dscp(const struct iphdr *ip4h) +{ + return inet_dsfield_to_dscp(ip4h->tos); +} + static inline int ip_mtu_locked(const struct dst_entry *dst) { const struct rtable *rt = dst_rtable(dst); @@ -681,6 +690,11 @@ static inline unsigned int ipv4_addr_hash(__be32 ip) return (__force unsigned int) ip; } +static inline u32 __ipv4_addr_hash(const __be32 ip, const u32 initval) +{ + return jhash_1word((__force u32)ip, initval); +} + static inline u32 ipv4_portaddr_hash(const struct net *net, __be32 saddr, unsigned int port) @@ -794,9 +808,8 @@ static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0); } -bool icmp_global_allow(void); -extern int sysctl_icmp_msgs_per_sec; -extern int sysctl_icmp_msgs_burst; +bool icmp_global_allow(struct net *net); +void icmp_global_consume(struct net *net); #ifdef CONFIG_PROC_FS int ip_misc_proc_init(void); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 6cb867ce4878..7c87873ae211 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -394,7 +394,7 @@ struct fib6_table { struct fib6_node tb6_root; struct inet_peer_base tb6_peers; unsigned int flags; - unsigned int fib_seq; + unsigned int fib_seq; /* writes protected by rtnl_mutex */ struct hlist_head tb6_gc_hlist; /* GC candidates */ #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; @@ -563,7 +563,7 @@ int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, int __net_init fib6_notifier_init(struct net *net); void __net_exit fib6_notifier_exit(struct net *net); -unsigned int fib6_tables_seq_read(struct net *net); +unsigned int fib6_tables_seq_read(const struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); @@ -632,7 +632,7 @@ void fib6_rules_cleanup(void); bool fib6_rule_default(const struct fib_rule *rule); int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); -unsigned int fib6_rules_seq_read(struct net *net); +unsigned int fib6_rules_seq_read(const struct net *net); static inline bool fib6_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, @@ -676,7 +676,7 @@ static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb, { return 0; } -static inline unsigned int fib6_rules_seq_read(struct net *net) +static inline unsigned int fib6_rules_seq_read(const struct net *net) { return 0; } diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 72af2f223e59..a113c11ab56b 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -22,6 +22,8 @@ #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/refcount.h> +#include <linux/ip.h> +#include <linux/in_route.h> struct fib_config { u8 fc_dst_len; @@ -345,7 +347,7 @@ static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb, return 0; } -static inline unsigned int fib4_rules_seq_read(struct net *net) +static inline unsigned int fib4_rules_seq_read(const struct net *net) { return 0; } @@ -409,7 +411,7 @@ static inline bool fib4_has_custom_rules(const struct net *net) bool fib4_rule_default(const struct fib_rule *rule); int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); -unsigned int fib4_rules_seq_read(struct net *net); +unsigned int fib4_rules_seq_read(const struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, @@ -434,6 +436,11 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net, #endif /* CONFIG_IP_MULTIPLE_TABLES */ +static inline bool fib_dscp_masked_match(dscp_t dscp, const struct flowi4 *fl4) +{ + return dscp == inet_dsfield_to_dscp(RT_TOS(fl4->flowi4_tos)); +} + /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); @@ -442,8 +449,21 @@ int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, __be32 fib_compute_spec_dst(struct sk_buff *skb); bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, - u8 tos, int oif, struct net_device *dev, + dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); + +static inline enum skb_drop_reason +fib_validate_source_reason(struct sk_buff *skb, __be32 src, __be32 dst, + dscp_t dscp, int oif, struct net_device *dev, + struct in_device *idev, u32 *itag) +{ + int err = fib_validate_source(skb, src, dst, dscp, oif, dev, idev, + itag); + if (err < 0) + return -err; + return SKB_NOT_DROPPED_YET; +} + #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 1db2417b8ff5..1aa31bdb2b31 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -354,7 +354,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4, memset(fl4, 0, sizeof(*fl4)); if (oif) { - fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); + fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index(net, oif); /* Legacy VRF/l3mdev use case */ fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; } @@ -439,7 +439,8 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap); -static inline bool pskb_inet_may_pull(struct sk_buff *skb) +static inline enum skb_drop_reason +pskb_inet_may_pull_reason(struct sk_buff *skb) { int nhlen; @@ -456,16 +457,22 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb) nhlen = 0; } - return pskb_network_may_pull(skb, nhlen); + return pskb_network_may_pull_reason(skb, nhlen); +} + +static inline bool pskb_inet_may_pull(struct sk_buff *skb) +{ + return pskb_inet_may_pull_reason(skb) == SKB_NOT_DROPPED_YET; } /* Variant of pskb_inet_may_pull(). */ -static inline bool skb_vlan_inet_prepare(struct sk_buff *skb, - bool inner_proto_inherit) +static inline enum skb_drop_reason +skb_vlan_inet_prepare(struct sk_buff *skb, bool inner_proto_inherit) { int nhlen = 0, maclen = inner_proto_inherit ? 0 : ETH_HLEN; __be16 type = skb->protocol; + enum skb_drop_reason reason; /* Essentially this is skb_protocol(skb, true) * And we get MAC len. @@ -486,11 +493,13 @@ static inline bool skb_vlan_inet_prepare(struct sk_buff *skb, /* For ETH_P_IPV6/ETH_P_IP we make sure to pull * a base network header in skb->head. */ - if (!pskb_may_pull(skb, maclen + nhlen)) - return false; + reason = pskb_may_pull_reason(skb, maclen + nhlen); + if (reason) + return reason; skb_set_network_header(skb, maclen); - return true; + + return SKB_NOT_DROPPED_YET; } static inline int ip_encap_hlen(struct ip_tunnel_encap *e) @@ -573,7 +582,7 @@ static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, return 0; } -/* Propogate ECN bits out */ +/* Propagate ECN bits out */ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, const struct sk_buff *skb) { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 88a8e554f7a1..248bfb26e2af 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -851,7 +851,7 @@ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int * we should *never* get to this point since that * would mean the addrs are equal * - * However, we do get to it 8) And exacly, when + * However, we do get to it 8) And exactly, when * addresses are equal 8) * * ip route add 1111::/128 via ... @@ -973,7 +973,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); @@ -1365,4 +1365,16 @@ static inline void ip6_sock_set_recvpktinfo(struct sock *sk) release_sock(sk); } +#define IPV6_ADDR_WORDS 4 + +static inline void ipv6_addr_cpu_to_be32(__be32 *dst, const u32 *src) +{ + cpu_to_be32_array(dst, src, IPV6_ADDR_WORDS); +} + +static inline void ipv6_addr_be32_to_cpu(u32 *dst, const __be32 *src) +{ + be32_to_cpu_array(dst, src, IPV6_ADDR_WORDS); +} + #endif /* _NET_IPV6_H */ diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 11cefd50704d..8a3465c8c2c5 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -82,7 +82,7 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly; struct ipv6_bpf_stub { int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags); - struct sock *(*udp6_lib_lookup)(struct net *net, + struct sock *(*udp6_lib_lookup)(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 4d114e6d6d23..dd9e93c12260 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -15,7 +15,7 @@ * To explore any of the IUCV functions, one must first register their * program using iucv_register(). Once your program has successfully * completed a register, it can exploit the other functions. - * For furthur reference on all IUCV functionality, refer to the + * For further reference on all IUCV functionality, refer to the * CP Programming Services book, also available on the web thru * www.vm.ibm.com/pubs, manual # SC24-6084 * diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index b2cf243ebe44..b80e474cb0aa 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -23,7 +23,7 @@ * to handle wireless statistics. * * The initial APIs served us well and has proven a reasonably good design. - * However, there is a few shortcommings : + * However, there are a few shortcomings : * o No events, everything is a request to the driver. * o Large ioctl function in driver with gigantic switch statement * (i.e. spaghetti code). @@ -38,13 +38,13 @@ * ------------------------------- * The new driver API is just a bunch of standard functions (handlers), * each handling a specific Wireless Extension. The driver just export - * the list of handler it supports, and those will be called apropriately. + * the list of handler it supports, and those will be called appropriately. * * I tried to keep the main advantage of the previous API (simplicity, * efficiency and light weight), and also I provide a good dose of backward * compatibility (most structures are the same, driver can use both API * simultaneously, ...). - * Hopefully, I've also addressed the shortcomming of the initial API. + * Hopefully, I've also addressed the shortcoming of the initial API. * * The advantage of the new API are : * o Handling of Extensions in driver broken in small contained functions @@ -84,7 +84,7 @@ /* ---------------------- THE IMPLEMENTATION ---------------------- */ /* - * Some of the choice I've made are pretty controversials. Defining an + * Some of the choice I've made are pretty controversial. Defining an * API is very much weighting compromises. This goes into some of the * details and the thinking behind the implementation. * @@ -140,7 +140,7 @@ * example to distinguish setting max rate and basic rate), I would * break the prototype. Using iwreq_data is more flexible. * 3) Also, the above form is not generic (see above). - * 4) I don't expect driver developper using the wrong field of the + * 4) I don't expect driver developer using the wrong field of the * union (Doh !), so static typechecking doesn't add much value. * 5) Lastly, you can skip the union by doing : * static int mydriver_ioctl_setrate(struct net_device *dev, @@ -279,8 +279,6 @@ #define IW_DESCR_FLAG_RESTRICT 0x0004 /* GET : request is ROOT only */ /* SET : Omit payload from generated iwevent */ #define IW_DESCR_FLAG_NOMAX 0x0008 /* GET : no limit on request size */ -/* Driver level flags */ -#define IW_DESCR_FLAG_WAIT 0x0100 /* Wait for driver event */ /****************************** TYPES ******************************/ @@ -373,11 +371,10 @@ struct iw_handler_def { */ struct iw_ioctl_description { __u8 header_type; /* NULL, iw_point or other */ - __u8 token_type; /* Future */ + __u8 flags; /* Special handling of the request */ __u16 token_size; /* Granularity of payload */ __u16 min_tokens; /* Min acceptable token number */ __u16 max_tokens; /* Max acceptable token number */ - __u32 flags; /* Special handling of the request */ }; /* Need to think of short header translation table. Later. */ @@ -404,26 +401,6 @@ struct iw_spy_data { u_char spy_thr_under[IW_MAX_SPY]; }; -/* --------------------- DEVICE WIRELESS DATA --------------------- */ -/* - * This is all the wireless data specific to a device instance that - * is managed by the core of Wireless Extensions or the 802.11 layer. - * We only keep pointer to those structures, so that a driver is free - * to share them between instances. - * This structure should be initialised before registering the device. - * Access to this data follow the same rules as any other struct net_device - * data (i.e. valid as long as struct net_device exist, same locking rules). - */ -/* Forward declaration */ -struct libipw_device; -/* The struct */ -struct iw_public_data { - /* Driver enhanced spy support */ - struct iw_spy_data * spy_data; - /* Legacy structure managed by the ipw2x00-specific IEEE 802.11 layer */ - struct libipw_device * libipw; -}; - /**************************** PROTOTYPES ****************************/ /* * Functions part of the Wireless Extensions (defined in net/wireless/wext-core.c). @@ -443,23 +420,7 @@ static inline void wireless_nlevent_flush(void) {} /* We may need a function to send a stream of events to user space. * More on that later... */ -/* Standard handler for SIOCSIWSPY */ -int iw_handler_set_spy(struct net_device *dev, struct iw_request_info *info, - union iwreq_data *wrqu, char *extra); -/* Standard handler for SIOCGIWSPY */ -int iw_handler_get_spy(struct net_device *dev, struct iw_request_info *info, - union iwreq_data *wrqu, char *extra); -/* Standard handler for SIOCSIWTHRSPY */ -int iw_handler_set_thrspy(struct net_device *dev, struct iw_request_info *info, - union iwreq_data *wrqu, char *extra); -/* Standard handler for SIOCGIWTHRSPY */ -int iw_handler_get_thrspy(struct net_device *dev, struct iw_request_info *info, - union iwreq_data *wrqu, char *extra); -/* Driver call to update spy records */ -void wireless_spy_update(struct net_device *dev, unsigned char *address, - struct iw_quality *wstats); - -/************************* INLINE FUNTIONS *************************/ +/************************* INLINE FUNCTIONS *************************/ /* * Function that are so simple that it's more efficient inlining them */ diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 031c661aa14d..2d6141f28b53 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -78,7 +78,7 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) struct net_device *dev; int rc = 0; - if (likely(ifindex)) { + if (ifindex) { rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); diff --git a/include/net/lapb.h b/include/net/lapb.h index 124ee122f2c8..6c07420644e4 100644 --- a/include/net/lapb.h +++ b/include/net/lapb.h @@ -4,7 +4,7 @@ #include <linux/lapb.h> #include <linux/refcount.h> -#define LAPB_HEADER_LEN 20 /* LAPB over Ethernet + a bit more */ +#define LAPB_HEADER_LEN MAX_HEADER /* LAPB over Ethernet + a bit more */ #define LAPB_ACK_PENDING_CONDITION 0x01 #define LAPB_REJECT_CONDITION 0x02 diff --git a/include/net/lib80211.h b/include/net/lib80211.h deleted file mode 100644 index 8b47d3a51cf8..000000000000 --- a/include/net/lib80211.h +++ /dev/null @@ -1,122 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * lib80211.h -- common bits for IEEE802.11 wireless drivers - * - * Copyright (c) 2008, John W. Linville <linville@tuxdriver.com> - * - * Some bits copied from old ieee80211 component, w/ original copyright - * notices below: - * - * Original code based on Host AP (software wireless LAN access point) driver - * for Intersil Prism2/2.5/3. - * - * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen - * <j@w1.fi> - * Copyright (c) 2002-2003, Jouni Malinen <j@w1.fi> - * - * Adaption to a generic IEEE 802.11 stack by James Ketrenos - * <jketreno@linux.intel.com> - * - * Copyright (c) 2004, Intel Corporation - * - */ - -#ifndef LIB80211_H -#define LIB80211_H - -#include <linux/types.h> -#include <linux/list.h> -#include <linux/atomic.h> -#include <linux/if.h> -#include <linux/skbuff.h> -#include <linux/ieee80211.h> -#include <linux/timer.h> -#include <linux/seq_file.h> - -#define NUM_WEP_KEYS 4 - -enum { - IEEE80211_CRYPTO_TKIP_COUNTERMEASURES = (1 << 0), -}; - -struct module; - -struct lib80211_crypto_ops { - const char *name; - struct list_head list; - - /* init new crypto context (e.g., allocate private data space, - * select IV, etc.); returns NULL on failure or pointer to allocated - * private data on success */ - void *(*init) (int keyidx); - - /* deinitialize crypto context and free allocated private data */ - void (*deinit) (void *priv); - - /* encrypt/decrypt return < 0 on error or >= 0 on success. The return - * value from decrypt_mpdu is passed as the keyidx value for - * decrypt_msdu. skb must have enough head and tail room for the - * encryption; if not, error will be returned; these functions are - * called for all MPDUs (i.e., fragments). - */ - int (*encrypt_mpdu) (struct sk_buff * skb, int hdr_len, void *priv); - int (*decrypt_mpdu) (struct sk_buff * skb, int hdr_len, void *priv); - - /* These functions are called for full MSDUs, i.e. full frames. - * These can be NULL if full MSDU operations are not needed. */ - int (*encrypt_msdu) (struct sk_buff * skb, int hdr_len, void *priv); - int (*decrypt_msdu) (struct sk_buff * skb, int keyidx, int hdr_len, - void *priv); - - int (*set_key) (void *key, int len, u8 * seq, void *priv); - int (*get_key) (void *key, int len, u8 * seq, void *priv); - - /* procfs handler for printing out key information and possible - * statistics */ - void (*print_stats) (struct seq_file *m, void *priv); - - /* Crypto specific flag get/set for configuration settings */ - unsigned long (*get_flags) (void *priv); - unsigned long (*set_flags) (unsigned long flags, void *priv); - - /* maximum number of bytes added by encryption; encrypt buf is - * allocated with extra_prefix_len bytes, copy of in_buf, and - * extra_postfix_len; encrypt need not use all this space, but - * the result must start at the beginning of the buffer and correct - * length must be returned */ - int extra_mpdu_prefix_len, extra_mpdu_postfix_len; - int extra_msdu_prefix_len, extra_msdu_postfix_len; - - struct module *owner; -}; - -struct lib80211_crypt_data { - struct list_head list; /* delayed deletion list */ - struct lib80211_crypto_ops *ops; - void *priv; - atomic_t refcnt; -}; - -struct lib80211_crypt_info { - char *name; - /* Most clients will already have a lock, - so just point to that. */ - spinlock_t *lock; - - struct lib80211_crypt_data *crypt[NUM_WEP_KEYS]; - int tx_keyidx; /* default TX key index (crypt[tx_keyidx]) */ - struct list_head crypt_deinit_list; - struct timer_list crypt_deinit_timer; - int crypt_quiesced; -}; - -int lib80211_crypt_info_init(struct lib80211_crypt_info *info, char *name, - spinlock_t *lock); -void lib80211_crypt_info_free(struct lib80211_crypt_info *info); -int lib80211_register_crypto_ops(struct lib80211_crypto_ops *ops); -int lib80211_unregister_crypto_ops(struct lib80211_crypto_ops *ops); -struct lib80211_crypto_ops *lib80211_get_crypto_ops(const char *name); -void lib80211_crypt_delayed_deinit(struct lib80211_crypt_info *info, - struct lib80211_crypt_data **crypt); - -#endif /* LIB80211_H */ diff --git a/include/net/libeth/tx.h b/include/net/libeth/tx.h new file mode 100644 index 000000000000..35614f9523f6 --- /dev/null +++ b/include/net/libeth/tx.h @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBETH_TX_H +#define __LIBETH_TX_H + +#include <linux/skbuff.h> + +#include <net/libeth/types.h> + +/* Tx buffer completion */ + +/** + * enum libeth_sqe_type - type of &libeth_sqe to act on Tx completion + * @LIBETH_SQE_EMPTY: unused/empty, no action required + * @LIBETH_SQE_CTX: context descriptor with empty SQE, no action required + * @LIBETH_SQE_SLAB: kmalloc-allocated buffer, unmap and kfree() + * @LIBETH_SQE_FRAG: mapped skb frag, only unmap DMA + * @LIBETH_SQE_SKB: &sk_buff, unmap and napi_consume_skb(), update stats + */ +enum libeth_sqe_type { + LIBETH_SQE_EMPTY = 0U, + LIBETH_SQE_CTX, + LIBETH_SQE_SLAB, + LIBETH_SQE_FRAG, + LIBETH_SQE_SKB, +}; + +/** + * struct libeth_sqe - represents a Send Queue Element / Tx buffer + * @type: type of the buffer, see the enum above + * @rs_idx: index of the last buffer from the batch this one was sent in + * @raw: slab buffer to free via kfree() + * @skb: &sk_buff to consume + * @dma: DMA address to unmap + * @len: length of the mapped region to unmap + * @nr_frags: number of frags in the frame this buffer belongs to + * @packets: number of physical packets sent for this frame + * @bytes: number of physical bytes sent for this frame + * @priv: driver-private scratchpad + */ +struct libeth_sqe { + enum libeth_sqe_type type:32; + u32 rs_idx; + + union { + void *raw; + struct sk_buff *skb; + }; + + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + + u32 nr_frags; + u32 packets; + u32 bytes; + + unsigned long priv; +} __aligned_largest; + +/** + * LIBETH_SQE_CHECK_PRIV - check the driver's private SQE data + * @p: type or name of the object the driver wants to fit into &libeth_sqe + * + * Make sure the driver's private data fits into libeth_sqe::priv. To be used + * right after its declaration. + */ +#define LIBETH_SQE_CHECK_PRIV(p) \ + static_assert(sizeof(p) <= sizeof_field(struct libeth_sqe, priv)) + +/** + * struct libeth_cq_pp - completion queue poll params + * @dev: &device to perform DMA unmapping + * @ss: onstack NAPI stats to fill + * @napi: whether it's called from the NAPI context + * + * libeth uses this structure to access objects needed for performing full + * Tx complete operation without passing lots of arguments and change the + * prototypes each time a new one is added. + */ +struct libeth_cq_pp { + struct device *dev; + struct libeth_sq_napi_stats *ss; + + bool napi; +}; + +/** + * libeth_tx_complete - perform Tx completion for one SQE + * @sqe: SQE to complete + * @cp: poll params + * + * Do Tx complete for all the types of buffers, incl. freeing, unmapping, + * updating the stats etc. + */ +static inline void libeth_tx_complete(struct libeth_sqe *sqe, + const struct libeth_cq_pp *cp) +{ + switch (sqe->type) { + case LIBETH_SQE_EMPTY: + return; + case LIBETH_SQE_SKB: + case LIBETH_SQE_FRAG: + case LIBETH_SQE_SLAB: + dma_unmap_page(cp->dev, dma_unmap_addr(sqe, dma), + dma_unmap_len(sqe, len), DMA_TO_DEVICE); + break; + default: + break; + } + + switch (sqe->type) { + case LIBETH_SQE_SKB: + cp->ss->packets += sqe->packets; + cp->ss->bytes += sqe->bytes; + + napi_consume_skb(sqe->skb, cp->napi); + break; + case LIBETH_SQE_SLAB: + kfree(sqe->raw); + break; + default: + break; + } + + sqe->type = LIBETH_SQE_EMPTY; +} + +#endif /* __LIBETH_TX_H */ diff --git a/include/net/libeth/types.h b/include/net/libeth/types.h new file mode 100644 index 000000000000..603825e45133 --- /dev/null +++ b/include/net/libeth/types.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBETH_TYPES_H +#define __LIBETH_TYPES_H + +#include <linux/types.h> + +/** + * struct libeth_sq_napi_stats - "hot" counters to update in Tx completion loop + * @packets: completed frames counter + * @bytes: sum of bytes of completed frames above + * @raw: alias to access all the fields as an array + */ +struct libeth_sq_napi_stats { + union { + struct { + u32 packets; + u32 bytes; + }; + DECLARE_FLEX_ARRAY(u32, raw); + }; +}; + +#endif /* __LIBETH_TYPES_H */ diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 1d55ba7c45be..86681f29bda7 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -254,7 +254,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, } /** - * llc_pdu_decode_sa - extracs source address (MAC) of input frame + * llc_pdu_decode_sa - extracts, source address (MAC) of input frame * @skb: input skb that source address must be extracted from it. * @sa: pointer to source address (6 byte array). * diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 0a04eaf5343c..ab8dce1f2c27 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -22,7 +22,7 @@ #include <net/cfg80211.h> #include <net/codel.h> #include <net/ieee80211_radiotap.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * DOC: Introduction @@ -213,7 +213,7 @@ struct ieee80211_low_level_stats { * @IEEE80211_CHANCTX_CHANGE_RADAR: radar detection flag changed * @IEEE80211_CHANCTX_CHANGE_CHANNEL: switched to another operating channel, * this is used only with channel switching with CSA - * @IEEE80211_CHANCTX_CHANGE_MIN_WIDTH: The min required channel width changed + * @IEEE80211_CHANCTX_CHANGE_MIN_DEF: The min chandef changed * @IEEE80211_CHANCTX_CHANGE_AP: The AP channel definition changed, so (wider * bandwidth) OFDMA settings need to be changed * @IEEE80211_CHANCTX_CHANGE_PUNCTURING: The punctured channel(s) bitmap @@ -224,7 +224,7 @@ enum ieee80211_chanctx_change { IEEE80211_CHANCTX_CHANGE_RX_CHAINS = BIT(1), IEEE80211_CHANCTX_CHANGE_RADAR = BIT(2), IEEE80211_CHANCTX_CHANGE_CHANNEL = BIT(3), - IEEE80211_CHANCTX_CHANGE_MIN_WIDTH = BIT(4), + IEEE80211_CHANCTX_CHANGE_MIN_DEF = BIT(4), IEEE80211_CHANCTX_CHANGE_AP = BIT(5), IEEE80211_CHANCTX_CHANGE_PUNCTURING = BIT(6), }; @@ -740,6 +740,19 @@ struct ieee80211_parsed_tpe { * @eht_80mhz_full_bw_ul_mumimo: in AP-mode, does this BSS support the * reception of an EHT TB PPDU on an RU that spans the entire PPDU * bandwidth + * @bss_param_ch_cnt: in BSS-mode, the BSS params change count. This + * information is the latest known value. It can come from this link's + * beacon or from a beacon sent by another link. + * @bss_param_ch_cnt_link_id: in BSS-mode, the link_id to which the beacon + * that updated &bss_param_ch_cnt belongs. E.g. if link 1 doesn't hear + * its beacons, and link 2 sent a beacon with an RNR element that updated + * link 1's BSS params change count, then, link 1's + * bss_param_ch_cnt_link_id will be 2. That means that link 1 knows that + * link 2 was the link that updated its bss_param_ch_cnt value. + * In case link 1 hears its beacon again, bss_param_ch_cnt_link_id will + * be updated to 1, even if bss_param_ch_cnt didn't change. This allows + * the link to know that it heard the latest value from its own beacon + * (as opposed to hearing its value from another link's beacon). */ struct ieee80211_bss_conf { struct ieee80211_vif *vif; @@ -834,6 +847,8 @@ struct ieee80211_bss_conf { bool eht_su_beamformee; bool eht_mu_beamformer; bool eht_80mhz_full_bw_ul_mumimo; + u8 bss_param_ch_cnt; + u8 bss_param_ch_cnt_link_id; }; /** @@ -994,8 +1009,9 @@ enum mac80211_tx_info_flags { * of their QoS TID or other priority field values. * @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally * for sequence number assignment - * @IEEE80211_TX_CTRL_SCAN_TX: Indicates that this frame is transmitted - * due to scanning, not in normal operation on the interface. + * @IEEE80211_TX_CTRL_DONT_USE_RATE_MASK: Don't use rate mask for this frame + * which is transmitted due to scanning or offchannel TX, not in normal + * operation on the interface. * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this * frame should be transmitted on the specific link. This really is * only relevant for frames that do not have data present, and is @@ -1016,7 +1032,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX = BIT(9), - IEEE80211_TX_CTRL_SCAN_TX = BIT(10), + IEEE80211_TX_CTRL_DONT_USE_RATE_MASK = BIT(10), IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000, }; @@ -1447,8 +1463,6 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_AMPDU_IS_LAST: this subframe is the last subframe of the A-MPDU * @RX_FLAG_AMPDU_DELIM_CRC_ERROR: A delimiter CRC error has been detected * on this subframe - * @RX_FLAG_AMPDU_DELIM_CRC_KNOWN: The delimiter CRC field is known (the CRC - * is stored in the @ampdu_delimiter_crc field) * @RX_FLAG_MIC_STRIPPED: The mic was stripped of this packet. Decryption was * done by the hardware * @RX_FLAG_ONLY_MONITOR: Report frame only to monitor interfaces without @@ -1520,7 +1534,7 @@ enum mac80211_rx_flags { RX_FLAG_AMPDU_LAST_KNOWN = BIT(12), RX_FLAG_AMPDU_IS_LAST = BIT(13), RX_FLAG_AMPDU_DELIM_CRC_ERROR = BIT(14), - RX_FLAG_AMPDU_DELIM_CRC_KNOWN = BIT(15), + /* one free bit at 15 */ RX_FLAG_MACTIME = BIT(16) | BIT(17), RX_FLAG_MACTIME_PLCP_START = 1 << 16, RX_FLAG_MACTIME_START = 2 << 16, @@ -1617,7 +1631,6 @@ enum mac80211_rx_encoding { * @rx_flags: internal RX flags for mac80211 * @ampdu_reference: A-MPDU reference number, must be a different value for * each A-MPDU but the same for each subframe within one A-MPDU - * @ampdu_delimiter_crc: A-MPDU delimiter CRC * @zero_length_psdu_type: radiotap type of the 0-length PSDU * @link_valid: if the link which is identified by @link_id is valid. This flag * is set only when connection is MLO. @@ -1655,7 +1668,6 @@ struct ieee80211_rx_status { s8 signal; u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; - u8 ampdu_delimiter_crc; u8 zero_length_psdu_type; u8 link_valid:1, link_id:4; }; @@ -1975,6 +1987,8 @@ enum ieee80211_neg_ttlm_res { * @neg_ttlm: negotiated TID to link mapping info. * see &struct ieee80211_neg_ttlm. * @addr: address of this interface + * @addr_valid: indicates if the address is actively used. Set to false for + * passive monitor interfaces, true in all other cases. * @p2p: indicates whether this AP or STA interface is a p2p * interface, i.e. a GO or p2p-sta respectively * @netdev_features: tx netdev features supported by the hardware for this @@ -2014,6 +2028,7 @@ struct ieee80211_vif { u16 valid_links, active_links, dormant_links, suspended_links; struct ieee80211_neg_ttlm neg_ttlm; u8 addr[ETH_ALEN] __aligned(2); + bool addr_valid; bool p2p; u8 cab_queue; @@ -2487,7 +2502,7 @@ struct ieee80211_link_sta { * @spp_amsdu: indicates whether the STA uses SPP A-MSDU or not. */ struct ieee80211_sta { - u8 addr[ETH_ALEN]; + u8 addr[ETH_ALEN] __aligned(2); u16 aid; u16 max_rx_aggregation_subframes; bool wme; @@ -2682,6 +2697,11 @@ struct ieee80211_txq { * a virtual monitor interface when monitor interfaces are the only * active interfaces. * + * @IEEE80211_HW_NO_VIRTUAL_MONITOR: The driver would like to be informed + * of any monitor interface, as well as their configured channel. + * This is useful for supporting multiple monitor interfaces on different + * channels. + * * @IEEE80211_HW_NO_AUTO_VIF: The driver would like for no wlanX to * be created. It is expected user-space will create vifs as * desired (and thus have them named as desired). @@ -2841,6 +2861,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_DYNAMIC_PS, IEEE80211_HW_MFP_CAPABLE, IEEE80211_HW_WANT_MONITOR_VIF, + IEEE80211_HW_NO_VIRTUAL_MONITOR, IEEE80211_HW_NO_AUTO_VIF, IEEE80211_HW_SW_CRYPTO_CONTROL, IEEE80211_HW_SUPPORT_FAST_XMIT, @@ -3181,6 +3202,19 @@ ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw, void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); /** + * ieee80211_purge_tx_queue - purge TX skb queue + * @hw: the hardware + * @skbs: the skbs + * + * Free a set of transmit skbs. Use this function when device is going to stop + * but some transmit skbs without TX status are still queued. + * This function does not take the list lock and the caller must hold the + * relevant locks to use it. + */ +void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, + struct sk_buff_head *skbs); + +/** * DOC: Hardware crypto acceleration * * mac80211 is capable of taking advantage of many hardware @@ -4061,8 +4095,8 @@ struct ieee80211_prep_tx_info { * in @sta_state. * The callback can sleep. * - * @sta_rc_update: Notifies the driver of changes to the bitrates that can be - * used to transmit to the station. The changes are advertised with bits + * @link_sta_rc_update: Notifies the driver of changes to the bitrates that can + * be used to transmit to the station. The changes are advertised with bits * from &enum ieee80211_rate_control_changed and the values are reflected * in the station data. This callback should only be used when the driver * uses hardware rate control (%IEEE80211_HW_HAS_RATE_CONTROL) since @@ -4430,6 +4464,12 @@ struct ieee80211_prep_tx_info { * if the requested TID-To-Link mapping can be accepted or not. * If it's not accepted the driver may suggest a preferred mapping and * modify @ttlm parameter with the suggested TID-to-Link mapping. + * @prep_add_interface: prepare for interface addition. This can be used by + * drivers to prepare for the addition of a new interface, e.g., allocate + * the needed resources etc. This callback doesn't guarantee that an + * interface with the specified type would be added, and thus drivers that + * implement this callback need to handle such cases. The type is the full + * &enum nl80211_iftype. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4546,10 +4586,10 @@ struct ieee80211_ops { void (*sta_pre_rcu_remove)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); - void (*sta_rc_update)(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta, - u32 changed); + void (*link_sta_rc_update)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_link_sta *link_sta, + u32 changed); void (*sta_rate_tbl_update)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); @@ -4814,6 +4854,8 @@ struct ieee80211_ops { enum ieee80211_neg_ttlm_res (*can_neg_ttlm)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_neg_ttlm *ttlm); + void (*prep_add_interface)(struct ieee80211_hw *hw, + enum nl80211_iftype type); }; /** @@ -6242,6 +6284,24 @@ void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw, void (*iterator)(void *data, struct ieee80211_sta *sta), void *data); + +/** + * ieee80211_iterate_stations_mtx - iterate stations + * + * This function iterates over all stations associated with a given + * hardware that are currently uploaded to the driver and calls the callback + * function for them. This version can only be used while holding the wiphy + * mutex. + * + * @hw: the hardware struct of which the interfaces should be iterated over + * @iterator: the iterator function to call + * @data: first argument of the iterator function + */ +void ieee80211_iterate_stations_mtx(struct ieee80211_hw *hw, + void (*iterator)(void *data, + struct ieee80211_sta *sta), + void *data); + /** * ieee80211_queue_work - add work onto the mac80211 workqueue * @@ -6716,8 +6776,11 @@ void ieee80211_cqm_beacon_loss_notify(struct ieee80211_vif *vif, gfp_t gfp); * ieee80211_radar_detected - inform that a radar was detected * * @hw: pointer as obtained from ieee80211_alloc_hw() + * @chanctx_conf: Channel context on which radar is detected. Mandatory to + * pass a valid pointer during MLO. For non-MLO %NULL can be passed */ -void ieee80211_radar_detected(struct ieee80211_hw *hw); +void ieee80211_radar_detected(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *chanctx_conf); /** * ieee80211_chswitch_done - Complete channel switch process @@ -6735,14 +6798,12 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success, /** * ieee80211_channel_switch_disconnect - disconnect due to channel switch error * @vif: &struct ieee80211_vif pointer from the add_interface callback. - * @block_tx: if %true, do not send deauth frame. * * Instruct mac80211 to disconnect due to a channel switch error. The channel * switch can request to block the tx and so, we need to make sure we do not send * a deauth frame in this case. */ -void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, - bool block_tx); +void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif); /** * ieee80211_request_smps - request SM PS transition @@ -7612,12 +7673,12 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb) * * - change_vif_links(0x11) * - unassign_vif_chanctx(link_id=0) + * - assign_vif_chanctx(link_id=4) * - change_sta_links(0x11) for each affected STA (the AP) * (TDLS connections on now inactive links should be torn down) * - remove group keys on the old link (link_id 0) * - add new group keys (GTK/IGTK/BIGTK) on the new link (link_id 4) * - change_sta_links(0x10) for each affected STA (the AP) - * - assign_vif_chanctx(link_id=4) * - change_vif_links(0x10) * * Return: 0 on success. An error code otherwise. @@ -7646,6 +7707,33 @@ void ieee80211_set_active_links_async(struct ieee80211_vif *vif, */ void ieee80211_send_teardown_neg_ttlm(struct ieee80211_vif *vif); +/** + * ieee80211_chan_width_to_rx_bw - convert channel width to STA RX bandwidth + * @width: the channel width value to convert + * Return: the STA RX bandwidth value for the channel width + */ +static inline enum ieee80211_sta_rx_bandwidth +ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width) +{ + switch (width) { + default: + WARN_ON_ONCE(1); + fallthrough; + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + return IEEE80211_STA_RX_BW_20; + case NL80211_CHAN_WIDTH_40: + return IEEE80211_STA_RX_BW_40; + case NL80211_CHAN_WIDTH_80: + return IEEE80211_STA_RX_BW_80; + case NL80211_CHAN_WIDTH_160: + case NL80211_CHAN_WIDTH_80P80: + return IEEE80211_STA_RX_BW_160; + case NL80211_CHAN_WIDTH_320: + return IEEE80211_STA_RX_BW_320; + } +} + /* for older drivers - let's not document these ... */ int ieee80211_emulate_add_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx); diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 4a3a9de9da73..d72006a85f02 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -7,7 +7,7 @@ #ifndef NET_MAC802154_H #define NET_MAC802154_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/af_ieee802154.h> #include <linux/ieee802154.h> #include <linux/skbuff.h> @@ -140,7 +140,7 @@ enum ieee802154_hw_flags { * * xmit_sync: * Handler that 802.15.4 module calls for each transmitted frame. - * skb cntains the buffer starting from the IEEE 802.15.4 header. + * skb contains the buffer starting from the IEEE 802.15.4 header. * The low-level driver should send the frame based on available * configuration. This is called by a workqueue and useful for * synchronous 802.15.4 drivers. @@ -152,7 +152,7 @@ enum ieee802154_hw_flags { * * xmit_async: * Handler that 802.15.4 module calls for each transmitted frame. - * skb cntains the buffer starting from the IEEE 802.15.4 header. + * skb contains the buffer starting from the IEEE 802.15.4 header. * The low-level driver should send the frame based on available * configuration. * This function should return zero or negative errno. diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index de47fa533b15..90f56656b572 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -267,7 +267,8 @@ struct gdma_event { struct gdma_queue; struct mana_eq { - struct gdma_queue *eq; + struct gdma_queue *eq; + struct dentry *mana_eq_debugfs; }; typedef void gdma_eq_callback(void *context, struct gdma_queue *q, @@ -365,6 +366,7 @@ struct gdma_irq_context { struct gdma_context { struct device *dev; + struct dentry *mana_pci_debugfs; /* Per-vPort max number of queues */ unsigned int max_num_queues; @@ -878,5 +880,7 @@ int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, u32 resp_len, void *resp); int mana_gd_destroy_dma_region(struct gdma_context *gc, u64 dma_region_handle); +void mana_register_debugfs(void); +void mana_unregister_debugfs(void); #endif /* _GDMA_H */ diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 7caa334f4888..0d00b24eacaf 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -38,9 +38,21 @@ enum TRI_STATE { #define COMP_ENTRY_SIZE 64 -#define RX_BUFFERS_PER_QUEUE 512 +/* This Max value for RX buffers is derived from __alloc_page()'s max page + * allocation calculation. It allows maximum 2^(MAX_ORDER -1) pages. RX buffer + * size beyond this value gets rejected by __alloc_page() call. + */ +#define MAX_RX_BUFFERS_PER_QUEUE 8192 +#define DEF_RX_BUFFERS_PER_QUEUE 1024 +#define MIN_RX_BUFFERS_PER_QUEUE 128 -#define MAX_SEND_BUFFERS_PER_QUEUE 256 +/* This max value for TX buffers is derived as the maximum allocatable + * pages supported on host per guest through testing. TX buffer size beyond + * this value is rejected by the hardware. + */ +#define MAX_TX_BUFFERS_PER_QUEUE 16384 +#define DEF_TX_BUFFERS_PER_QUEUE 256 +#define MIN_TX_BUFFERS_PER_QUEUE 128 #define EQ_SIZE (8 * MANA_PAGE_SIZE) @@ -98,6 +110,8 @@ struct mana_txq { atomic_t pending_sends; + bool napi_initialized; + struct mana_stats_tx stats; }; @@ -286,7 +300,7 @@ struct mana_recv_buf_oob { void *buf_va; bool from_pool; /* allocated from a page pool */ - /* SGL of the buffer going to be sent has part of the work request. */ + /* SGL of the buffer going to be sent as part of the work request. */ u32 num_sge; struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES]; @@ -336,6 +350,7 @@ struct mana_rxq { int xdp_rc; /* XDP redirect return code */ struct page_pool *page_pool; + struct dentry *mana_rx_debugfs; /* MUST BE THE LAST MEMBER: * Each receive buffer has an associated mana_recv_buf_oob. @@ -349,6 +364,8 @@ struct mana_tx_qp { struct mana_cq tx_cq; mana_handle_t tx_object; + + struct dentry *mana_tx_debugfs; }; struct mana_ethtool_stats { @@ -393,6 +410,7 @@ struct mana_context { u16 num_ports; struct mana_eq *eqs; + struct dentry *mana_eqs_debugfs; struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; }; @@ -438,6 +456,9 @@ struct mana_port_context { unsigned int max_queues; unsigned int num_queues; + unsigned int rx_queue_size; + unsigned int tx_queue_size; + mana_handle_t port_handle; mana_handle_t pf_filter_handle; @@ -451,6 +472,9 @@ struct mana_port_context { bool port_st_save; /* Saved port state */ struct mana_ethtool_stats eth_stats; + + /* Debugfs */ + struct dentry *mana_port_debugfs; }; netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); @@ -473,8 +497,11 @@ struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); void mana_query_gf_stats(struct mana_port_context *apc); +int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues); +void mana_pre_dealloc_rxbufs(struct mana_port_context *apc); extern const struct ethtool_ops mana_ethtool_ops; +extern struct dentry *mana_debugfs_root; /* A CQ can be created not associated with any EQ */ #define GDMA_CQ_NO_EQ 0xffff diff --git a/include/net/mctp.h b/include/net/mctp.h index 7b17c52e8ce2..1ecbff7116f6 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -295,7 +295,25 @@ void mctp_neigh_remove_dev(struct mctp_dev *mdev); int mctp_routes_init(void); void mctp_routes_exit(void); -void mctp_device_init(void); +int mctp_device_init(void); void mctp_device_exit(void); +/* MCTP IDs and Codes from DMTF specification + * "DSP0239 Management Component Transport Protocol (MCTP) IDs and Codes" + * https://www.dmtf.org/sites/default/files/standards/documents/DSP0239_1.11.1.pdf + */ +enum mctp_phys_binding { + MCTP_PHYS_BINDING_UNSPEC = 0x00, + MCTP_PHYS_BINDING_SMBUS = 0x01, + MCTP_PHYS_BINDING_PCIE_VDM = 0x02, + MCTP_PHYS_BINDING_USB = 0x03, + MCTP_PHYS_BINDING_KCS = 0x04, + MCTP_PHYS_BINDING_SERIAL = 0x05, + MCTP_PHYS_BINDING_I3C = 0x06, + MCTP_PHYS_BINDING_MMBI = 0x07, + MCTP_PHYS_BINDING_PCC = 0x08, + MCTP_PHYS_BINDING_UCIE = 0x09, + MCTP_PHYS_BINDING_VENDOR = 0xFF, +}; + #endif /* __NET_MCTP_H */ diff --git a/include/net/mctpdevice.h b/include/net/mctpdevice.h index 5c0d04b5c12c..957d9ef924c5 100644 --- a/include/net/mctpdevice.h +++ b/include/net/mctpdevice.h @@ -22,6 +22,7 @@ struct mctp_dev { refcount_t refs; unsigned int net; + enum mctp_phys_binding binding; const struct mctp_netdev_ops *ops; @@ -44,7 +45,8 @@ struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev); struct mctp_dev *__mctp_dev_get(const struct net_device *dev); int mctp_register_netdev(struct net_device *dev, - const struct mctp_netdev_ops *ops); + const struct mctp_netdev_ops *ops, + enum mctp_phys_binding binding); void mctp_unregister_netdev(struct net_device *dev); void mctp_dev_hold(struct mctp_dev *mdev); diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 0bc4ab03f487..814b5f2e3ed5 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -223,6 +223,8 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb) return htonl(0u); } + +void mptcp_active_detect_blackhole(struct sock *sk, bool expired); #else static inline void mptcp_init(void) @@ -307,6 +309,8 @@ static inline struct request_sock *mptcp_subflow_reqsk_alloc(const struct reques } static inline __be32 mptcp_reset_option(const struct sk_buff *skb) { return htonl(0u); } + +static inline void mptcp_active_detect_blackhole(struct sock *sk, bool expired) { } #endif /* CONFIG_MPTCP */ #if IS_ENABLED(CONFIG_MPTCP_IPV6) diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 7a533d5b1d59..3c88d5bc5eed 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -147,11 +147,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * - * int (*is_useropt)(u8 nd_opt_type): - * This function is called when IPv6 decide RA userspace options. if - * this function returns 1 then the option given by nd_opt_type will - * be handled as userspace option additional to the IPv6 options. - * * int (*parse_options)(const struct net_device *dev, * struct nd_opt_hdr *nd_opt, * struct ndisc_options *ndopts): @@ -200,7 +195,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, * addresses. E.g. 802.15.4 6LoWPAN. */ struct ndisc_ops { - int (*is_useropt)(u8 nd_opt_type); int (*parse_options)(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts); @@ -224,15 +218,6 @@ struct ndisc_ops { }; #if IS_ENABLED(CONFIG_IPV6) -static inline int ndisc_ops_is_useropt(const struct net_device *dev, - u8 nd_opt_type) -{ - if (dev->ndisc_ops && dev->ndisc_ops->is_useropt) - return dev->ndisc_ops->is_useropt(nd_opt_type); - else - return 0; -} - static inline int ndisc_ops_parse_options(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index a44f262a7384..9a832cab5b1d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -29,6 +29,7 @@ #include <linux/sysctl.h> #include <linux/workqueue.h> #include <net/rtnetlink.h> +#include <net/neighbour_tables.h> /* * NUD stands for "neighbor unreachability detection" @@ -135,7 +136,8 @@ struct neigh_statistics { #define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field) struct neighbour { - struct neighbour __rcu *next; + struct hlist_node hash; + struct hlist_node dev_list; struct neigh_table *tbl; struct neigh_parms *parms; unsigned long confirmed; @@ -190,7 +192,7 @@ struct pneigh_entry { #define NEIGH_NUM_HASH_RND 4 struct neigh_hash_table { - struct neighbour __rcu **hash_buckets; + struct hlist_head *hash_heads; unsigned int hash_shift; __u32 hash_rnd[NEIGH_NUM_HASH_RND]; struct rcu_head rcu; @@ -236,14 +238,6 @@ struct neigh_table { struct pneigh_entry **phash_buckets; }; -enum { - NEIGH_ARP_TABLE = 0, - NEIGH_ND_TABLE = 1, - NEIGH_DN_TABLE = 2, - NEIGH_NR_TABLES, - NEIGH_LINK_TABLE = NEIGH_NR_TABLES /* Pseudo table for neigh_xmit */ -}; - static inline int neigh_parms_family(struct neigh_parms *p) { return p->tbl->family; @@ -276,6 +270,12 @@ static inline void *neighbour_priv(const struct neighbour *n) extern const struct nla_policy nda_policy[]; +#define neigh_for_each_in_bucket(pos, head) hlist_for_each_entry(pos, head, hash) +#define neigh_for_each_in_bucket_rcu(pos, head) \ + hlist_for_each_entry_rcu(pos, head, hash) +#define neigh_for_each_in_bucket_safe(pos, tmp, head) \ + hlist_for_each_entry_safe(pos, tmp, head, hash) + static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) { return *(const u32 *)n->primary_key == *(const u32 *)pkey; @@ -304,12 +304,9 @@ static inline struct neighbour *___neigh_lookup_noref( u32 hash_val; hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); - for (n = rcu_dereference(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference(n->next)) { + neigh_for_each_in_bucket_rcu(n, &nht->hash_heads[hash_val]) if (n->dev == dev && key_eq(n, pkey)) return n; - } return NULL; } @@ -350,7 +347,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); -bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl); +bool neigh_remove_one(struct neighbour *ndel); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev); diff --git a/include/net/neighbour_tables.h b/include/net/neighbour_tables.h new file mode 100644 index 000000000000..bcffbe8f7601 --- /dev/null +++ b/include/net/neighbour_tables.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NET_NEIGHBOUR_TABLES_H +#define _NET_NEIGHBOUR_TABLES_H + +enum { + NEIGH_ARP_TABLE = 0, + NEIGH_ND_TABLE = 1, + NEIGH_NR_TABLES, + NEIGH_LINK_TABLE = NEIGH_NR_TABLES /* Pseudo table for neigh_xmit */ +}; + +#endif diff --git a/include/net/net_debug.h b/include/net/net_debug.h index 1e74684cbbdb..47f7a4a878b9 100644 --- a/include/net/net_debug.h +++ b/include/net/net_debug.h @@ -27,7 +27,7 @@ void netdev_info(const struct net_device *dev, const char *format, ...); #define netdev_level_once(level, dev, fmt, ...) \ do { \ - static bool __section(".data.once") __print_once; \ + static bool __section(".data..once") __print_once; \ \ if (!__print_once) { \ __print_once = true; \ @@ -149,9 +149,11 @@ do { \ #if defined(CONFIG_DEBUG_NET) -#define DEBUG_NET_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) +#define DEBUG_NET_WARN_ON_ONCE(cond) ((void)WARN_ON_ONCE(cond)) +#define DEBUG_NET_WARN_ONCE(cond, format...) ((void)WARN_ONCE(cond, format)) #else #define DEBUG_NET_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#define DEBUG_NET_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif #endif /* _LINUX_NET_DEBUG_H */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 20c34bd7a077..5a2a0df8ad91 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -80,6 +80,7 @@ struct net { * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ + struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ #ifdef CONFIG_KEYS @@ -188,6 +189,10 @@ struct net { #if IS_ENABLED(CONFIG_SMC) struct netns_smc smc; #endif +#ifdef CONFIG_DEBUG_NET_SMALL_RTNL + /* Move to a better place when the config guard is removed. */ + struct mutex rtnl_mutex; +#endif } __randomize_layout; #include <linux/seq_file_net.h> @@ -321,6 +326,11 @@ static inline int check_net(const struct net *net) #define net_drop_ns NULL #endif +/* Returns true if the netns initialization is completed successfully */ +static inline bool net_initialized(const struct net *net) +{ + return READ_ONCE(net->list.next); +} static inline void __netns_tracker_alloc(struct net *net, netns_tracker *tracker, @@ -451,8 +461,8 @@ struct pernet_operations { /* Following method is called with RTNL held. */ void (*exit_batch_rtnl)(struct list_head *net_exit_list, struct list_head *dev_kill_list); - unsigned int *id; - size_t size; + unsigned int * const id; + const size_t size; }; /* diff --git a/include/net/net_shaper.h b/include/net/net_shaper.h new file mode 100644 index 000000000000..5c3f49b52fe9 --- /dev/null +++ b/include/net/net_shaper.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _NET_SHAPER_H_ +#define _NET_SHAPER_H_ + +#include <linux/types.h> + +#include <uapi/linux/net_shaper.h> + +struct net_device; +struct devlink; +struct netlink_ext_ack; + +enum net_shaper_binding_type { + NET_SHAPER_BINDING_TYPE_NETDEV, + /* NET_SHAPER_BINDING_TYPE_DEVLINK_PORT */ +}; + +struct net_shaper_binding { + enum net_shaper_binding_type type; + union { + struct net_device *netdev; + struct devlink *devlink; + }; +}; + +struct net_shaper_handle { + enum net_shaper_scope scope; + u32 id; +}; + +/** + * struct net_shaper - represents a shaping node on the NIC H/W + * zeroed field are considered not set. + * @parent: Unique identifier for the shaper parent, usually implied + * @handle: Unique identifier for this shaper + * @metric: Specify if the rate limits refers to PPS or BPS + * @bw_min: Minimum guaranteed rate for this shaper + * @bw_max: Maximum peak rate allowed for this shaper + * @burst: Maximum burst for the peek rate of this shaper + * @priority: Scheduling priority for this shaper + * @weight: Scheduling weight for this shaper + */ +struct net_shaper { + struct net_shaper_handle parent; + struct net_shaper_handle handle; + enum net_shaper_metric metric; + u64 bw_min; + u64 bw_max; + u64 burst; + u32 priority; + u32 weight; + + /* private: */ + u32 leaves; /* accounted only for NODE scope */ + struct rcu_head rcu; +}; + +/** + * struct net_shaper_ops - Operations on device H/W shapers + * + * The operations applies to either net_device and devlink objects. + * The initial shaping configuration at device initialization is empty: + * does not constraint the rate in any way. + * The network core keeps track of the applied user-configuration in + * the net_device or devlink structure. + * The operations are serialized via a per device lock. + * + * Device not supporting any kind of nesting should not provide the + * group operation. + * + * Each shaper is uniquely identified within the device with a 'handle' + * comprising the shaper scope and a scope-specific id. + */ +struct net_shaper_ops { + /** + * @group: create the specified shapers scheduling group + * + * Nest the @leaves shapers identified under the * @node shaper. + * All the shapers belong to the device specified by @binding. + * The @leaves arrays size is specified by @leaves_count. + * Create either the @leaves and the @node shaper; or if they already + * exists, links them together in the desired way. + * @leaves scope must be NET_SHAPER_SCOPE_QUEUE. + */ + int (*group)(struct net_shaper_binding *binding, int leaves_count, + const struct net_shaper *leaves, + const struct net_shaper *node, + struct netlink_ext_ack *extack); + + /** + * @set: Updates the specified shaper + * + * Updates or creates the @shaper on the device specified by @binding. + */ + int (*set)(struct net_shaper_binding *binding, + const struct net_shaper *shaper, + struct netlink_ext_ack *extack); + + /** + * @delete: Removes the specified shaper + * + * Removes the shaper configuration as identified by the given @handle + * on the device specified by @binding, restoring the default behavior. + */ + int (*delete)(struct net_shaper_binding *binding, + const struct net_shaper_handle *handle, + struct netlink_ext_ack *extack); + + /** + * @capabilities: get the shaper features supported by the device + * + * Fills the bitmask @cap with the supported capabilities for the + * specified @scope and device specified by @binding. + */ + void (*capabilities)(struct net_shaper_binding *binding, + enum net_shaper_scope scope, unsigned long *cap); +}; + +#endif diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index aa1716fb0e53..596836abf7bf 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -6,6 +6,7 @@ #include <linux/netdevice.h> #include <linux/sysfs.h> #include <net/xdp.h> +#include <net/page_pool/types.h> /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { @@ -25,6 +26,7 @@ struct netdev_rx_queue { * Readers and writers must hold RTNL */ struct napi_struct *napi; + struct pp_memory_provider_params mp_params; } ____cacheline_aligned_in_smp; /* @@ -43,7 +45,6 @@ __netif_get_rx_queue(struct net_device *dev, unsigned int rxq) return dev->_rx + rxq; } -#ifdef CONFIG_SYSFS static inline unsigned int get_netdev_rx_queue_index(struct netdev_rx_queue *queue) { @@ -53,5 +54,7 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue) BUG_ON(index >= dev->num_rx_queues); return index; } -#endif + +int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq); + #endif diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index e227d997fc71..1b58b5b91ff6 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -15,10 +15,8 @@ struct nf_conncount_list { unsigned int count; /* length of list */ }; -struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, - unsigned int keylen); -void nf_conncount_destroy(struct net *net, unsigned int family, - struct nf_conncount_data *data); +struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen); +void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data); unsigned int nf_conncount_count(struct net *net, struct nf_conncount_data *data, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 1bfdd16890fa..4afa64c81304 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -2,7 +2,7 @@ #ifndef _NET_NF_TABLES_H #define _NET_NF_TABLES_H -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/list.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> @@ -209,6 +209,7 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src, * @family: protocol family * @level: depth of the chains * @report: notify via unicast netlink message + * @reg_inited: bitmap of initialised registers */ struct nft_ctx { struct net *net; @@ -221,6 +222,7 @@ struct nft_ctx { u8 family; u8 level; bool report; + DECLARE_BITMAP(reg_inited, NFT_REG32_NUM); }; enum nft_data_desc_flags { @@ -254,7 +256,8 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); -int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len); +int nft_parse_register_load(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *sreg, u32 len); int nft_parse_register_store(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *dreg, const struct nft_data *data, @@ -311,6 +314,7 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) /** * enum nft_iter_type - nftables set iterator type * + * @NFT_ITER_UNSPEC: unspecified, to catch errors * @NFT_ITER_READ: read-only iteration over set elements * @NFT_ITER_UPDATE: iteration under mutex to update set element state */ @@ -683,9 +687,8 @@ void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); * @NFT_SET_EXT_DATA: mapping data * @NFT_SET_EXT_FLAGS: element flags * @NFT_SET_EXT_TIMEOUT: element timeout - * @NFT_SET_EXT_EXPIRATION: element expiration time * @NFT_SET_EXT_USERDATA: user data associated with the element - * @NFT_SET_EXT_EXPRESSIONS: expressions assiciated with the element + * @NFT_SET_EXT_EXPRESSIONS: expressions associated with the element * @NFT_SET_EXT_OBJREF: stateful object reference associated with element * @NFT_SET_EXT_NUM: number of extension types */ @@ -695,7 +698,6 @@ enum nft_set_extensions { NFT_SET_EXT_DATA, NFT_SET_EXT_FLAGS, NFT_SET_EXT_TIMEOUT, - NFT_SET_EXT_EXPIRATION, NFT_SET_EXT_USERDATA, NFT_SET_EXT_EXPRESSIONS, NFT_SET_EXT_OBJREF, @@ -807,14 +809,14 @@ static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext) return nft_set_ext(ext, NFT_SET_EXT_FLAGS); } -static inline u64 *nft_set_ext_timeout(const struct nft_set_ext *ext) -{ - return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT); -} +struct nft_timeout { + u64 timeout; + u64 expiration; +}; -static inline u64 *nft_set_ext_expiration(const struct nft_set_ext *ext) +static inline struct nft_timeout *nft_set_ext_timeout(const struct nft_set_ext *ext) { - return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION); + return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT); } static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext) @@ -830,8 +832,11 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext, u64 tstamp) { - return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) && - time_after_eq64(tstamp, *nft_set_ext_expiration(ext)); + if (!nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) || + READ_ONCE(nft_set_ext_timeout(ext)->timeout) == 0) + return false; + + return time_after_eq64(tstamp, READ_ONCE(nft_set_ext_timeout(ext)->expiration)); } static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) @@ -959,8 +964,7 @@ struct nft_expr_ops { const struct nft_expr *expr, bool reset); int (*validate)(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data); + const struct nft_expr *expr); bool (*reduce)(struct nft_regs_track *track, const struct nft_expr *expr); bool (*gc)(struct net *net, @@ -1459,7 +1463,8 @@ struct nft_flowtable { struct nf_flowtable data; }; -struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, +struct nft_flowtable *nft_flowtable_lookup(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u8 genmask); @@ -1674,6 +1679,7 @@ struct nft_trans_rule { struct nft_trans_set { struct nft_trans_binding nft_trans_binding; + struct list_head list_trans_newset; struct nft_set *set; u32 set_id; u32 gc_int; @@ -1744,19 +1750,34 @@ struct nft_trans_table { #define nft_trans_table_update(trans) \ nft_trans_container_table(trans)->update +enum nft_trans_elem_flags { + NFT_TRANS_UPD_TIMEOUT = (1 << 0), + NFT_TRANS_UPD_EXPIRATION = (1 << 1), +}; + +struct nft_elem_update { + u64 timeout; + u64 expiration; + u8 flags; +}; + +struct nft_trans_one_elem { + struct nft_elem_priv *priv; + struct nft_elem_update *update; +}; + struct nft_trans_elem { struct nft_trans nft_trans; struct nft_set *set; - struct nft_elem_priv *elem_priv; bool bound; + unsigned int nelems; + struct nft_trans_one_elem elems[] __counted_by(nelems); }; #define nft_trans_container_elem(t) \ container_of(t, struct nft_trans_elem, nft_trans) #define nft_trans_elem_set(trans) \ nft_trans_container_elem(trans)->set -#define nft_trans_elem_priv(trans) \ - nft_trans_container_elem(trans)->elem_priv #define nft_trans_elem_set_bound(trans) \ nft_trans_container_elem(trans)->bound @@ -1875,6 +1896,7 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re struct nftables_pernet { struct list_head tables; struct list_head commit_list; + struct list_head commit_set_list; struct list_head binding_list; struct list_head module_list; struct list_head notify_list; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index ff27cb2e1662..03b6165756fc 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -161,6 +161,7 @@ enum { }; struct nft_inner_tun_ctx { + unsigned long cookie; u16 type; u16 inner_tunoff; u16 inner_lloff; diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h index faa108b1ba67..5adf6fda11e8 100644 --- a/include/net/netfilter/nf_tproxy.h +++ b/include/net/netfilter/nf_tproxy.h @@ -36,6 +36,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr); /** * nf_tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections + * @net: The network namespace. * @skb: The skb being processed. * @laddr: IPv4 address to redirect to or zero. * @lport: TCP port to redirect to or zero. diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index 167640b843ef..38cae7113de4 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -21,9 +21,7 @@ nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in) int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset); int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); -int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nft_data **data); - +int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr); void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index ba1238f12a48..d602263590fe 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -41,8 +41,7 @@ void nft_meta_set_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr); int nft_meta_set_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data); + const struct nft_expr *expr); bool nft_meta_get_reduce(struct nft_regs_track *track, const struct nft_expr *expr); diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h index 6d9ba62efd75..19060212988a 100644 --- a/include/net/netfilter/nft_reject.h +++ b/include/net/netfilter/nft_reject.h @@ -15,8 +15,7 @@ struct nft_reject { extern const struct nla_policy nft_reject_policy[]; int nft_reject_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data); + const struct nft_expr *expr); int nft_reject_init(const struct nft_ctx *ctx, const struct nft_expr *expr, diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 654bc777d2a7..02914b1df38b 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -30,7 +30,7 @@ struct calipso_doi; /* * NetLabel - A management interface for maintaining network packet label - * mapping tables for explicit packet labling protocols. + * mapping tables for explicit packet labeling protocols. * * Network protocols such as CIPSO and RIPSO require a label translation layer * to convert the label on the packet into something meaningful on the host @@ -97,7 +97,7 @@ struct calipso_doi; /* NetLabel audit information */ struct netlbl_audit { - u32 secid; + struct lsm_prop prop; kuid_t loginuid; unsigned int sessionid; }; @@ -208,6 +208,7 @@ struct netlbl_lsm_secattr { * struct netlbl_calipso_ops - NetLabel CALIPSO operations * @doi_add: add a CALIPSO DOI * @doi_free: free a CALIPSO DOI + * @doi_remove: remove a CALIPSO DOI * @doi_getdef: returns a reference to a DOI * @doi_putdef: releases a reference of a DOI * @doi_walk: enumerate the DOI list diff --git a/include/net/netlink.h b/include/net/netlink.h index e78ce008e07c..39eaa6be6ca8 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -142,6 +142,8 @@ * nla_get_flag(nla) return 1 if flag is true * nla_get_msecs(nla) get payload for a msecs attribute * + * The same functions also exist with _default(). + * * Attribute Misc: * nla_memcpy(dest, nla, count) copy attribute into memory * nla_memcmp(nla, data, size) compare attribute with memory area @@ -469,6 +471,7 @@ struct nla_policy { .max = _len \ } #define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len) +#define NLA_POLICY_MAX_LEN(_len) NLA_POLICY_MAX(NLA_BINARY, _len) /** * struct nl_info - netlink source information @@ -827,7 +830,7 @@ nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. @@ -849,7 +852,7 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in liberal mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ @@ -872,7 +875,7 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in strict mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ @@ -887,7 +890,7 @@ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, /** * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct @@ -933,7 +936,7 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ @@ -1034,7 +1037,7 @@ static inline struct sk_buff *nlmsg_new_large(size_t payload) * @skb: socket buffer the message is stored in * @nlh: netlink message header * - * Corrects the netlink message header to include the appeneded + * Corrects the netlink message header to include the appended * attributes. Only necessary if attributes have been added to * the message. */ @@ -1695,6 +1698,20 @@ static inline u32 nla_get_u32(const struct nlattr *nla) } /** + * nla_get_u32_default - return payload of u32 attribute or default + * @nla: u32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u32 nla_get_u32_default(const struct nlattr *nla, u32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u32(nla); +} + +/** * nla_get_be32 - return payload of __be32 attribute * @nla: __be32 netlink attribute */ @@ -1704,6 +1721,21 @@ static inline __be32 nla_get_be32(const struct nlattr *nla) } /** + * nla_get_be32_default - return payload of be32 attribute or default + * @nla: __be32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be32 nla_get_be32_default(const struct nlattr *nla, + __be32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_be32(nla); +} + +/** * nla_get_le32 - return payload of __le32 attribute * @nla: __le32 netlink attribute */ @@ -1713,6 +1745,21 @@ static inline __le32 nla_get_le32(const struct nlattr *nla) } /** + * nla_get_le32_default - return payload of le32 attribute or default + * @nla: __le32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __le32 nla_get_le32_default(const struct nlattr *nla, + __le32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_le32(nla); +} + +/** * nla_get_u16 - return payload of u16 attribute * @nla: u16 netlink attribute */ @@ -1722,6 +1769,20 @@ static inline u16 nla_get_u16(const struct nlattr *nla) } /** + * nla_get_u16_default - return payload of u16 attribute or default + * @nla: u16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u16 nla_get_u16_default(const struct nlattr *nla, u16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u16(nla); +} + +/** * nla_get_be16 - return payload of __be16 attribute * @nla: __be16 netlink attribute */ @@ -1731,6 +1792,21 @@ static inline __be16 nla_get_be16(const struct nlattr *nla) } /** + * nla_get_be16_default - return payload of be16 attribute or default + * @nla: __be16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be16 nla_get_be16_default(const struct nlattr *nla, + __be16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_be16(nla); +} + +/** * nla_get_le16 - return payload of __le16 attribute * @nla: __le16 netlink attribute */ @@ -1740,6 +1816,21 @@ static inline __le16 nla_get_le16(const struct nlattr *nla) } /** + * nla_get_le16_default - return payload of le16 attribute or default + * @nla: __le16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __le16 nla_get_le16_default(const struct nlattr *nla, + __le16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_le16(nla); +} + +/** * nla_get_u8 - return payload of u8 attribute * @nla: u8 netlink attribute */ @@ -1749,6 +1840,20 @@ static inline u8 nla_get_u8(const struct nlattr *nla) } /** + * nla_get_u8_default - return payload of u8 attribute or default + * @nla: u8 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u8 nla_get_u8_default(const struct nlattr *nla, u8 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u8(nla); +} + +/** * nla_get_u64 - return payload of u64 attribute * @nla: u64 netlink attribute */ @@ -1762,6 +1867,20 @@ static inline u64 nla_get_u64(const struct nlattr *nla) } /** + * nla_get_u64_default - return payload of u64 attribute or default + * @nla: u64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u64 nla_get_u64_default(const struct nlattr *nla, u64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u64(nla); +} + +/** * nla_get_uint - return payload of uint attribute * @nla: uint netlink attribute */ @@ -1773,6 +1892,20 @@ static inline u64 nla_get_uint(const struct nlattr *nla) } /** + * nla_get_uint_default - return payload of uint attribute or default + * @nla: uint netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u64 nla_get_uint_default(const struct nlattr *nla, u64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_uint(nla); +} + +/** * nla_get_be64 - return payload of __be64 attribute * @nla: __be64 netlink attribute */ @@ -1786,6 +1919,21 @@ static inline __be64 nla_get_be64(const struct nlattr *nla) } /** + * nla_get_be64_default - return payload of be64 attribute or default + * @nla: __be64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be64 nla_get_be64_default(const struct nlattr *nla, + __be64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_be64(nla); +} + +/** * nla_get_le64 - return payload of __le64 attribute * @nla: __le64 netlink attribute */ @@ -1795,6 +1943,21 @@ static inline __le64 nla_get_le64(const struct nlattr *nla) } /** + * nla_get_le64_default - return payload of le64 attribute or default + * @nla: __le64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __le64 nla_get_le64_default(const struct nlattr *nla, + __le64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_le64(nla); +} + +/** * nla_get_s32 - return payload of s32 attribute * @nla: s32 netlink attribute */ @@ -1804,6 +1967,20 @@ static inline s32 nla_get_s32(const struct nlattr *nla) } /** + * nla_get_s32_default - return payload of s32 attribute or default + * @nla: s32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s32 nla_get_s32_default(const struct nlattr *nla, s32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s32(nla); +} + +/** * nla_get_s16 - return payload of s16 attribute * @nla: s16 netlink attribute */ @@ -1813,6 +1990,20 @@ static inline s16 nla_get_s16(const struct nlattr *nla) } /** + * nla_get_s16_default - return payload of s16 attribute or default + * @nla: s16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s16 nla_get_s16_default(const struct nlattr *nla, s16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s16(nla); +} + +/** * nla_get_s8 - return payload of s8 attribute * @nla: s8 netlink attribute */ @@ -1822,6 +2013,20 @@ static inline s8 nla_get_s8(const struct nlattr *nla) } /** + * nla_get_s8_default - return payload of s8 attribute or default + * @nla: s8 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s8 nla_get_s8_default(const struct nlattr *nla, s8 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s8(nla); +} + +/** * nla_get_s64 - return payload of s64 attribute * @nla: s64 netlink attribute */ @@ -1835,6 +2040,20 @@ static inline s64 nla_get_s64(const struct nlattr *nla) } /** + * nla_get_s64_default - return payload of s64 attribute or default + * @nla: s64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s64 nla_get_s64_default(const struct nlattr *nla, s64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s64(nla); +} + +/** * nla_get_sint - return payload of uint attribute * @nla: uint netlink attribute */ @@ -1846,6 +2065,20 @@ static inline s64 nla_get_sint(const struct nlattr *nla) } /** + * nla_get_sint_default - return payload of sint attribute or default + * @nla: sint netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s64 nla_get_sint_default(const struct nlattr *nla, s64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_sint(nla); +} + +/** * nla_get_flag - return payload of flag attribute * @nla: flag netlink attribute */ @@ -1868,6 +2101,21 @@ static inline unsigned long nla_get_msecs(const struct nlattr *nla) } /** + * nla_get_msecs_default - return payload of msecs attribute or default + * @nla: msecs netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline unsigned long nla_get_msecs_default(const struct nlattr *nla, + unsigned long defvalue) +{ + if (!nla) + return defvalue; + return nla_get_msecs(nla); +} + +/** * nla_get_in_addr - return payload of IPv4 address attribute * @nla: IPv4 address netlink attribute */ @@ -1877,6 +2125,21 @@ static inline __be32 nla_get_in_addr(const struct nlattr *nla) } /** + * nla_get_in_addr_default - return payload of be32 attribute or default + * @nla: IPv4 address netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be32 nla_get_in_addr_default(const struct nlattr *nla, + __be32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_in_addr(nla); +} + +/** * nla_get_in6_addr - return payload of IPv6 address attribute * @nla: IPv6 address netlink attribute */ @@ -1954,7 +2217,7 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) * @start: container attribute * * Corrects the container attribute header to include the all - * appeneded attributes. + * appended attributes. * * Returns the total data length of the skb. */ @@ -1987,7 +2250,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) * * Validates all attributes in the nested attribute stream against the * specified policy. Attributes with a type exceeding maxtype will be - * ignored. See documenation of struct nla_policy for more details. + * ignored. See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ diff --git a/include/net/netmem.h b/include/net/netmem.h index 46cc9b89ac79..8a6e20be4b9d 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -8,6 +8,54 @@ #ifndef _NET_NETMEM_H #define _NET_NETMEM_H +#include <linux/mm.h> +#include <net/net_debug.h> + +/* net_iov */ + +DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers); + +/* We overload the LSB of the struct page pointer to indicate whether it's + * a page or net_iov. + */ +#define NET_IOV 0x01UL + +struct net_iov { + unsigned long __unused_padding; + unsigned long pp_magic; + struct page_pool *pp; + struct dmabuf_genpool_chunk_owner *owner; + unsigned long dma_addr; + atomic_long_t pp_ref_count; +}; + +/* These fields in struct page are used by the page_pool and net stack: + * + * struct { + * unsigned long pp_magic; + * struct page_pool *pp; + * unsigned long _pp_mapping_pad; + * unsigned long dma_addr; + * atomic_long_t pp_ref_count; + * }; + * + * We mirror the page_pool fields here so the page_pool can access these fields + * without worrying whether the underlying fields belong to a page or net_iov. + * + * The non-net stack fields of struct page are private to the mm stack and must + * never be mirrored to net_iov. + */ +#define NET_IOV_ASSERT_OFFSET(pg, iov) \ + static_assert(offsetof(struct page, pg) == \ + offsetof(struct net_iov, iov)) +NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic); +NET_IOV_ASSERT_OFFSET(pp, pp); +NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr); +NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count); +#undef NET_IOV_ASSERT_OFFSET + +/* netmem */ + /** * typedef netmem_ref - a nonexistent type marking a reference to generic * network memory. @@ -19,20 +67,37 @@ */ typedef unsigned long __bitwise netmem_ref; +static inline bool netmem_is_net_iov(const netmem_ref netmem) +{ + return (__force unsigned long)netmem & NET_IOV; +} + /* This conversion fails (returns NULL) if the netmem_ref is not struct page * backed. - * - * Currently struct page is the only possible netmem, and this helper never - * fails. */ static inline struct page *netmem_to_page(netmem_ref netmem) { + if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) + return NULL; + return (__force struct page *)netmem; } -/* Converting from page to netmem is always safe, because a page can always be - * a netmem. - */ +static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return (struct net_iov *)((__force unsigned long)netmem & + ~NET_IOV); + + DEBUG_NET_WARN_ON_ONCE(true); + return NULL; +} + +static inline netmem_ref net_iov_to_netmem(struct net_iov *niov) +{ + return (__force netmem_ref)((unsigned long)niov | NET_IOV); +} + static inline netmem_ref page_to_netmem(struct page *page) { return (__force netmem_ref)page; @@ -40,17 +105,70 @@ static inline netmem_ref page_to_netmem(struct page *page) static inline int netmem_ref_count(netmem_ref netmem) { + /* The non-pp refcount of net_iov is always 1. On net_iov, we only + * support pp refcounting which uses the pp_ref_count field. + */ + if (netmem_is_net_iov(netmem)) + return 1; + return page_ref_count(netmem_to_page(netmem)); } -static inline unsigned long netmem_to_pfn(netmem_ref netmem) +static inline unsigned long netmem_pfn_trace(netmem_ref netmem) { + if (netmem_is_net_iov(netmem)) + return 0; + return page_to_pfn(netmem_to_page(netmem)); } +static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem) +{ + return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); +} + +static inline struct page_pool *netmem_get_pp(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->pp; +} + +static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem) +{ + return &__netmem_clear_lsb(netmem)->pp_ref_count; +} + +static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid) +{ + /* NUMA node preference only makes sense if we're allocating + * system memory. Memory providers (which give us net_iovs) + * choose for us. + */ + if (netmem_is_net_iov(netmem)) + return true; + + return page_to_nid(netmem_to_page(netmem)) == pref_nid; +} + static inline netmem_ref netmem_compound_head(netmem_ref netmem) { + /* niov are never compounded */ + if (netmem_is_net_iov(netmem)) + return netmem; + return page_to_netmem(compound_head(netmem_to_page(netmem))); } +static inline void *netmem_address(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return NULL; + + return page_address(netmem_to_page(netmem)); +} + +static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->dma_addr; +} + #endif /* _NET_NETMEM_H */ diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 78214f1b43a2..9b36f0ff0c20 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -15,6 +15,7 @@ struct netns_core { int sysctl_somaxconn; int sysctl_optmem_max; u8 sysctl_txrehash; + u8 sysctl_tstamp_allow_data; #ifdef CONFIG_PROC_FS struct prot_inuse __percpu *prot_inuse; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 5fcd61ada622..3c014170e001 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -76,6 +76,8 @@ struct netns_ipv4 { __cacheline_group_begin(netns_ipv4_read_rx); u8 sysctl_ip_early_demux; u8 sysctl_tcp_early_demux; + u8 sysctl_tcp_l3mdev_accept; + /* 3 bytes hole, try to pack */ int sysctl_tcp_reordering; int sysctl_tcp_rmem[3]; __cacheline_group_end(netns_ipv4_read_rx); @@ -122,7 +124,10 @@ struct netns_ipv4 { u8 sysctl_icmp_errors_use_inbound_ifaddr; int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; - + int sysctl_icmp_msgs_per_sec; + int sysctl_icmp_msgs_burst; + atomic_t icmp_global_credit; + u32 icmp_global_stamp; u32 ip_rt_min_pmtu; int ip_rt_mtu_expires; int ip_rt_min_advmss; @@ -148,9 +153,6 @@ struct netns_ipv4 { u8 sysctl_fwmark_reflect; u8 sysctl_tcp_fwmark_accept; -#ifdef CONFIG_NET_L3_MASTER_DEV - u8 sysctl_tcp_l3mdev_accept; -#endif u8 sysctl_tcp_mtu_probing; int sysctl_tcp_mtu_probe_floor; int sysctl_tcp_base_mss; @@ -260,12 +262,14 @@ struct netns_ipv4 { #endif struct fib_notifier_ops *notifier_ops; - unsigned int fib_seq; /* protected by rtnl_mutex */ + unsigned int fib_seq; /* writes protected by rtnl_mutex */ struct fib_notifier_ops *ipmr_notifier_ops; unsigned int ipmr_seq; /* protected by rtnl_mutex */ atomic_t rt_genid; siphash_key_t ip_id_key; + struct hlist_head *inet_addr_lst; + struct delayed_work addr_chk_work; }; #endif diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 7eff3d981b89..d25cd7a9c5ff 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -125,14 +125,14 @@ struct netns_sctp { int pf_expose; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_sndbuf * 1 - do sctp accounting, each asoc may use sk_sndbuf bytes */ int sndbuf_policy; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_rcvbuf * 1 - do sctp accounting, each asoc may use sk_rcvbuf bytes */ diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index d489d9250bff..23dd647fe024 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -43,6 +43,7 @@ struct netns_xfrm { struct hlist_head __rcu *state_bysrc; struct hlist_head __rcu *state_byspi; struct hlist_head __rcu *state_byseq; + struct hlist_head __percpu *state_cache_input; unsigned int state_hmask; unsigned int state_num; struct work_struct state_hash_work; @@ -51,7 +52,6 @@ struct netns_xfrm { struct hlist_head *policy_byidx; unsigned int policy_idx_hmask; unsigned int idx_generator; - struct hlist_head policy_inexact[XFRM_POLICY_MAX]; struct xfrm_policy_hash policy_bydst[XFRM_POLICY_MAX]; unsigned int policy_count[XFRM_POLICY_MAX * 2]; struct work_struct policy_hash_work; diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 68463aebcc05..d9fb44e8b321 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -105,7 +105,7 @@ struct nh_grp_entry_stats { struct nh_grp_entry { struct nexthop *nh; struct nh_grp_entry_stats __percpu *stats; - u8 weight; + u16 weight; union { struct { @@ -192,7 +192,7 @@ struct nh_notifier_single_info { }; struct nh_notifier_grp_entry_info { - u8 weight; + u16 weight; struct nh_notifier_single_info nh; }; diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index e82f55f543bb..09efcaed7c3f 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -332,7 +332,7 @@ struct nci_core_init_rsp_1 { __le32 nfcc_features; __u8 num_supported_rf_interfaces; __u8 supported_rf_interfaces[]; /* variable size array */ - /* continuted in nci_core_init_rsp_2 */ + /* continued in nci_core_init_rsp_2 */ } __packed; struct nci_core_init_rsp_2 { @@ -475,7 +475,7 @@ struct nci_rf_discover_ntf { #define NCI_OP_RF_INTF_ACTIVATED_NTF nci_opcode_pack(NCI_GID_RF_MGMT, 0x05) struct activation_params_nfca_poll_iso_dep { __u8 rats_res_len; - __u8 rats_res[20]; + __u8 rats_res[NFC_ATS_MAXSIZE]; }; struct activation_params_nfcb_poll_iso_dep { diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index ea8595651c38..e180bdf2f82b 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -265,6 +265,10 @@ struct nci_dev { /* stored during intf_activated_ntf */ __u8 remote_gb[NFC_MAX_GT_LEN]; __u8 remote_gb_len; + + /* stored during intf_activated_ntf */ + __u8 target_ats[NFC_ATS_MAXSIZE]; + __u8 target_ats_len; }; /* ----- NCI Devices ----- */ diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 3d07abacf08b..127e6c7d910d 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -80,12 +80,14 @@ struct nfc_ops { #define NFC_ATR_REQ_GT_OFFSET 14 /** - * struct nfc_target - NFC target descriptiom + * struct nfc_target - NFC target description * * @sens_res: 2 bytes describing the target SENS_RES response, if the target * is a type A one. The %sens_res most significant byte must be byte 2 * as described by the NFC Forum digital specification (i.e. the platform * configuration one) while %sens_res least significant byte is byte 1. + * @ats_len: length of Answer To Select in bytes + * @ats: Answer To Select returned by an ISO 14443 Type A target upon activation */ struct nfc_target { u32 idx; @@ -105,6 +107,8 @@ struct nfc_target { u8 is_iso15693; u8 iso15693_dsfid; u8 iso15693_uid[NFC_ISO15693_UID_MAXSIZE]; + u8 ats_len; + u8 ats[NFC_ATS_MAXSIZE]; }; /** @@ -230,10 +234,10 @@ static inline void nfc_set_parent_dev(struct nfc_dev *nfc_dev, } /** - * nfc_set_drvdata - set driver specifc data + * nfc_set_drvdata - set driver specific data * * @dev: The nfc device - * @data: Pointer to driver specifc data + * @data: Pointer to driver specific data */ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) { @@ -241,7 +245,7 @@ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) } /** - * nfc_get_drvdata - get driver specifc data + * nfc_get_drvdata - get driver specific data * * @dev: The nfc device */ diff --git a/include/net/nl802154.h b/include/net/nl802154.h index 4c752f799957..a994dea74596 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -192,7 +192,7 @@ enum nl802154_iftype { * @NL802154_CAP_ATTR_TX_POWERS: a nested attribute for * nl802154_wpan_phy_tx_power * @NL802154_CAP_ATTR_MIN_CCA_ED_LEVEL: minimum value for cca_ed_level - * @NL802154_CAP_ATTR_MAX_CCA_ED_LEVEL: maxmimum value for cca_ed_level + * @NL802154_CAP_ATTR_MAX_CCA_ED_LEVEL: maximum value for cca_ed_level * @NL802154_CAP_ATTR_CCA_MODES: nl802154_cca_modes flags * @NL802154_CAP_ATTR_CCA_OPTS: nl802154_cca_opts flags * @NL802154_CAP_ATTR_MIN_MINBE: minimum of minbe value diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 2b43a893c619..793e6fd78bc5 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -216,7 +216,7 @@ page_pool_get_dma_dir(const struct page_pool *pool) static inline void page_pool_fragment_netmem(netmem_ref netmem, long nr) { - atomic_long_set(&netmem_to_page(netmem)->pp_ref_count, nr); + atomic_long_set(netmem_get_pp_ref_count_ref(netmem), nr); } /** @@ -244,7 +244,7 @@ static inline void page_pool_fragment_page(struct page *page, long nr) static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) { - struct page *page = netmem_to_page(netmem); + atomic_long_t *pp_ref_count = netmem_get_pp_ref_count_ref(netmem); long ret; /* If nr == pp_ref_count then we have cleared all remaining @@ -261,19 +261,19 @@ static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) * initially, and only overwrite it when the page is partitioned into * more than one piece. */ - if (atomic_long_read(&page->pp_ref_count) == nr) { + if (atomic_long_read(pp_ref_count) == nr) { /* As we have ensured nr is always one for constant case using * the BUILD_BUG_ON(), only need to handle the non-constant case * here for pp_ref_count draining, which is a rare case. */ BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1); if (!__builtin_constant_p(nr)) - atomic_long_set(&page->pp_ref_count, 1); + atomic_long_set(pp_ref_count, 1); return 0; } - ret = atomic_long_sub_return(nr, &page->pp_ref_count); + ret = atomic_long_sub_return(nr, pp_ref_count); WARN_ON(ret < 0); /* We are the last user here too, reset pp_ref_count back to 1 to @@ -282,7 +282,7 @@ static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) * page_pool_unref_page() currently. */ if (unlikely(!ret)) - atomic_long_set(&page->pp_ref_count, 1); + atomic_long_set(pp_ref_count, 1); return ret; } @@ -401,9 +401,7 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va, static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem) { - struct page *page = netmem_to_page(netmem); - - dma_addr_t ret = page->dma_addr; + dma_addr_t ret = netmem_get_dma_addr(netmem); if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) ret <<= PAGE_SHIFT; @@ -423,24 +421,6 @@ static inline dma_addr_t page_pool_get_dma_addr(const struct page *page) return page_pool_get_dma_addr_netmem(page_to_netmem((struct page *)page)); } -static inline bool page_pool_set_dma_addr_netmem(netmem_ref netmem, - dma_addr_t addr) -{ - struct page *page = netmem_to_page(netmem); - - if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) { - page->dma_addr = addr >> PAGE_SHIFT; - - /* We assume page alignment to shave off bottom bits, - * if this "compression" doesn't work we need to drop. - */ - return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT; - } - - page->dma_addr = addr; - return false; -} - /** * page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW * @pool: &page_pool the @page belongs to @@ -463,11 +443,6 @@ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool, page_pool_get_dma_dir(pool)); } -static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) -{ - return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr); -} - static inline bool page_pool_put(struct page_pool *pool) { return refcount_dec_and_test(&pool->user_cnt); diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 50569fed7868..c022c410abe3 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -20,8 +20,18 @@ * device driver responsibility */ #define PP_FLAG_SYSTEM_POOL BIT(2) /* Global system page_pool */ + +/* Allow unreadable (net_iov backed) netmem in this page_pool. Drivers setting + * this must be able to support unreadable netmem, where netmem_address() would + * return NULL. This flag should not be set for header page_pools. + * + * If the driver sets PP_FLAG_ALLOW_UNREADABLE_NETMEM, it should also set + * page_pool_params.slow.queue_idx. + */ +#define PP_FLAG_ALLOW_UNREADABLE_NETMEM BIT(3) + #define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV | \ - PP_FLAG_SYSTEM_POOL) + PP_FLAG_SYSTEM_POOL | PP_FLAG_ALLOW_UNREADABLE_NETMEM) /* * Fast allocation side cache array/stack @@ -57,7 +67,9 @@ struct pp_alloc_cache { * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV * @slow: params with slowpath access only (initialization and Netlink) * @netdev: netdev this pool will serve (leave as NULL if none or multiple) - * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL + * @queue_idx: queue idx this page_pool is being created for. + * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL, + * PP_FLAG_ALLOW_UNREADABLE_NETMEM. */ struct page_pool_params { struct_group_tagged(page_pool_params_fast, fast, @@ -72,6 +84,7 @@ struct page_pool_params { ); struct_group_tagged(page_pool_params_slow, slow, struct net_device *netdev; + unsigned int queue_idx; unsigned int flags; /* private: used by test code only */ void (*init_callback)(netmem_ref netmem, void *arg); @@ -139,6 +152,10 @@ struct page_pool_stats { */ #define PAGE_POOL_FRAG_GROUP_ALIGN (4 * sizeof(long)) +struct pp_memory_provider_params { + void *mp_priv; +}; + struct page_pool { struct page_pool_params_fast p; @@ -197,6 +214,8 @@ struct page_pool { */ struct ptr_ring ring; + void *mp_priv; + #ifdef CONFIG_PAGE_POOL_STATS /* recycle stats are per-cpu to avoid locking */ struct page_pool_recycle_stats __percpu *recycle_stats; diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h index e9dc8dca5817..37a3e83531c6 100644 --- a/include/net/phonet/pn_dev.h +++ b/include/net/phonet/pn_dev.h @@ -11,13 +11,13 @@ #define PN_DEV_H #include <linux/list.h> -#include <linux/mutex.h> +#include <linux/spinlock.h> struct net; struct phonet_device_list { struct list_head list; - struct mutex lock; + spinlock_t lock; }; struct phonet_device_list *phonet_device_list(struct net *net); @@ -38,11 +38,11 @@ int phonet_address_add(struct net_device *dev, u8 addr); int phonet_address_del(struct net_device *dev, u8 addr); u8 phonet_address_get(struct net_device *dev, u8 addr); int phonet_address_lookup(struct net *net, u8 addr); -void phonet_address_notify(int event, struct net_device *dev, u8 addr); +void phonet_address_notify(struct net *net, int event, u32 ifindex, u8 addr); int phonet_route_add(struct net_device *dev, u8 daddr); int phonet_route_del(struct net_device *dev, u8 daddr); -void rtm_phonet_notify(int event, struct net_device *dev, u8 dst); +void rtm_phonet_notify(struct net *net, int event, u32 ifindex, u8 dst); struct net_device *phonet_route_get_rcu(struct net *net, u8 daddr); struct net_device *phonet_route_output(struct net *net, u8 daddr); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 41297bd38dff..cf199af85c52 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -491,7 +491,7 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, struct tcf_pkt_info *); /** - * tcf_em_tree_match - evaulate an ematch tree + * tcf_em_tree_match - evaluate an ematch tree * * @skb: socket buffer of the packet in question * @tree: ematch tree to be used for evaluation @@ -755,6 +755,7 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, cls_common->chain_index = tp->chain->index; cls_common->protocol = tp->protocol; cls_common->prio = tp->prio >> 16; + cls_common->skip_sw = tc_skip_sw(flags); if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE) cls_common->extack = extack; } diff --git a/include/net/red.h b/include/net/red.h index 802287d52c9e..159a09359fc0 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -40,7 +40,7 @@ max_P should be small (not 1), usually 0.01..0.02 is good value. max_P is chosen as a number, so that max_P/(th_max-th_min) - is a negative power of two in order arithmetics to contain + is a negative power of two in order arithmetic to contain only shifts. @@ -159,7 +159,7 @@ static inline u32 red_maxp(u8 Plog) static inline void red_set_vars(struct red_vars *v) { /* Reset average queue length, the value is strictly bound - * to the parameters below, reseting hurts a bit but leaving + * to the parameters below, resetting hurts a bit but leaving * it might result in an unreasonable qavg for a while. --TGR */ v->qavg = 0; @@ -340,7 +340,7 @@ static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p { /* * NOTE: v->qavg is fixed point number with point at Wlog. - * The formula below is equvalent to floating point + * The formula below is equivalent to floating point * version: * * qavg = qavg*(1-W) + backlog*W; @@ -375,7 +375,7 @@ static inline int red_mark_probability(const struct red_parms *p, OK. qR is random number in the interval (0..1/max_P)*(qth_max-qth_min) i.e. 0..(2^Plog). If we used floating point - arithmetics, it would be: (2^Plog)*rnd_num, + arithmetic, it would be: (2^Plog)*rnd_num, where rnd_num is less 1. Taking into account, that qavg have fixed diff --git a/include/net/regulatory.h b/include/net/regulatory.h index a103f4c8cf75..6633627f6e76 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -121,7 +121,7 @@ struct regulatory_request { * @REGULATORY_DISABLE_BEACON_HINTS: enable this if your driver needs to * ensure that passive scan flags and beaconing flags may not be lifted by * cfg80211 due to regulatory beacon hints. For more information on beacon - * hints read the documenation for regulatory_hint_found_beacon() + * hints read the documentation for regulatory_hint_found_beacon() * @REGULATORY_COUNTRY_IE_FOLLOW_POWER: for devices that have a preference * that even though they may have programmed their own custom power * setting prior to wiphy registration, they want to ensure their channel diff --git a/include/net/route.h b/include/net/route.h index 93833cfe9c96..84cb1e04f5cd 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -27,6 +27,7 @@ #include <net/ip_fib.h> #include <net/arp.h> #include <net/ndisc.h> +#include <net/inet_dscp.h> #include <linux/in_route.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> @@ -45,7 +46,7 @@ static inline __u8 ip_sock_rt_scope(const struct sock *sk) static inline __u8 ip_sock_rt_tos(const struct sock *sk) { - return RT_TOS(READ_ONCE(inet_sk(sk)->tos)); + return READ_ONCE(inet_sk(sk)->tos) & INET_DSCP_MASK; } struct ip_tunnel_info; @@ -155,12 +156,12 @@ static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 * structure is only partially set, it may bypass some fib-rules. */ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr, - __be32 saddr, u8 tos, int oif, - __u8 scope) + __be32 saddr, dscp_t dscp, + int oif, __u8 scope) { struct flowi4 fl4 = { .flowi4_oif = oif, - .flowi4_tos = tos, + .flowi4_tos = inet_dscp_to_dsfield(dscp), .flowi4_scope = scope, .daddr = daddr, .saddr = saddr, @@ -197,30 +198,35 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 fl4->fl4_gre_key = gre_key; return ip_route_output_key(net, fl4); } -int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev, - struct in_device *in_dev, u32 *itag); -int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, - u8 tos, struct net_device *devin); -int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src, - u8 tos, struct net_device *devin, - const struct sk_buff *hint); - -static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, - u8 tos, struct net_device *devin) + +enum skb_drop_reason +ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev, + struct in_device *in_dev, u32 *itag); +enum skb_drop_reason +ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev); +enum skb_drop_reason +ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev, + const struct sk_buff *hint); + +static inline enum skb_drop_reason +ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, dscp_t dscp, + struct net_device *devin) { - int err; + enum skb_drop_reason reason; rcu_read_lock(); - err = ip_route_input_noref(skb, dst, src, tos, devin); - if (!err) { + reason = ip_route_input_noref(skb, dst, src, dscp, devin); + if (!reason) { skb_dst_force(skb); if (!skb_dst(skb)) - err = -EINVAL; + reason = SKB_DROP_REASON_NOT_SPECIFIED; } rcu_read_unlock(); - return err; + return reason; } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, @@ -265,8 +271,6 @@ static inline void ip_rt_put(struct rtable *rt) dst_release(&rt->dst); } -#define IPTOS_RT_MASK (IPTOS_TOS_MASK & ~3) - extern const __u8 ip_tos2prio[16]; static inline char rt_tos2priority(u8 tos) diff --git a/include/net/rstreason.h b/include/net/rstreason.h index 2575c85d7f7a..69cb2e52b7da 100644 --- a/include/net/rstreason.h +++ b/include/net/rstreason.h @@ -17,6 +17,12 @@ FN(TCP_ABORT_ON_DATA) \ FN(TCP_TIMEWAIT_SOCKET) \ FN(INVALID_SYN) \ + FN(TCP_ABORT_ON_CLOSE) \ + FN(TCP_ABORT_ON_LINGER) \ + FN(TCP_ABORT_ON_MEMORY) \ + FN(TCP_STATE) \ + FN(TCP_KEEPALIVE_TIMEOUT) \ + FN(TCP_DISCONNECT_WITH_DATA) \ FN(MPTCP_RST_EUNSPEC) \ FN(MPTCP_RST_EMPTCP) \ FN(MPTCP_RST_ERESOURCE) \ @@ -84,6 +90,39 @@ enum sk_rst_reason { * an error, send a reset" */ SK_RST_REASON_INVALID_SYN, + /** + * @SK_RST_REASON_TCP_ABORT_ON_CLOSE: abort on close + * corresponding to LINUX_MIB_TCPABORTONCLOSE + */ + SK_RST_REASON_TCP_ABORT_ON_CLOSE, + /** + * @SK_RST_REASON_TCP_ABORT_ON_LINGER: abort on linger + * corresponding to LINUX_MIB_TCPABORTONLINGER + */ + SK_RST_REASON_TCP_ABORT_ON_LINGER, + /** + * @SK_RST_REASON_TCP_ABORT_ON_MEMORY: abort on memory + * corresponding to LINUX_MIB_TCPABORTONMEMORY + */ + SK_RST_REASON_TCP_ABORT_ON_MEMORY, + /** + * @SK_RST_REASON_TCP_STATE: abort on tcp state + * Please see RFC 9293 for all possible reset conditions + */ + SK_RST_REASON_TCP_STATE, + /** + * @SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT: time to timeout + * When we have already run out of all the chances, which means + * keepalive timeout, we have to reset the connection + */ + SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT, + /** + * @SK_RST_REASON_TCP_DISCONNECT_WITH_DATA: disconnect when write + * queue is not empty + * It means user has written data into the write queue when doing + * disconnecting, so we have to send an RST. + */ + SK_RST_REASON_TCP_DISCONNECT_WITH_DATA, /* Copy from include/uapi/linux/mptcp.h. * These reset fields will not be changed since they adhere to diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index b45d57b5968a..bc0069a8b6ea 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -3,6 +3,7 @@ #define __NET_RTNETLINK_H #include <linux/rtnetlink.h> +#include <linux/srcu.h> #include <net/netlink.h> typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, @@ -11,6 +12,8 @@ typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = BIT(0), +#define RTNL_FLAG_DOIT_PERNET RTNL_FLAG_DOIT_UNLOCKED +#define RTNL_FLAG_DOIT_PERNET_WIP RTNL_FLAG_DOIT_UNLOCKED RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), RTNL_FLAG_DUMP_UNLOCKED = BIT(2), RTNL_FLAG_DUMP_SPLIT_NLM_DONE = BIT(3), /* legacy behavior */ @@ -29,13 +32,35 @@ static inline enum rtnl_kinds rtnl_msgtype_kind(int msgtype) return msgtype & RTNL_KIND_MASK; } -void rtnl_register(int protocol, int msgtype, - rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); -int rtnl_register_module(struct module *owner, int protocol, int msgtype, - rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); -int rtnl_unregister(int protocol, int msgtype); +/** + * struct rtnl_msg_handler - rtnetlink message type and handlers + * + * @owner: NULL for built-in, THIS_MODULE for module + * @protocol: Protocol family or PF_UNSPEC + * @msgtype: rtnetlink message type + * @doit: Function pointer called for each request message + * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message + * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions + */ +struct rtnl_msg_handler { + struct module *owner; + int protocol; + int msgtype; + rtnl_doit_func doit; + rtnl_dumpit_func dumpit; + int flags; +}; + void rtnl_unregister_all(int protocol); +int __rtnl_register_many(const struct rtnl_msg_handler *handlers, int n); +void __rtnl_unregister_many(const struct rtnl_msg_handler *handlers, int n); + +#define rtnl_register_many(handlers) \ + __rtnl_register_many(handlers, ARRAY_SIZE(handlers)) +#define rtnl_unregister_many(handlers) \ + __rtnl_unregister_many(handlers, ARRAY_SIZE(handlers)) + static inline int rtnl_msg_family(const struct nlmsghdr *nlh) { if (nlmsg_len(nlh) >= sizeof(struct rtgenmsg)) @@ -47,9 +72,11 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) /** * struct rtnl_link_ops - rtnetlink link operations * - * @list: Used internally + * @list: Used internally, protected by link_ops_mutex and SRCU + * @srcu: Used internally * @kind: Identifier * @netns_refund: Physical device, move to init_net on netns exit + * @peer_type: Peer device specific netlink attribute number (e.g. VETH_INFO_PEER) * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters @@ -78,6 +105,7 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) */ struct rtnl_link_ops { struct list_head list; + struct srcu_struct srcu; const char *kind; @@ -90,6 +118,7 @@ struct rtnl_link_ops { void (*setup)(struct net_device *dev); bool netns_refund; + const u16 peer_type; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], @@ -138,16 +167,14 @@ struct rtnl_link_ops { int *prividx, int attr); }; -int __rtnl_link_register(struct rtnl_link_ops *ops); -void __rtnl_link_unregister(struct rtnl_link_ops *ops); - int rtnl_link_register(struct rtnl_link_ops *ops); void rtnl_link_unregister(struct rtnl_link_ops *ops); /** * struct rtnl_af_ops - rtnetlink address family operations * - * @list: Used internally + * @list: Used internally, protected by RTNL and SRCU + * @srcu: Used internally * @family: Address family * @fill_link_af: Function to fill IFLA_AF_SPEC with address family * specific netlink attributes. @@ -160,6 +187,8 @@ void rtnl_link_unregister(struct rtnl_link_ops *ops); */ struct rtnl_af_ops { struct list_head list; + struct srcu_struct srcu; + int family; int (*fill_link_af)(struct sk_buff *skb, @@ -179,7 +208,7 @@ struct rtnl_af_ops { size_t (*get_stats_af_size)(const struct net_device *dev); }; -void rtnl_af_register(struct rtnl_af_ops *ops); +int rtnl_af_register(struct rtnl_af_ops *ops); void rtnl_af_unregister(struct rtnl_af_ops *ops); struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 79edd5b5e3c9..5d74fa7e694c 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -848,7 +848,6 @@ static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { - qdisc_calculate_pkt_len(skb, sch); return sch->enqueue(skb, sch, to_free); } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a2310fa995f6..84e6b9fd5610 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -28,7 +28,7 @@ #define __net_sctp_h__ /* Header Strategy. - * Start getting some control over the header file depencies: + * Start getting some control over the header file dependencies: * includes * constants * structs diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index f24a1bbcb3ef..31248cfdfb23 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -521,7 +521,7 @@ struct sctp_datamsg { refcount_t refcnt; /* When is this message no longer interesting to the peer? */ unsigned long expires_at; - /* Did the messenge fail to send? */ + /* Did the message fail to send? */ int send_error; u8 send_failed:1, can_delay:1, /* should this message be Nagle delayed */ @@ -792,7 +792,7 @@ struct sctp_transport { */ hb_sent:1, - /* Is the Path MTU update pending on this tranport */ + /* Is the Path MTU update pending on this transport */ pmtu_pending:1, dst_pending_confirm:1, /* need to confirm neighbour */ @@ -1223,7 +1223,7 @@ enum sctp_endpoint_type { }; /* - * A common base class to bridge the implmentation view of a + * A common base class to bridge the implementation view of a * socket (usually listening) endpoint versus an association's * local endpoint. * This common structure is useful for several purposes: @@ -1353,7 +1353,7 @@ struct sctp_endpoint { struct rcu_head rcu; }; -/* Recover the outter endpoint structure. */ +/* Recover the outer endpoint structure. */ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base) { struct sctp_endpoint *ep; @@ -1906,7 +1906,7 @@ struct sctp_association { __u32 rwnd_over; /* Keeps treack of rwnd pressure. This happens when we have - * a window, but not recevie buffer (i.e small packets). This one + * a window, but not receive buffer (i.e small packets). This one * is releases slowly (1 PMTU at a time ). */ __u32 rwnd_press; @@ -1994,7 +1994,7 @@ struct sctp_association { /* ADDIP Section 5.2 Upon reception of an ASCONF Chunk. * - * This is needed to implement itmes E1 - E4 of the updated + * This is needed to implement items E1 - E4 of the updated * spec. Here is the justification: * * Since the peer may bundle multiple ASCONF chunks toward us, @@ -2005,7 +2005,7 @@ struct sctp_association { /* These ASCONF chunks are waiting to be sent. * - * These chunaks can't be pushed to outqueue until receiving + * These chunks can't be pushed to outqueue until receiving * ASCONF_ACK for the previous ASCONF indicated by * addip_last_asconf, so as to guarantee that only one ASCONF * is in flight at any time. @@ -2059,13 +2059,13 @@ struct sctp_association { struct sctp_transport *new_transport; /* SCTP AUTH: list of the endpoint shared keys. These - * keys are provided out of band by the user applicaton + * keys are provided out of band by the user application * and can't change during the lifetime of the association */ struct list_head endpoint_shared_keys; /* SCTP AUTH: - * The current generated assocaition shared key (secret) + * The current generated association shared key (secret) */ struct sctp_auth_bytes *asoc_shared_key; struct sctp_shared_key *shkey; @@ -2121,7 +2121,7 @@ enum { SCTP_ASSOC_EYECATCHER = 0xa550c123, }; -/* Recover the outter association structure. */ +/* Recover the outer association structure. */ static inline struct sctp_association *sctp_assoc(struct sctp_ep_common *base) { struct sctp_association *asoc; diff --git a/include/net/sock.h b/include/net/sock.h index cce23ac4d514..7464e9f9f47c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -337,6 +337,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_user_frags: xarray of pages the user is holding a reference on. */ struct sock { /* @@ -542,6 +543,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct xarray sk_user_frags; }; struct sock_bh_locked { @@ -892,6 +894,8 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) +#define sk_for_each_bound_safe(__sk, tmp, list) \ + hlist_for_each_entry_safe(__sk, tmp, list, sk_bind_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset @@ -952,6 +956,12 @@ enum sock_flags { }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) +/* + * The highest bit of sk_tsflags is reserved for kernel-internal + * SOCKCM_FLAG_TS_OPT_ID. There is a check in core/sock.c to control that + * SOF_TIMESTAMPING* values do not reach this reserved area + */ +#define SOCKCM_FLAG_TS_OPT_ID BIT(31) static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { @@ -1624,7 +1634,7 @@ 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 + * This version should be used for very small section, where process won't block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled @@ -1750,6 +1760,15 @@ void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); void sock_pfree(struct sk_buff *skb); + +static inline void skb_set_owner_edemux(struct sk_buff *skb, struct sock *sk) +{ + skb_orphan(skb); + if (refcount_inc_not_zero(&sk->sk_refcnt)) { + skb->sk = sk; + skb->destructor = sock_edemux; + } +} #else #define sock_edemux sock_efree #endif @@ -1794,6 +1813,7 @@ struct sockcm_cookie { u64 transmit_time; u32 mark; u32 tsflags; + u32 ts_opt_id; }; static inline void sockcm_init(struct sockcm_cookie *sockc, @@ -2546,7 +2566,7 @@ struct sock_skb_cb { /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its - * alignement guarantee. + * alignment guarantee. */ #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) @@ -2651,39 +2671,48 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, sock_write_timestamp(sk, 0); } -void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags); +void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags); /** * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet - * @tsflags: timestamping flags to use + * @sockc: pointer to socket cmsg cookie to get timestamping info * @tx_flags: completed with instructions for time stamping * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno) * * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ -static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags, +static inline void _sock_tx_timestamp(struct sock *sk, + const struct sockcm_cookie *sockc, __u8 *tx_flags, __u32 *tskey) { + __u32 tsflags = sockc->tsflags; + if (unlikely(tsflags)) { __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && - tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) - *tskey = atomic_inc_return(&sk->sk_tskey) - 1; + tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) { + if (tsflags & SOCKCM_FLAG_TS_OPT_ID) + *tskey = sockc->ts_opt_id; + else + *tskey = atomic_inc_return(&sk->sk_tskey) - 1; + } } if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) *tx_flags |= SKBTX_WIFI_STATUS; } -static inline void sock_tx_timestamp(struct sock *sk, __u16 tsflags, +static inline void sock_tx_timestamp(struct sock *sk, + const struct sockcm_cookie *sockc, __u8 *tx_flags) { - _sock_tx_timestamp(sk, tsflags, tx_flags, NULL); + _sock_tx_timestamp(sk, sockc, tx_flags, NULL); } -static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) +static inline void skb_setup_tx_timestamp(struct sk_buff *skb, + const struct sockcm_cookie *sockc) { - _sock_tx_timestamp(skb->sk, tsflags, &skb_shinfo(skb)->tx_flags, + _sock_tx_timestamp(skb->sk, sockc, &skb_shinfo(skb)->tx_flags, &skb_shinfo(skb)->tskey); } @@ -2713,6 +2742,11 @@ static inline bool sk_is_stream_unix(const struct sock *sk) return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM; } +static inline bool sk_is_vsock(const struct sock *sk) +{ + return sk->sk_family == AF_VSOCK; +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from @@ -2782,6 +2816,16 @@ static inline bool sk_listener(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } +/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV or TIME_WAIT + * TCP SYNACK messages can be attached to LISTEN or NEW_SYN_RECV (depending on SYNCOOKIE) + * TCP RST and ACK can be attached to TIME_WAIT. + */ +static inline bool sk_listener_or_tw(const struct sock *sk) +{ + return (1 << READ_ONCE(sk->sk_state)) & + (TCPF_LISTEN | TCPF_NEW_SYN_RECV | TCPF_TIME_WAIT); +} + void sock_enable_timestamp(struct sock *sk, enum sock_flags flag); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); @@ -2806,8 +2850,6 @@ void sk_get_meminfo(const struct sock *sk, u32 *meminfo); extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; -extern int sysctl_tstamp_allow_data; - extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 6ec140b0a61b..6e4faf3ee76f 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -26,7 +26,7 @@ struct sock_reuseport { unsigned int bind_inany:1; unsigned int has_conns:1; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ - struct sock *socks[]; /* array of sock pointers */ + struct sock *socks[] __counted_by(max_socks); }; extern int reuseport_alloc(struct sock *sk, bool bind_inany); diff --git a/include/net/tcp.h b/include/net/tcp.h index 2aac11e7e1cc..e9b37b76e894 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1069,7 +1069,8 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to, /* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */ return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from) && - skb_pure_zcopy_same(to, from)); + skb_pure_zcopy_same(to, from) && + skb_frags_readable(to) == skb_frags_readable(from)); } static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to, @@ -2429,14 +2430,35 @@ void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb); void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb); +static inline void tcp_warn_once(const struct sock *sk, bool cond, const char *str) +{ + WARN_ONCE(cond, + "%scwn:%u out:%u sacked:%u lost:%u retrans:%u tlp_high_seq:%u sk_state:%u ca_state:%u advmss:%u mss_cache:%u pmtu:%u\n", + str, + tcp_snd_cwnd(tcp_sk(sk)), + tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out, + tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out, + tcp_sk(sk)->tlp_high_seq, sk->sk_state, + inet_csk(sk)->icsk_ca_state, + tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache, + inet_csk(sk)->icsk_pmtu_cookie); +} + /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; - u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); - return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; + if (likely(skb)) { + u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); + + return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; + } else { + tcp_warn_once(sk, 1, "rtx queue empty: "); + return jiffies_to_usecs(rto); + } + } /* diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 1d46460d0fef..df655ce6987d 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -183,7 +183,8 @@ int tcp_ao_hash_skb(unsigned short int family, const u8 *tkey, int hash_offset, u32 sne); int tcp_parse_ao(struct sock *sk, int cmd, unsigned short int family, sockptr_t optval, int optlen); -struct tcp_ao_key *tcp_ao_established_key(struct tcp_ao_info *ao, +struct tcp_ao_key *tcp_ao_established_key(const struct sock *sk, + struct tcp_ao_info *ao, int sndid, int rcvid); int tcp_ao_copy_all_matching(const struct sock *sk, struct sock *newsk, struct request_sock *req, struct sk_buff *skb, diff --git a/include/net/tls.h b/include/net/tls.h index 3a33924db2bc..61fef2880114 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -390,8 +390,12 @@ tls_offload_ctx_tx(const struct tls_context *tls_ctx) static inline bool tls_sw_has_ctx_tx(const struct sock *sk) { - struct tls_context *ctx = tls_get_ctx(sk); + struct tls_context *ctx; + + if (!sk_is_inet(sk) || !inet_test_bit(IS_ICSK, sk)) + return false; + ctx = tls_get_ctx(sk); if (!ctx) return false; return !!tls_sw_ctx_tx(ctx); @@ -399,8 +403,12 @@ static inline bool tls_sw_has_ctx_tx(const struct sock *sk) static inline bool tls_sw_has_ctx_rx(const struct sock *sk) { - struct tls_context *ctx = tls_get_ctx(sk); + struct tls_context *ctx; + + if (!sk_is_inet(sk) || !inet_test_bit(IS_ICSK, sk)) + return false; + ctx = tls_get_ctx(sk); if (!ctx) return false; return !!tls_sw_ctx_rx(ctx); diff --git a/include/net/udp.h b/include/net/udp.h index c4e05b14b648..6e89520e100d 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -50,39 +50,68 @@ struct udp_skb_cb { #define UDP_SKB_CB(__skb) ((struct udp_skb_cb *)((__skb)->cb)) /** - * struct udp_hslot - UDP hash slot + * struct udp_hslot - UDP hash slot used by udp_table.hash/hash4 * * @head: head of list of sockets + * @nulls_head: head of list of sockets, only used by hash4 * @count: number of sockets in 'head' list * @lock: spinlock protecting changes to head/count */ struct udp_hslot { - struct hlist_head head; + union { + struct hlist_head head; + /* hash4 uses hlist_nulls to avoid moving wrongly onto another + * hlist, because rehash() can happen with lookup(). + */ + struct hlist_nulls_head nulls_head; + }; int count; spinlock_t lock; -} __attribute__((aligned(2 * sizeof(long)))); +} __aligned(2 * sizeof(long)); + +/** + * struct udp_hslot_main - UDP hash slot used by udp_table.hash2 + * + * @hslot: basic hash slot + * @hash4_cnt: number of sockets in hslot4 of the same + * (local port, local address) + */ +struct udp_hslot_main { + struct udp_hslot hslot; /* must be the first member */ +#if !IS_ENABLED(CONFIG_BASE_SMALL) + u32 hash4_cnt; +#endif +} __aligned(2 * sizeof(long)); +#define UDP_HSLOT_MAIN(__hslot) ((struct udp_hslot_main *)(__hslot)) /** * struct udp_table - UDP table * * @hash: hash table, sockets are hashed on (local port) * @hash2: hash table, sockets are hashed on (local port, local address) + * @hash4: hash table, connected sockets are hashed on + * (local port, local address, remote port, remote address) * @mask: number of slots in hash tables, minus 1 * @log: log2(number of slots in hash table) */ struct udp_table { struct udp_hslot *hash; - struct udp_hslot *hash2; + struct udp_hslot_main *hash2; +#if !IS_ENABLED(CONFIG_BASE_SMALL) + struct udp_hslot *hash4; +#endif unsigned int mask; unsigned int log; }; extern struct udp_table udp_table; void udp_table_init(struct udp_table *, const char *); static inline struct udp_hslot *udp_hashslot(struct udp_table *table, - struct net *net, unsigned int num) + const struct net *net, + unsigned int num) { return &table->hash[udp_hashfn(net, num, table->mask)]; } + /* * For secondary hash, net_hash_mix() is performed before calling * udp_hashslot2(), this explains difference with udp_hashslot() @@ -90,8 +119,89 @@ static inline struct udp_hslot *udp_hashslot(struct udp_table *table, static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, unsigned int hash) { - return &table->hash2[hash & table->mask]; + return &table->hash2[hash & table->mask].hslot; +} + +#if IS_ENABLED(CONFIG_BASE_SMALL) +static inline void udp_table_hash4_init(struct udp_table *table) +{ +} + +static inline struct udp_hslot *udp_hashslot4(struct udp_table *table, + unsigned int hash) +{ + BUILD_BUG(); + return NULL; +} + +static inline bool udp_hashed4(const struct sock *sk) +{ + return false; +} + +static inline unsigned int udp_hash4_slot_size(void) +{ + return 0; +} + +static inline bool udp_has_hash4(const struct udp_hslot *hslot2) +{ + return false; +} + +static inline void udp_hash4_inc(struct udp_hslot *hslot2) +{ +} + +static inline void udp_hash4_dec(struct udp_hslot *hslot2) +{ } +#else /* !CONFIG_BASE_SMALL */ + +/* Must be called with table->hash2 initialized */ +static inline void udp_table_hash4_init(struct udp_table *table) +{ + table->hash4 = (void *)(table->hash2 + (table->mask + 1)); + for (int i = 0; i <= table->mask; i++) { + table->hash2[i].hash4_cnt = 0; + + INIT_HLIST_NULLS_HEAD(&table->hash4[i].nulls_head, i); + table->hash4[i].count = 0; + spin_lock_init(&table->hash4[i].lock); + } +} + +static inline struct udp_hslot *udp_hashslot4(struct udp_table *table, + unsigned int hash) +{ + return &table->hash4[hash & table->mask]; +} + +static inline bool udp_hashed4(const struct sock *sk) +{ + return !hlist_nulls_unhashed(&udp_sk(sk)->udp_lrpa_node); +} + +static inline unsigned int udp_hash4_slot_size(void) +{ + return sizeof(struct udp_hslot); +} + +static inline bool udp_has_hash4(const struct udp_hslot *hslot2) +{ + return UDP_HSLOT_MAIN(hslot2)->hash4_cnt; +} + +static inline void udp_hash4_inc(struct udp_hslot *hslot2) +{ + UDP_HSLOT_MAIN(hslot2)->hash4_cnt++; +} + +static inline void udp_hash4_dec(struct udp_hslot *hslot2) +{ + UDP_HSLOT_MAIN(hslot2)->hash4_cnt--; +} +#endif /* CONFIG_BASE_SMALL */ extern struct proto udp_prot; @@ -192,13 +302,29 @@ static inline int udp_lib_hash(struct sock *sk) } void udp_lib_unhash(struct sock *sk); -void udp_lib_rehash(struct sock *sk, u16 new_hash); +void udp_lib_rehash(struct sock *sk, u16 new_hash, u16 new_hash4); +u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, + const __be32 faddr, const __be16 fport); static inline void udp_lib_close(struct sock *sk, long timeout) { sk_common_release(sk); } +/* hash4 routines shared between UDPv4/6 */ +#if IS_ENABLED(CONFIG_BASE_SMALL) +static inline void udp_lib_hash4(struct sock *sk, u16 hash) +{ +} + +static inline void udp4_hash4(struct sock *sk) +{ +} +#else /* !CONFIG_BASE_SMALL */ +void udp_lib_hash4(struct sock *sk, u16 hash); +void udp4_hash4(struct sock *sk); +#endif /* CONFIG_BASE_SMALL */ + int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned int hash2_nulladdr); @@ -231,7 +357,7 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, } /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only upper 16 bits are relevant in the * computation for 16 bit port value. */ @@ -245,7 +371,7 @@ static inline int udp_rqueue_get(struct sock *sk) return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } -static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, +static inline bool udp_sk_bound_dev_eq(const struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) @@ -296,18 +422,19 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); -struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); -struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, + __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); -struct sock *udp6_lib_lookup(struct net *net, +struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif); -struct sock *__udp6_lib_lookup(struct net *net, +struct sock *__udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, diff --git a/include/net/x25.h b/include/net/x25.h index 597eb53c471e..5e833cfc864e 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -81,7 +81,7 @@ enum { #define X25_DEFAULT_WINDOW_SIZE 2 /* Default Window Size */ #define X25_DEFAULT_PACKET_SIZE X25_PS128 /* Default Packet Size */ -#define X25_DEFAULT_THROUGHPUT 0x0A /* Deafult Throughput */ +#define X25_DEFAULT_THROUGHPUT 0x0A /* Default Throughput */ #define X25_DEFAULT_REVERSE 0x00 /* Default Reverse Charging */ #define X25_SMODULUS 8 diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 0a5dca2b2b3f..40085afd9160 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -126,8 +126,8 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) if (likely(!xdp_buff_has_frags(xdp))) goto out; - list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) { - list_del(&pos->xskb_list_node); + list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { + list_del(&pos->list_node); xp_free(pos); } @@ -140,7 +140,7 @@ static inline void xsk_buff_add_frag(struct xdp_buff *xdp) { struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp); - list_add_tail(&frag->xskb_list_node, &frag->pool->xskb_list); + list_add_tail(&frag->list_node, &frag->pool->xskb_list); } static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) @@ -150,9 +150,9 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) struct xdp_buff_xsk *frag; frag = list_first_entry_or_null(&xskb->pool->xskb_list, - struct xdp_buff_xsk, xskb_list_node); + struct xdp_buff_xsk, list_node); if (frag) { - list_del(&frag->xskb_list_node); + list_del(&frag->list_node); ret = &frag->xdp; } @@ -163,7 +163,7 @@ static inline void xsk_buff_del_tail(struct xdp_buff *tail) { struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp); - list_del(&xskb->xskb_list_node); + list_del(&xskb->list_node); } static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first) @@ -172,7 +172,7 @@ static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first) struct xdp_buff_xsk *frag; frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk, - xskb_list_node); + list_node); return &frag->xdp; } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 54cef89f6c1e..32c09e85a64c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -19,6 +19,7 @@ #include <net/sock.h> #include <net/dst.h> +#include <net/inet_dscp.h> #include <net/ip.h> #include <net/route.h> #include <net/ipv6.h> @@ -67,27 +68,27 @@ - instance of a transformer, struct xfrm_state (=SA) - template to clone xfrm_state, struct xfrm_tmpl - SPD is plain linear list of xfrm_policy rules, ordered by priority. + SPD is organized as hash table (for policies that meet minimum address prefix + length setting, net->xfrm.policy_hthresh). Other policies are stored in + lists, sorted into rbtree ordered by destination and source address networks. + See net/xfrm/xfrm_policy.c for details. + (To be compatible with existing pfkeyv2 implementations, many rules with priority of 0x7fffffff are allowed to exist and such rules are ordered in an unpredictable way, thanks to bsd folks.) - Lookup is plain linear search until the first match with selector. - If "action" is "block", then we prohibit the flow, otherwise: if "xfrms_nr" is zero, the flow passes untransformed. Otherwise, policy entry has list of up to XFRM_MAX_DEPTH transformations, described by templates xfrm_tmpl. Each template is resolved to a complete xfrm_state (see below) and we pack bundle of transformations - to a dst_entry returned to requestor. + to a dst_entry returned to requester. dst -. xfrm .-> xfrm_state #1 |---. child .-> dst -. xfrm .-> xfrm_state #2 |---. child .-> dst -. xfrm .-> xfrm_state #3 |---. child .-> NULL - Bundles are cached at xrfm_policy struct (field ->bundles). - Resolution of xrfm_tmpl ----------------------- @@ -184,10 +185,13 @@ struct xfrm_state { }; struct hlist_node byspi; struct hlist_node byseq; + struct hlist_node state_cache; + struct hlist_node state_cache_input; refcount_t refcnt; spinlock_t lock; + u32 pcpu_num; struct xfrm_id id; struct xfrm_selector sel; struct xfrm_mark mark; @@ -349,20 +353,25 @@ struct xfrm_if_cb { void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); void xfrm_if_unregister_cb(void); +struct xfrm_dst_lookup_params { + struct net *net; + dscp_t dscp; + int oif; + xfrm_address_t *saddr; + xfrm_address_t *daddr; + u32 mark; + __u8 ipproto; + union flowi_uli uli; +}; + struct net_device; struct xfrm_type; struct xfrm_dst; struct xfrm_policy_afinfo { struct dst_ops *dst_ops; - struct dst_entry *(*dst_lookup)(struct net *net, - int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - u32 mark); - int (*get_saddr)(struct net *net, int oif, - xfrm_address_t *saddr, - xfrm_address_t *daddr, - u32 mark); + struct dst_entry *(*dst_lookup)(const struct xfrm_dst_lookup_params *params); + int (*get_saddr)(xfrm_address_t *saddr, + const struct xfrm_dst_lookup_params *params); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl); @@ -526,11 +535,44 @@ struct xfrm_policy_queue { unsigned long timeout; }; +/** + * struct xfrm_policy - xfrm policy + * @xp_net: network namespace the policy lives in + * @bydst: hlist node for SPD hash table or rbtree list + * @byidx: hlist node for index hash table + * @state_cache_list: hlist head for policy cached xfrm states + * @lock: serialize changes to policy structure members + * @refcnt: reference count, freed once it reaches 0 + * @pos: kernel internal tie-breaker to determine age of policy + * @timer: timer + * @genid: generation, used to invalidate old policies + * @priority: priority, set by userspace + * @index: policy index (autogenerated) + * @if_id: virtual xfrm interface id + * @mark: packet mark + * @selector: selector + * @lft: liftime configuration data + * @curlft: liftime state + * @walk: list head on pernet policy list + * @polq: queue to hold packets while aqcuire operaion in progress + * @bydst_reinsert: policy tree node needs to be merged + * @type: XFRM_POLICY_TYPE_MAIN or _SUB + * @action: XFRM_POLICY_ALLOW or _BLOCK + * @flags: XFRM_POLICY_LOCALOK, XFRM_POLICY_ICMP + * @xfrm_nr: number of used templates in @xfrm_vec + * @family: protocol family + * @security: SELinux security label + * @xfrm_vec: array of templates to resolve state + * @rcu: rcu head, used to defer memory release + * @xdo: hardware offload state + */ struct xfrm_policy { possible_net_t xp_net; struct hlist_node bydst; struct hlist_node byidx; + struct hlist_head state_cache_list; + /* This lock only affects elements except for entry. */ rwlock_t lock; refcount_t refcnt; @@ -555,7 +597,6 @@ struct xfrm_policy { u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; - struct hlist_node bydst_inexact_list; struct rcu_head rcu; struct xfrm_dev_offload xdo; @@ -1016,7 +1057,7 @@ void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); struct xfrm_if_parms { int link; /* ifindex of underlying L2 interface */ - u32 if_id; /* interface identifyer */ + u32 if_id; /* interface identifier */ bool collect_md; }; @@ -1611,6 +1652,10 @@ int xfrm_state_update(struct xfrm_state *x); struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family); +struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, + const xfrm_address_t *daddr, + __be32 spi, u8 proto, + unsigned short family); struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, @@ -1650,7 +1695,7 @@ struct xfrmk_spdinfo { u32 spdhmcnt; }; -struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); +struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_delete(struct xfrm_state *x); int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); @@ -1735,10 +1780,7 @@ static inline int xfrm_user_policy(struct sock *sk, int optname, } #endif -struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - int family, u32 mark); +struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params); struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp); @@ -1765,7 +1807,7 @@ int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack); int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi, struct netlink_ext_ack *extack); struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, - u8 mode, u32 reqid, u32 if_id, u8 proto, + u8 mode, u32 reqid, u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family); diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index bacb33f1e3e5..bb03cee716b3 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -28,9 +28,7 @@ struct xdp_buff_xsk { dma_addr_t dma; dma_addr_t frame_dma; struct xsk_buff_pool *pool; - u64 orig_addr; - struct list_head free_list_node; - struct list_head xskb_list_node; + struct list_head list_node; }; #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb)) @@ -78,6 +76,7 @@ struct xsk_buff_pool { u32 chunk_size; u32 chunk_shift; u32 frame_len; + u32 xdp_zc_max_segs; u8 tx_metadata_len; /* inherited from umem */ u8 cached_need_wakeup; bool uses_need_wakeup; @@ -120,7 +119,6 @@ void xp_free(struct xdp_buff_xsk *xskb); static inline void xp_init_xskb_addr(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool, u64 addr) { - xskb->orig_addr = addr; xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom; } @@ -222,14 +220,19 @@ static inline void xp_release(struct xdp_buff_xsk *xskb) xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb; } -static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb) +static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb, + struct xsk_buff_pool *pool) { - u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start; + u64 orig_addr = xskb->xdp.data - pool->addrs; + u64 offset; - offset += xskb->pool->headroom; - if (!xskb->pool->unaligned) - return xskb->orig_addr + offset; - return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); + if (!pool->unaligned) + return orig_addr; + + offset = xskb->xdp.data - xskb->xdp.data_hard_start; + orig_addr -= offset; + offset += pool->headroom; + return orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); } static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool) |