From 8665bd53f2f2e27e5511d90428cb3f60e6d0ce15 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 18 May 2024 20:50:12 +0200 Subject: Merging upstream version 6.8.9. Signed-off-by: Daniel Baumann --- include/net/act_api.h | 6 +- include/net/addrconf.h | 4 + include/net/af_unix.h | 5 +- include/net/bluetooth/bluetooth.h | 11 +++ include/net/bluetooth/hci.h | 25 ++++++ include/net/bluetooth/hci_core.h | 63 +++++++++++++-- include/net/bluetooth/hci_sync.h | 20 ++++- include/net/bluetooth/l2cap.h | 2 +- include/net/cfg80211.h | 148 +++++++++++++++++++++++++++++----- include/net/cfg802154.h | 72 +++++++++++++++++ include/net/dropreason-core.h | 24 +++++- include/net/fib_rules.h | 3 +- include/net/genetlink.h | 55 +++++++++++-- include/net/ieee802154_netdev.h | 60 ++++++++++++++ include/net/inet_connection_sock.h | 1 + include/net/inet_hashtables.h | 21 ++--- include/net/inet_sock.h | 5 +- include/net/inet_timewait_sock.h | 4 - include/net/ip.h | 10 ++- include/net/ip_tunnels.h | 44 ++++++++++ include/net/ipv6.h | 5 -- include/net/iucv/iucv.h | 4 +- include/net/mac80211.h | 61 ++++++++------ include/net/macsec.h | 56 +++++++++++++ include/net/mana/gdma.h | 12 ++- include/net/mana/mana.h | 47 +++++++---- include/net/netdev_rx_queue.h | 4 + include/net/netfilter/nf_flow_table.h | 21 +++-- include/net/netfilter/nf_tables.h | 63 ++++++++++++--- include/net/netlink.h | 47 +++++++++-- include/net/netns/core.h | 1 + include/net/netns/ipv4.h | 50 ++++++++---- include/net/netns/smc.h | 2 + include/net/nl802154.h | 22 ++++- include/net/page_pool/helpers.h | 85 ++++++++++--------- include/net/page_pool/types.h | 49 +++++++---- include/net/pkt_cls.h | 6 -- include/net/pkt_sched.h | 18 ----- include/net/sch_generic.h | 44 ++++++++-- include/net/scm.h | 9 +++ include/net/smc.h | 16 ++-- include/net/sock.h | 76 +++++++---------- include/net/tc_act/tc_ipt.h | 17 ---- include/net/tc_act/tc_mirred.h | 1 + include/net/tc_wrapper.h | 4 - include/net/tcp.h | 22 ++--- include/net/tcp_ao.h | 6 +- include/net/tcp_states.h | 2 + include/net/tls.h | 3 +- include/net/vxlan.h | 33 ++++---- include/net/xdp.h | 20 ++++- include/net/xdp_sock.h | 113 ++++++++++++++++++++++++++ include/net/xdp_sock_drv.h | 51 ++++++++++++ include/net/xfrm.h | 9 +++ include/net/xsk_buff_pool.h | 10 +++ 55 files changed, 1223 insertions(+), 349 deletions(-) delete mode 100644 include/net/tc_act/tc_ipt.h (limited to 'include/net') diff --git a/include/net/act_api.h b/include/net/act_api.h index 4ae0580b63..e1e5e72b90 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -137,6 +137,7 @@ struct tc_action_ops { #ifdef CONFIG_NET_CLS_ACT +#define ACT_P_BOUND 0 #define ACT_P_CREATED 1 #define ACT_P_DELETED 1 @@ -191,7 +192,7 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, u32 flags); -void tcf_idr_insert_many(struct tc_action *actions[]); +void tcf_idr_insert_many(struct tc_action *actions[], int init_res[]); void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tc_action **a, int bind); @@ -207,8 +208,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, struct tc_action *actions[], int init_res[], size_t *attr_size, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack); -struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police, - bool rtnl_held, +struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, u32 flags, struct netlink_ext_ack *extack); struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 61ebe723ee..facb7a469e 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -437,6 +437,10 @@ static inline void in6_ifa_hold(struct inet6_ifaddr *ifp) refcount_inc(&ifp->refcnt); } +static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp) +{ + return refcount_inc_not_zero(&ifp->refcnt); +} /* * compute link-local solicited-node multicast address diff --git a/include/net/af_unix.h b/include/net/af_unix.h index afd40dce40..77bf30203d 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -55,7 +55,7 @@ struct unix_sock { struct mutex iolock, bindlock; struct sock *peer; struct list_head link; - atomic_long_t inflight; + unsigned long inflight; spinlock_t lock; unsigned long gc_flags; #define UNIX_GC_CANDIDATE 0 @@ -77,6 +77,9 @@ enum unix_socket_lock_class { U_LOCK_NORMAL, U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ + U_LOCK_GC_LISTENER, /* used for listening socket while determining gc + * candidates to close a small race window. + */ }; static inline void unix_state_lock_nested(struct sock *sk, diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 7ffa8c192c..eaec5d6caa 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -164,6 +164,8 @@ struct bt_voice { #define BT_ISO_QOS_BIG_UNSET 0xff #define BT_ISO_QOS_BIS_UNSET 0xff +#define BT_ISO_SYNC_TIMEOUT 0x07d0 /* 20 secs */ + struct bt_iso_io_qos { __u32 interval; __u16 latency; @@ -583,6 +585,15 @@ 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 0d23102457..2cfd8d8626 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -176,6 +176,15 @@ enum { */ HCI_QUIRK_USE_BDADDR_PROPERTY, + /* When this quirk is set, the Bluetooth Device Address provided by + * the 'local-bd-address' fwnode property is incorrectly specified in + * big-endian order. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BDADDR_PROPERTY_BROKEN, + /* When this quirk is set, the duplicate filtering during * scanning is based on Bluetooth devices addresses. To allow * RSSI based updates, restart scanning if needed. @@ -330,6 +339,14 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_BROKEN_LE_CODED, + + /* + * When this quirk is set, the HCI_OP_READ_ENC_KEY_SIZE command is + * skipped during an HCI_EV_ENCRYPT_CHANGE event. This is required + * for Actions Semiconductor ATS2851 based controllers, which erroneously + * claim to support it. + */ + HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, }; /* HCI device flags */ @@ -436,6 +453,7 @@ enum { #define HCI_NCMD_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ #define HCI_ACL_TX_TIMEOUT msecs_to_jiffies(45000) /* 45 seconds */ #define HCI_AUTO_OFF_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ +#define HCI_ACL_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ #define HCI_LE_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ #define HCI_LE_AUTOCONN_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ @@ -651,6 +669,7 @@ enum { #define HCI_ERROR_PIN_OR_KEY_MISSING 0x06 #define HCI_ERROR_MEMORY_EXCEEDED 0x07 #define HCI_ERROR_CONNECTION_TIMEOUT 0x08 +#define HCI_ERROR_COMMAND_DISALLOWED 0x0c #define HCI_ERROR_REJ_LIMITED_RESOURCES 0x0d #define HCI_ERROR_REJ_BAD_ADDR 0x0f #define HCI_ERROR_INVALID_PARAMETERS 0x12 @@ -659,6 +678,7 @@ enum { #define HCI_ERROR_REMOTE_POWER_OFF 0x15 #define HCI_ERROR_LOCAL_HOST_TERM 0x16 #define HCI_ERROR_PAIRING_NOT_ALLOWED 0x18 +#define HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE 0x1e #define HCI_ERROR_INVALID_LL_PARAMS 0x1e #define HCI_ERROR_UNSPECIFIED 0x1f #define HCI_ERROR_ADVERTISING_TIMEOUT 0x3c @@ -2033,6 +2053,7 @@ struct hci_cp_le_set_per_adv_params { } __packed; #define HCI_MAX_PER_AD_LENGTH 252 +#define HCI_MAX_PER_AD_TOT_LEN 1650 #define HCI_OP_LE_SET_PER_ADV_DATA 0x203f struct hci_cp_le_set_per_adv_data { @@ -2793,6 +2814,10 @@ struct hci_ev_le_per_adv_report { __u8 data[]; } __packed; +#define LE_PA_DATA_COMPLETE 0x00 +#define LE_PA_DATA_MORE_TO_COME 0x01 +#define LE_PA_DATA_TRUNCATED 0x02 + #define HCI_EV_LE_EXT_ADV_SET_TERM 0x12 struct hci_evt_le_ext_adv_set_term { __u8 status; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 24446038d8..fe9e1524d3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -539,7 +539,6 @@ struct hci_dev { struct work_struct tx_work; struct delayed_work le_scan_disable; - struct delayed_work le_scan_restart; struct sk_buff_head rx_q; struct sk_buff_head raw_q; @@ -736,8 +735,11 @@ struct hci_conn { __u16 le_supv_timeout; __u8 le_adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 le_adv_data_len; - __u8 le_per_adv_data[HCI_MAX_PER_AD_LENGTH]; - __u8 le_per_adv_data_len; + __u8 le_per_adv_data[HCI_MAX_PER_AD_TOT_LEN]; + __u16 le_per_adv_data_len; + __u16 le_per_adv_data_offset; + __u8 le_adv_phy; + __u8 le_adv_sec_phy; __u8 le_tx_phy; __u8 le_rx_phy; __s8 rssi; @@ -1085,6 +1087,24 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev) return c->acl_num + c->amp_num + c->sco_num + c->le_num + c->iso_num; } +static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) +{ + 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 == conn) { + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); + + return false; +} + static inline __u8 hci_conn_lookup_type(struct hci_dev *hdev, __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; @@ -1297,6 +1317,30 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, 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; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (bacmp(&c->dst, BDADDR_ANY) || c->type != ISO_LINK || + c->state != state) + continue; + + if (handle == c->iso_qos.bcast.big) { + rcu_read_unlock(); + return c; + } + } + + rcu_read_unlock(); + + return NULL; +} + static inline struct hci_conn * hci_conn_hash_lookup_pa_sync_big_handle(struct hci_dev *hdev, __u8 big) { @@ -1458,7 +1502,6 @@ struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role); void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); -void hci_conn_check_pending(struct hci_dev *hdev); struct hci_chan *hci_chan_create(struct hci_conn *conn); void hci_chan_del(struct hci_chan *chan); @@ -1471,12 +1514,14 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, enum conn_reasons conn_reason); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, - u16 conn_timeout, u8 role); + u16 conn_timeout, u8 role, u8 phy, u8 sec_phy); +void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, - enum conn_reasons conn_reason); + enum conn_reasons conn_reason, u16 timeout); struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, - __u16 setting, struct bt_codec *codec); + __u16 setting, struct bt_codec *codec, + u16 timeout); struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos); struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, @@ -1862,6 +1907,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ (hdev->commands[39] & 0x04)) +#define read_key_size_capable(dev) \ + ((dev)->commands[20] & 0x10 && \ + !test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) + /* Use enhanced synchronous connection if command is supported and its quirk * has not been set. */ diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index e2582c2425..6a9d063e9f 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -48,6 +48,18 @@ int hci_cmd_sync_submit(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(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); +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); +void hci_cmd_sync_cancel_entry(struct hci_dev *hdev, + struct hci_cmd_sync_work_entry *entry); +bool hci_cmd_sync_dequeue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +bool hci_cmd_sync_dequeue_once(struct hci_dev *hdev, + hci_cmd_sync_work_func_t func, void *data, + hci_cmd_sync_work_destroy_t destroy); int hci_update_eir_sync(struct hci_dev *hdev); int hci_update_class_sync(struct hci_dev *hdev); @@ -127,8 +139,6 @@ struct hci_conn; int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason); -int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn); - int hci_le_create_cis_sync(struct hci_dev *hdev); int hci_le_remove_cig_sync(struct hci_dev *hdev, u8 handle); @@ -138,3 +148,9 @@ int hci_le_terminate_big_sync(struct hci_dev *hdev, u8 handle, u8 reason); int hci_le_big_terminate_sync(struct hci_dev *hdev, u8 handle); int hci_le_pa_terminate_sync(struct hci_dev *hdev, u16 handle); + +int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn); + +int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn); + +int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn); diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 92d7197f9a..a4278aa618 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -939,7 +939,7 @@ int l2cap_add_scid(struct l2cap_chan *chan, __u16 scid); struct l2cap_chan *l2cap_chan_create(void); void l2cap_chan_close(struct l2cap_chan *chan, int reason); int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, - bdaddr_t *dst, u8 dst_type); + bdaddr_t *dst, u8 dst_type, u16 timeout); int l2cap_chan_reconfigure(struct l2cap_chan *chan, __u16 mtu); int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len); void l2cap_chan_busy(struct l2cap_chan *chan, int busy); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e90596e21c..0180eaec45 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -52,7 +52,7 @@ * such wiphy can have zero, one, or many virtual interfaces associated with * it, which need to be identified as such by pointing the network interface's * @ieee80211_ptr pointer to a &struct wireless_dev which further describes - * the wireless part of the interface, normally this struct is embedded in the + * the wireless part of the interface. Normally this struct is embedded in the * network interface's private data area. Drivers can optionally allow creating * or destroying virtual interfaces on the fly, but without at least one or the * ability to create some the wireless device isn't useful. @@ -117,6 +117,11 @@ struct wiphy; * This may be due to the driver or due to regulatory bandwidth * restrictions. * @IEEE80211_CHAN_NO_EHT: EHT operation is not permitted on this channel. + * @IEEE80211_CHAN_DFS_CONCURRENT: See %NL80211_RRF_DFS_CONCURRENT + * @IEEE80211_CHAN_NO_UHB_VLP_CLIENT: Client connection with VLP AP + * not permitted using this channel + * @IEEE80211_CHAN_NO_UHB_AFC_CLIENT: Client connection with AFC AP + * not permitted using this channel */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = 1<<0, @@ -140,6 +145,9 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_16MHZ = 1<<18, IEEE80211_CHAN_NO_320MHZ = 1<<19, IEEE80211_CHAN_NO_EHT = 1<<20, + IEEE80211_CHAN_DFS_CONCURRENT = 1<<21, + IEEE80211_CHAN_NO_UHB_VLP_CLIENT= 1<<22, + IEEE80211_CHAN_NO_UHB_AFC_CLIENT= 1<<23, }; #define IEEE80211_CHAN_NO_HT40 \ @@ -976,6 +984,15 @@ const struct cfg80211_chan_def * cfg80211_chandef_compatible(const struct cfg80211_chan_def *chandef1, const struct cfg80211_chan_def *chandef2); +/** + * nl80211_chan_width_to_mhz - get the channel width in MHz + * @chan_width: the channel width from &enum nl80211_chan_width + * + * Return: channel width in MHz if the chan_width from &enum nl80211_chan_width + * is valid. -1 otherwise. + */ +int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width); + /** * cfg80211_chandef_valid - check if a channel definition is valid * @chandef: the channel definition to check @@ -1664,6 +1681,21 @@ struct link_station_del_parameters { u32 link_id; }; +/** + * struct cfg80211_ttlm_params: TID to link mapping parameters + * + * Used for setting a TID to link mapping. + * + * @dlink: Downlink TID to link mapping, as defined in section 9.4.2.314 + * (TID-To-Link Mapping element) in Draft P802.11be_D4.0. + * @ulink: Uplink TID to link mapping, as defined in section 9.4.2.314 + * (TID-To-Link Mapping element) in Draft P802.11be_D4.0. + */ +struct cfg80211_ttlm_params { + u16 dlink[8]; + u16 ulink[8]; +}; + /** * struct station_parameters - station parameters * @@ -2560,7 +2592,7 @@ struct cfg80211_scan_info { * @short_ssid: short ssid to scan for * @bssid: bssid to scan for * @channel_idx: idx of the channel in the channel array in the scan request - * which the above info relvant to + * which the above info is relevant to * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU * @short_ssid_valid: @short_ssid is valid and can be used * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait @@ -2608,6 +2640,8 @@ struct cfg80211_scan_6ghz_params { * @n_6ghz_params: number of 6 GHz params * @scan_6ghz_params: 6 GHz params * @bssid: BSSID to scan for (most commonly, the wildcard BSSID) + * @tsf_report_link_id: for MLO, indicates the link ID of the BSS that should be + * used for TSF reporting. Can be set to -1 to indicate no preference. */ struct cfg80211_scan_request { struct cfg80211_ssid *ssids; @@ -2636,6 +2670,7 @@ struct cfg80211_scan_request { bool scan_6ghz; u32 n_6ghz_params; struct cfg80211_scan_6ghz_params *scan_6ghz_params; + s8 tsf_report_link_id; /* keep last */ struct ieee80211_channel *channels[] __counted_by(n_channels); @@ -2816,6 +2851,13 @@ enum cfg80211_signal_type { * the BSS that requested the scan in which the beacon/probe was received. * @chains: bitmask for filled values in @chain_signal. * @chain_signal: per-chain signal strength of last received BSS in dBm. + * @restrict_use: restrict usage, if not set, assume @use_for is + * %NL80211_BSS_USE_FOR_NORMAL. + * @use_for: bitmap of possible usage for this BSS, see + * &enum nl80211_bss_use_for + * @cannot_use_reasons: the reasons (bitmap) for not being able to connect, + * if @restrict_use is set and @use_for is zero (empty); may be 0 for + * unspecified reasons; see &enum nl80211_bss_cannot_use_reasons * @drv_data: Data to be passed through to @inform_bss */ struct cfg80211_inform_bss { @@ -2827,6 +2869,9 @@ struct cfg80211_inform_bss { u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; + u8 restrict_use:1, use_for:7; + u8 cannot_use_reasons; + void *drv_data; }; @@ -2880,6 +2925,11 @@ struct cfg80211_bss_ies { * @chain_signal: per-chain signal strength of last received BSS in dBm. * @bssid_index: index in the multiple BSS set * @max_bssid_indicator: max number of members in the BSS set + * @use_for: bitmap of possible usage for this BSS, see + * &enum nl80211_bss_use_for + * @cannot_use_reasons: the reasons (bitmap) for not being able to connect, + * if @restrict_use is set and @use_for is zero (empty); may be 0 for + * unspecified reasons; see &enum nl80211_bss_cannot_use_reasons * @priv: private area for driver use, has at least wiphy->bss_priv_size bytes */ struct cfg80211_bss { @@ -2907,6 +2957,9 @@ struct cfg80211_bss { u8 bssid_index; u8 max_bssid_indicator; + u8 use_for; + u8 cannot_use_reasons; + u8 priv[] __aligned(sizeof(void *)); }; @@ -3184,8 +3237,8 @@ struct cfg80211_ibss_params { * * @behaviour: requested BSS selection behaviour. * @param: parameters for requestion behaviour. - * @band_pref: preferred band for %NL80211_BSS_SELECT_ATTR_BAND_PREF. - * @adjust: parameters for %NL80211_BSS_SELECT_ATTR_RSSI_ADJUST. + * @param.band_pref: preferred band for %NL80211_BSS_SELECT_ATTR_BAND_PREF. + * @param.adjust: parameters for %NL80211_BSS_SELECT_ATTR_RSSI_ADJUST. */ struct cfg80211_bss_selection { enum nl80211_bss_select_attr behaviour; @@ -4497,6 +4550,7 @@ struct mgmt_frame_regs { * @del_link_station: Remove a link of a station. * * @set_hw_timestamp: Enable/disable HW timestamping of TM/FTM frames. + * @set_ttlm: set the TID to link mapping. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4856,6 +4910,8 @@ struct cfg80211_ops { struct link_station_del_parameters *params); int (*set_hw_timestamp)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_set_hw_timestamp *hwts); + int (*set_ttlm)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_ttlm_params *params); }; /* @@ -4914,6 +4970,8 @@ struct cfg80211_ops { * NL80211_REGDOM_SET_BY_DRIVER. * @WIPHY_FLAG_CHANNEL_CHANGE_ON_BEACON: reg_call_notifier() is called if driver * set this flag to update channels on beacon hints. + * @WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY: support connection to non-primary link + * of an NSTR mobile AP MLD. * @WIPHY_FLAG_DISABLE_WEXT: disable wireless extensions for this device */ enum wiphy_flags { @@ -4929,7 +4987,7 @@ enum wiphy_flags { WIPHY_FLAG_DISABLE_WEXT = BIT(9), WIPHY_FLAG_MESH_AUTH = BIT(10), WIPHY_FLAG_SUPPORTS_EXT_KCK_32 = BIT(11), - /* use hole at 12 */ + WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY = BIT(12), WIPHY_FLAG_SUPPORTS_FW_ROAM = BIT(13), WIPHY_FLAG_AP_UAPSD = BIT(14), WIPHY_FLAG_SUPPORTS_TDLS = BIT(15), @@ -6019,7 +6077,6 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, * wireless device if it has no netdev * @u: union containing data specific to @iftype * @connected: indicates if connected or not (STA mode) - * @bssid: (private) Used by the internal configuration code * @wext: (private) Used by the internal wireless extensions compat code * @wext.ibss: (private) IBSS data part of wext handling * @wext.connect: (private) connection handling data @@ -6039,8 +6096,6 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, * @mgmt_registrations: list of registrations for management frames * @mgmt_registrations_need_update: mgmt registrations were updated, * need to propagate the update to the driver - * @beacon_interval: beacon interval used on this device for transmitting - * beacons, 0 when not valid * @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. @@ -7121,6 +7176,23 @@ enum cfg80211_bss_frame_type { int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, enum nl80211_band band); +/** + * cfg80211_ssid_eq - compare two SSIDs + * @a: first SSID + * @b: second SSID + * + * Return: %true if SSIDs are equal, %false otherwise. + */ +static inline bool +cfg80211_ssid_eq(struct cfg80211_ssid *a, struct cfg80211_ssid *b) +{ + if (WARN_ON(!a || !b)) + return false; + if (a->ssid_len != b->ssid_len) + return false; + return memcmp(a->ssid, b->ssid, a->ssid_len) ? false : true; +} + /** * cfg80211_inform_bss_data - inform cfg80211 of a new BSS * @@ -7167,6 +7239,25 @@ cfg80211_inform_bss(struct wiphy *wiphy, gfp); } +/** + * __cfg80211_get_bss - get a BSS reference + * @wiphy: the wiphy this BSS struct belongs to + * @channel: the channel to search on (or %NULL) + * @bssid: the desired BSSID (or %NULL) + * @ssid: the desired SSID (or %NULL) + * @ssid_len: length of the SSID (or 0) + * @bss_type: type of BSS, see &enum ieee80211_bss_type + * @privacy: privacy filter, see &enum ieee80211_privacy + * @use_for: indicates which use is intended + */ +struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy, + struct ieee80211_channel *channel, + const u8 *bssid, + const u8 *ssid, size_t ssid_len, + enum ieee80211_bss_type bss_type, + enum ieee80211_privacy privacy, + u32 use_for); + /** * cfg80211_get_bss - get a BSS reference * @wiphy: the wiphy this BSS struct belongs to @@ -7176,13 +7267,20 @@ cfg80211_inform_bss(struct wiphy *wiphy, * @ssid_len: length of the SSID (or 0) * @bss_type: type of BSS, see &enum ieee80211_bss_type * @privacy: privacy filter, see &enum ieee80211_privacy + * + * This version implies regular usage, %NL80211_BSS_USE_FOR_NORMAL. */ -struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, - struct ieee80211_channel *channel, - const u8 *bssid, - const u8 *ssid, size_t ssid_len, - enum ieee80211_bss_type bss_type, - enum ieee80211_privacy privacy); +static inline struct cfg80211_bss * +cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, + const u8 *bssid, const u8 *ssid, size_t ssid_len, + enum ieee80211_bss_type bss_type, + enum ieee80211_privacy privacy) +{ + return __cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len, + bss_type, privacy, + NL80211_BSS_USE_FOR_NORMAL); +} + static inline struct cfg80211_bss * cfg80211_get_ibss(struct wiphy *wiphy, struct ieee80211_channel *channel, @@ -7276,8 +7374,6 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr); /** * struct cfg80211_rx_assoc_resp_data - association response data - * @bss: the BSS that association was requested with, ownership of the pointer - * moves to cfg80211 in the call to cfg80211_rx_assoc_resp() * @buf: (Re)Association Response frame (header + body) * @len: length of the frame data * @uapsd_queues: bitmap of queues configured for uapsd. Same format @@ -7287,6 +7383,8 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr); * @ap_mld_addr: AP MLD address (in case of MLO) * @links: per-link information indexed by link ID, use links[0] for * non-MLO connections + * @links.bss: the BSS that association was requested with, ownership of the + * pointer moves to cfg80211 in the call to cfg80211_rx_assoc_resp() * @links.status: Set this (along with a BSS pointer) for links that * were rejected by the AP. */ @@ -7315,7 +7413,7 @@ struct cfg80211_rx_assoc_resp_data { * This function may sleep. The caller must hold the corresponding wdev's mutex. */ void cfg80211_rx_assoc_resp(struct net_device *dev, - struct cfg80211_rx_assoc_resp_data *data); + const struct cfg80211_rx_assoc_resp_data *data); /** * struct cfg80211_assoc_failure - association failure data @@ -7434,7 +7532,7 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev, * RFkill integration in cfg80211 is almost invisible to drivers, * as cfg80211 automatically registers an rfkill instance for each * wireless device it knows about. Soft kill is also translated - * into disconnecting and turning all interfaces off, drivers are + * into disconnecting and turning all interfaces off. Drivers are * expected to turn off the device when all interfaces are down. * * However, devices may have a hard RFkill line, in which case they @@ -7482,7 +7580,7 @@ static inline void wiphy_rfkill_stop_polling(struct wiphy *wiphy) * the configuration mechanism. * * A driver supporting vendor commands must register them as an array - * in struct wiphy, with handlers for each one, each command has an + * in struct wiphy, with handlers for each one. Each command has an * OUI and sub command ID to identify it. * * Note that this feature should not be (ab)used to implement protocol @@ -7646,7 +7744,7 @@ static inline void cfg80211_vendor_event(struct sk_buff *skb, gfp_t gfp) * interact with driver-specific tools to aid, for instance, * factory programming. * - * This chapter describes how drivers interact with it, for more + * This chapter describes how drivers interact with it. For more * information see the nl80211 book's chapter on it. */ @@ -9305,6 +9403,16 @@ bool cfg80211_valid_disable_subchannel_bitmap(u16 *bitmap, */ void cfg80211_links_removed(struct net_device *dev, u16 link_mask); +/** + * cfg80211_schedule_channels_check - schedule regulatory check if needed + * @wdev: the wireless device to check + * + * In case the device supports NO_IR or DFS relaxations, schedule regulatory + * channels check, as previous concurrent operation conditions may not + * hold anymore. + */ +void cfg80211_schedule_channels_check(struct wireless_dev *wdev); + #ifdef CONFIG_CFG80211_DEBUGFS /** * wiphy_locked_debugfs_read - do a locked read in debugfs diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 519d23941b..76d2cd2e2b 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -20,6 +20,7 @@ struct wpan_phy; struct wpan_phy_cca; struct cfg802154_scan_request; struct cfg802154_beacon_request; +struct ieee802154_addr; #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL struct ieee802154_llsec_device_key; @@ -77,6 +78,12 @@ struct cfg802154_ops { struct cfg802154_beacon_request *request); int (*stop_beacons)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev); + int (*associate)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + struct ieee802154_addr *coord); + int (*disassociate)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + struct ieee802154_addr *target); #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL void (*get_llsec_table)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, @@ -303,6 +310,22 @@ struct ieee802154_coord_desc { bool gts_permit; }; +/** + * struct ieee802154_pan_device - PAN device information + * @pan_id: the PAN ID of this device + * @mode: the preferred mode to reach the device + * @short_addr: the short address of this device + * @extended_addr: the extended address of this device + * @node: the list node + */ +struct ieee802154_pan_device { + __le16 pan_id; + u8 mode; + __le16 short_addr; + __le64 extended_addr; + struct list_head node; +}; + /** * struct cfg802154_scan_request - Scan request * @@ -479,6 +502,13 @@ struct wpan_dev { /* fallback for acknowledgment bit setting */ bool ackreq; + + /* Associations */ + struct mutex association_lock; + struct ieee802154_pan_device *parent; + struct list_head children; + unsigned int max_associations; + unsigned int nchildren; }; #define to_phy(_dev) container_of(_dev, struct wpan_phy, dev) @@ -530,4 +560,46 @@ static inline const char *wpan_phy_name(struct wpan_phy *phy) void ieee802154_configure_durations(struct wpan_phy *phy, unsigned int page, unsigned int channel); +/** + * cfg802154_device_is_associated - Checks whether we are associated to any device + * @wpan_dev: the wpan device + * @return: true if we are associated + */ +bool cfg802154_device_is_associated(struct wpan_dev *wpan_dev); + +/** + * cfg802154_device_is_parent - Checks if a device is our coordinator + * @wpan_dev: the wpan device + * @target: the expected parent + * @return: true if @target is our coordinator + */ +bool cfg802154_device_is_parent(struct wpan_dev *wpan_dev, + struct ieee802154_addr *target); + +/** + * cfg802154_device_is_child - Checks whether a device is associated to us + * @wpan_dev: the wpan device + * @target: the expected child + * @return: the PAN device + */ +struct ieee802154_pan_device * +cfg802154_device_is_child(struct wpan_dev *wpan_dev, + struct ieee802154_addr *target); + +/** + * cfg802154_set_max_associations - Limit the number of future associations + * @wpan_dev: the wpan device + * @max: the maximum number of devices we accept to associate + * @return: the old maximum value + */ +unsigned int cfg802154_set_max_associations(struct wpan_dev *wpan_dev, + unsigned int max); + +/** + * cfg802154_get_free_short_addr - Get a free address among the known devices + * @wpan_dev: the wpan device + * @return: a random short address expectedly unused on our PAN + */ +__le16 cfg802154_get_free_short_addr(struct wpan_dev *wpan_dev); + #endif /* __NET_CFG802154_H */ diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 3c70ad53a4..6d3a201632 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -85,7 +85,10 @@ FN(IPV6_NDISC_BAD_OPTIONS) \ FN(IPV6_NDISC_NS_OTHERHOST) \ FN(QUEUE_PURGE) \ - FN(TC_ERROR) \ + FN(TC_COOKIE_ERROR) \ + FN(PACKET_SOCK_ERROR) \ + FN(TC_CHAIN_NOTFOUND) \ + FN(TC_RECLASSIFY_LOOP) \ FNe(MAX) /** @@ -376,8 +379,23 @@ enum skb_drop_reason { SKB_DROP_REASON_IPV6_NDISC_NS_OTHERHOST, /** @SKB_DROP_REASON_QUEUE_PURGE: bulk free. */ SKB_DROP_REASON_QUEUE_PURGE, - /** @SKB_DROP_REASON_TC_ERROR: generic internal tc error. */ - SKB_DROP_REASON_TC_ERROR, + /** + * @SKB_DROP_REASON_TC_COOKIE_ERROR: An error occurred whilst + * processing a tc ext cookie. + */ + SKB_DROP_REASON_TC_COOKIE_ERROR, + /** + * @SKB_DROP_REASON_PACKET_SOCK_ERROR: generic packet socket errors + * after its filter matches an incoming packet. + */ + SKB_DROP_REASON_PACKET_SOCK_ERROR, + /** @SKB_DROP_REASON_TC_CHAIN_NOTFOUND: tc chain lookup failed. */ + SKB_DROP_REASON_TC_CHAIN_NOTFOUND, + /** + * @SKB_DROP_REASON_TC_RECLASSIFY_LOOP: tc exceeded max reclassify loop + * iterations. + */ + SKB_DROP_REASON_TC_RECLASSIFY_LOOP, /** * @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/fib_rules.h b/include/net/fib_rules.h index 82da359bca..d17855c52e 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -172,8 +172,7 @@ void fib_rules_unregister(struct fib_rules_ops *); int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags, struct fib_lookup_arg *); -int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, - u32 flags); +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); diff --git a/include/net/genetlink.h b/include/net/genetlink.h index c53244f204..e614691294 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -8,16 +8,19 @@ #define GENLMSG_DEFAULT_SIZE (NLMSG_DEFAULT_SIZE - GENL_HDRLEN) +/* Binding to multicast group requires %CAP_NET_ADMIN */ +#define GENL_MCAST_CAP_NET_ADMIN BIT(0) +/* Binding to multicast group requires %CAP_SYS_ADMIN */ +#define GENL_MCAST_CAP_SYS_ADMIN BIT(1) + /** * struct genl_multicast_group - generic netlink multicast group * @name: name of the multicast group, names are per-family - * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) - * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding + * @flags: GENL_MCAST_* flags */ struct genl_multicast_group { char name[GENL_NAMSIZ]; u8 flags; - u8 cap_sys_admin:1; }; struct genl_split_ops; @@ -51,6 +54,9 @@ struct genl_info; * @split_ops: the split do/dump form of operation definition * @n_split_ops: number of entries in @split_ops, not that with split do/dump * ops the number of entries is not the same as number of commands + * @sock_priv_size: the size of per-socket private memory + * @sock_priv_init: the per-socket private memory initializer + * @sock_priv_destroy: the per-socket private memory destructor * * Attribute policies (the combination of @policy and @maxattr fields) * can be attached at the family level or at the operation level. @@ -84,11 +90,17 @@ struct genl_family { const struct genl_multicast_group *mcgrps; struct module *module; + size_t sock_priv_size; + void (*sock_priv_init)(void *priv); + void (*sock_priv_destroy)(void *priv); + /* private: internal use only */ /* protocol family identifier */ int id; /* starting number of multicast group IDs in this family */ unsigned int mcgrp_offset; + /* list of per-socket privs */ + struct xarray *sock_privs; }; /** @@ -298,6 +310,8 @@ static inline bool genl_info_is_ntf(const struct genl_info *info) return !info->nlhdr; } +void *__genl_sk_priv_get(struct genl_family *family, struct sock *sk); +void *genl_sk_priv_get(struct genl_family *family, struct sock *sk); int genl_register_family(struct genl_family *family); int genl_unregister_family(const struct genl_family *family); void genl_notify(const struct genl_family *family, struct sk_buff *skb, @@ -437,6 +451,35 @@ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } +/** + * genlmsg_multicast_netns_filtered - multicast a netlink message + * to a specific netns with filter + * function + * @family: the generic netlink family + * @net: the net namespace + * @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 + * @filter: filter function + * @filter_data: filter function private data + * + * Return: 0 on success, negative error code for failure. + */ +static inline int +genlmsg_multicast_netns_filtered(const struct genl_family *family, + struct net *net, struct sk_buff *skb, + u32 portid, unsigned int group, gfp_t flags, + netlink_filter_fn filter, + void *filter_data) +{ + if (WARN_ON_ONCE(group >= family->n_mcgrps)) + return -EINVAL; + group = family->mcgrp_offset + group; + return nlmsg_multicast_filtered(net->genl_sock, skb, portid, group, + flags, filter, filter_data); +} + /** * genlmsg_multicast_netns - multicast a netlink message to a specific netns * @family: the generic netlink family @@ -450,10 +493,8 @@ static inline int genlmsg_multicast_netns(const struct genl_family *family, struct net *net, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { - if (WARN_ON_ONCE(group >= family->n_mcgrps)) - return -EINVAL; - group = family->mcgrp_offset + group; - return nlmsg_multicast(net->genl_sock, skb, portid, group, flags); + return genlmsg_multicast_netns_filtered(family, net, skb, portid, + group, flags, NULL, NULL); } /** diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index 063313df44..4de858f992 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -125,6 +125,35 @@ struct ieee802154_hdr_fc { #endif }; +struct ieee802154_assoc_req_pl { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved1:1, + device_type:1, + power_source:1, + rx_on_when_idle:1, + assoc_type:1, + reserved2:1, + security_cap:1, + alloc_addr:1; +#elif defined(__BIG_ENDIAN_BITFIELD) + u8 alloc_addr:1, + security_cap:1, + reserved2:1, + assoc_type:1, + rx_on_when_idle:1, + power_source:1, + device_type:1, + reserved1:1; +#else +#error "Please fix " +#endif +} __packed; + +struct ieee802154_assoc_resp_pl { + __le16 short_addr; + u8 status; +} __packed; + enum ieee802154_frame_version { IEEE802154_2003_STD, IEEE802154_2006_STD, @@ -140,6 +169,19 @@ enum ieee802154_addressing_mode { IEEE802154_EXTENDED_ADDRESSING, }; +enum ieee802154_association_status { + IEEE802154_ASSOCIATION_SUCCESSFUL = 0x00, + IEEE802154_PAN_AT_CAPACITY = 0x01, + IEEE802154_PAN_ACCESS_DENIED = 0x02, + IEEE802154_HOPPING_SEQUENCE_OFFSET_DUP = 0x03, + IEEE802154_FAST_ASSOCIATION_SUCCESSFUL = 0x80, +}; + +enum ieee802154_disassociation_reason { + IEEE802154_COORD_WISHES_DEVICE_TO_LEAVE = 0x1, + IEEE802154_DEVICE_WISHES_TO_LEAVE = 0x2, +}; + struct ieee802154_hdr { struct ieee802154_hdr_fc fc; u8 seq; @@ -163,6 +205,24 @@ struct ieee802154_beacon_req_frame { struct ieee802154_mac_cmd_pl mac_pl; }; +struct ieee802154_association_req_frame { + struct ieee802154_hdr mhr; + struct ieee802154_mac_cmd_pl mac_pl; + struct ieee802154_assoc_req_pl assoc_req_pl; +}; + +struct ieee802154_association_resp_frame { + struct ieee802154_hdr mhr; + struct ieee802154_mac_cmd_pl mac_pl; + struct ieee802154_assoc_resp_pl assoc_resp_pl; +}; + +struct ieee802154_disassociation_notif_frame { + struct ieee802154_hdr mhr; + struct ieee802154_mac_cmd_pl mac_pl; + u8 disassoc_pl; +}; + /* pushes hdr onto the skb. fields of hdr->fc that can be calculated from * the contents of hdr will be, and the actual value of those bits in * hdr->fc will be ignored. this includes the INTRA_PAN bit and the frame diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 9ab4bf704e..ccf171f7eb 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -175,6 +175,7 @@ void inet_csk_init_xmit_timers(struct sock *sk, void (*delack_handler)(struct timer_list *), void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); +void inet_csk_clear_xmit_timers_sync(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) { diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 3ecfeadbfa..7f1b384587 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -88,7 +88,7 @@ struct inet_bind_bucket { unsigned short fast_sk_family; bool fast_ipv6_only; struct hlist_node node; - struct hlist_head owners; + struct hlist_head bhash2; }; struct inet_bind2_bucket { @@ -96,22 +96,17 @@ struct inet_bind2_bucket { int l3mdev; unsigned short port; #if IS_ENABLED(CONFIG_IPV6) - unsigned short family; -#endif - union { -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr v6_rcv_saddr; + unsigned short addr_type; + struct in6_addr v6_rcv_saddr; +#define rcv_saddr v6_rcv_saddr.s6_addr32[3] +#else + __be32 rcv_saddr; #endif - __be32 rcv_saddr; - }; /* Node in the bhash2 inet_bind_hashbucket chain */ struct hlist_node node; + struct hlist_node bhash_node; /* List of sockets hashed to this bucket */ struct hlist_head owners; - /* bhash has twsk in owners, but bhash2 has twsk in - * deathrow not to add a member in struct sock_common. - */ - struct hlist_head deathrow; }; static inline struct net *ib_net(const struct inet_bind_bucket *ib) @@ -241,7 +236,7 @@ bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, struct inet_bind2_bucket * inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, - unsigned short port, int l3mdev, + struct inet_bind_bucket *tb, const struct sock *sk); void inet_bind2_bucket_destroy(struct kmem_cache *cachep, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 8d5fe15b0f..d94c242eb3 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -234,10 +234,7 @@ struct inet_sock { int uc_index; int mc_index; __be32 mc_addr; - struct { - __u16 lo; - __u16 hi; - } local_port_range; + u32 local_port_range; /* high << 16 | low */ struct ip_mc_socklist __rcu *mc_list; struct inet_cork_full cork; diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index b14999ff55..f28da08a37 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -75,13 +75,9 @@ struct inet_timewait_sock { struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; struct inet_bind2_bucket *tw_tb2; - struct hlist_node tw_bind2_node; }; #define tw_tclass tw_tos -#define twsk_for_each_bound_bhash2(__tw, list) \ - hlist_for_each_entry(__tw, list, tw_bind2_node) - static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk) { return (struct inet_timewait_sock *)sk; diff --git a/include/net/ip.h b/include/net/ip.h index 6390dd08da..25cb688bdc 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -349,8 +349,14 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o } \ } -void inet_get_local_port_range(const struct net *net, int *low, int *high); -void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high); +static inline void inet_get_local_port_range(const struct net *net, int *low, int *high) +{ + u32 range = READ_ONCE(net->ipv4.ip_local_ports.range); + + *low = range & 0xffff; + *high = range >> 16; +} +bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high); #ifdef CONFIG_SYSCTL static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index f346b4efbc..6690939f24 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -360,6 +360,39 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb) return pskb_network_may_pull(skb, nhlen); } +/* Variant of pskb_inet_may_pull(). + */ +static inline bool skb_vlan_inet_prepare(struct sk_buff *skb) +{ + int nhlen = 0, maclen = ETH_HLEN; + __be16 type = skb->protocol; + + /* Essentially this is skb_protocol(skb, true) + * And we get MAC len. + */ + if (eth_type_vlan(type)) + type = __vlan_get_protocol(skb, type, &maclen); + + switch (type) { +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + nhlen = sizeof(struct ipv6hdr); + break; +#endif + case htons(ETH_P_IP): + nhlen = sizeof(struct iphdr); + break; + } + /* 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; + + skb_set_network_header(skb, maclen); + return true; +} + static inline int ip_encap_hlen(struct ip_tunnel_encap *e) { const struct ip_tunnel_encap_ops *ops; @@ -416,6 +449,17 @@ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, return 0; } +static inline __be32 ip_tunnel_get_flowlabel(const struct iphdr *iph, + const struct sk_buff *skb) +{ + __be16 payload_protocol = skb_protocol(skb, true); + + if (payload_protocol == htons(ETH_P_IPV6)) + return ip6_flowlabel((const struct ipv6hdr *)iph); + else + return 0; +} + static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, const struct sk_buff *skb) { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 78d38dd88a..cf25ea21d7 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -784,11 +784,6 @@ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) cpu_to_be32(0x0000ffff))) == 0UL; } -static inline bool ipv6_addr_v4mapped_any(const struct in6_addr *a) -{ - return ipv6_addr_v4mapped(a) && ipv4_is_zeronet(a->s6_addr32[3]); -} - static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]); diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index f9e88401d7..8b2055d64a 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -80,7 +80,7 @@ struct iucv_array { u32 length; } __attribute__ ((aligned (8))); -extern struct bus_type iucv_bus; +extern const struct bus_type iucv_bus; extern struct device *iucv_root; /* @@ -489,7 +489,7 @@ struct iucv_interface { int (*path_sever)(struct iucv_path *path, u8 userdata[16]); int (*iucv_register)(struct iucv_handler *handler, int smp); void (*iucv_unregister)(struct iucv_handler *handler, int smp); - struct bus_type *bus; + const struct bus_type *bus; struct device *root; }; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 580781ff9d..d400fe2e86 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -476,9 +476,9 @@ struct ieee80211_ba_event { /** * struct ieee80211_event - event to be sent to the driver * @type: The event itself. See &enum ieee80211_event_type. - * @rssi: relevant if &type is %RSSI_EVENT - * @mlme: relevant if &type is %AUTH_EVENT - * @ba: relevant if &type is %BAR_RX_EVENT or %BA_FRAME_TIMEOUT + * @u.rssi: relevant if &type is %RSSI_EVENT + * @u.mlme: relevant if &type is %AUTH_EVENT + * @u.ba: relevant if &type is %BAR_RX_EVENT or %BA_FRAME_TIMEOUT * @u:union holding the fields above */ struct ieee80211_event { @@ -541,8 +541,6 @@ struct ieee80211_fils_discovery { * @link_id: link ID, or 0 for non-MLO * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE * @uora_exists: is the UORA element advertised by AP - * @ack_enabled: indicates support to receive a multi-TID that solicits either - * ACK, BACK or both * @uora_ocw_range: UORA element's OCW Range field * @frame_time_rts_th: HE duration RTS threshold, in units of 32us * @he_support: does this BSS support HE @@ -1150,11 +1148,6 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * @ack: union part for pure ACK data * @ack.cookie: cookie for the ACK * @driver_data: array of driver_data pointers - * @ampdu_ack_len: number of acked aggregated frames. - * relevant only if IEEE80211_TX_STAT_AMPDU was set. - * @ampdu_len: number of aggregated frames. - * relevant only if IEEE80211_TX_STAT_AMPDU was set. - * @ack_signal: signal strength of the ACK frame */ struct ieee80211_tx_info { /* common information */ @@ -1362,6 +1355,9 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * the frame. * @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on * the frame. + * @RX_FLAG_MACTIME: The timestamp passed in the RX status (@mactime + * field) is valid if this field is non-zero, and the position + * where the timestamp was sampled depends on the value. * @RX_FLAG_MACTIME_START: The timestamp passed in the RX status (@mactime * field) is valid and contains the time the first symbol of the MPDU * was received. This is useful in monitor mode and for proper IBSS @@ -1371,6 +1367,11 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * (including FCS) was received. * @RX_FLAG_MACTIME_PLCP_START: The timestamp passed in the RX status (@mactime * field) is valid and contains the time the SYNC preamble was received. + * @RX_FLAG_MACTIME_IS_RTAP_TS64: The timestamp passed in the RX status @mactime + * is only for use in the radiotap timestamp header, not otherwise a valid + * @mactime value. Note this is a separate flag so that we continue to see + * %RX_FLAG_MACTIME as unset. Also note that in this case the timestamp is + * reported to be 64 bits wide, not just 32. * @RX_FLAG_NO_SIGNAL_VAL: The signal strength value is not present. * Valid only for data frames (mainly A-MPDU) * @RX_FLAG_AMPDU_DETAILS: A-MPDU details are known, in particular the reference @@ -1441,12 +1442,12 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), RX_FLAG_DECRYPTED = BIT(1), - RX_FLAG_MACTIME_PLCP_START = BIT(2), + RX_FLAG_ONLY_MONITOR = BIT(2), RX_FLAG_MMIC_STRIPPED = BIT(3), RX_FLAG_IV_STRIPPED = BIT(4), RX_FLAG_FAILED_FCS_CRC = BIT(5), RX_FLAG_FAILED_PLCP_CRC = BIT(6), - RX_FLAG_MACTIME_START = BIT(7), + RX_FLAG_MACTIME_IS_RTAP_TS64 = BIT(7), RX_FLAG_NO_SIGNAL_VAL = BIT(8), RX_FLAG_AMPDU_DETAILS = BIT(9), RX_FLAG_PN_VALIDATED = BIT(10), @@ -1455,8 +1456,10 @@ enum mac80211_rx_flags { RX_FLAG_AMPDU_IS_LAST = BIT(13), RX_FLAG_AMPDU_DELIM_CRC_ERROR = BIT(14), RX_FLAG_AMPDU_DELIM_CRC_KNOWN = BIT(15), - RX_FLAG_MACTIME_END = BIT(16), - RX_FLAG_ONLY_MONITOR = BIT(17), + RX_FLAG_MACTIME = BIT(16) | BIT(17), + RX_FLAG_MACTIME_PLCP_START = 1 << 16, + RX_FLAG_MACTIME_START = 2 << 16, + RX_FLAG_MACTIME_END = 3 << 16, RX_FLAG_SKIP_MONITOR = BIT(18), RX_FLAG_AMSDU_MORE = BIT(19), RX_FLAG_RADIOTAP_TLV_AT_END = BIT(20), @@ -2686,6 +2689,9 @@ struct ieee80211_txq { * @IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX: Hardware/driver handles transmitting * multicast frames on all links, mac80211 should not do that. * + * @IEEE80211_HW_DISALLOW_PUNCTURING: HW requires disabling puncturing in EHT + * and connecting with a lower bandwidth instead + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2743,6 +2749,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP, IEEE80211_HW_DETECTS_COLOR_COLLISION, IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX, + IEEE80211_HW_DISALLOW_PUNCTURING, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -2831,8 +2838,6 @@ enum ieee80211_hw_flags { * the default is _GI | _BANDWIDTH. * Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values. * - * @radiotap_he: HE radiotap validity flags - * * @radiotap_timestamp: Information for the radiotap timestamp field; if the * @units_pos member is set to a non-negative value then the timestamp * field will be added and populated from the &struct ieee80211_rx_status @@ -4267,6 +4272,8 @@ struct ieee80211_prep_tx_info { * disable background CAC/radar detection. * @net_fill_forward_path: Called from .ndo_fill_forward_path in order to * resolve a path for hardware flow offloading + * @can_activate_links: Checks if a specific active_links bitmap is + * supported by the driver. * @change_vif_links: Change the valid links on an interface, note that while * removing the old link information is still valid (link_conf pointer), * but may immediately disappear after the function returns. The old or @@ -4647,6 +4654,9 @@ struct ieee80211_ops { struct ieee80211_sta *sta, struct net_device_path_ctx *ctx, struct net_device_path *path); + bool (*can_activate_links)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u16 active_links); int (*change_vif_links)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 old_links, u16 new_links, @@ -5809,12 +5819,11 @@ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf, * ieee80211_remove_key - remove the given key * @keyconf: the parameter passed with the set key * + * Context: Must be called with the wiphy mutex held. + * * Remove the given key. If the key was uploaded to the hardware at the * time this function is called, it is not deleted in the hardware but * instead assumed to have been removed already. - * - * Note that due to locking considerations this function can (currently) - * only be called during key iteration (ieee80211_iter_keys().) */ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf); @@ -6368,12 +6377,12 @@ ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq); * @iter: iterator function that will be called for each key * @iter_data: custom data to pass to the iterator function * + * Context: Must be called with wiphy mutex held; can sleep. + * * This function can be used to iterate all the keys known to * mac80211, even those that weren't previously programmed into * the device. This is intended for use in WoWLAN if the device - * needs reprogramming of the keys during suspend. Note that due - * to locking reasons, it is also only safe to call this at few - * spots since it must hold the RTNL and be able to sleep. + * needs reprogramming of the keys during suspend. * * The order in which the keys are iterated matches the order * in which they were originally installed and handed to the @@ -7435,6 +7444,9 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb) * @vif: interface to set active links on * @active_links: the new active links bitmap * + * Context: Must be called with wiphy mutex held; may sleep; calls + * back into the driver. + * * This changes the active links on an interface. The interface * must be in client mode (in AP mode, all links are always active), * and @active_links must be a subset of the vif's valid_links. @@ -7442,6 +7454,7 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb) * If a link is switched off and another is switched on at the same * time (e.g. active_links going from 0x1 to 0x10) then you will get * a sequence of calls like + * * - change_vif_links(0x11) * - unassign_vif_chanctx(link_id=0) * - change_sta_links(0x11) for each affected STA (the AP) @@ -7451,10 +7464,6 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb) * - change_sta_links(0x10) for each affected STA (the AP) * - assign_vif_chanctx(link_id=4) * - change_vif_links(0x10) - * - * Note: This function acquires some mac80211 locks and must not - * be called with any driver locks held that could cause a - * lock dependency inversion. Best call it without locks. */ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links); diff --git a/include/net/macsec.h b/include/net/macsec.h index ebf9bc5403..de216cbc6b 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -247,6 +247,23 @@ struct macsec_secy { /** * struct macsec_context - MACsec context for hardware offloading + * @netdev: a valid pointer to a struct net_device if @offload == + * MACSEC_OFFLOAD_MAC + * @phydev: a valid pointer to a struct phy_device if @offload == + * MACSEC_OFFLOAD_PHY + * @offload: MACsec offload status + * @secy: pointer to a MACsec SecY + * @rx_sc: pointer to a RX SC + * @update_pn: when updating the SA, update the next PN + * @assoc_num: association number of the target SA + * @key: key of the target SA + * @rx_sa: pointer to an RX SA if a RX SA is added/updated/removed + * @tx_sa: pointer to an TX SA if a TX SA is added/updated/removed + * @tx_sc_stats: pointer to TX SC stats structure + * @tx_sa_stats: pointer to TX SA stats structure + * @rx_sc_stats: pointer to RX SC stats structure + * @rx_sa_stats: pointer to RX SA stats structure + * @dev_stats: pointer to dev stats structure */ struct macsec_context { union { @@ -277,6 +294,34 @@ struct macsec_context { /** * struct macsec_ops - MACsec offloading operations + * @mdo_dev_open: called when the MACsec interface transitions to the up state + * @mdo_dev_stop: called when the MACsec interface transitions to the down + * state + * @mdo_add_secy: called when a new SecY is added + * @mdo_upd_secy: called when the SecY flags are changed or the MAC address of + * the MACsec interface is changed + * @mdo_del_secy: called when the hw offload is disabled or the MACsec + * interface is removed + * @mdo_add_rxsc: called when a new RX SC is added + * @mdo_upd_rxsc: called when a certain RX SC is updated + * @mdo_del_rxsc: called when a certain RX SC is removed + * @mdo_add_rxsa: called when a new RX SA is added + * @mdo_upd_rxsa: called when a certain RX SA is updated + * @mdo_del_rxsa: called when a certain RX SA is removed + * @mdo_add_txsa: called when a new TX SA is added + * @mdo_upd_txsa: called when a certain TX SA is updated + * @mdo_del_txsa: called when a certain TX SA is removed + * @mdo_get_dev_stats: called when dev stats are read + * @mdo_get_tx_sc_stats: called when TX SC stats are read + * @mdo_get_tx_sa_stats: called when TX SA stats are read + * @mdo_get_rx_sc_stats: called when RX SC stats are read + * @mdo_get_rx_sa_stats: called when RX SA stats are read + * @mdo_insert_tx_tag: called to insert the TX tag + * @needed_headroom: number of bytes reserved at the beginning of the sk_buff + * for the TX tag + * @needed_tailroom: number of bytes reserved at the end of the sk_buff for the + * TX tag + * @rx_uses_md_dst: whether MACsec device offload supports sk_buff md_dst */ struct macsec_ops { /* Device wide */ @@ -303,6 +348,12 @@ struct macsec_ops { int (*mdo_get_tx_sa_stats)(struct macsec_context *ctx); int (*mdo_get_rx_sc_stats)(struct macsec_context *ctx); int (*mdo_get_rx_sa_stats)(struct macsec_context *ctx); + /* Offload tag */ + int (*mdo_insert_tx_tag)(struct phy_device *phydev, + struct sk_buff *skb); + unsigned int needed_headroom; + unsigned int needed_tailroom; + bool rx_uses_md_dst; }; void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa); @@ -325,4 +376,9 @@ static inline void *macsec_netdev_priv(const struct net_device *dev) return netdev_priv(dev); } +static inline u64 sci_to_cpu(sci_t sci) +{ + return be64_to_cpu((__force __be64)sci); +} + #endif /* _NET_MACSEC_H_ */ diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 88b6ef7ce1..27684135bb 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -66,6 +66,7 @@ enum { GDMA_DEVICE_NONE = 0, GDMA_DEVICE_HWC = 1, GDMA_DEVICE_MANA = 2, + GDMA_DEVICE_MANA_IB = 3, }; struct gdma_resource { @@ -149,6 +150,7 @@ struct gdma_general_req { #define GDMA_MESSAGE_V1 1 #define GDMA_MESSAGE_V2 2 +#define GDMA_MESSAGE_V3 3 struct gdma_general_resp { struct gdma_resp_hdr hdr; @@ -293,6 +295,7 @@ struct gdma_queue { u32 head; u32 tail; + struct list_head entry; /* Extra fields specific to EQ/CQ. */ union { @@ -328,6 +331,7 @@ struct gdma_queue_spec { void *context; unsigned long log2_throttle_limit; + unsigned int msix_index; } eq; struct { @@ -344,7 +348,9 @@ struct gdma_queue_spec { struct gdma_irq_context { void (*handler)(void *arg); - void *arg; + /* Protect the eq_list */ + spinlock_t lock; + struct list_head eq_list; char name[MANA_IRQ_NAME_SZ]; }; @@ -355,7 +361,6 @@ struct gdma_context { unsigned int max_num_queues; unsigned int max_num_msix; unsigned int num_msix_usable; - struct gdma_resource msix_resource; struct gdma_irq_context *irq_contexts; /* L2 MTU */ @@ -387,6 +392,9 @@ struct gdma_context { /* Azure network adapter */ struct gdma_dev mana; + + /* Azure RDMA adapter */ + struct gdma_dev mana_ib; }; #define MAX_NUM_GDMA_DEVICES 4 diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 6e3e9c1363..4eeedf1471 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -39,7 +39,6 @@ enum TRI_STATE { #define COMP_ENTRY_SIZE 64 #define RX_BUFFERS_PER_QUEUE 512 -#define MANA_RX_DATA_ALIGN 64 #define MAX_SEND_BUFFERS_PER_QUEUE 256 @@ -353,6 +352,25 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; + u64 hc_rx_discards_no_wqe; + u64 hc_rx_err_vport_disabled; + u64 hc_rx_bytes; + u64 hc_rx_ucast_pkts; + u64 hc_rx_ucast_bytes; + u64 hc_rx_bcast_pkts; + u64 hc_rx_bcast_bytes; + u64 hc_rx_mcast_pkts; + u64 hc_rx_mcast_bytes; + u64 hc_tx_err_gf_disabled; + u64 hc_tx_err_vport_disabled; + u64 hc_tx_err_inval_vportoffset_pkt; + u64 hc_tx_err_vlan_enforcement; + u64 hc_tx_err_eth_type_enforcement; + u64 hc_tx_err_sa_enforcement; + u64 hc_tx_err_sqpdid_enforcement; + u64 hc_tx_err_cqpdid_enforcement; + u64 hc_tx_err_mtu_violation; + u64 hc_tx_err_inval_oob; u64 hc_tx_bytes; u64 hc_tx_ucast_pkts; u64 hc_tx_ucast_bytes; @@ -360,6 +378,7 @@ struct mana_ethtool_stats { u64 hc_tx_bcast_bytes; u64 hc_tx_mcast_pkts; u64 hc_tx_mcast_bytes; + u64 hc_tx_err_gdma; u64 tx_cqe_err; u64 tx_cqe_unknown_type; u64 rx_coalesced_err; @@ -602,8 +621,8 @@ struct mana_query_gf_stat_resp { struct gdma_resp_hdr hdr; u64 reported_stats; /* rx errors/discards */ - u64 discard_rx_nowqe; - u64 err_rx_vport_disabled; + u64 rx_discards_nowqe; + u64 rx_err_vport_disabled; /* rx bytes/packets */ u64 hc_rx_bytes; u64 hc_rx_ucast_pkts; @@ -613,16 +632,16 @@ struct mana_query_gf_stat_resp { u64 hc_rx_mcast_pkts; u64 hc_rx_mcast_bytes; /* tx errors */ - u64 err_tx_gf_disabled; - u64 err_tx_vport_disabled; - u64 err_tx_inval_vport_offset_pkt; - u64 err_tx_vlan_enforcement; - u64 err_tx_ethtype_enforcement; - u64 err_tx_SA_enforecement; - u64 err_tx_SQPDID_enforcement; - u64 err_tx_CQPDID_enforcement; - u64 err_tx_mtu_violation; - u64 err_tx_inval_oob; + u64 tx_err_gf_disabled; + u64 tx_err_vport_disabled; + u64 tx_err_inval_vport_offset_pkt; + u64 tx_err_vlan_enforcement; + u64 tx_err_ethtype_enforcement; + u64 tx_err_SA_enforcement; + u64 tx_err_SQPDID_enforcement; + u64 tx_err_CQPDID_enforcement; + u64 tx_err_mtu_violation; + u64 tx_err_inval_oob; /* tx bytes/packets */ u64 hc_tx_bytes; u64 hc_tx_ucast_pkts; @@ -632,7 +651,7 @@ struct mana_query_gf_stat_resp { u64 hc_tx_mcast_pkts; u64 hc_tx_mcast_bytes; /* tx error */ - u64 err_tx_gdma; + u64 tx_err_gdma; }; /* HW DATA */ /* Configure vPort Rx Steering */ diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index cdcafb30d4..aa1716fb0e 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -21,6 +21,10 @@ struct netdev_rx_queue { #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif + /* NAPI instance for the queue + * Readers and writers must hold RTNL + */ + struct napi_struct *napi; } ____cacheline_aligned_in_smp; /* diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 4a767b3d20..9abb7ee40d 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -74,12 +74,13 @@ enum nf_flowtable_flags { }; struct nf_flowtable { - struct list_head list; - struct rhashtable rhashtable; - int priority; + unsigned int flags; /* readonly in datapath */ + int priority; /* control path (padding hole) */ + struct rhashtable rhashtable; /* datapath, read-mostly members come first */ + + struct list_head list; /* slowpath parts */ const struct nf_flowtable_type *type; struct delayed_work gc_work; - unsigned int flags; struct flow_block flow_block; struct rw_semaphore flow_block_lock; /* Guards flow_block */ possible_net_t net; @@ -335,7 +336,7 @@ int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, int nf_flow_table_offload_init(void); void nf_flow_table_offload_exit(void); -static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) +static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb) { __be16 proto; @@ -351,6 +352,16 @@ static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) return 0; } +static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto) +{ + if (!pskb_may_pull(skb, PPPOE_SES_HLEN)) + return false; + + *inner_proto = __nf_flow_pppoe_proto(skb); + + return true; +} + #define NF_FLOW_TABLE_STAT_INC(net, count) __this_cpu_inc((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_DEC(net, count) __this_cpu_dec((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count) \ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 62013d0184..1cf9cb0f0a 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -205,6 +205,7 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src, * @nla: netlink attributes * @portid: netlink portID of the original message * @seq: netlink sequence number + * @flags: modifiers to new request * @family: protocol family * @level: depth of the chains * @report: notify via unicast netlink message @@ -282,6 +283,7 @@ struct nft_elem_priv { }; * * @key: element key * @key_end: closing element key + * @data: element data * @priv: element private data and extensions */ struct nft_set_elem { @@ -305,9 +307,23 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) return (void *)priv; } + +/** + * enum nft_iter_type - nftables set iterator type + * + * @NFT_ITER_READ: read-only iteration over set elements + * @NFT_ITER_UPDATE: iteration under mutex to update set element state + */ +enum nft_iter_type { + NFT_ITER_UNSPEC, + NFT_ITER_READ, + NFT_ITER_UPDATE, +}; + struct nft_set; struct nft_set_iter { u8 genmask; + enum nft_iter_type type:8; unsigned int count; unsigned int skip; int err; @@ -325,10 +341,10 @@ struct nft_set_iter { * @dtype: data type * @dlen: data length * @objtype: object type - * @flags: flags * @size: number of set elements * @policy: set policy * @gc_int: garbage collector interval + * @timeout: element timeout * @field_len: length of each field in concatenation, bytes * @field_count: number of concatenated fields in element * @expr: set must support for expressions @@ -351,9 +367,9 @@ struct nft_set_desc { /** * enum nft_set_class - performance class * - * @NFT_LOOKUP_O_1: constant, O(1) - * @NFT_LOOKUP_O_LOG_N: logarithmic, O(log N) - * @NFT_LOOKUP_O_N: linear, O(N) + * @NFT_SET_CLASS_O_1: constant, O(1) + * @NFT_SET_CLASS_O_LOG_N: logarithmic, O(log N) + * @NFT_SET_CLASS_O_N: linear, O(N) */ enum nft_set_class { NFT_SET_CLASS_O_1, @@ -422,9 +438,13 @@ struct nft_set_ext; * @remove: remove element from set * @walk: iterate over all set elements * @get: get set elements + * @commit: commit set elements + * @abort: abort set elements * @privsize: function to return size of set private data + * @estimate: estimate the required memory size and the lookup complexity class * @init: initialize private data of new set instance * @destroy: destroy private data of set instance + * @gc_init: initialize garbage collection * @elemsize: element private size * * Operations lookup, update and delete have simpler interfaces, are faster @@ -540,13 +560,16 @@ struct nft_set_elem_expr { * @policy: set parameterization (see enum nft_set_policies) * @udlen: user data length * @udata: user data - * @expr: stateful expression + * @pending_update: list of pending update set element * @ops: set ops * @flags: set flags * @dead: set will be freed, never cleared * @genmask: generation mask * @klen: key length * @dlen: data length + * @num_exprs: numbers of exprs + * @exprs: stateful expression + * @catchall_list: list of catch-all set element * @data: private set data */ struct nft_set { @@ -692,6 +715,7 @@ extern const struct nft_set_ext_type nft_set_ext_types[]; * * @len: length of extension area * @offset: offsets of individual extension types + * @ext_len: length of the expected extension(used to sanity check) */ struct nft_set_ext_tmpl { u16 len; @@ -846,6 +870,7 @@ struct nft_expr_ops; * @select_ops: function to select nft_expr_ops * @release_ops: release nft_expr_ops * @ops: default ops, used when no select_ops functions is present + * @inner_ops: inner ops, used for inner packet operation * @list: used internally * @name: Identifier * @owner: module reference @@ -887,14 +912,22 @@ struct nft_offload_ctx; * struct nft_expr_ops - nf_tables expression operations * * @eval: Expression evaluation function + * @clone: Expression clone function * @size: full expression size, including private data size * @init: initialization function * @activate: activate expression in the next generation * @deactivate: deactivate expression in next generation * @destroy: destruction function, called after synchronize_rcu + * @destroy_clone: destruction clone function * @dump: function to dump parameters - * @type: expression type * @validate: validate expression, called during loop detection + * @reduce: reduce expression + * @gc: garbage collection expression + * @offload: hardware offload expression + * @offload_action: function to report true/false to allocate one slot or not in the flow + * offload array + * @offload_stats: function to synchronize hardware stats via updating the counter expression + * @type: expression type * @data: extra data to attach to this expression operation */ struct nft_expr_ops { @@ -1047,14 +1080,21 @@ struct nft_rule_blob { /** * struct nft_chain - nf_tables chain * + * @blob_gen_0: rule blob pointer to the current generation + * @blob_gen_1: rule blob pointer to the future generation * @rules: list of rules in the chain * @list: used internally * @rhlhead: used internally * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain - * @flags: bitmask of enum nft_chain_flags + * @flags: bitmask of enum NFTA_CHAIN_FLAGS + * @bound: bind or not + * @genmask: generation mask * @name: name of the chain + * @udlen: user data length + * @udata: user data in the chain + * @blob_next: rule blob pointer to the next in the chain */ struct nft_chain { struct nft_rule_blob __rcu *blob_gen_0; @@ -1152,6 +1192,7 @@ struct nft_hook { * @hook_list: list of netfilter hooks (for NFPROTO_NETDEV family) * @type: chain type * @policy: default policy + * @flags: indicate the base chain disabled or not * @stats: per-cpu chain stats * @chain: the chain * @flow_block: flow block (for hardware offload) @@ -1280,11 +1321,13 @@ struct nft_object_hash_key { * struct nft_object - nf_tables stateful object * * @list: table stateful object list node - * @key: keys that identify this object * @rhlhead: nft_objname_ht node + * @key: keys that identify this object * @genmask: generation mask * @use: number of references to this stateful object * @handle: unique object handle + * @udlen: length of user data + * @udata: user data * @ops: object operations * @data: object data, layout depends on type */ @@ -1352,6 +1395,7 @@ struct nft_object_type { * @destroy: release existing stateful object * @dump: netlink dump stateful object * @update: update stateful object + * @type: pointer to object type */ struct nft_object_ops { void (*eval)(struct nft_object *obj, @@ -1387,9 +1431,8 @@ void nft_unregister_obj(struct nft_object_type *obj_type); * @genmask: generation mask * @use: number of references to this flow table * @handle: unique object handle - * @dev_name: array of device names + * @hook_list: hook list for hooks per net_device in flowtables * @data: rhashtable and garbage collector - * @ops: array of hooks */ struct nft_flowtable { struct list_head list; diff --git a/include/net/netlink.h b/include/net/netlink.h index 83bdf787ae..c19ff921b6 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1010,6 +1010,20 @@ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags) return alloc_skb(nlmsg_total_size(payload), flags); } +/** + * nlmsg_new_large - Allocate a new netlink message with non-contiguous + * physical memory + * @payload: size of the message payload + * + * The allocated skb is unable to have frag page for shinfo->frags*, + * as the NULL setting for skb->head in netlink_skb_destructor() will + * bypass most of the handling in skb_release_data() + */ +static inline struct sk_buff *nlmsg_new_large(size_t payload) +{ + return netlink_alloc_large_skb(nlmsg_total_size(payload), 0); +} + /** * nlmsg_end - Finalize a netlink message * @skb: socket buffer the message is stored in @@ -1073,27 +1087,50 @@ static inline void nlmsg_free(struct sk_buff *skb) } /** - * nlmsg_multicast - multicast a netlink message + * nlmsg_multicast_filtered - multicast a netlink message with filter function * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags + * @filter: filter function + * @filter_data: filter function private data + * + * Return: 0 on success, negative error code for failure. */ -static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb, - u32 portid, unsigned int group, gfp_t flags) +static inline int nlmsg_multicast_filtered(struct sock *sk, struct sk_buff *skb, + u32 portid, unsigned int group, + gfp_t flags, + netlink_filter_fn filter, + void *filter_data) { int err; NETLINK_CB(skb).dst_group = group; - err = netlink_broadcast(sk, skb, portid, group, flags); + err = netlink_broadcast_filtered(sk, skb, portid, group, flags, + filter, filter_data); if (err > 0) err = 0; return err; } +/** + * nlmsg_multicast - multicast a netlink message + * @sk: netlink socket to spread messages to + * @skb: netlink message as socket buffer + * @portid: own netlink portid to avoid sending to yourself + * @group: multicast group id + * @flags: allocation flags + */ +static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb, + u32 portid, unsigned int group, gfp_t flags) +{ + return nlmsg_multicast_filtered(sk, skb, portid, group, flags, + NULL, NULL); +} + /** * nlmsg_unicast - unicast a netlink message * @sk: netlink socket to spread message to @@ -1200,7 +1237,7 @@ static inline void *nla_data(const struct nlattr *nla) * nla_len - length of payload * @nla: netlink attribute */ -static inline int nla_len(const struct nlattr *nla) +static inline u16 nla_len(const struct nlattr *nla) { return nla->nla_len - NLA_HDRLEN; } diff --git a/include/net/netns/core.h b/include/net/netns/core.h index a91ef9f8de..78214f1b43 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -13,6 +13,7 @@ struct netns_core { struct ctl_table_header *sysctl_hdr; int sysctl_somaxconn; + int sysctl_optmem_max; u8 sysctl_txrehash; #ifdef CONFIG_PROC_FS diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 73f43f6991..c356c458b3 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -19,8 +19,7 @@ struct hlist_head; struct fib_table; struct sock; struct local_ports { - seqlock_t lock; - int range[2]; + u32 range; /* high << 16 | low */ bool warned; }; @@ -42,6 +41,38 @@ struct inet_timewait_death_row { struct tcp_fastopen_context; struct netns_ipv4 { + /* Cacheline organization can be found documented in + * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst. + * Please update the document when adding new fields. + */ + + /* TX readonly hotpath cache lines */ + __cacheline_group_begin(netns_ipv4_read_tx); + u8 sysctl_tcp_early_retrans; + u8 sysctl_tcp_tso_win_divisor; + u8 sysctl_tcp_tso_rtt_log; + u8 sysctl_tcp_autocorking; + int sysctl_tcp_min_snd_mss; + unsigned int sysctl_tcp_notsent_lowat; + int sysctl_tcp_limit_output_bytes; + int sysctl_tcp_min_rtt_wlen; + int sysctl_tcp_wmem[3]; + u8 sysctl_ip_fwd_use_pmtu; + __cacheline_group_end(netns_ipv4_read_tx); + + /* TXRX readonly hotpath cache lines */ + __cacheline_group_begin(netns_ipv4_read_txrx); + u8 sysctl_tcp_moderate_rcvbuf; + __cacheline_group_end(netns_ipv4_read_txrx); + + /* RX readonly hotpath cache line */ + __cacheline_group_begin(netns_ipv4_read_rx); + u8 sysctl_ip_early_demux; + u8 sysctl_tcp_early_demux; + int sysctl_tcp_reordering; + int sysctl_tcp_rmem[3]; + __cacheline_group_end(netns_ipv4_read_rx); + struct inet_timewait_death_row tcp_death_row; struct udp_table *udp_table; @@ -96,17 +127,14 @@ struct netns_ipv4 { u8 sysctl_ip_default_ttl; u8 sysctl_ip_no_pmtu_disc; - u8 sysctl_ip_fwd_use_pmtu; u8 sysctl_ip_fwd_update_priority; u8 sysctl_ip_nonlocal_bind; u8 sysctl_ip_autobind_reuse; /* Shall we try to damage output packets if routing dev changes? */ u8 sysctl_ip_dynaddr; - u8 sysctl_ip_early_demux; #ifdef CONFIG_NET_L3_MASTER_DEV u8 sysctl_raw_l3mdev_accept; #endif - u8 sysctl_tcp_early_demux; u8 sysctl_udp_early_demux; u8 sysctl_nexthop_compat_mode; @@ -119,7 +147,6 @@ struct netns_ipv4 { u8 sysctl_tcp_mtu_probing; int sysctl_tcp_mtu_probe_floor; int sysctl_tcp_base_mss; - int sysctl_tcp_min_snd_mss; int sysctl_tcp_probe_threshold; u32 sysctl_tcp_probe_interval; @@ -135,17 +162,14 @@ struct netns_ipv4 { u8 sysctl_tcp_backlog_ack_defer; u8 sysctl_tcp_pingpong_thresh; - int sysctl_tcp_reordering; u8 sysctl_tcp_retries1; u8 sysctl_tcp_retries2; u8 sysctl_tcp_orphan_retries; u8 sysctl_tcp_tw_reuse; int sysctl_tcp_fin_timeout; - unsigned int sysctl_tcp_notsent_lowat; u8 sysctl_tcp_sack; u8 sysctl_tcp_window_scaling; u8 sysctl_tcp_timestamps; - u8 sysctl_tcp_early_retrans; u8 sysctl_tcp_recovery; u8 sysctl_tcp_thin_linear_timeouts; u8 sysctl_tcp_slow_start_after_idle; @@ -161,21 +185,13 @@ struct netns_ipv4 { u8 sysctl_tcp_frto; u8 sysctl_tcp_nometrics_save; u8 sysctl_tcp_no_ssthresh_metrics_save; - u8 sysctl_tcp_moderate_rcvbuf; - u8 sysctl_tcp_tso_win_divisor; u8 sysctl_tcp_workaround_signed_windows; - int sysctl_tcp_limit_output_bytes; int sysctl_tcp_challenge_ack_limit; - int sysctl_tcp_min_rtt_wlen; u8 sysctl_tcp_min_tso_segs; - u8 sysctl_tcp_tso_rtt_log; - u8 sysctl_tcp_autocorking; u8 sysctl_tcp_reflect_tos; int sysctl_tcp_invalid_ratelimit; int sysctl_tcp_pacing_ss_ratio; int sysctl_tcp_pacing_ca_ratio; - int sysctl_tcp_wmem[3]; - int sysctl_tcp_rmem[3]; unsigned int sysctl_tcp_child_ehash_entries; unsigned long sysctl_tcp_comp_sack_delay_ns; unsigned long sysctl_tcp_comp_sack_slack_ns; diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h index 582212ada3..fc752a50f9 100644 --- a/include/net/netns/smc.h +++ b/include/net/netns/smc.h @@ -22,5 +22,7 @@ struct netns_smc { int sysctl_smcr_testlink_time; int sysctl_wmem; int sysctl_rmem; + int sysctl_max_links_per_lgr; + int sysctl_max_conns_per_lgr; }; #endif diff --git a/include/net/nl802154.h b/include/net/nl802154.h index 8cd9d141f5..4c752f7999 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -78,6 +78,10 @@ enum nl802154_commands { NL802154_CMD_SCAN_DONE, NL802154_CMD_SEND_BEACONS, NL802154_CMD_STOP_BEACONS, + NL802154_CMD_ASSOCIATE, + NL802154_CMD_DISASSOCIATE, + NL802154_CMD_SET_MAX_ASSOCIATIONS, + NL802154_CMD_LIST_ASSOCIATIONS, /* add new commands above here */ @@ -147,6 +151,8 @@ enum nl802154_attrs { NL802154_ATTR_SCAN_DURATION, NL802154_ATTR_SCAN_DONE_REASON, NL802154_ATTR_BEACON_INTERVAL, + NL802154_ATTR_MAX_ASSOCIATIONS, + NL802154_ATTR_PEER, /* add attributes here, update the policy in nl802154.c */ @@ -385,8 +391,6 @@ enum nl802154_supported_bool_states { NL802154_SUPPORTED_BOOL_MAX = __NL802154_SUPPORTED_BOOL_AFTER_LAST - 1 }; -#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL - enum nl802154_dev_addr_modes { NL802154_DEV_ADDR_NONE, __NL802154_DEV_ADDR_INVALID, @@ -406,12 +410,26 @@ enum nl802154_dev_addr_attrs { NL802154_DEV_ADDR_ATTR_SHORT, NL802154_DEV_ADDR_ATTR_EXTENDED, NL802154_DEV_ADDR_ATTR_PAD, + NL802154_DEV_ADDR_ATTR_PEER_TYPE, /* keep last */ __NL802154_DEV_ADDR_ATTR_AFTER_LAST, NL802154_DEV_ADDR_ATTR_MAX = __NL802154_DEV_ADDR_ATTR_AFTER_LAST - 1 }; +enum nl802154_peer_type { + NL802154_PEER_TYPE_UNSPEC, + + NL802154_PEER_TYPE_PARENT, + NL802154_PEER_TYPE_CHILD, + + /* keep last */ + __NL802154_PEER_TYPE_AFTER_LAST, + NL802154_PEER_TYPE_MAX = __NL802154_PEER_TYPE_AFTER_LAST - 1 +}; + +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + enum nl802154_key_id_modes { NL802154_KEY_ID_MODE_IMPLICIT, NL802154_KEY_ID_MODE_INDEX, diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 4ebd544ae9..1d397c1a00 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -11,7 +11,7 @@ * The page_pool allocator is optimized for recycling page or page fragment used * by skb packet and xdp frame. * - * Basic use involves replacing and alloc_pages() calls with page_pool_alloc(), + * Basic use involves replacing any alloc_pages() calls with page_pool_alloc(), * which allocate memory with or without page splitting depending on the * requested memory size. * @@ -29,7 +29,7 @@ * page allocated from page pool. Page splitting enables memory saving and thus * avoids TLB/cache miss for data access, but there also is some cost to * implement page splitting, mainly some cache line dirtying/bouncing for - * 'struct page' and atomic operation for page->pp_frag_count. + * 'struct page' and atomic operation for page->pp_ref_count. * * The API keeps track of in-flight pages, in order to let API users know when * it is safe to free a page_pool object, the API users must call @@ -37,15 +37,15 @@ * attach the page_pool object to a page_pool-aware object like skbs marked with * skb_mark_for_recycle(). * - * page_pool_put_page() may be called multi times on the same page if a page is - * split into multi fragments. For the last fragment, it will either recycle the - * page, or in case of page->_refcount > 1, it will release the DMA mapping and - * in-flight state accounting. + * page_pool_put_page() may be called multiple times on the same page if a page + * is split into multiple fragments. For the last fragment, it will either + * recycle the page, or in case of page->_refcount > 1, it will release the DMA + * mapping and in-flight state accounting. * * dma_sync_single_range_for_device() is only called for the last fragment when * page_pool is created with PP_FLAG_DMA_SYNC_DEV flag, so it depends on the * last freed fragment to do the sync_for_device operation for all fragments in - * the same page when a page is split, the API user must setup pool->p.max_len + * the same page when a page is split. The API user must setup pool->p.max_len * and pool->p.offset correctly and ensure that page_pool_put_page() is called * with dma_sync_size being -1 for fragment API. */ @@ -55,16 +55,12 @@ #include #ifdef CONFIG_PAGE_POOL_STATS +/* Deprecated driver-facing API, use netlink instead */ int page_pool_ethtool_stats_get_count(void); u8 *page_pool_ethtool_stats_get_strings(u8 *data); u64 *page_pool_ethtool_stats_get(u64 *data, void *stats); -/* - * Drivers that wish to harvest page pool stats and report them to users - * (perhaps via ethtool, debugfs, or another mechanism) can allocate a - * struct page_pool_stats call page_pool_get_stats to get stats for the specified pool. - */ -bool page_pool_get_stats(struct page_pool *pool, +bool page_pool_get_stats(const struct page_pool *pool, struct page_pool_stats *stats); #else static inline int page_pool_ethtool_stats_get_count(void) @@ -214,69 +210,82 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) return pool->p.dma_dir; } -/* pp_frag_count represents the number of writers who can update the page - * either by updating skb->data or via DMA mappings for the device. - * We can't rely on the page refcnt for that as we don't know who might be - * holding page references and we can't reliably destroy or sync DMA mappings - * of the fragments. +/** + * page_pool_fragment_page() - split a fresh page into fragments + * @page: page to split + * @nr: references to set + * + * pp_ref_count represents the number of outstanding references to the page, + * which will be freed using page_pool APIs (rather than page allocator APIs + * like put_page()). Such references are usually held by page_pool-aware + * objects like skbs marked for page pool recycling. * - * When pp_frag_count reaches 0 we can either recycle the page if the page - * refcnt is 1 or return it back to the memory allocator and destroy any - * mappings we have. + * This helper allows the caller to take (set) multiple references to a + * freshly allocated page. The page must be freshly allocated (have a + * pp_ref_count of 1). This is commonly done by drivers and + * "fragment allocators" to save atomic operations - either when they know + * upfront how many references they will need; or to take MAX references and + * return the unused ones with a single atomic dec(), instead of performing + * multiple atomic inc() operations. */ static inline void page_pool_fragment_page(struct page *page, long nr) { - atomic_long_set(&page->pp_frag_count, nr); + atomic_long_set(&page->pp_ref_count, nr); } -static inline long page_pool_defrag_page(struct page *page, long nr) +static inline long page_pool_unref_page(struct page *page, long nr) { long ret; - /* If nr == pp_frag_count then we have cleared all remaining + /* If nr == pp_ref_count then we have cleared all remaining * references to the page: * 1. 'n == 1': no need to actually overwrite it. * 2. 'n != 1': overwrite it with one, which is the rare case - * for pp_frag_count draining. + * for pp_ref_count draining. * * The main advantage to doing this is that not only we avoid a atomic * update, as an atomic_read is generally a much cheaper operation than * an atomic update, especially when dealing with a page that may be - * partitioned into only 2 or 3 pieces; but also unify the pp_frag_count + * referenced by only 2 or 3 users; but also unify the pp_ref_count * handling by ensuring all pages have partitioned into only 1 piece * initially, and only overwrite it when the page is partitioned into * more than one piece. */ - if (atomic_long_read(&page->pp_frag_count) == nr) { + if (atomic_long_read(&page->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_frag_count draining, which is a rare 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_frag_count, 1); + atomic_long_set(&page->pp_ref_count, 1); return 0; } - ret = atomic_long_sub_return(nr, &page->pp_frag_count); + ret = atomic_long_sub_return(nr, &page->pp_ref_count); WARN_ON(ret < 0); - /* We are the last user here too, reset pp_frag_count back to 1 to + /* We are the last user here too, reset pp_ref_count back to 1 to * ensure all pages have been partitioned into 1 piece initially, * this should be the rare case when the last two fragment users call - * page_pool_defrag_page() currently. + * page_pool_unref_page() currently. */ if (unlikely(!ret)) - atomic_long_set(&page->pp_frag_count, 1); + atomic_long_set(&page->pp_ref_count, 1); return ret; } -static inline bool page_pool_is_last_frag(struct page *page) +static inline void page_pool_ref_page(struct page *page) +{ + atomic_long_inc(&page->pp_ref_count); +} + +static inline bool page_pool_is_last_ref(struct page *page) { - /* If page_pool_defrag_page() returns 0, we were the last user */ - return page_pool_defrag_page(page, 1) == 0; + /* If page_pool_unref_page() returns 0, we were the last user */ + return page_pool_unref_page(page, 1) == 0; } /** @@ -301,10 +310,10 @@ static inline void page_pool_put_page(struct page_pool *pool, * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - if (!page_pool_is_last_frag(page)) + if (!page_pool_is_last_ref(page)) return; - page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct); + page_pool_put_unrefed_page(pool, page, dma_sync_size, allow_direct); #endif } diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 6fc5134095..76481c4653 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -5,6 +5,7 @@ #include #include +#include #define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA * map/unmap @@ -48,24 +49,30 @@ struct pp_alloc_cache { * @pool_size: size of the ptr_ring * @nid: NUMA node id to allocate from pages from * @dev: device, for DMA pre-mapping purposes + * @netdev: netdev this pool will serve (leave as NULL if none or multiple) * @napi: NAPI which is the sole consumer of pages, otherwise NULL * @dma_dir: DMA mapping direction * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV */ struct page_pool_params { - unsigned int flags; - unsigned int order; - unsigned int pool_size; - int nid; - struct device *dev; - struct napi_struct *napi; - enum dma_data_direction dma_dir; - unsigned int max_len; - unsigned int offset; + struct_group_tagged(page_pool_params_fast, fast, + unsigned int flags; + unsigned int order; + unsigned int pool_size; + int nid; + struct device *dev; + struct napi_struct *napi; + enum dma_data_direction dma_dir; + unsigned int max_len; + unsigned int offset; + ); + struct_group_tagged(page_pool_params_slow, slow, + struct net_device *netdev; /* private: used by test code only */ - void (*init_callback)(struct page *page, void *arg); - void *init_arg; + void (*init_callback)(struct page *page, void *arg); + void *init_arg; + ); }; #ifdef CONFIG_PAGE_POOL_STATS @@ -119,7 +126,9 @@ struct page_pool_stats { #endif struct page_pool { - struct page_pool_params p; + struct page_pool_params_fast p; + + bool has_init_callback; long frag_users; struct page *frag_page; @@ -178,6 +187,16 @@ struct page_pool { refcount_t user_cnt; u64 destroy_cnt; + + /* Slow/Control-path information follows */ + struct page_pool_params_slow slow; + /* User-facing fields, protected by page_pools_lock */ + struct { + struct hlist_node list; + u64 detach_time; + u32 napi_id; + u32 id; + } user; }; struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); @@ -215,9 +234,9 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, } #endif -void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, - bool allow_direct); +void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, + bool allow_direct); static inline bool is_page_pool_compiled_in(void) { diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a76c9171db..f308e82686 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -154,12 +154,6 @@ __cls_set_class(unsigned long *clp, unsigned long cl) return xchg(clp, cl); } -static inline void tcf_set_drop_reason(struct tcf_result *res, - enum skb_drop_reason reason) -{ - res->drop_reason = reason; -} - static inline void __tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base) { diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 9fa1d0794d..1e200d9a06 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -275,24 +275,6 @@ static inline void skb_txtime_consumed(struct sk_buff *skb) skb->tstamp = ktime_set(0, 0); } -struct tc_skb_cb { - struct qdisc_skb_cb qdisc_cb; - - u16 mru; - u8 post_ct:1; - u8 post_ct_snat:1; - u8 post_ct_dnat:1; - u16 zone; /* Only valid if post_ct = true */ -}; - -static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) -{ - struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb; - - BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); - return cb; -} - static inline bool tc_qdisc_stats_dump(struct Qdisc *sch, unsigned long cl, struct qdisc_walker *arg) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 959a7725c2..41ca14e81d 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -19,6 +19,7 @@ #include #include #include +#include struct Qdisc_ops; struct qdisc_walker; @@ -116,6 +117,7 @@ struct Qdisc { struct qdisc_skb_head q; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; + int owner; unsigned long state; unsigned long state2; /* must be written under qdisc spinlock */ struct Qdisc *next_sched; @@ -237,12 +239,7 @@ static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq) { -#ifdef CONFIG_BQL - /* Non-BQL migrated drivers will return 0, too. */ - return dql_avail(&txq->dql); -#else - return 0; -#endif + return netdev_queue_dql_avail(txq); } struct Qdisc_class_ops { @@ -332,7 +329,6 @@ struct tcf_result { }; const struct tcf_proto *goto_tp; }; - enum skb_drop_reason drop_reason; }; struct tcf_chain; @@ -461,6 +457,7 @@ struct tcf_chain { }; struct tcf_block { + struct xarray ports; /* datapath accessible */ /* Lock protects tcf_block and lifetime-management data of chains * attached to the block (refcnt, action_refcnt, explicitly_created). */ @@ -487,6 +484,8 @@ struct tcf_block { struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */ }; +struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index); + static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain) { return lockdep_is_held(&chain->filter_chain_lock); @@ -1041,6 +1040,37 @@ static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) return skb; } +struct tc_skb_cb { + struct qdisc_skb_cb qdisc_cb; + u32 drop_reason; + + u16 zone; /* Only valid if post_ct = true */ + u16 mru; + u8 post_ct:1; + u8 post_ct_snat:1; + u8 post_ct_dnat:1; +}; + +static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) +{ + struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb; + + BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); + return cb; +} + +static inline enum skb_drop_reason +tcf_get_drop_reason(const struct sk_buff *skb) +{ + return tc_skb_cb(skb)->drop_reason; +} + +static inline void tcf_set_drop_reason(const struct sk_buff *skb, + enum skb_drop_reason reason) +{ + tc_skb_cb(skb)->drop_reason = reason; +} + /* Instead of calling kfree_skb() while root qdisc lock is held, * queue the skb for future freeing at end of __dev_xmit_skb() */ diff --git a/include/net/scm.h b/include/net/scm.h index e8c76b4be2..cf68acec4d 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -208,5 +209,13 @@ static inline void scm_recv_unix(struct socket *sock, struct msghdr *msg, scm_destroy_cred(scm); } +static inline int scm_recv_one_fd(struct file *f, int __user *ufd, + unsigned int flags) +{ + if (!ufd) + return -EFAULT; + return receive_fd(f, ufd, flags); +} + #endif /* __LINUX_NET_SCM_H */ diff --git a/include/net/smc.h b/include/net/smc.h index a002552be2..c9dcb30e3f 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -52,9 +52,14 @@ struct smcd_dmb { struct smcd_dev; struct ism_client; +struct smcd_gid { + u64 gid; + u64 gid_ext; +}; + struct smcd_ops { - int (*query_remote_gid)(struct smcd_dev *dev, u64 rgid, u32 vid_valid, - u32 vid); + int (*query_remote_gid)(struct smcd_dev *dev, struct smcd_gid *rgid, + u32 vid_valid, u32 vid); int (*register_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb, struct ism_client *client); int (*unregister_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb); @@ -62,14 +67,13 @@ struct smcd_ops { int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id); int (*set_vlan_required)(struct smcd_dev *dev); int (*reset_vlan_required)(struct smcd_dev *dev); - int (*signal_event)(struct smcd_dev *dev, u64 rgid, u32 trigger_irq, - u32 event_code, u64 info); + int (*signal_event)(struct smcd_dev *dev, struct smcd_gid *rgid, + u32 trigger_irq, u32 event_code, u64 info); int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx, bool sf, unsigned int offset, void *data, unsigned int size); int (*supports_v2)(void); - u8* (*get_system_eid)(void); - u64 (*get_local_gid)(struct smcd_dev *dev); + void (*get_local_gid)(struct smcd_dev *dev, struct smcd_gid *gid); u16 (*get_chid)(struct smcd_dev *dev); struct device* (*get_dev)(struct smcd_dev *dev); }; diff --git a/include/net/sock.h b/include/net/sock.h index f9a9f61fa1..54a7967613 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -76,19 +76,6 @@ * the other protocols. */ -/* Define this to get the SOCK_DBG debugging facility. */ -#define SOCK_DEBUGGING -#ifdef SOCK_DEBUGGING -#define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \ - printk(KERN_DEBUG msg); } while (0) -#else -/* Validate arguments and do nothing */ -static inline __printf(2, 3) -void SOCK_DEBUG(const struct sock *sk, const char *msg, ...) -{ -} -#endif - /* This is the per-socket lock. The spinlock provides a synchronization * between user contexts and software interrupt processing, whereas the * mini-semaphore synchronizes multiple users amongst themselves. @@ -277,8 +264,6 @@ struct sk_filter; * @sk_pacing_status: Pacing status (requested, handled by sch_fq) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes - * @__sk_flags_offset: empty field used to determine location of bitfield - * @sk_padding: unused element for alignment * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) @@ -352,7 +337,6 @@ 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_bind2_node: bind node in the bhash2 table */ struct sock { /* @@ -544,7 +528,6 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; - struct hlist_node sk_bind2_node; }; enum sk_pacing { @@ -873,16 +856,6 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_add_head(&sk->sk_bind_node, list); } -static inline void __sk_del_bind2_node(struct sock *sk) -{ - __hlist_del(&sk->sk_bind2_node); -} - -static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) -{ - hlist_add_head(&sk->sk_bind2_node, list); -} - #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ @@ -900,8 +873,6 @@ static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) 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_bhash2(__sk, list) \ - hlist_for_each_entry(__sk, list, sk_bind2_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset @@ -1458,33 +1429,36 @@ sk_memory_allocated(const struct sock *sk) /* 1 MB per cpu, in page units */ #define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) +extern int sysctl_mem_pcpu_rsv; + +static inline void proto_memory_pcpu_drain(struct proto *proto) +{ + int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); + + if (val) + atomic_long_add(val, proto->memory_allocated); +} static inline void -sk_memory_allocated_add(struct sock *sk, int amt) +sk_memory_allocated_add(const struct sock *sk, int val) { - int local_reserve; + struct proto *proto = sk->sk_prot; - preempt_disable(); - local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve >= SK_MEMORY_PCPU_RESERVE) { - __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); - atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); - } - preempt_enable(); + val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val >= READ_ONCE(sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); } static inline void -sk_memory_allocated_sub(struct sock *sk, int amt) +sk_memory_allocated_sub(const struct sock *sk, int val) { - int local_reserve; + struct proto *proto = sk->sk_prot; - preempt_disable(); - local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) { - __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); - atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); - } - preempt_enable(); + val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val <= -READ_ONCE(sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 @@ -1808,6 +1782,13 @@ static inline void sock_owned_by_me(const struct sock *sk) #endif } +static inline void sock_not_owned_by_me(const struct sock *sk) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); +#endif +} + static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); @@ -2941,7 +2922,6 @@ extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; extern int sysctl_tstamp_allow_data; -extern int sysctl_optmem_max; extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; diff --git a/include/net/tc_act/tc_ipt.h b/include/net/tc_act/tc_ipt.h deleted file mode 100644 index 4225fcb1c6..0000000000 --- a/include/net/tc_act/tc_ipt.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NET_TC_IPT_H -#define __NET_TC_IPT_H - -#include - -struct xt_entry_target; - -struct tcf_ipt { - struct tc_action common; - u32 tcfi_hook; - char *tcfi_tname; - struct xt_entry_target *tcfi_t; -}; -#define to_ipt(a) ((struct tcf_ipt *)a) - -#endif /* __NET_TC_IPT_H */ diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 32ce8ea369..75722d967b 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -8,6 +8,7 @@ struct tcf_mirred { struct tc_action common; int tcfm_eaction; + u32 tcfm_blockid; bool tcfm_mac_header_xmit; struct net_device __rcu *tcfm_dev; netdevice_tracker tcfm_dev_tracker; diff --git a/include/net/tc_wrapper.h b/include/net/tc_wrapper.h index a6d481b5bc..a608546bce 100644 --- a/include/net/tc_wrapper.h +++ b/include/net/tc_wrapper.h @@ -117,10 +117,6 @@ static inline int tc_act(struct sk_buff *skb, const struct tc_action *a, if (a->ops->act == tcf_ife_act) return tcf_ife_act(skb, a, res); #endif -#if IS_BUILTIN(CONFIG_NET_ACT_IPT) - if (a->ops->act == tcf_ipt_act) - return tcf_ipt_act(skb, a, res); -#endif #if IS_BUILTIN(CONFIG_NET_ACT_SIMP) if (a->ops->act == tcf_simp_act) return tcf_simp_act(skb, a, res); diff --git a/include/net/tcp.h b/include/net/tcp.h index 2ac9475be1..f6eba9652d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -490,13 +490,14 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct dst_entry *dst, u32 tsoff); -int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, - u32 cookie); + struct dst_entry *dst); +int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, - const struct tcp_request_sock_ops *af_ops, - struct sock *sk, struct sk_buff *skb); + struct sock *sk, struct sk_buff *skb, + struct tcp_options_received *tcp_opt, + int mss, u32 tsoff); + #ifdef CONFIG_SYN_COOKIES /* Syncookies use a monotonic timer which increments every 60 seconds. @@ -582,12 +583,15 @@ __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); u64 cookie_init_timestamp(struct request_sock *req, u64 now); bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *opt); -bool cookie_ecn_ok(const struct tcp_options_received *opt, - const struct net *net, const struct dst_entry *dst); + +static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *dst) +{ + return READ_ONCE(net->ipv4.sysctl_tcp_ecn) || + dst_feature(dst, RTAX_FEATURE_ECN); +} /* From net/ipv6/syncookies.c */ -int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, - u32 cookie); +int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index b04afced4c..471e177362 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -291,8 +291,7 @@ void tcp_ao_established(struct sock *sk); void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb); void tcp_ao_connect_init(struct sock *sk); void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, - struct tcp_request_sock *treq, - unsigned short int family, int l3index); + struct request_sock *req, unsigned short int family); #else /* CONFIG_TCP_AO */ static inline int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, @@ -303,8 +302,7 @@ static inline int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, } static inline void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, - struct tcp_request_sock *treq, - unsigned short int family, int l3index) + struct request_sock *req, unsigned short int family) { } diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h index cc00118acc..d60e8148ff 100644 --- a/include/net/tcp_states.h +++ b/include/net/tcp_states.h @@ -22,6 +22,7 @@ enum { TCP_LISTEN, TCP_CLOSING, /* Now a valid state */ TCP_NEW_SYN_RECV, + TCP_BOUND_INACTIVE, /* Pseudo-state for inet_diag */ TCP_MAX_STATES /* Leave at the end! */ }; @@ -43,6 +44,7 @@ enum { TCPF_LISTEN = (1 << TCP_LISTEN), TCPF_CLOSING = (1 << TCP_CLOSING), TCPF_NEW_SYN_RECV = (1 << TCP_NEW_SYN_RECV), + TCPF_BOUND_INACTIVE = (1 << TCP_BOUND_INACTIVE), }; #endif /* _LINUX_TCP_STATES_H */ diff --git a/include/net/tls.h b/include/net/tls.h index 340ad43971..33f657d3c0 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -111,7 +111,8 @@ struct tls_strparser { u32 stopped : 1; u32 copy_mode : 1; u32 mixed_decrypted : 1; - u32 msg_ready : 1; + + bool msg_ready; struct strp_msg stm; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 6a9f8a5f38..33ba6fc151 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -210,22 +210,23 @@ struct vxlan_rdst { }; struct vxlan_config { - union vxlan_addr remote_ip; - union vxlan_addr saddr; - __be32 vni; - int remote_ifindex; - int mtu; - __be16 dst_port; - u16 port_min; - u16 port_max; - u8 tos; - u8 ttl; - __be32 label; - u32 flags; - unsigned long age_interval; - unsigned int addrmax; - bool no_share; - enum ifla_vxlan_df df; + union vxlan_addr remote_ip; + union vxlan_addr saddr; + __be32 vni; + int remote_ifindex; + int mtu; + __be16 dst_port; + u16 port_min; + u16 port_max; + u8 tos; + u8 ttl; + __be32 label; + enum ifla_vxlan_label_policy label_policy; + u32 flags; + unsigned long age_interval; + unsigned int addrmax; + bool no_share; + enum ifla_vxlan_df df; }; enum { diff --git a/include/net/xdp.h b/include/net/xdp.h index 349c36fb5f..e6770dd40c 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -16,7 +16,7 @@ * * The XDP RX-queue info (xdp_rxq_info) is associated with the driver * level RX-ring queues. It is information that is specific to how - * the driver have configured a given RX-ring queue. + * the driver has configured a given RX-ring queue. * * Each xdp_buff frame received in the driver carries a (pointer) * reference to this xdp_rxq_info structure. This provides the XDP @@ -32,7 +32,7 @@ * The struct is not directly tied to the XDP prog. A new XDP prog * can be attached as long as it doesn't change the underlying * RX-ring. If the RX-ring does change significantly, the NIC driver - * naturally need to stop the RX-ring before purging and reallocating + * naturally needs to stop the RX-ring before purging and reallocating * memory. In that process the driver MUST call unregister (which * also applies for driver shutdown and unload). The register API is * also mandatory during RX-ring setup. @@ -369,7 +369,12 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp) static inline bool xdp_metalen_invalid(unsigned long metalen) { - return (metalen & (sizeof(__u32) - 1)) || (metalen > 32); + unsigned long meta_max; + + meta_max = type_max(typeof_member(struct skb_shared_info, meta_len)); + BUILD_BUG_ON(!__builtin_constant_p(meta_max)); + + return !IS_ALIGNED(metalen, sizeof(u32)) || metalen > meta_max; } struct xdp_attachment_info { @@ -399,6 +404,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info, NETDEV_XDP_RX_METADATA_HASH, \ bpf_xdp_metadata_rx_hash, \ xmo_rx_hash) \ + XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \ + NETDEV_XDP_RX_METADATA_VLAN_TAG, \ + bpf_xdp_metadata_rx_vlan_tag, \ + xmo_rx_vlan_tag) \ enum xdp_rx_metadata { #define XDP_METADATA_KFUNC(name, _, __, ___) name, @@ -427,6 +436,7 @@ enum xdp_rss_hash_type { XDP_RSS_L4_UDP = BIT(5), XDP_RSS_L4_SCTP = BIT(6), XDP_RSS_L4_IPSEC = BIT(7), /* L4 based hash include IPSEC SPI */ + XDP_RSS_L4_ICMP = BIT(8), /* Second part: RSS hash type combinations used for driver HW mapping */ XDP_RSS_TYPE_NONE = 0, @@ -442,11 +452,13 @@ enum xdp_rss_hash_type { XDP_RSS_TYPE_L4_IPV4_UDP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV4_SCTP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV4_IPSEC = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, + XDP_RSS_TYPE_L4_IPV4_ICMP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP, XDP_RSS_TYPE_L4_IPV6_UDP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV6_SCTP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV6_IPSEC = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, + XDP_RSS_TYPE_L4_IPV6_ICMP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP_EX = XDP_RSS_TYPE_L4_IPV6_TCP | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_IPV6_UDP_EX = XDP_RSS_TYPE_L4_IPV6_UDP | XDP_RSS_L3_DYNHDR, @@ -457,6 +469,8 @@ struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type); + int (*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto, + u16 *vlan_tci); }; #ifdef CONFIG_NET diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index f83128007f..3d54de168a 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -30,6 +30,7 @@ struct xdp_umem { struct user_struct *user; refcount_t users; u8 flags; + u8 tx_metadata_len; bool zc; struct page **pgs; int id; @@ -92,12 +93,107 @@ struct xdp_sock { struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */ }; +/* + * AF_XDP TX metadata hooks for network devices. + * The following hooks can be defined; unless noted otherwise, they are + * optional and can be filled with a null pointer. + * + * void (*tmo_request_timestamp)(void *priv) + * Called when AF_XDP frame requested egress timestamp. + * + * u64 (*tmo_fill_timestamp)(void *priv) + * Called when AF_XDP frame, that had requested egress timestamp, + * received a completion. The hook needs to return the actual HW timestamp. + * + * void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv) + * Called when AF_XDP frame requested HW checksum offload. csum_start + * indicates position where checksumming should start. + * csum_offset indicates position where checksum should be stored. + * + */ +struct xsk_tx_metadata_ops { + void (*tmo_request_timestamp)(void *priv); + u64 (*tmo_fill_timestamp)(void *priv); + void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv); +}; + #ifdef CONFIG_XDP_SOCKETS int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp); void __xsk_map_flush(void); +/** + * xsk_tx_metadata_to_compl - Save enough relevant metadata information + * to perform tx completion in the future. + * @meta: pointer to AF_XDP metadata area + * @compl: pointer to output struct xsk_tx_metadata_to_compl + * + * This function should be called by the networking device when + * it prepares AF_XDP egress packet. The value of @compl should be stored + * and passed to xsk_tx_metadata_complete upon TX completion. + */ +static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, + struct xsk_tx_metadata_compl *compl) +{ + if (!meta) + return; + + if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) + compl->tx_timestamp = &meta->completion.tx_timestamp; + else + compl->tx_timestamp = NULL; +} + +/** + * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission + * and call appropriate xsk_tx_metadata_ops operation. + * @meta: pointer to AF_XDP metadata area + * @ops: pointer to struct xsk_tx_metadata_ops + * @priv: pointer to driver-private aread + * + * This function should be called by the networking device when + * it prepares AF_XDP egress packet. + */ +static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ + if (!meta) + return; + + if (ops->tmo_request_timestamp) + if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) + ops->tmo_request_timestamp(priv); + + if (ops->tmo_request_checksum) + if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) + ops->tmo_request_checksum(meta->request.csum_start, + meta->request.csum_offset, priv); +} + +/** + * xsk_tx_metadata_complete - Evaluate AF_XDP TX metadata at completion + * and call appropriate xsk_tx_metadata_ops operation. + * @compl: pointer to completion metadata produced from xsk_tx_metadata_to_compl + * @ops: pointer to struct xsk_tx_metadata_ops + * @priv: pointer to driver-private aread + * + * This function should be called by the networking device upon + * AF_XDP egress completion. + */ +static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ + if (!compl) + return; + if (!compl->tx_timestamp) + return; + + *compl->tx_timestamp = ops->tmo_fill_timestamp(priv); +} + #else static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) @@ -114,6 +210,23 @@ static inline void __xsk_map_flush(void) { } +static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, + struct xsk_tx_metadata_compl *compl) +{ +} + +static inline void xsk_tx_metadata_request(struct xsk_tx_metadata *meta, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ +} + +static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, + const struct xsk_tx_metadata_ops *ops, + void *priv) +{ +} + #endif /* CONFIG_XDP_SOCKETS */ #if defined(CONFIG_XDP_SOCKETS) && defined(CONFIG_DEBUG_NET) diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 5425f7ad5e..c9aec9ab61 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -12,6 +12,12 @@ #define XDP_UMEM_MIN_CHUNK_SHIFT 11 #define XDP_UMEM_MIN_CHUNK_SIZE (1 << XDP_UMEM_MIN_CHUNK_SHIFT) +struct xsk_cb_desc { + void *src; + u8 off; + u8 bytes; +}; + #ifdef CONFIG_XDP_SOCKETS void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); @@ -47,6 +53,12 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, xp_set_rxq_info(pool, rxq); } +static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool, + struct xsk_cb_desc *desc) +{ + xp_fill_cb(pool, desc); +} + static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool) { #ifdef CONFIG_NET_RX_BUSY_POLL @@ -183,6 +195,30 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return xp_raw_get_data(pool, addr); } +#define XDP_TXMD_FLAGS_VALID ( \ + XDP_TXMD_FLAGS_TIMESTAMP | \ + XDP_TXMD_FLAGS_CHECKSUM | \ + 0) + +static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta) +{ + return !(meta->flags & ~XDP_TXMD_FLAGS_VALID); +} + +static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr) +{ + struct xsk_tx_metadata *meta; + + if (!pool->tx_metadata_len) + return NULL; + + meta = xp_raw_get_data(pool, addr) - pool->tx_metadata_len; + if (unlikely(!xsk_buff_valid_tx_metadata(meta))) + return NULL; /* no way to signal the error to the user */ + + return meta; +} + static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); @@ -268,6 +304,11 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, { } +static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool, + struct xsk_cb_desc *desc) +{ +} + static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool) { return 0; @@ -351,6 +392,16 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) return NULL; } +static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta) +{ + return false; +} + +static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr) +{ + return NULL; +} + static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c9bb0f892f..1d107241b9 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -2190,4 +2190,13 @@ static inline int register_xfrm_interface_bpf(void) #endif +#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF) +int register_xfrm_state_bpf(void); +#else +static inline int register_xfrm_state_bpf(void) +{ + return 0; +} +#endif + #endif /* _NET_XFRM_H */ diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index b0bdff26fc..99dd7376df 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -12,6 +12,7 @@ struct xsk_buff_pool; struct xdp_rxq_info; +struct xsk_cb_desc; struct xsk_queue; struct xdp_desc; struct xdp_umem; @@ -33,6 +34,7 @@ struct xdp_buff_xsk { }; #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb)) +#define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t)) struct xsk_dma_map { dma_addr_t *dma_pages; @@ -77,10 +79,12 @@ struct xsk_buff_pool { u32 chunk_size; u32 chunk_shift; u32 frame_len; + u8 tx_metadata_len; /* inherited from umem */ u8 cached_need_wakeup; bool uses_need_wakeup; bool dma_need_sync; bool unaligned; + bool tx_sw_csum; void *addrs; /* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect: * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when @@ -132,6 +136,7 @@ static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_p /* AF_XDP ZC drivers, via xdp_sock_buff.h */ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq); +void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc); int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages); void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs); @@ -233,4 +238,9 @@ static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb) return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); } +static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool) +{ + return pool->tx_metadata_len > 0; +} + #endif /* XSK_BUFF_POOL_H_ */ -- cgit v1.2.3