diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-10-24 07:47:44 +0200 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-10-24 07:47:44 +0200 |
| commit | 50b825d7e87f4cff7070df6eb26390152bb29537 (patch) | |
| tree | ec82aba49ab0c4743266ff37e18c8304a0367d06 /include/net | |
| parent | Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc (diff) | |
| parent | tcp: add tcp_reset_xmit_timer() helper (diff) | |
| download | linux-50b825d7e87f4cff7070df6eb26390152bb29537.tar.xz linux-50b825d7e87f4cff7070df6eb26390152bb29537.zip | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Add VF IPSEC offload support in ixgbe, from Shannon Nelson.
2) Add zero-copy AF_XDP support to i40e, from Björn Töpel.
3) All in-tree drivers are converted to {g,s}et_link_ksettings() so we
can get rid of the {g,s}et_settings ethtool callbacks, from Michal
Kubecek.
4) Add software timestamping to veth driver, from Michael Walle.
5) More work to make packet classifiers and actions lockless, from Vlad
Buslov.
6) Support sticky FDB entries in bridge, from Nikolay Aleksandrov.
7) Add ipv6 version of IP_MULTICAST_ALL sockopt, from Andre Naujoks.
8) Support batching of XDP buffers in vhost_net, from Jason Wang.
9) Add flow dissector BPF hook, from Petar Penkov.
10) i40e vf --> generic iavf conversion, from Jesse Brandeburg.
11) Add NLA_REJECT netlink attribute policy type, to signal when users
provide attributes in situations which don't make sense. From
Johannes Berg.
12) Switch TCP and fair-queue scheduler over to earliest departure time
model. From Eric Dumazet.
13) Improve guest receive performance by doing rx busy polling in tx
path of vhost networking driver, from Tonghao Zhang.
14) Add per-cgroup local storage to bpf
15) Add reference tracking to BPF, from Joe Stringer. The verifier can
now make sure that references taken to objects are properly released
by the program.
16) Support in-place encryption in TLS, from Vakul Garg.
17) Add new taprio packet scheduler, from Vinicius Costa Gomes.
18) Lots of selftests additions, too numerous to mention one by one here
but all of which are very much appreciated.
19) Support offloading of eBPF programs containing BPF to BPF calls in
nfp driver, frm Quentin Monnet.
20) Move dpaa2_ptp driver out of staging, from Yangbo Lu.
21) Lots of u32 classifier cleanups and simplifications, from Al Viro.
22) Add new strict versions of netlink message parsers, and enable them
for some situations. From David Ahern.
23) Evict neighbour entries on carrier down, also from David Ahern.
24) Support BPF sk_msg verdict programs with kTLS, from Daniel Borkmann
and John Fastabend.
25) Add support for filtering route dumps, from David Ahern.
26) New igc Intel driver for 2.5G parts, from Sasha Neftin et al.
27) Allow vxlan enslavement to bridges in mlxsw driver, from Ido
Schimmel.
28) Add queue and stack map types to eBPF, from Mauricio Vasquez B.
29) Add back byte-queue-limit support to r8169, with all the bug fixes
in other areas of the driver it works now! From Florian Westphal and
Heiner Kallweit.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2147 commits)
tcp: add tcp_reset_xmit_timer() helper
qed: Fix static checker warning
Revert "be2net: remove desc field from be_eq_obj"
Revert "net: simplify sock_poll_wait"
net: socionext: Reset tx queue in ndo_stop
net: socionext: Add dummy PHY register read in phy_write()
net: socionext: Stop PHY before resetting netsec
net: stmmac: Set OWN bit for jumbo frames
arm64: dts: stratix10: Support Ethernet Jumbo frame
tls: Add maintainers
net: ethernet: ti: cpsw: unsync mcast entries while switch promisc mode
octeontx2-af: Support for NIXLF's UCAST/PROMISC/ALLMULTI modes
octeontx2-af: Support for setting MAC address
octeontx2-af: Support for changing RSS algorithm
octeontx2-af: NIX Rx flowkey configuration for RSS
octeontx2-af: Install ucast and bcast pkt forwarding rules
octeontx2-af: Add LMAC channel info to NIXLF_ALLOC response
octeontx2-af: NPC MCAM and LDATA extract minimal configuration
octeontx2-af: Enable packet length and csum validation
octeontx2-af: Support for VTAG strip and capture
...
Diffstat (limited to 'include/net')
48 files changed, 979 insertions, 192 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index 970303448c90..05c7df41d737 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -13,7 +13,7 @@ #include <net/netns/generic.h> struct tcf_idrinfo { - spinlock_t lock; + struct mutex lock; struct idr action_idr; }; @@ -31,10 +31,12 @@ struct tc_action { int tcfa_action; struct tcf_t tcfa_tm; struct gnet_stats_basic_packed tcfa_bstats; + struct gnet_stats_basic_packed tcfa_bstats_hw; struct gnet_stats_queue tcfa_qstats; struct net_rate_estimator __rcu *tcfa_rate_est; spinlock_t tcfa_lock; struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_basic_cpu __percpu *cpu_bstats_hw; struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie __rcu *act_cookie; struct tcf_chain *goto_chain; @@ -85,8 +87,7 @@ struct tc_action_ops { struct tcf_result *); /* called under RCU BH lock*/ int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *); - int (*lookup)(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack); + int (*lookup)(struct net *net, struct tc_action **a, u32 index); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, int ovr, int bind, bool rtnl_held, @@ -95,7 +96,7 @@ struct tc_action_ops { struct netlink_callback *, int, const struct tc_action_ops *, struct netlink_ext_ack *); - void (*stats_update)(struct tc_action *, u64, u32, u64); + void (*stats_update)(struct tc_action *, u64, u32, u64, bool); size_t (*get_fill_size)(const struct tc_action *act); struct net_device *(*get_dev)(const struct tc_action *a); void (*put_dev)(struct net_device *dev); @@ -116,7 +117,7 @@ int tc_action_net_init(struct tc_action_net *tn, if (!tn->idrinfo) return -ENOMEM; tn->ops = ops; - spin_lock_init(&tn->idrinfo->lock); + mutex_init(&tn->idrinfo->lock); idr_init(&tn->idrinfo->action_idr); return err; } @@ -183,13 +184,13 @@ int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); #endif /* CONFIG_NET_CLS_ACT */ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, - u64 packets, u64 lastuse) + u64 packets, u64 lastuse, bool hw) { #ifdef CONFIG_NET_CLS_ACT if (!a->ops->stats_update) return; - a->ops->stats_update(a, bytes, packets, lastuse); + a->ops->stats_update(a, bytes, packets, lastuse, hw); #endif } diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 6def0351bcc3..14b789a123e7 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -265,6 +265,11 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly; struct ipv6_bpf_stub { int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len, bool force_bind_address_no_port, bool with_lock); + struct sock *(*udp6_lib_lookup)(struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, + int dif, int sdif, struct udp_table *tbl, + struct sk_buff *skb); }; extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index f53edb3754bc..de587948042a 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -13,6 +13,7 @@ #define _NET_RXRPC_H #include <linux/rxrpc.h> +#include <linux/ktime.h> struct key; struct sock; @@ -77,5 +78,8 @@ int rxrpc_kernel_retry_call(struct socket *, struct rxrpc_call *, int rxrpc_kernel_check_call(struct socket *, struct rxrpc_call *, enum rxrpc_call_completion *, u32 *); u32 rxrpc_kernel_check_life(struct socket *, struct rxrpc_call *); +u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *); +bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *, + ktime_t *); #endif /* _NET_RXRPC_H */ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index a5ba41b3b867..e2695c4bf358 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -52,7 +52,7 @@ struct unix_skb_parms { struct unix_sock { /* WARNING: sk has to be the first member */ struct sock sk; - struct unix_address *addr; + struct unix_address *addr; struct path path; struct mutex iolock, bindlock; struct sock *peer; @@ -63,7 +63,7 @@ struct unix_sock { #define UNIX_GC_CANDIDATE 0 #define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; - wait_queue_entry_t peer_wake; + wait_queue_entry_t peer_wake; }; static inline struct unix_sock *unix_sk(const struct sock *sk) diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index cdd9f1fe7cfa..c36dc1e20556 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1517,6 +1517,20 @@ struct hci_cp_le_write_def_data_len { __le16 tx_time; } __packed; +#define HCI_OP_LE_ADD_TO_RESOLV_LIST 0x2027 +struct hci_cp_le_add_to_resolv_list { + __u8 bdaddr_type; + bdaddr_t bdaddr; + __u8 peer_irk[16]; + __u8 local_irk[16]; +} __packed; + +#define HCI_OP_LE_DEL_FROM_RESOLV_LIST 0x2028 +struct hci_cp_le_del_from_resolv_list { + __u8 bdaddr_type; + bdaddr_t bdaddr; +} __packed; + #define HCI_OP_LE_CLEAR_RESOLV_LIST 0x2029 #define HCI_OP_LE_READ_RESOLV_LIST_SIZE 0x202a diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 0db1b9b428b7..e5ea633ea368 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -103,6 +103,14 @@ struct bdaddr_list { u8 bdaddr_type; }; +struct bdaddr_list_with_irk { + struct list_head list; + bdaddr_t bdaddr; + u8 bdaddr_type; + u8 peer_irk[16]; + u8 local_irk[16]; +}; + struct bt_uuid { struct list_head list; u8 uuid[16]; @@ -259,6 +267,8 @@ struct hci_dev { __u16 le_max_tx_time; __u16 le_max_rx_len; __u16 le_max_rx_time; + __u8 le_max_key_size; + __u8 le_min_key_size; __u16 discov_interleaved_timeout; __u16 conn_info_min_age; __u16 conn_info_max_age; @@ -1058,8 +1068,15 @@ int hci_inquiry(void __user *arg); struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *list, bdaddr_t *bdaddr, u8 type); +struct bdaddr_list_with_irk *hci_bdaddr_list_lookup_with_irk( + struct list_head *list, bdaddr_t *bdaddr, + u8 type); int hci_bdaddr_list_add(struct list_head *list, bdaddr_t *bdaddr, u8 type); +int hci_bdaddr_list_add_with_irk(struct list_head *list, bdaddr_t *bdaddr, + u8 type, u8 *peer_irk, u8 *local_irk); int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type); +int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, + u8 type); void hci_bdaddr_list_clear(struct list_head *list); struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 0697fd413087..093aedebdf0c 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -277,12 +277,19 @@ struct l2cap_conn_rsp { #define L2CAP_CR_SEC_BLOCK 0x0003 #define L2CAP_CR_NO_MEM 0x0004 #define L2CAP_CR_BAD_AMP 0x0005 -#define L2CAP_CR_AUTHENTICATION 0x0005 -#define L2CAP_CR_AUTHORIZATION 0x0006 -#define L2CAP_CR_BAD_KEY_SIZE 0x0007 -#define L2CAP_CR_ENCRYPTION 0x0008 -#define L2CAP_CR_INVALID_SCID 0x0009 -#define L2CAP_CR_SCID_IN_USE 0x000A +#define L2CAP_CR_INVALID_SCID 0x0006 +#define L2CAP_CR_SCID_IN_USE 0x0007 + +/* credit based connect results */ +#define L2CAP_CR_LE_SUCCESS 0x0000 +#define L2CAP_CR_LE_BAD_PSM 0x0002 +#define L2CAP_CR_LE_NO_MEM 0x0004 +#define L2CAP_CR_LE_AUTHENTICATION 0x0005 +#define L2CAP_CR_LE_AUTHORIZATION 0x0006 +#define L2CAP_CR_LE_BAD_KEY_SIZE 0x0007 +#define L2CAP_CR_LE_ENCRYPTION 0x0008 +#define L2CAP_CR_LE_INVALID_SCID 0x0009 +#define L2CAP_CR_LE_SCID_IN_USE 0X000A /* connect/create channel status */ #define L2CAP_CS_NO_INFO 0x0000 @@ -455,9 +462,6 @@ struct l2cap_conn_param_update_rsp { #define L2CAP_CONN_PARAM_ACCEPTED 0x0000 #define L2CAP_CONN_PARAM_REJECTED 0x0001 -#define L2CAP_LE_MAX_CREDITS 10 -#define L2CAP_LE_DEFAULT_MPS 230 - struct l2cap_le_conn_req { __le16 psm; __le16 scid; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4de121e24ce5..1fa41b7a1be3 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -149,7 +149,7 @@ enum ieee80211_channel_flags { */ struct ieee80211_channel { enum nl80211_band band; - u16 center_freq; + u32 center_freq; u16 hw_value; u32 flags; int max_antenna_gain; @@ -775,6 +775,12 @@ struct cfg80211_crypto_settings { * @assocresp_ies_len: length of assocresp_ies in octets * @probe_resp_len: length of probe response template (@probe_resp) * @probe_resp: probe response template (AP mode only) + * @ftm_responder: enable FTM responder functionality; -1 for no change + * (which also implies no change in LCI/civic location data) + * @lci: LCI subelement content + * @civicloc: Civic location subelement content + * @lci_len: LCI data length + * @civicloc_len: Civic location data length */ struct cfg80211_beacon_data { const u8 *head, *tail; @@ -782,12 +788,17 @@ struct cfg80211_beacon_data { const u8 *proberesp_ies; const u8 *assocresp_ies; const u8 *probe_resp; + const u8 *lci; + const u8 *civicloc; + s8 ftm_responder; size_t head_len, tail_len; size_t beacon_ies_len; size_t proberesp_ies_len; size_t assocresp_ies_len; size_t probe_resp_len; + size_t lci_len; + size_t civicloc_len; }; struct mac_address { @@ -849,6 +860,7 @@ struct cfg80211_bitrate_mask { * @beacon_rate: bitrate to be used for beacons * @ht_cap: HT capabilities (or %NULL if HT isn't enabled) * @vht_cap: VHT capabilities (or %NULL if VHT isn't enabled) + * @he_cap: HE capabilities (or %NULL if HE isn't enabled) * @ht_required: stations must support HT * @vht_required: stations must support VHT */ @@ -874,6 +886,7 @@ struct cfg80211_ap_settings { const struct ieee80211_ht_cap *ht_cap; const struct ieee80211_vht_cap *vht_cap; + const struct ieee80211_he_cap_elem *he_cap; bool ht_required, vht_required; }; @@ -1290,6 +1303,10 @@ struct cfg80211_tid_stats { * @ack_signal: signal strength (in dBm) of the last ACK frame. * @avg_ack_signal: average rssi value of ack packet for the no of msdu's has * been sent. + * @rx_mpdu_count: number of MPDUs received from this station + * @fcs_err_count: number of packets (MPDUs) received from this station with + * an FCS error. This counter should be incremented only when TA of the + * received packet with an FCS error matches the peer MAC address. */ struct station_info { u64 filled; @@ -1336,6 +1353,9 @@ struct station_info { struct cfg80211_tid_stats *pertid; s8 ack_signal; s8 avg_ack_signal; + + u32 rx_mpdu_count; + u32 fcs_err_count; }; #if IS_ENABLED(CONFIG_CFG80211) @@ -2795,6 +2815,40 @@ struct cfg80211_external_auth_params { }; /** + * cfg80211_ftm_responder_stats - FTM responder statistics + * + * @filled: bitflag of flags using the bits of &enum nl80211_ftm_stats to + * indicate the relevant values in this struct for them + * @success_num: number of FTM sessions in which all frames were successfully + * answered + * @partial_num: number of FTM sessions in which part of frames were + * successfully answered + * @failed_num: number of failed FTM sessions + * @asap_num: number of ASAP FTM sessions + * @non_asap_num: number of non-ASAP FTM sessions + * @total_duration_ms: total sessions durations - gives an indication + * of how much time the responder was busy + * @unknown_triggers_num: number of unknown FTM triggers - triggers from + * initiators that didn't finish successfully the negotiation phase with + * the responder + * @reschedule_requests_num: number of FTM reschedule requests - initiator asks + * for a new scheduling although it already has scheduled FTM slot + * @out_of_window_triggers_num: total FTM triggers out of scheduled window + */ +struct cfg80211_ftm_responder_stats { + u32 filled; + u32 success_num; + u32 partial_num; + u32 failed_num; + u32 asap_num; + u32 non_asap_num; + u64 total_duration_ms; + u32 unknown_triggers_num; + u32 reschedule_requests_num; + u32 out_of_window_triggers_num; +}; + +/** * struct cfg80211_ops - backend description for wireless configuration * * This struct is registered by fullmac card drivers and/or wireless stacks @@ -3126,6 +3180,9 @@ struct cfg80211_external_auth_params { * * @tx_control_port: TX a control port frame (EAPoL). The noencrypt parameter * tells the driver that the frame should not be encrypted. + * + * @get_ftm_responder_stats: Retrieve FTM responder statistics, if available. + * Statistics should be cumulative, currently no way to reset is provided. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -3431,6 +3488,10 @@ struct cfg80211_ops { const u8 *buf, size_t len, const u8 *dest, const __be16 proto, const bool noencrypt); + + int (*get_ftm_responder_stats)(struct wiphy *wiphy, + struct net_device *dev, + struct cfg80211_ftm_responder_stats *ftm_stats); }; /* @@ -3958,7 +4019,6 @@ struct wiphy_iftype_ext_capab { * by the driver in the .connect() callback. The bit position maps to the * attribute indices defined in &enum nl80211_bss_select_attr. * - * @cookie_counter: unique generic cookie counter, used to identify objects. * @nan_supported_bands: bands supported by the device in NAN mode, a * bitmap of &enum nl80211_band values. For instance, for * NL80211_BAND_2GHZ, bit 0 would be set @@ -4097,8 +4157,6 @@ struct wiphy { u32 bss_select_support; - u64 cookie_counter; - u8 nan_supported_bands; u32 txq_limit; @@ -4733,6 +4791,17 @@ const u8 *cfg80211_find_vendor_ie(unsigned int oui, int oui_type, const u8 *ies, int len); /** + * cfg80211_send_layer2_update - send layer 2 update frame + * + * @dev: network device + * @addr: STA MAC address + * + * Wireless drivers can use this function to update forwarding tables in bridge + * devices upon STA association. + */ +void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr); + +/** * DOC: Regulatory enforcement infrastructure * * TODO diff --git a/include/net/devlink.h b/include/net/devlink.h index 99efc156a309..45db0c79462d 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -362,6 +362,9 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_MAX_MACS, DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT, + DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -380,6 +383,15 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME "region_snapshot_enable" #define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE DEVLINK_PARAM_TYPE_BOOL +#define DEVLINK_PARAM_GENERIC_IGNORE_ARI_NAME "ignore_ari" +#define DEVLINK_PARAM_GENERIC_IGNORE_ARI_TYPE DEVLINK_PARAM_TYPE_BOOL + +#define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_NAME "msix_vec_per_pf_max" +#define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_TYPE DEVLINK_PARAM_TYPE_U32 + +#define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME "msix_vec_per_pf_min" +#define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE DEVLINK_PARAM_TYPE_U32 + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ @@ -451,11 +463,14 @@ struct devlink_ops { u32 *p_cur, u32 *p_max); int (*eswitch_mode_get)(struct devlink *devlink, u16 *p_mode); - int (*eswitch_mode_set)(struct devlink *devlink, u16 mode); + int (*eswitch_mode_set)(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack); int (*eswitch_inline_mode_get)(struct devlink *devlink, u8 *p_inline_mode); - int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode); + int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode, + struct netlink_ext_ack *extack); int (*eswitch_encap_mode_get)(struct devlink *devlink, u8 *p_encap_mode); - int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode); + int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode, + struct netlink_ext_ack *extack); }; static inline void *devlink_priv(struct devlink *devlink) diff --git a/include/net/dsa.h b/include/net/dsa.h index 461e8a7661b7..23690c44e167 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -35,6 +35,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_BRCM_PREPEND, DSA_TAG_PROTO_DSA, DSA_TAG_PROTO_EDSA, + DSA_TAG_PROTO_GSWIP, DSA_TAG_PROTO_KSZ, DSA_TAG_PROTO_LAN9303, DSA_TAG_PROTO_MTK, diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 883bb9085f15..946bd53a9f81 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -44,6 +44,10 @@ void __gnet_stats_copy_basic(const seqcount_t *running, struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); +int gnet_stats_copy_basic_hw(const seqcount_t *running, + struct gnet_dump *d, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b); int gnet_stats_copy_rate_est(struct gnet_dump *d, struct net_rate_estimator __rcu **ptr); int gnet_stats_copy_queue(struct gnet_dump *d, diff --git a/include/net/genetlink.h b/include/net/genetlink.h index decf6012a401..aa2e5888f18d 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -112,7 +112,7 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) static inline int genl_err_attr(struct genl_info *info, int err, - struct nlattr *attr) + const struct nlattr *attr) { info->extack->bad_attr = attr; diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index feef706e1158..8014153bdd49 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -75,6 +75,8 @@ enum ieee80211_radiotap_presence { IEEE80211_RADIOTAP_TIMESTAMP = 22, IEEE80211_RADIOTAP_HE = 23, IEEE80211_RADIOTAP_HE_MU = 24, + IEEE80211_RADIOTAP_ZERO_LEN_PSDU = 26, + IEEE80211_RADIOTAP_LSIG = 27, /* valid in every it_present bitmap, even vendor namespaces */ IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29, @@ -325,6 +327,25 @@ enum ieee80211_radiotap_he_mu_bits { IEEE80211_RADIOTAP_HE_MU_FLAGS2_CH2_CTR_26T_RU = 0x0800, }; +enum ieee80211_radiotap_lsig_data1 { + IEEE80211_RADIOTAP_LSIG_DATA1_RATE_KNOWN = 0x0001, + IEEE80211_RADIOTAP_LSIG_DATA1_LENGTH_KNOWN = 0x0002, +}; + +enum ieee80211_radiotap_lsig_data2 { + IEEE80211_RADIOTAP_LSIG_DATA2_RATE = 0x000f, + IEEE80211_RADIOTAP_LSIG_DATA2_LENGTH = 0xfff0, +}; + +struct ieee80211_radiotap_lsig { + __le16 data1, data2; +}; + +enum ieee80211_radiotap_zero_len_psdu_type { + IEEE80211_RADIOTAP_ZERO_LEN_PSDU_SOUNDING = 0, + IEEE80211_RADIOTAP_ZERO_LEN_PSDU_VENDOR = 0xff, +}; + /** * ieee80211_get_radiotap_len - get radiotap header length */ diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index 482a1b705362..c8e2bebd8d93 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -183,8 +183,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) * 1 if something is broken and should be logged (!!! above) * 2 if packet should be dropped */ -static inline int INET_ECN_decapsulate(struct sk_buff *skb, - __u8 outer, __u8 inner) +static inline int __INET_ECN_decapsulate(__u8 outer, __u8 inner, bool *set_ce) { if (INET_ECN_is_not_ect(inner)) { switch (outer & INET_ECN_MASK) { @@ -198,10 +197,21 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb, } } - if (INET_ECN_is_ce(outer)) + *set_ce = INET_ECN_is_ce(outer); + return 0; +} + +static inline int INET_ECN_decapsulate(struct sk_buff *skb, + __u8 outer, __u8 inner) +{ + bool set_ce = false; + int rc; + + rc = __INET_ECN_decapsulate(outer, inner, &set_ce); + if (!rc && set_ce) INET_ECN_set_ce(skb); - return 0; + return rc; } static inline int IP_ECN_decapsulate(const struct iphdr *oiph, diff --git a/include/net/ip.h b/include/net/ip.h index e44b1a44f67a..72593e171d14 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -420,8 +420,35 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk, return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU); } -int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len, - u32 *metrics); +struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, + int fc_mx_len); +static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics) +{ + if (fib_metrics != &dst_default_metrics && + refcount_dec_and_test(&fib_metrics->refcnt)) + kfree(fib_metrics); +} + +/* ipv4 and ipv6 both use refcounted metrics if it is not the default */ +static inline +void ip_dst_init_metrics(struct dst_entry *dst, struct dst_metrics *fib_metrics) +{ + dst_init_metrics(dst, fib_metrics->metrics, true); + + if (fib_metrics != &dst_default_metrics) { + dst->_metrics |= DST_METRICS_REFCOUNTED; + refcount_inc(&fib_metrics->refcnt); + } +} + +static inline +void ip_dst_metrics_put(struct dst_entry *dst) +{ + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); + + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) + kfree(p); +} u32 ip_idents_reserve(u32 hash, int segs); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 2d31e22babd8..84097010237c 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -186,7 +186,6 @@ struct rt6_info { struct in6_addr rt6i_gateway; struct inet6_dev *rt6i_idev; u32 rt6i_flags; - struct rt6key rt6i_prefsrc; struct list_head rt6i_uncached; struct uncached_list *rt6i_uncached_list; @@ -412,11 +411,33 @@ struct fib6_node *fib6_locate(struct fib6_node *root, void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg), void *arg); +void fib6_clean_all_skip_notify(struct net *net, + int (*func)(struct fib6_info *, void *arg), + void *arg); int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack); int fib6_del(struct fib6_info *rt, struct nl_info *info); +static inline +void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) +{ + const struct fib6_info *from; + + rcu_read_lock(); + + from = rcu_dereference(rt->from); + if (from) { + *addr = from->fib6_prefsrc.addr; + } else { + struct in6_addr in6_zero = {}; + + *addr = in6_zero; + } + + rcu_read_unlock(); +} + static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i) { return f6i->fib6_nh.nh_dev; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 7b9c82de11cc..7ab119936e69 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -165,8 +165,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu); void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, kuid_t uid); -void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif, - u32 mark); +void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif); void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk); struct netlink_callback; @@ -175,6 +174,7 @@ struct rt6_rtnl_dump_arg { struct sk_buff *skb; struct netlink_callback *cb; struct net *net; + struct fib_dump_filter filter; }; int rt6_dump_route(struct fib6_info *f6i, void *p_arg); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index c9b7b136939d..e8d9456bf36e 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -222,6 +222,16 @@ struct fib_table { unsigned long __data[0]; }; +struct fib_dump_filter { + u32 table_id; + /* filter_set is an optimization that an entry is set */ + bool filter_set; + unsigned char protocol; + unsigned char rt_type; + unsigned int flags; + struct net_device *dev; +}; + int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, @@ -229,7 +239,7 @@ int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, - struct netlink_callback *cb); + struct netlink_callback *cb, struct fib_dump_filter *filter); int fib_table_flush(struct net *net, struct fib_table *table); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); @@ -373,6 +383,7 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net, extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); __be32 fib_compute_spec_dst(struct sk_buff *skb); +bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); @@ -452,4 +463,7 @@ static inline void fib_proc_exit(struct net *net) u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr); +int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, + struct fib_dump_filter *filter, + struct netlink_callback *cb); #endif /* _NET_FIB_H */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index ff33f498c137..829650540780 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1089,8 +1089,6 @@ static inline int snmp6_unregister_dev(struct inet6_dev *idev) { return 0; } #endif #ifdef CONFIG_SYSCTL -extern struct ctl_table ipv6_route_table_template[]; - struct ctl_table *ipv6_icmp_sysctl_init(struct net *net); struct ctl_table *ipv6_route_sysctl_init(struct net *net); int ipv6_sysctl_register(void); diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h index f4c21b5a1242..14a490246be9 100644 --- a/include/net/iucv/af_iucv.h +++ b/include/net/iucv/af_iucv.h @@ -80,6 +80,11 @@ struct af_iucv_trans_hdr { u8 pad; /* total 104 bytes */ } __packed; +static inline struct af_iucv_trans_hdr *iucv_trans_hdr(struct sk_buff *skb) +{ + return (struct af_iucv_trans_hdr *)skb_network_header(skb); +} + enum iucv_tx_notify { /* transmission of skb is completed and was successful */ TX_NOTIFY_OK = 0, diff --git a/include/net/llc.h b/include/net/llc.h index 890a87318014..df282d9b4017 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -66,6 +66,7 @@ struct llc_sap { int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; + struct rcu_head rcu; }; static inline diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 5790f55c241d..71985e95d2d9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -101,8 +101,9 @@ * Drivers indicate that they use this model by implementing the .wake_tx_queue * driver operation. * - * Intermediate queues (struct ieee80211_txq) are kept per-sta per-tid, with a - * single per-vif queue for multicast data frames. + * Intermediate queues (struct ieee80211_txq) are kept per-sta per-tid, with + * another per-sta for non-data/non-mgmt and bufferable management frames, and + * a single per-vif queue for multicast data frames. * * The driver is expected to initialize its private per-queue data for stations * and interfaces in the .add_interface and .sta_add ops. @@ -308,6 +309,8 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_KEEP_ALIVE: keep alive options (idle period or protected * keep alive) changed. * @BSS_CHANGED_MCAST_RATE: Multicast Rate setting changed for this interface + * @BSS_CHANGED_FTM_RESPONDER: fime timing reasurement request responder + * functionality changed for this BSS (AP mode). * */ enum ieee80211_bss_change { @@ -337,6 +340,7 @@ enum ieee80211_bss_change { BSS_CHANGED_MU_GROUPS = 1<<23, BSS_CHANGED_KEEP_ALIVE = 1<<24, BSS_CHANGED_MCAST_RATE = 1<<25, + BSS_CHANGED_FTM_RESPONDER = 1<<26, /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -463,6 +467,21 @@ struct ieee80211_mu_group_data { }; /** + * ieee80211_ftm_responder_params - FTM responder parameters + * + * @lci: LCI subelement content + * @civicloc: CIVIC location subelement content + * @lci_len: LCI data length + * @civicloc_len: Civic data length + */ +struct ieee80211_ftm_responder_params { + const u8 *lci; + const u8 *civicloc; + size_t lci_len; + size_t civicloc_len; +}; + +/** * struct ieee80211_bss_conf - holds the BSS's changing parameters * * This structure keeps information about a BSS (and an association @@ -561,6 +580,9 @@ struct ieee80211_mu_group_data { * @protected_keep_alive: if set, indicates that the station should send an RSN * protected frame to the AP to reset the idle timer at the AP for the * station. + * @ftm_responder: whether to enable or disable fine timing measurement FTM + * responder functionality. + * @ftmr_params: configurable lci/civic parameter when enabling FTM responder. */ struct ieee80211_bss_conf { const u8 *bssid; @@ -611,6 +633,8 @@ struct ieee80211_bss_conf { bool allow_p2p_go_ps; u16 max_idle_period; bool protected_keep_alive; + bool ftm_responder; + struct ieee80211_ftm_responder_params *ftmr_params; }; /** @@ -1140,6 +1164,11 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * from the RX info data, so leave those zeroed when building this data) * @RX_FLAG_RADIOTAP_HE_MU: HE MU radiotap data is present * (&struct ieee80211_radiotap_he_mu) + * @RX_FLAG_RADIOTAP_LSIG: L-SIG radiotap data is present + * @RX_FLAG_NO_PSDU: use the frame only for radiotap reporting, with + * the "0-length PSDU" field included there. The value for it is + * in &struct ieee80211_rx_status. Note that if this value isn't + * known the frame shouldn't be reported. */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), @@ -1170,6 +1199,8 @@ enum mac80211_rx_flags { RX_FLAG_AMPDU_EOF_BIT_KNOWN = BIT(25), RX_FLAG_RADIOTAP_HE = BIT(26), RX_FLAG_RADIOTAP_HE_MU = BIT(27), + RX_FLAG_RADIOTAP_LSIG = BIT(28), + RX_FLAG_NO_PSDU = BIT(29), }; /** @@ -1242,6 +1273,7 @@ enum mac80211_rx_encoding { * @ampdu_reference: A-MPDU reference number, must be a different value for * each A-MPDU but the same for each subframe within one A-MPDU * @ampdu_delimiter_crc: A-MPDU delimiter CRC + * @zero_length_psdu_type: radiotap type of the 0-length PSDU */ struct ieee80211_rx_status { u64 mactime; @@ -1262,6 +1294,7 @@ struct ieee80211_rx_status { u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; u8 ampdu_delimiter_crc; + u8 zero_length_psdu_type; }; /** @@ -1504,6 +1537,8 @@ enum ieee80211_vif_flags { * @drv_priv: data area for driver use, will always be aligned to * sizeof(void \*). * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) + * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped, + * protected by fq->lock. */ struct ieee80211_vif { enum nl80211_iftype type; @@ -1528,6 +1563,8 @@ struct ieee80211_vif { unsigned int probe_req_reg; + bool txqs_stopped[IEEE80211_NUM_ACS]; + /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); }; @@ -1839,7 +1876,9 @@ struct ieee80211_sta_rates { * unlimited. * @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not. * @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control. - * @txq: per-TID data TX queues (if driver uses the TXQ abstraction) + * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID + * @txq: per-TID data TX queues (if driver uses the TXQ abstraction); note that + * the last entry (%IEEE80211_NUM_TIDS) is used for non-data frames */ struct ieee80211_sta { u32 supp_rates[NUM_NL80211_BANDS]; @@ -1879,8 +1918,9 @@ struct ieee80211_sta { u16 max_amsdu_len; bool support_p2p_ps; u16 max_rc_amsdu_len; + u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS]; - struct ieee80211_txq *txq[IEEE80211_NUM_TIDS]; + struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); @@ -1914,7 +1954,8 @@ struct ieee80211_tx_control { * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @sta: station table entry, %NULL for per-vif queue - * @tid: the TID for this queue (unused for per-vif queue) + * @tid: the TID for this queue (unused for per-vif queue), + * %IEEE80211_NUM_TIDS for non-data (if enabled) * @ac: the AC for this queue * @drv_priv: driver private area, sized by hw->txq_data_size * @@ -2127,6 +2168,19 @@ struct ieee80211_txq { * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't * support QoS NDP for AP probing - that's most likely a driver bug. * + * @IEEE80211_HW_BUFF_MMPDU_TXQ: use the TXQ for bufferable MMPDUs, this of + * course requires the driver to use TXQs to start with. + * + * @IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW: (Hardware) rate control supports VHT + * extended NSS BW (dot11VHTExtendedNSSBWCapable). This flag will be set if + * the selected rate control algorithm sets %RATE_CTRL_CAPA_VHT_EXT_NSS_BW + * but if the rate control is built-in then it must be set by the driver. + * See also the documentation for that flag. + * + * @IEEE80211_HW_STA_MMPDU_TXQ: use the extra non-TID per-station TXQ for all + * MMPDUs on station interfaces. This of course requires the driver to use + * TXQs to start with. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2172,6 +2226,9 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA, IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP, IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP, + IEEE80211_HW_BUFF_MMPDU_TXQ, + IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW, + IEEE80211_HW_STA_MMPDU_TXQ, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -2290,6 +2347,10 @@ enum ieee80211_hw_flags { * supported by HW. * @max_nan_de_entries: maximum number of NAN DE functions supported by the * device. + * + * @tx_sk_pacing_shift: Pacing shift to set on TCP sockets when frames from + * them are encountered. The default should typically not be changed, + * unless the driver has good reasons for needing more buffers. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -2325,6 +2386,7 @@ struct ieee80211_hw { u8 n_cipher_schemes; const struct ieee80211_cipher_scheme *cipher_schemes; u8 max_nan_de_entries; + u8 tx_sk_pacing_shift; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, @@ -2506,6 +2568,19 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * The set_default_unicast_key() call updates the default WEP key index * configured to the hardware for WEP encryption type. This is required * for devices that support offload of data packets (e.g. ARP responses). + * + * Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag + * when they are able to replace in-use PTK keys according to to following + * requirements: + * 1) They do not hand over frames decrypted with the old key to + mac80211 once the call to set_key() with command %DISABLE_KEY has been + completed when also setting @IEEE80211_KEY_FLAG_GENERATE_IV for any key, + 2) either drop or continue to use the old key for any outgoing frames queued + at the time of the key deletion (including re-transmits), + 3) never send out a frame queued prior to the set_key() %SET_KEY command + encrypted with the new key and + 4) never send out a frame unencrypted when it should be encrypted. + Mac80211 will not queue any new frames for a deleted key to the driver. */ /** @@ -3542,6 +3617,12 @@ enum ieee80211_reconfig_type { * @del_nan_func: Remove a NAN function. The driver must call * ieee80211_nan_func_terminated() with * NL80211_NAN_FUNC_TERM_REASON_USER_REQUEST reason code upon removal. + * @can_aggregate_in_amsdu: Called in order to determine if HW supports + * aggregating two specific frames in the same A-MSDU. The relation + * between the skbs should be symmetric and transitive. Note that while + * skb is always a real frame, head may or may not be an A-MSDU. + * @get_ftm_responder_stats: Retrieve FTM responder statistics, if available. + * Statistics should be cumulative, currently no way to reset is provided. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -3824,6 +3905,12 @@ struct ieee80211_ops { void (*del_nan_func)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u8 instance_id); + bool (*can_aggregate_in_amsdu)(struct ieee80211_hw *hw, + struct sk_buff *head, + struct sk_buff *skb); + int (*get_ftm_responder_stats)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct cfg80211_ftm_responder_stats *ftm_stats); }; /** @@ -4293,6 +4380,21 @@ void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta, u32 thr); /** + * ieee80211_tx_rate_update - transmit rate update callback + * + * Drivers should call this functions with a non-NULL pub sta + * This function can be used in drivers that does not have provision + * in updating the tx rate in data path. + * + * @hw: the hardware the frame was transmitted by + * @pubsta: the station to update the tx rate for. + * @info: tx status information + */ +void ieee80211_tx_rate_update(struct ieee80211_hw *hw, + struct ieee80211_sta *pubsta, + struct ieee80211_tx_info *info); + +/** * ieee80211_tx_status - transmit status callback * * Call this function for all transmitted frames after they have been @@ -5644,7 +5746,22 @@ struct ieee80211_tx_rate_control { bool bss; }; +/** + * enum rate_control_capabilities - rate control capabilities + */ +enum rate_control_capabilities { + /** + * @RATE_CTRL_CAPA_VHT_EXT_NSS_BW: + * Support for extended NSS BW support (dot11VHTExtendedNSSCapable) + * Note that this is only looked at if the minimum number of chains + * that the AP uses is < the number of TX chains the hardware has, + * otherwise the NSS difference doesn't bother us. + */ + RATE_CTRL_CAPA_VHT_EXT_NSS_BW = BIT(0), +}; + struct rate_control_ops { + unsigned long capa; const char *name; void *(*alloc)(struct ieee80211_hw *hw, struct dentry *debugfsdir); void (*free)(void *priv); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 6c1eecd56a4d..f58b384aa6c9 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -323,6 +323,7 @@ void __neigh_set_probe_once(struct neighbour *neigh); bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); +int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev); int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb); @@ -544,4 +545,19 @@ static inline void neigh_update_ext_learned(struct neighbour *neigh, u32 flags, *notify = 1; } } + +static inline void neigh_update_is_router(struct neighbour *neigh, u32 flags, + int *notify) +{ + u8 ndm_flags = 0; + + ndm_flags |= (flags & NEIGH_UPDATE_F_ISROUTER) ? NTF_ROUTER : 0; + if ((neigh->flags ^ ndm_flags) & NTF_ROUTER) { + if (ndm_flags & NTF_ROUTER) + neigh->flags |= NTF_ROUTER; + else + neigh->flags &= ~NTF_ROUTER; + *notify = 1; + } +} #endif diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 9b5fdc50519a..99d4148e0f90 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -43,6 +43,7 @@ struct ctl_table_header; struct net_generic; struct uevent_sock; struct netns_ipvs; +struct bpf_prog; #define NETDEV_HASHBITS 8 @@ -145,6 +146,8 @@ struct net { #endif struct net_generic __rcu *gen; + struct bpf_prog __rcu *flow_dissector_prog; + /* Note : following structs are cache line aligned */ #ifdef CONFIG_XFRM struct netns_xfrm xfrm; diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h index c84b51682f08..135ee702c7b0 100644 --- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h +++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h @@ -10,20 +10,17 @@ #ifndef _NF_CONNTRACK_IPV4_H #define _NF_CONNTRACK_IPV4_H -extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4; -extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp; extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp; #ifdef CONFIG_NF_CT_PROTO_DCCP -extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp; #endif #ifdef CONFIG_NF_CT_PROTO_SCTP -extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp; #endif #ifdef CONFIG_NF_CT_PROTO_UDPLITE -extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4; +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite; #endif -int nf_conntrack_ipv4_compat_init(void); -void nf_conntrack_ipv4_compat_fini(void); - #endif /*_NF_CONNTRACK_IPV4_H*/ diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h index effa8dfba68c..7b3c873f8839 100644 --- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h +++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h @@ -2,20 +2,7 @@ #ifndef _NF_CONNTRACK_IPV6_H #define _NF_CONNTRACK_IPV6_H -extern const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6; - -extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6; -extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6; extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6; -#ifdef CONFIG_NF_CT_PROTO_DCCP -extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6; -#endif -#ifdef CONFIG_NF_CT_PROTO_SCTP -extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6; -#endif -#ifdef CONFIG_NF_CT_PROTO_UDPLITE -extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6; -#endif #include <linux/sysctl.h> extern struct ctl_table nf_ct_ipv6_sysctl_table[]; diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 2a3e0974a6af..afc9b3620473 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -20,8 +20,7 @@ /* This header is used to share core functionality between the standalone connection tracking module, and the compatibility layer's use of connection tracking. */ -unsigned int nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, - struct sk_buff *skb); +unsigned int nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state); int nf_conntrack_init_net(struct net *net); void nf_conntrack_cleanup_net(struct net *net); diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 8465263b297d..eed04af9b75e 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -18,9 +18,6 @@ struct seq_file; struct nf_conntrack_l4proto { - /* L3 Protocol number. */ - u_int16_t l3proto; - /* L4 Protocol number. */ u_int8_t l4proto; @@ -43,22 +40,14 @@ struct nf_conntrack_l4proto { /* Returns verdict for packet, or -1 for invalid. */ int (*packet)(struct nf_conn *ct, - const struct sk_buff *skb, + struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info ctinfo); - - /* Called when a new connection for this protocol found; - * returns TRUE if it's OK. If so, packet() called next. */ - bool (*new)(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff); + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); /* Called when a conntrack entry is destroyed */ void (*destroy)(struct nf_conn *ct); - int (*error)(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, - unsigned int dataoff, - u_int8_t pf, unsigned int hooknum); - /* called by gc worker if table is full */ bool (*can_early_drop)(const struct nf_conn *ct); @@ -92,7 +81,7 @@ struct nf_conntrack_l4proto { #endif unsigned int *net_id; /* Init l4proto pernet data */ - int (*init_net)(struct net *net, u_int16_t proto); + int (*init_net)(struct net *net); /* Return the per-net protocol part. */ struct nf_proto_net *(*get_net_proto)(struct net *net); @@ -101,16 +90,23 @@ struct nf_conntrack_l4proto { struct module *me; }; +int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, + struct sk_buff *skb, + unsigned int dataoff, + const struct nf_hook_state *state); + +int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, + struct sk_buff *skb, + unsigned int dataoff, + const struct nf_hook_state *state); /* Existing built-in generic protocol */ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; -#define MAX_NF_CT_PROTO 256 +#define MAX_NF_CT_PROTO IPPROTO_UDPLITE -const struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u_int16_t l3proto, - u_int8_t l4proto); +const struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u8 l4proto); -const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u_int16_t l3proto, - u_int8_t l4proto); +const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u8 l4proto); void nf_ct_l4proto_put(const struct nf_conntrack_l4proto *p); /* Protocol pernet registration. */ diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 0e355f4a3d76..77e2761d4f2f 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -99,7 +99,7 @@ int nf_flow_table_iterate(struct nf_flowtable *flow_table, void (*iter)(struct flow_offload *flow, void *data), void *data); -void nf_flow_table_cleanup(struct net *net, struct net_device *dev); +void nf_flow_table_cleanup(struct net_device *dev); int nf_flow_table_init(struct nf_flowtable *flow_table); void nf_flow_table_free(struct nf_flowtable *flow_table); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 0f39ac487012..841835a387e1 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -470,6 +470,9 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); +void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_binding *binding); +void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); /** * enum nft_set_extensions - set extension type IDs @@ -724,7 +727,9 @@ struct nft_expr_type { * @eval: Expression evaluation function * @size: full expression size, including private data size * @init: initialization function - * @destroy: destruction function + * @activate: activate expression in the next generation + * @deactivate: deactivate expression in next generation + * @destroy: destruction function, called after synchronize_rcu * @dump: function to dump parameters * @type: expression type * @validate: validate expression, called during loop detection @@ -1293,12 +1298,14 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) * * @list: used internally * @msg_type: message type + * @put_net: ctx->net needs to be put * @ctx: transaction context * @data: internal information related to the transaction */ struct nft_trans { struct list_head list; int msg_type; + bool put_net; struct nft_ctx ctx; char data[0]; }; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 8da837d2aaf9..2046d104f323 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -16,6 +16,10 @@ extern struct nft_expr_type nft_meta_type; extern struct nft_expr_type nft_rt_type; extern struct nft_expr_type nft_exthdr_type; +#ifdef CONFIG_NETWORK_SECMARK +extern struct nft_object_type nft_secmark_obj_type; +#endif + int nf_tables_core_module_init(void); void nf_tables_core_module_exit(void); diff --git a/include/net/netfilter/nfnetlink_log.h b/include/net/netfilter/nfnetlink_log.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/include/net/netfilter/nfnetlink_log.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/include/net/netlink.h b/include/net/netlink.h index 39e1d875d507..4c1e99303b5a 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -172,7 +172,7 @@ enum { NLA_FLAG, NLA_MSECS, NLA_NESTED, - NLA_NESTED_COMPAT, + NLA_NESTED_ARRAY, NLA_NUL_STRING, NLA_BINARY, NLA_S8, @@ -180,14 +180,28 @@ enum { NLA_S32, NLA_S64, NLA_BITFIELD32, + NLA_REJECT, + NLA_EXACT_LEN, + NLA_EXACT_LEN_WARN, __NLA_TYPE_MAX, }; #define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1) +enum nla_policy_validation { + NLA_VALIDATE_NONE, + NLA_VALIDATE_RANGE, + NLA_VALIDATE_MIN, + NLA_VALIDATE_MAX, + NLA_VALIDATE_FUNCTION, +}; + /** * struct nla_policy - attribute validation policy * @type: Type of attribute or NLA_UNSPEC + * @validation_type: type of attribute validation done in addition to + * type-specific validation (e.g. range, function call), see + * &enum nla_policy_validation * @len: Type specific length of payload * * Policies are defined as arrays of this struct, the array must be @@ -198,9 +212,11 @@ enum { * NLA_NUL_STRING Maximum length of string (excluding NUL) * NLA_FLAG Unused * NLA_BINARY Maximum length of attribute payload - * NLA_NESTED Don't use `len' field -- length verification is - * done by checking len of nested header (or empty) - * NLA_NESTED_COMPAT Minimum length of structure payload + * NLA_NESTED, + * NLA_NESTED_ARRAY Length verification is done by checking len of + * nested header (or empty); len field is used if + * validation_data is also used, for the max attr + * number in the nested policy. * NLA_U8, NLA_U16, * NLA_U32, NLA_U64, * NLA_S8, NLA_S16, @@ -208,9 +224,59 @@ enum { * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" - * NLA_BITFIELD32 A 32-bit bitmap/bitselector attribute + * NLA_BITFIELD32 Unused + * NLA_REJECT Unused + * NLA_EXACT_LEN Attribute must have exactly this length, otherwise + * it is rejected. + * NLA_EXACT_LEN_WARN Attribute should have exactly this length, a warning + * is logged if it is longer, shorter is rejected. * All other Minimum length of attribute payload * + * Meaning of `validation_data' field: + * NLA_BITFIELD32 This is a 32-bit bitmap/bitselector attribute and + * validation data must point to a u32 value of valid + * flags + * NLA_REJECT This attribute is always rejected and validation data + * may point to a string to report as the error instead + * of the generic one in extended ACK. + * NLA_NESTED Points to a nested policy to validate, must also set + * `len' to the max attribute number. + * Note that nla_parse() will validate, but of course not + * parse, the nested sub-policies. + * NLA_NESTED_ARRAY Points to a nested policy to validate, must also set + * `len' to the max attribute number. The difference to + * NLA_NESTED is the structure - NLA_NESTED has the + * nested attributes directly inside, while an array has + * the nested attributes at another level down and the + * attributes directly in the nesting don't matter. + * All other Unused - but note that it's a union + * + * Meaning of `min' and `max' fields, use via NLA_POLICY_MIN, NLA_POLICY_MAX + * and NLA_POLICY_RANGE: + * NLA_U8, + * NLA_U16, + * NLA_U32, + * NLA_U64, + * NLA_S8, + * NLA_S16, + * NLA_S32, + * NLA_S64 These are used depending on the validation_type + * field, if that is min/max/range then the minimum, + * maximum and both are used (respectively) to check + * the value of the integer attribute. + * Note that in the interest of code simplicity and + * struct size both limits are s16, so you cannot + * enforce a range that doesn't fall within the range + * of s16 - do that as usual in the code instead. + * All other Unused - but note that it's a union + * + * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: + * NLA_BINARY Validation function called for the attribute, + * not compatible with use of the validation_data + * as in NLA_BITFIELD32, NLA_REJECT, NLA_NESTED and + * NLA_NESTED_ARRAY. + * All other Unused - but note that it's a union + * * Example: * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, @@ -220,11 +286,69 @@ enum { * }; */ struct nla_policy { - u16 type; + u8 type; + u8 validation_type; u16 len; - void *validation_data; + union { + const void *validation_data; + struct { + s16 min, max; + }; + int (*validate)(const struct nlattr *attr, + struct netlink_ext_ack *extack); + }; }; +#define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len } +#define NLA_POLICY_EXACT_LEN_WARN(_len) { .type = NLA_EXACT_LEN_WARN, \ + .len = _len } + +#define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) +#define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) + +#define NLA_POLICY_NESTED(maxattr, policy) \ + { .type = NLA_NESTED, .validation_data = policy, .len = maxattr } +#define NLA_POLICY_NESTED_ARRAY(maxattr, policy) \ + { .type = NLA_NESTED_ARRAY, .validation_data = policy, .len = maxattr } + +#define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) +#define NLA_ENSURE_INT_TYPE(tp) \ + (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 || \ + tp == NLA_S16 || tp == NLA_U16 || \ + tp == NLA_S32 || tp == NLA_U32 || \ + tp == NLA_S64 || tp == NLA_U64) + tp) +#define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ + (__NLA_ENSURE(tp != NLA_BITFIELD32 && \ + tp != NLA_REJECT && \ + tp != NLA_NESTED && \ + tp != NLA_NESTED_ARRAY) + tp) + +#define NLA_POLICY_RANGE(tp, _min, _max) { \ + .type = NLA_ENSURE_INT_TYPE(tp), \ + .validation_type = NLA_VALIDATE_RANGE, \ + .min = _min, \ + .max = _max \ +} + +#define NLA_POLICY_MIN(tp, _min) { \ + .type = NLA_ENSURE_INT_TYPE(tp), \ + .validation_type = NLA_VALIDATE_MIN, \ + .min = _min, \ +} + +#define NLA_POLICY_MAX(tp, _max) { \ + .type = NLA_ENSURE_INT_TYPE(tp), \ + .validation_type = NLA_VALIDATE_MAX, \ + .max = _max, \ +} + +#define NLA_POLICY_VALIDATE_FN(tp, fn, ...) { \ + .type = NLA_ENSURE_NO_VALIDATION_PTR(tp), \ + .validation_type = NLA_VALIDATE_FUNCTION, \ + .validate = fn, \ + .len = __VA_ARGS__ + 0, \ +} + /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request @@ -249,6 +373,9 @@ int nla_validate(const struct nlattr *head, int len, int maxtype, int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack); +int nla_parse_strict(struct nlattr **tb, int maxtype, const struct nlattr *head, + int len, const struct nla_policy *policy, + struct netlink_ext_ack *extack); int nla_policy_len(const struct nla_policy *, int); struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype); size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize); @@ -392,13 +519,29 @@ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, const struct nla_policy *policy, struct netlink_ext_ack *extack) { - if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) + if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) { + NL_SET_ERR_MSG(extack, "Invalid header length"); return -EINVAL; + } return nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), policy, extack); } +static inline int nlmsg_parse_strict(const struct nlmsghdr *nlh, int hdrlen, + struct nlattr *tb[], int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) { + NL_SET_ERR_MSG(extack, "Invalid header length"); + return -EINVAL; + } + + return nla_parse_strict(tb, maxtype, nlmsg_attrdata(nlh, hdrlen), + nlmsg_attrlen(nlh, hdrlen), policy, extack); +} + /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index f0e396ab9bec..ef1ed529f33c 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -45,6 +45,7 @@ struct netns_sysctl_ipv6 { int max_dst_opts_len; int max_hbh_opts_len; int seg6_flowlabel; + bool skip_notify_on_dev_down; }; struct netns_ipv6 { diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 75a3f3fdb359..72ffb3120ced 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -65,11 +65,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return block->q; } -static inline struct net_device *tcf_block_dev(struct tcf_block *block) -{ - return tcf_block_q(block)->dev_queue->dev; -} - void *tcf_block_cb_priv(struct tcf_block_cb *block_cb); struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident); @@ -122,11 +117,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return NULL; } -static inline struct net_device *tcf_block_dev(struct tcf_block *block) -{ - return NULL; -} - static inline int tc_setup_cb_block_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_priv) @@ -318,7 +308,7 @@ tcf_exts_stats_update(const struct tcf_exts *exts, for (i = 0; i < exts->nr_actions; i++) { struct tc_action *a = exts->actions[i]; - tcf_action_stats_update(a, bytes, packets, lastuse); + tcf_action_stats_update(a, bytes, packets, lastuse, true); } preempt_enable(); diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 7dc769e5452b..a16fbe9a2a67 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -102,6 +102,7 @@ int qdisc_set_default(const char *id); void qdisc_hash_add(struct Qdisc *q, bool invisible); void qdisc_hash_del(struct Qdisc *q); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); +struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle); struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab, struct netlink_ext_ack *extack); diff --git a/include/net/route.h b/include/net/route.h index bb53cdba38dc..9883dc82f723 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -201,10 +201,9 @@ static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, - u32 mark, u8 protocol, int flow_flags); + u8 protocol); void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu); -void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, - u8 protocol, int flow_flags); +void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk); void ip_rt_send_redirect(struct sk_buff *skb); diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 0bbaa5488423..cf26e5aacac4 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -165,6 +165,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm); int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, struct netlink_ext_ack *exterr); +struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index a6d00093f35e..4d736427a4cb 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -19,6 +19,7 @@ struct Qdisc_ops; struct qdisc_walker; struct tcf_walker; struct module; +struct bpf_flow_keys; typedef int tc_setup_cb_t(enum tc_setup_type type, void *type_data, void *cb_priv); @@ -105,6 +106,7 @@ struct Qdisc { spinlock_t busylock ____cacheline_aligned_in_smp; spinlock_t seqlock; + struct rcu_head rcu; }; static inline void qdisc_refcount_inc(struct Qdisc *qdisc) @@ -114,6 +116,19 @@ static inline void qdisc_refcount_inc(struct Qdisc *qdisc) refcount_inc(&qdisc->refcnt); } +/* Intended to be used by unlocked users, when concurrent qdisc release is + * possible. + */ + +static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN) + return qdisc; + if (refcount_inc_not_zero(&qdisc->refcnt)) + return qdisc; + return NULL; +} + static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) @@ -307,9 +322,14 @@ struct tcf_proto { }; struct qdisc_skb_cb { - unsigned int pkt_len; - u16 slave_dev_queue_mapping; - u16 tc_classid; + union { + struct { + unsigned int pkt_len; + u16 slave_dev_queue_mapping; + u16 tc_classid; + }; + struct bpf_flow_keys *flow_keys; + }; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; }; @@ -331,7 +351,7 @@ struct tcf_chain { struct tcf_block { struct list_head chain_list; u32 index; /* block index for shared blocks */ - unsigned int refcnt; + refcount_t refcnt; struct net *net; struct Qdisc *q; struct list_head cb_list; @@ -343,6 +363,7 @@ struct tcf_block { struct tcf_chain *chain; struct list_head filter_chain_list; } chain0; + struct rcu_head rcu; }; static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) @@ -362,7 +383,7 @@ static inline void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) } static inline void -tc_cls_offload_cnt_update(struct tcf_block *block, unsigned int *cnt, +tc_cls_offload_cnt_update(struct tcf_block *block, u32 *cnt, u32 *flags, bool add) { if (add) { @@ -554,7 +575,8 @@ void dev_deactivate_many(struct list_head *head); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); -void qdisc_destroy(struct Qdisc *qdisc); +void qdisc_put(struct Qdisc *qdisc); +void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, unsigned int len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, @@ -828,8 +850,8 @@ static inline void qdisc_skb_head_init(struct qdisc_skb_head *qh) qh->qlen = 0; } -static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, - struct qdisc_skb_head *qh) +static inline void __qdisc_enqueue_tail(struct sk_buff *skb, + struct qdisc_skb_head *qh) { struct sk_buff *last = qh->tail; @@ -842,14 +864,24 @@ static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, qh->head = skb; } qh->qlen++; - qdisc_qstats_backlog_inc(sch, skb); +} +static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) +{ + __qdisc_enqueue_tail(skb, &sch->q); + qdisc_qstats_backlog_inc(sch, skb); return NET_XMIT_SUCCESS; } -static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) +static inline void __qdisc_enqueue_head(struct sk_buff *skb, + struct qdisc_skb_head *qh) { - return __qdisc_enqueue_tail(skb, sch, &sch->q); + skb->next = qh->head; + + if (!qh->head) + qh->tail = skb; + qh->head = skb; + qh->qlen++; } static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 86f034b524d4..8dadc74c22e7 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -148,11 +148,6 @@ SCTP_SUBTYPE_CONSTRUCTOR(PRIMITIVE, enum sctp_event_primitive, primitive) #define sctp_chunk_is_data(a) (a->chunk_hdr->type == SCTP_CID_DATA || \ a->chunk_hdr->type == SCTP_CID_I_DATA) -/* Calculate the actual data size in a data chunk */ -#define SCTP_DATA_SNDSIZE(c) ((int)((unsigned long)(c->chunk_end) - \ - (unsigned long)(c->chunk_hdr) - \ - sctp_datachk_len(&c->asoc->stream))) - /* Internal error codes */ enum sctp_ierror { SCTP_IERROR_NO_ERROR = 0, diff --git a/include/net/sock.h b/include/net/sock.h index 433f45fc2d68..f665d74ae509 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -422,8 +422,8 @@ struct sock { struct timer_list sk_timer; __u32 sk_priority; __u32 sk_mark; - u32 sk_pacing_rate; /* bytes per second */ - u32 sk_max_pacing_rate; + unsigned long sk_pacing_rate; /* bytes per second */ + unsigned long sk_max_pacing_rate; struct page_frag sk_frag; netdev_features_t sk_route_caps; netdev_features_t sk_route_nocaps; @@ -800,6 +800,7 @@ enum sock_flags { SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ SOCK_TXTIME, + SOCK_XDP, /* XDP is attached */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) @@ -1491,6 +1492,7 @@ static inline void lock_sock(struct sock *sk) lock_sock_nested(sk, 0); } +void __release_sock(struct sock *sk); void release_sock(struct sock *sk); /* BH context may only use the following locking interface. */ @@ -2057,14 +2059,20 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) /** * sock_poll_wait - place memory barrier behind the poll_wait call. * @filp: file + * @sock: socket to wait on * @p: poll_table * * See the comments in the wq_has_sleeper function. + * + * Do not derive sock from filp->private_data here. An SMC socket establishes + * an internal TCP socket that is used in the fallback case. All socket + * operations on the SMC socket are then forwarded to the TCP socket. In case of + * poll, the filp->private_data pointer references the SMC socket because the + * TCP socket has no file assigned. */ -static inline void sock_poll_wait(struct file *filp, poll_table *p) +static inline void sock_poll_wait(struct file *filp, struct socket *sock, + poll_table *p) { - struct socket *sock = filp->private_data; - if (!poll_does_not_wait(p)) { poll_wait(filp, &sock->wq->wait, p); /* We need to be sure we are in sync with the @@ -2212,10 +2220,6 @@ static inline struct page_frag *sk_page_frag(struct sock *sk) bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); -int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg, - int sg_start, int *sg_curr, unsigned int *sg_size, - int first_coalesce); - /* * Default write policy as shown to user space via poll/select/SIGIO */ diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d574ce63bf22..881ecb1555bf 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -145,6 +145,10 @@ enum switchdev_notifier_type { SWITCHDEV_FDB_ADD_TO_DEVICE, SWITCHDEV_FDB_DEL_TO_DEVICE, SWITCHDEV_FDB_OFFLOADED, + + SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, + SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE, + SWITCHDEV_VXLAN_FDB_OFFLOADED, }; struct switchdev_notifier_info { @@ -155,7 +159,8 @@ struct switchdev_notifier_fdb_info { struct switchdev_notifier_info info; /* must be first */ const unsigned char *addr; u16 vid; - bool added_by_user; + u8 added_by_user:1, + offloaded:1; }; static inline struct net_device * diff --git a/include/net/tcp.h b/include/net/tcp.h index 770917d0caa7..a18914d20486 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -732,7 +732,7 @@ void tcp_send_window_probe(struct sock *sk); static inline u64 tcp_clock_ns(void) { - return local_clock(); + return ktime_get_ns(); } static inline u64 tcp_clock_us(void) @@ -752,17 +752,7 @@ static inline u32 tcp_time_stamp_raw(void) return div_u64(tcp_clock_ns(), NSEC_PER_SEC / TCP_TS_HZ); } - -/* Refresh 1us clock of a TCP socket, - * ensuring monotically increasing values. - */ -static inline void tcp_mstamp_refresh(struct tcp_sock *tp) -{ - u64 val = tcp_clock_us(); - - if (val > tp->tcp_mstamp) - tp->tcp_mstamp = val; -} +void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) { @@ -771,7 +761,13 @@ static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { - return div_u64(skb->skb_mstamp, USEC_PER_SEC / TCP_TS_HZ); + return div_u64(skb->skb_mstamp_ns, NSEC_PER_SEC / TCP_TS_HZ); +} + +/* provide the departure time in us unit */ +static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) +{ + return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } @@ -817,7 +813,7 @@ struct tcp_skb_cb { #define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ #define TCPCB_LOST 0x04 /* SKB is lost */ #define TCPCB_TAGBITS 0x07 /* All tag bits */ -#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp) */ +#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp_ns) */ #define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ TCPCB_REPAIRED) @@ -862,6 +858,21 @@ static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); } +static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb) +{ + return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS; +} + +static inline struct sock *tcp_skb_bpf_redirect_fetch(struct sk_buff *skb) +{ + return TCP_SKB_CB(skb)->bpf.sk_redir; +} + +static inline void tcp_skb_bpf_redirect_clear(struct sk_buff *skb) +{ + TCP_SKB_CB(skb)->bpf.sk_redir = NULL; +} + #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, * as TCP moves IP6CB into a different location in skb->cb[] @@ -1234,8 +1245,31 @@ static inline bool tcp_needs_internal_pacing(const struct sock *sk) return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; } +/* Return in jiffies the delay before one skb is sent. + * If @skb is NULL, we look at EDT for next packet being sent on the socket. + */ +static inline unsigned long tcp_pacing_delay(const struct sock *sk, + const struct sk_buff *skb) +{ + s64 pacing_delay = skb ? skb->tstamp : tcp_sk(sk)->tcp_wstamp_ns; + + pacing_delay -= tcp_sk(sk)->tcp_clock_cache; + + return pacing_delay > 0 ? nsecs_to_jiffies(pacing_delay) : 0; +} + +static inline void tcp_reset_xmit_timer(struct sock *sk, + const int what, + unsigned long when, + const unsigned long max_when, + const struct sk_buff *skb) +{ + inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk, skb), + max_when); +} + /* Something is really bad, we could not queue an additional packet, - * because qdisc is full or receiver sent a 0 window. + * because qdisc is full or receiver sent a 0 window, or we are paced. * We do not want to add fuel to the fire, or abort too early, * so make sure the timer we arm now is at least 200ms in the future, * regardless of current icsk_rto value (as it could be ~2ms) @@ -1257,8 +1291,9 @@ static inline unsigned long tcp_probe0_when(const struct sock *sk, static inline void tcp_check_probe_timer(struct sock *sk) { if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) - inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - tcp_probe0_base(sk), TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, + tcp_probe0_base(sk), TCP_RTO_MAX, + NULL); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) @@ -1940,7 +1975,7 @@ static inline s64 tcp_rto_delta_us(const struct sock *sk) { const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; - u64 rto_time_stamp_us = skb->skb_mstamp + jiffies_to_usecs(rto); + u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; } @@ -2040,11 +2075,6 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); #define TCP_ULP_MAX 128 #define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX) -enum { - TCP_ULP_TLS, - TCP_ULP_BPF, -}; - struct tcp_ulp_ops { struct list_head list; @@ -2053,15 +2083,12 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); - int uid; char name[TCP_ULP_NAME_MAX]; - bool user_visible; struct module *owner; }; int tcp_register_ulp(struct tcp_ulp_ops *type); void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); -int tcp_set_ulp_id(struct sock *sk, const int ulp); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); @@ -2069,6 +2096,18 @@ void tcp_cleanup_ulp(struct sock *sk); __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) +struct sk_msg; +struct sk_psock; + +int tcp_bpf_init(struct sock *sk); +void tcp_bpf_reinit(struct sock *sk); +int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, + int flags); +int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, int *addr_len); +int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, + struct msghdr *msg, int len, int flags); + /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF diff --git a/include/net/tls.h b/include/net/tls.h index 0a769cf2f5f3..bab5627ff5e3 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -39,9 +39,11 @@ #include <linux/crypto.h> #include <linux/socket.h> #include <linux/tcp.h> +#include <linux/skmsg.h> + #include <net/tcp.h> #include <net/strparser.h> - +#include <crypto/aead.h> #include <uapi/linux/tls.h> @@ -93,24 +95,45 @@ enum { TLS_NUM_CONFIG, }; -struct tls_sw_context_tx { - struct crypto_aead *aead_send; - struct crypto_wait async_wait; - - char aad_space[TLS_AAD_SPACE_SIZE]; - - unsigned int sg_plaintext_size; - int sg_plaintext_num_elem; - struct scatterlist sg_plaintext_data[MAX_SKB_FRAGS]; +/* TLS records are maintained in 'struct tls_rec'. It stores the memory pages + * allocated or mapped for each TLS record. After encryption, the records are + * stores in a linked list. + */ +struct tls_rec { + struct list_head list; + int tx_ready; + int tx_flags; + int inplace_crypto; - unsigned int sg_encrypted_size; - int sg_encrypted_num_elem; - struct scatterlist sg_encrypted_data[MAX_SKB_FRAGS]; + struct sk_msg msg_plaintext; + struct sk_msg msg_encrypted; - /* AAD | sg_plaintext_data | sg_tag */ + /* AAD | msg_plaintext.sg.data | sg_tag */ struct scatterlist sg_aead_in[2]; - /* AAD | sg_encrypted_data (data contain overhead for hdr&iv&tag) */ + /* AAD | msg_encrypted.sg.data (data contains overhead for hdr & iv & tag) */ struct scatterlist sg_aead_out[2]; + + char aad_space[TLS_AAD_SPACE_SIZE]; + struct aead_request aead_req; + u8 aead_req_ctx[]; +}; + +struct tx_work { + struct delayed_work work; + struct sock *sk; +}; + +struct tls_sw_context_tx { + struct crypto_aead *aead_send; + struct crypto_wait async_wait; + struct tx_work tx_work; + struct tls_rec *open_rec; + struct list_head tx_list; + atomic_t encrypt_pending; + int async_notify; + +#define BIT_TX_SCHEDULED 0 + unsigned long tx_bitmask; }; struct tls_sw_context_rx { @@ -119,11 +142,12 @@ struct tls_sw_context_rx { struct strparser strp; void (*saved_data_ready)(struct sock *sk); - unsigned int (*sk_poll)(struct file *file, struct socket *sock, - struct poll_table_struct *wait); + struct sk_buff *recv_pkt; u8 control; bool decrypted; + atomic_t decrypt_pending; + bool async_notify; }; struct tls_record_info { @@ -195,10 +219,11 @@ struct tls_context { struct scatterlist *partially_sent_record; u16 partially_sent_offset; + unsigned long flags; bool in_tcp_sendpages; + bool pending_open_record_frags; - u16 pending_open_record_frags; int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); @@ -246,8 +271,7 @@ void tls_sw_free_resources_rx(struct sock *sk); void tls_sw_release_resources_rx(struct sock *sk); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); -unsigned int tls_sw_poll(struct file *file, struct socket *sock, - struct poll_table_struct *wait); +bool tls_sw_stream_read(const struct sock *sk); ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); @@ -259,6 +283,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, void tls_device_sk_destruct(struct sock *sk); void tls_device_init(void); void tls_device_cleanup(void); +int tls_tx_records(struct sock *sk, int flags); struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn); @@ -277,6 +302,9 @@ void tls_sk_destruct(struct sock *sk, struct tls_context *ctx); int tls_push_sg(struct sock *sk, struct tls_context *ctx, struct scatterlist *sg, u16 first_offset, int flags); +int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, + int flags); + int tls_push_pending_closed_record(struct sock *sk, struct tls_context *ctx, int flags, long *timeo); @@ -310,6 +338,17 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) return tls_ctx->pending_open_record_frags; } +static inline bool is_tx_ready(struct tls_sw_context_tx *ctx) +{ + struct tls_rec *rec; + + rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); + if (!rec) + return false; + + return READ_ONCE(rec->tx_ready); +} + struct sk_buff * tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, struct sk_buff *skb); diff --git a/include/net/udp.h b/include/net/udp.h index 8482a990b0bb..9e82cb391dea 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -443,8 +443,10 @@ int udpv4_offload_init(void); void udp_init(void); +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); void udp_encap_enable(void); #if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void); #endif diff --git a/include/net/vxlan.h b/include/net/vxlan.h index b99a02ae3934..03431c148e16 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -5,7 +5,8 @@ #include <linux/if_vlan.h> #include <net/udp_tunnel.h> #include <net/dst_metadata.h> -#include <net/udp_tunnel.h> +#include <net/rtnetlink.h> +#include <net/switchdev.h> /* VXLAN protocol (RFC 7348) header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ @@ -191,6 +192,7 @@ union vxlan_addr { struct vxlan_rdst { union vxlan_addr remote_ip; __be16 remote_port; + u8 offloaded:1; __be32 remote_vni; u32 remote_ifindex; struct list_head list; @@ -371,4 +373,65 @@ static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs) return vs->sock->sk->sk_family; } +#if IS_ENABLED(CONFIG_IPV6) + +static inline bool vxlan_addr_any(const union vxlan_addr *ipa) +{ + if (ipa->sa.sa_family == AF_INET6) + return ipv6_addr_any(&ipa->sin6.sin6_addr); + else + return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY); +} + +static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa) +{ + if (ipa->sa.sa_family == AF_INET6) + return ipv6_addr_is_multicast(&ipa->sin6.sin6_addr); + else + return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr)); +} + +#else /* !IS_ENABLED(CONFIG_IPV6) */ + +static inline bool vxlan_addr_any(const union vxlan_addr *ipa) +{ + return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY); +} + +static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa) +{ + return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr)); +} + +#endif /* IS_ENABLED(CONFIG_IPV6) */ + +static inline bool netif_is_vxlan(const struct net_device *dev) +{ + return dev->rtnl_link_ops && + !strcmp(dev->rtnl_link_ops->kind, "vxlan"); +} + +struct switchdev_notifier_vxlan_fdb_info { + struct switchdev_notifier_info info; /* must be first */ + union vxlan_addr remote_ip; + __be16 remote_port; + __be32 remote_vni; + u32 remote_ifindex; + u8 eth_addr[ETH_ALEN]; + __be32 vni; + bool offloaded; +}; + +#if IS_ENABLED(CONFIG_VXLAN) +int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, + struct switchdev_notifier_vxlan_fdb_info *fdb_info); +#else +static inline int +vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, + struct switchdev_notifier_vxlan_fdb_info *fdb_info) +{ + return -ENOENT; +} +#endif + #endif diff --git a/include/net/xdp.h b/include/net/xdp.h index 76b95256c266..0f25b3675c5c 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -91,6 +91,8 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame) frame->dev_rx = NULL; } +struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); + /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) @@ -99,9 +101,8 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) int metasize; int headroom; - /* TODO: implement clone, copy, use "native" MEM_TYPE */ if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) - return NULL; + return xdp_convert_zc_to_xdp_frame(xdp); /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; @@ -135,6 +136,7 @@ void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); +void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 7161856bcf9c..13acb9803a6d 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -16,21 +16,23 @@ struct net_device; struct xsk_queue; -struct xdp_umem_props { - u64 chunk_mask; - u64 size; -}; - struct xdp_umem_page { void *addr; dma_addr_t dma; }; +struct xdp_umem_fq_reuse { + u32 nentries; + u32 length; + u64 handles[]; +}; + struct xdp_umem { struct xsk_queue *fq; struct xsk_queue *cq; struct xdp_umem_page *pages; - struct xdp_umem_props props; + u64 chunk_mask; + u64 size; u32 headroom; u32 chunk_size_nohr; struct user_struct *user; @@ -41,6 +43,7 @@ struct xdp_umem { struct page **pgs; u32 npgs; struct net_device *dev; + struct xdp_umem_fq_reuse *fq_reuse; u16 queue_id; bool zc; spinlock_t xsk_list_lock; @@ -79,6 +82,50 @@ void xsk_umem_discard_addr(struct xdp_umem *umem); void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len); void xsk_umem_consume_tx_done(struct xdp_umem *umem); +struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries); +struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem, + struct xdp_umem_fq_reuse *newq); +void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq); +struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id); + +static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) +{ + return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1)); +} + +static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) +{ + return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1)); +} + +/* Reuse-queue aware version of FILL queue helpers */ +static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) +{ + struct xdp_umem_fq_reuse *rq = umem->fq_reuse; + + if (!rq->length) + return xsk_umem_peek_addr(umem, addr); + + *addr = rq->handles[rq->length - 1]; + return addr; +} + +static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem) +{ + struct xdp_umem_fq_reuse *rq = umem->fq_reuse; + + if (!rq->length) + xsk_umem_discard_addr(umem); + else + rq->length--; +} + +static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr) +{ + struct xdp_umem_fq_reuse *rq = umem->fq_reuse; + + rq->handles[rq->length++] = addr; +} #else static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { @@ -98,6 +145,74 @@ static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) { return false; } + +static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) +{ + return NULL; +} + +static inline void xsk_umem_discard_addr(struct xdp_umem *umem) +{ +} + +static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +{ +} + +static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, + u32 *len) +{ + return false; +} + +static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) +{ +} + +static inline struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries) +{ + return NULL; +} + +static inline struct xdp_umem_fq_reuse *xsk_reuseq_swap( + struct xdp_umem *umem, + struct xdp_umem_fq_reuse *newq) +{ + return NULL; +} +static inline void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq) +{ +} + +static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, + u16 queue_id) +{ + return NULL; +} + +static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) +{ + return NULL; +} + +static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) +{ + return 0; +} + +static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) +{ + return NULL; +} + +static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem) +{ +} + +static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr) +{ +} + #endif /* CONFIG_XDP_SOCKETS */ #endif /* _LINUX_XDP_SOCK_H */ |