diff options
Diffstat (limited to 'include/net')
75 files changed, 708 insertions, 255 deletions
diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 62a407db1bf5..363dd63babe7 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -37,10 +37,14 @@ struct prefix_info { struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) __u8 onlink : 1, - autoconf : 1, - reserved : 6; + autoconf : 1, + routeraddr : 1, + preferpd : 1, + reserved : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - __u8 reserved : 6, + __u8 reserved : 4, + preferpd : 1, + routeraddr : 1, autoconf : 1, onlink : 1; #else @@ -183,10 +187,12 @@ static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) return 0; } +#define INFINITY_LIFE_TIME 0xFFFFFFFF + static inline unsigned long addrconf_timeout_fixup(u32 timeout, unsigned int unit) { - if (timeout == 0xffffffff) + if (timeout == INFINITY_LIFE_TIME) return ~0UL; /* @@ -327,7 +333,7 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) /** * __in6_dev_stats_get - get inet6_dev pointer for stats * @dev: network device - * @skb: skb for original incoming interface if neeeded + * @skb: skb for original incoming interface if needed * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 24d970f7a4fa..9e85424c8343 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -169,6 +169,9 @@ struct vsock_transport { void (*notify_buffer_size)(struct vsock_sock *, u64 *); int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val); + /* SIOCOUTQ ioctl */ + ssize_t (*unsent_bytes)(struct vsock_sock *vsk); + /* Shutdown. */ int (*shutdown)(struct vsock_sock *, int); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e372a88e8c3f..bab1e3d7452a 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -206,14 +206,17 @@ enum { */ HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, - /* When this quirk is set, the controller has validated that - * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are - * valid. This mechanism is necessary as many controllers have - * been seen has having trouble initiating a connectable - * advertisement despite the state combination being reported as - * supported. + /* When this quirk is set, the LE states reported through the + * HCI_LE_READ_SUPPORTED_STATES are invalid/broken. + * + * This mechanism is necessary as many controllers have been seen has + * having trouble initiating a connectable advertisement despite the + * state combination being reported as supported. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. */ - HCI_QUIRK_VALID_LE_STATES, + HCI_QUIRK_BROKEN_LE_STATES, /* When this quirk is set, then erroneous data reporting * is ignored. This is mainly due to the fact that the HCI @@ -2898,6 +2901,11 @@ static inline struct hci_sco_hdr *hci_sco_hdr(const struct sk_buff *skb) return (struct hci_sco_hdr *) skb->data; } +static inline struct hci_iso_hdr *hci_iso_hdr(const struct sk_buff *skb) +{ + return (struct hci_iso_hdr *)skb->data; +} + /* Command opcode pack/unpack */ #define hci_opcode_pack(ogf, ocf) ((__u16) ((ocf & 0x03ff)|(ogf << 10))) #define hci_opcode_ogf(op) (op >> 10) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 31020891fc68..88265d37aa72 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -186,7 +186,6 @@ struct blocked_key { struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; - u8 link_type; u8 type; u8 val[16]; }; @@ -196,7 +195,6 @@ struct smp_ltk { struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; - u8 link_type; u8 authenticated; u8 type; u8 enc_size; @@ -211,7 +209,6 @@ struct smp_irk { bdaddr_t rpa; bdaddr_t bdaddr; u8 addr_type; - u8 link_type; u8 val[16]; }; @@ -219,8 +216,6 @@ struct link_key { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; - u8 bdaddr_type; - u8 link_type; u8 type; u8 val[HCI_LINK_KEY_SIZE]; u8 pin_len; @@ -825,7 +820,7 @@ extern struct mutex hci_cb_list_lock; } while (0) #define hci_dev_le_state_simultaneous(hdev) \ - (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \ + (!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \ (hdev->le_states[4] & 0x08) && /* Central */ \ (hdev->le_states[4] & 0x40) && /* Peripheral */ \ (hdev->le_states[3] & 0x10)) /* Simultaneous */ @@ -2262,8 +2257,8 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, bool mgmt_connected); void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); -void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, - u8 addr_type, u8 status); +void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn, + u8 status); void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure); void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status); diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 75e052909b5f..f3052cb252ef 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -73,6 +73,10 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); +int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +int hci_cmd_sync_run_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); struct hci_cmd_sync_work_entry * hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 5cfdc813491a..313d0b972e06 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -968,10 +968,6 @@ void l2cap_chan_list(struct l2cap_conn *conn, l2cap_chan_func_t func, void *data); void l2cap_chan_del(struct l2cap_chan *chan, int err); void l2cap_send_conn_req(struct l2cap_chan *chan); -void l2cap_move_start(struct l2cap_chan *chan); -void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan, - u8 status); -void __l2cap_physical_cfm(struct l2cap_chan *chan, int result); struct l2cap_conn *l2cap_conn_get(struct l2cap_conn *conn); void l2cap_conn_put(struct l2cap_conn *conn); diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 9ce5ac2bfbad..2053cd8e788a 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -231,7 +231,10 @@ typedef struct port { mux_states_t sm_mux_state; /* state machine mux state */ u16 sm_mux_timer_counter; /* state machine mux timer counter */ tx_states_t sm_tx_state; /* state machine tx state */ - u16 sm_tx_timer_counter; /* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */ + u16 sm_tx_timer_counter; /* state machine tx timer counter + * (always on - enter to transmit + * state 3 time per second) + */ u16 sm_churn_actor_timer_counter; u16 sm_churn_partner_timer_counter; u32 churn_actor_count; diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index 9dc082b2d543..e5945427f38d 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -53,7 +53,7 @@ struct slave; struct tlb_client_info { - struct slave *tx_slave; /* A pointer to slave used for transmiting + struct slave *tx_slave; /* A pointer to slave used for transmitting * packets to a Client that the Hash function * gave this entry index. */ diff --git a/include/net/bonding.h b/include/net/bonding.h index b61fb1aa3a56..8bb5f016969f 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -260,7 +260,7 @@ struct bonding { #ifdef CONFIG_XFRM_OFFLOAD struct list_head ipsec_list; /* protecting ipsec_list */ - spinlock_t ipsec_lock; + struct mutex ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ struct bpf_prog *xdp_prog; }; diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 9b09acac538e..f03040baaefd 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -68,7 +68,7 @@ static inline bool sk_can_busy_loop(struct sock *sk) static inline unsigned long busy_loop_current_time(void) { #ifdef CONFIG_NET_RX_BUSY_POLL - return (unsigned long)(local_clock() >> 10); + return (unsigned long)(ktime_get_ns() >> 10); #else return 0; #endif @@ -131,7 +131,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb, #endif } -/* used in the protocol hanlder to propagate the napi_id to the socket */ +/* used in the protocol handler to propagate the napi_id to the socket */ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h index 0f45d875905f..053e7c6a6a66 100644 --- a/include/net/caif/caif_layer.h +++ b/include/net/caif/caif_layer.h @@ -20,7 +20,7 @@ struct caif_payload_info; * @assert: expression to evaluate. * * This function will print a error message and a do WARN_ON if the - * assertion failes. Normally this will do a stack up at the current location. + * assertion fails. Normally this will do a stack up at the current location. */ #define caif_assert(assert) \ do { \ @@ -116,7 +116,7 @@ enum caif_direction { * @dn: Pointer down to the layer below. * @node: List node used when layer participate in a list. * @receive: Packet receive function. - * @transmit: Packet transmit funciton. + * @transmit: Packet transmit function. * @ctrlcmd: Used for control signalling upwards in the stack. * @modemcmd: Used for control signaling downwards in the stack. * @id: The identity of this layer diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h index 44d914a50369..acf664227d96 100644 --- a/include/net/caif/cfpkt.h +++ b/include/net/caif/cfpkt.h @@ -18,7 +18,7 @@ struct cfpkt *cfpkt_create(u16 len); /* * Destroy a CAIF Packet. - * pkt Packet to be destoyed. + * pkt Packet to be destroyed. */ void cfpkt_destroy(struct cfpkt *pkt); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 192d72c8b465..69ec1eb41a09 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4837,9 +4837,9 @@ struct cfg80211_ops { int (*start_radar_detection)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef, - u32 cac_time_ms); + u32 cac_time_ms, int link_id); void (*end_cac)(struct wiphy *wiphy, - struct net_device *dev); + struct net_device *dev, unsigned int link_id); int (*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_update_ft_ies_params *ftie); int (*crit_proto_start)(struct wiphy *wiphy, @@ -6194,9 +6194,6 @@ enum ieee80211_ap_reg_power { * @address: The address for this device, valid only if @netdev is %NULL * @is_running: true if this is a non-netdev device that has been started, e.g. * the P2P Device. - * @cac_started: true if DFS channel availability check has been started - * @cac_start_time: timestamp (jiffies) when the dfs state was entered. - * @cac_time_ms: CAC time in ms * @ps: powersave mode is enabled * @ps_timeout: dynamic powersave timeout * @ap_unexpected_nlportid: (private) netlink port ID of application @@ -6220,6 +6217,11 @@ enum ieee80211_ap_reg_power { * unprotected beacon report * @links: array of %IEEE80211_MLD_MAX_NUM_LINKS elements containing @addr * @ap and @client for each link + * @links.cac_started: true if DFS channel availability check has been + * started + * @links.cac_start_time: timestamp (jiffies) when the dfs state was + * entered. + * @links.cac_time_ms: CAC time in ms * @valid_links: bitmap describing what elements of @links are valid */ struct wireless_dev { @@ -6261,11 +6263,6 @@ struct wireless_dev { u32 owner_nlportid; bool nl_owner_dead; - /* FIXME: need to rework radar detection for MLO */ - bool cac_started; - unsigned long cac_start_time; - unsigned int cac_time_ms; - #ifdef CONFIG_CFG80211_WEXT /* wext data */ struct { @@ -6332,6 +6329,10 @@ struct wireless_dev { struct cfg80211_internal_bss *current_bss; } client; }; + + bool cac_started; + unsigned long cac_start_time; + unsigned int cac_time_ms; } links[IEEE80211_MLD_MAX_NUM_LINKS]; u16 valid_links; }; @@ -8740,6 +8741,7 @@ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, * @chandef: chandef for the current channel * @event: type of event * @gfp: context flags + * @link_id: valid link_id for MLO operation or 0 otherwise. * * This function is called when a Channel availability check (CAC) is finished * or aborted. This must be called to notify the completion of a CAC process, @@ -8747,7 +8749,8 @@ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, */ void cfg80211_cac_event(struct net_device *netdev, const struct cfg80211_chan_def *chandef, - enum nl80211_radar_event event, gfp_t gfp); + enum nl80211_radar_event event, gfp_t gfp, + unsigned int link_id); /** * cfg80211_background_cac_abort - Channel Availability Check offchan abort event diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 9707ab54fdd5..4748680e8c88 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -155,8 +155,8 @@ enum skb_drop_reason { /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ SKB_DROP_REASON_SOCKET_RCVBUFF, /** - * @SKB_DROP_REASON_PROTO_MEM: proto memory limition, such as udp packet - * drop out of udp_memory_allocated. + * @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as + * udp packet drop out of udp_memory_allocated. */ SKB_DROP_REASON_PROTO_MEM, /** @@ -217,7 +217,7 @@ enum skb_drop_reason { */ SKB_DROP_REASON_TCP_ZEROWINDOW, /** - * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already + * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data received is already * received before (spurious retrans may happened), see * LINUX_MIB_DELAYEDACKLOST */ diff --git a/include/net/dsa.h b/include/net/dsa.h index b06f97ae3da1..d7a6c2930277 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -403,14 +403,18 @@ struct dsa_switch { */ u32 configure_vlan_while_not_filtering:1; - /* If the switch driver always programs the CPU port as egress tagged - * despite the VLAN configuration indicating otherwise, then setting - * @untag_bridge_pvid will force the DSA receive path to pop the - * bridge's default_pvid VLAN tagged frames to offer a consistent - * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge - * device. + /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. + * DEPRECATED: Do NOT set this field in new drivers. Instead look at + * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; + /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. + * Useful if the switch cannot preserve the VLAN tag as seen on the + * wire for user port ingress, and chooses to send all frames as + * VLAN-tagged to the CPU, including those which were originally + * untagged. + */ + u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. diff --git a/include/net/dst.h b/include/net/dst.h index 0aa331bd2fdb..0f303cc60252 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -341,7 +341,7 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; /* - * Clear hash so that we can recalulate the hash for the + * Clear hash so that we can recalculate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h index b4a55d2d5e71..1961699598e2 100644 --- a/include/net/dst_cache.h +++ b/include/net/dst_cache.h @@ -102,7 +102,7 @@ int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp); * @dst_cache: the cache * * No synchronization is enforced: it must be called only when the cache - * is unsed. + * is unused. */ void dst_cache_destroy(struct dst_cache *dst_cache); diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 4160731dcb6e..84c15402931c 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -163,8 +163,11 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) if (!new_md) return ERR_PTR(-ENOMEM); - memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, - sizeof(struct ip_tunnel_info) + md_size); + unsafe_memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, + sizeof(struct ip_tunnel_info) + md_size, + /* metadata_dst_alloc() reserves room (md_size bytes) for + * options right after the ip_tunnel_info struct. + */); #ifdef CONFIG_DST_CACHE /* Unclone the dst cache if there is one */ if (new_md->u.tun_info.dst_cache.cache) { diff --git a/include/net/erspan.h b/include/net/erspan.h index 6cb4cbd6a48f..c6209e7b6c96 100644 --- a/include/net/erspan.h +++ b/include/net/erspan.h @@ -89,7 +89,7 @@ enum erspan_encap_type { ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ ERSPAN_ENCAP_8021Q = 0x2, /* originally 802.1Q encapsulated */ - ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ + ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag preserved in frame */ }; #define ERSPAN_V1_MDSIZE 4 @@ -192,7 +192,7 @@ static inline void erspan_build_header(struct sk_buff *skb, enc_type = ERSPAN_ENCAP_NOVLAN; /* If mirrored packet has vlan tag, extract tci and - * perserve vlan header in the mirrored frame. + * preserve vlan header in the mirrored frame. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); diff --git a/include/net/hwbm.h b/include/net/hwbm.h index aa495decec35..bdbe91c609ff 100644 --- a/include/net/hwbm.h +++ b/include/net/hwbm.h @@ -11,9 +11,9 @@ struct hwbm_pool { int frag_size; /* Number of buffers currently used by this pool */ int buf_num; - /* constructor called during alocation */ + /* constructor called during allocation */ int (*construct)(struct hwbm_pool *bm_pool, void *buf); - /* protect acces to the buffer counter*/ + /* protect access to the buffer counter*/ struct mutex buf_lock; /* private data */ void *priv; diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 533a7337865a..74dd90ff5f12 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -40,7 +40,7 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash, * * The sockhash lock must be held as a reader here. */ -struct sock *__inet6_lookup_established(struct net *net, +struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, @@ -56,7 +56,7 @@ inet6_ehashfn_t inet6_ehashfn; INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); -struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, @@ -64,7 +64,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, unsigned short hnum, inet6_ehashfn_t *ehashfn); -struct sock *inet6_lookup_listener(struct net *net, +struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -73,7 +73,7 @@ struct sock *inet6_lookup_listener(struct net *net, const unsigned short hnum, const int dif, const int sdif); -struct sock *inet6_lookup_run_sk_lookup(struct net *net, +struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -82,7 +82,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn); -static inline struct sock *__inet6_lookup(struct net *net, +static inline struct sock *__inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -167,7 +167,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, iif, sdif, refcounted); } -struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, +struct sock *inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, @@ -175,7 +175,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, int inet6_hash(struct sock *sk); -static inline bool inet6_match(struct net *net, const struct sock *sk, +static inline bool inet6_match(const struct net *net, const struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, const __portpair ports, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 7f1b38458743..5eea47f135a4 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -304,7 +304,7 @@ int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); -struct sock *__inet_lookup_listener(struct net *net, +struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, @@ -351,7 +351,7 @@ static inline struct sock *inet_lookup_listener(struct net *net, ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -static inline bool inet_match(struct net *net, const struct sock *sk, +static inline bool inet_match(const struct net *net, const struct sock *sk, const __addrpair cookie, const __portpair ports, int dif, int sdif) { @@ -368,7 +368,7 @@ static inline bool inet_match(struct net *net, const struct sock *sk, /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM */ -struct sock *__inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, @@ -382,13 +382,13 @@ inet_ehashfn_t inet_ehashfn; INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); -struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, inet_ehashfn_t *ehashfn); -struct sock *inet_lookup_run_sk_lookup(struct net *net, +struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index f9ddd47dc4f8..394c3b66065e 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -150,7 +150,8 @@ static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, return bound_dev_if == dif || bound_dev_if == sdif; } -static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if, +static inline bool inet_sk_bound_dev_eq(const struct net *net, + int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index f88b68269012..beb533a0e880 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -58,7 +58,7 @@ struct inet_timewait_sock { #define tw_dr __tw_common.skc_tw_dr __u32 tw_mark; - volatile unsigned char tw_substate; + unsigned char tw_substate; unsigned char tw_rcv_wscale; /* Socket demultiplex comparisons on incoming packets. */ diff --git a/include/net/ip.h b/include/net/ip.h index c5606cadb1a5..d92d3bc3ec0e 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -33,6 +33,7 @@ #include <net/flow_dissector.h> #include <net/netns/hash.h> #include <net/lwtunnel.h> +#include <net/inet_dscp.h> #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ #define IPV4_MIN_MTU 68 /* RFC 791 */ @@ -258,7 +259,9 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet, static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet) { - return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(READ_ONCE(inet->tos)); + u8 dsfield = ipc->tos != -1 ? ipc->tos : READ_ONCE(inet->tos); + + return dsfield & INET_DSCP_MASK; } /* datagram.c */ @@ -794,9 +797,8 @@ static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0); } -bool icmp_global_allow(void); -extern int sysctl_icmp_msgs_per_sec; -extern int sysctl_icmp_msgs_burst; +bool icmp_global_allow(struct net *net); +void icmp_global_consume(struct net *net); #ifdef CONFIG_PROC_FS int ip_misc_proc_init(void); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 72af2f223e59..967e4dc555fa 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -22,6 +22,8 @@ #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/refcount.h> +#include <linux/ip.h> +#include <linux/in_route.h> struct fib_config { u8 fc_dst_len; @@ -434,6 +436,11 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net, #endif /* CONFIG_IP_MULTIPLE_TABLES */ +static inline bool fib_dscp_masked_match(dscp_t dscp, const struct flowi4 *fl4) +{ + return dscp == inet_dsfield_to_dscp(RT_TOS(fl4->flowi4_tos)); +} + /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 1db2417b8ff5..6194fbb564c6 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -573,7 +573,7 @@ static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, return 0; } -/* Propogate ECN bits out */ +/* Propagate ECN bits out */ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, const struct sk_buff *skb) { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 88a8e554f7a1..248bfb26e2af 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -851,7 +851,7 @@ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int * we should *never* get to this point since that * would mean the addrs are equal * - * However, we do get to it 8) And exacly, when + * However, we do get to it 8) And exactly, when * addresses are equal 8) * * ip route add 1111::/128 via ... @@ -973,7 +973,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); @@ -1365,4 +1365,16 @@ static inline void ip6_sock_set_recvpktinfo(struct sock *sk) release_sock(sk); } +#define IPV6_ADDR_WORDS 4 + +static inline void ipv6_addr_cpu_to_be32(__be32 *dst, const u32 *src) +{ + cpu_to_be32_array(dst, src, IPV6_ADDR_WORDS); +} + +static inline void ipv6_addr_be32_to_cpu(u32 *dst, const __be32 *src) +{ + be32_to_cpu_array(dst, src, IPV6_ADDR_WORDS); +} + #endif /* _NET_IPV6_H */ diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 11cefd50704d..8a3465c8c2c5 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -82,7 +82,7 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly; struct ipv6_bpf_stub { int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags); - struct sock *(*udp6_lib_lookup)(struct net *net, + struct sock *(*udp6_lib_lookup)(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 4d114e6d6d23..dd9e93c12260 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -15,7 +15,7 @@ * To explore any of the IUCV functions, one must first register their * program using iucv_register(). Once your program has successfully * completed a register, it can exploit the other functions. - * For furthur reference on all IUCV functionality, refer to the + * For further reference on all IUCV functionality, refer to the * CP Programming Services book, also available on the web thru * www.vm.ibm.com/pubs, manual # SC24-6084 * diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index b2cf243ebe44..7af1082ea9a0 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -23,7 +23,7 @@ * to handle wireless statistics. * * The initial APIs served us well and has proven a reasonably good design. - * However, there is a few shortcommings : + * However, there are a few shortcomings : * o No events, everything is a request to the driver. * o Large ioctl function in driver with gigantic switch statement * (i.e. spaghetti code). @@ -38,13 +38,13 @@ * ------------------------------- * The new driver API is just a bunch of standard functions (handlers), * each handling a specific Wireless Extension. The driver just export - * the list of handler it supports, and those will be called apropriately. + * the list of handler it supports, and those will be called appropriately. * * I tried to keep the main advantage of the previous API (simplicity, * efficiency and light weight), and also I provide a good dose of backward * compatibility (most structures are the same, driver can use both API * simultaneously, ...). - * Hopefully, I've also addressed the shortcomming of the initial API. + * Hopefully, I've also addressed the shortcoming of the initial API. * * The advantage of the new API are : * o Handling of Extensions in driver broken in small contained functions @@ -84,7 +84,7 @@ /* ---------------------- THE IMPLEMENTATION ---------------------- */ /* - * Some of the choice I've made are pretty controversials. Defining an + * Some of the choice I've made are pretty controversial. Defining an * API is very much weighting compromises. This goes into some of the * details and the thinking behind the implementation. * @@ -140,7 +140,7 @@ * example to distinguish setting max rate and basic rate), I would * break the prototype. Using iwreq_data is more flexible. * 3) Also, the above form is not generic (see above). - * 4) I don't expect driver developper using the wrong field of the + * 4) I don't expect driver developer using the wrong field of the * union (Doh !), so static typechecking doesn't add much value. * 5) Lastly, you can skip the union by doing : * static int mydriver_ioctl_setrate(struct net_device *dev, @@ -459,7 +459,7 @@ int iw_handler_get_thrspy(struct net_device *dev, struct iw_request_info *info, void wireless_spy_update(struct net_device *dev, unsigned char *address, struct iw_quality *wstats); -/************************* INLINE FUNTIONS *************************/ +/************************* INLINE FUNCTIONS *************************/ /* * Function that are so simple that it's more efficient inlining them */ diff --git a/include/net/kcm.h b/include/net/kcm.h index 90279e5e09a5..441e993be634 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -70,6 +70,7 @@ struct kcm_sock { struct work_struct tx_work; struct list_head wait_psock_list; struct sk_buff *seq_skb; + struct mutex tx_mutex; u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ diff --git a/include/net/lib80211.h b/include/net/lib80211.h index 8b47d3a51cf8..fd0f15d87d80 100644 --- a/include/net/lib80211.h +++ b/include/net/lib80211.h @@ -92,7 +92,7 @@ struct lib80211_crypto_ops { struct lib80211_crypt_data { struct list_head list; /* delayed deletion list */ - struct lib80211_crypto_ops *ops; + const struct lib80211_crypto_ops *ops; void *priv; atomic_t refcnt; }; @@ -113,9 +113,9 @@ struct lib80211_crypt_info { int lib80211_crypt_info_init(struct lib80211_crypt_info *info, char *name, spinlock_t *lock); void lib80211_crypt_info_free(struct lib80211_crypt_info *info); -int lib80211_register_crypto_ops(struct lib80211_crypto_ops *ops); -int lib80211_unregister_crypto_ops(struct lib80211_crypto_ops *ops); -struct lib80211_crypto_ops *lib80211_get_crypto_ops(const char *name); +int lib80211_register_crypto_ops(const struct lib80211_crypto_ops *ops); +int lib80211_unregister_crypto_ops(const struct lib80211_crypto_ops *ops); +const struct lib80211_crypto_ops *lib80211_get_crypto_ops(const char *name); void lib80211_crypt_delayed_deinit(struct lib80211_crypt_info *info, struct lib80211_crypt_data **crypt); diff --git a/include/net/libeth/tx.h b/include/net/libeth/tx.h new file mode 100644 index 000000000000..35614f9523f6 --- /dev/null +++ b/include/net/libeth/tx.h @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBETH_TX_H +#define __LIBETH_TX_H + +#include <linux/skbuff.h> + +#include <net/libeth/types.h> + +/* Tx buffer completion */ + +/** + * enum libeth_sqe_type - type of &libeth_sqe to act on Tx completion + * @LIBETH_SQE_EMPTY: unused/empty, no action required + * @LIBETH_SQE_CTX: context descriptor with empty SQE, no action required + * @LIBETH_SQE_SLAB: kmalloc-allocated buffer, unmap and kfree() + * @LIBETH_SQE_FRAG: mapped skb frag, only unmap DMA + * @LIBETH_SQE_SKB: &sk_buff, unmap and napi_consume_skb(), update stats + */ +enum libeth_sqe_type { + LIBETH_SQE_EMPTY = 0U, + LIBETH_SQE_CTX, + LIBETH_SQE_SLAB, + LIBETH_SQE_FRAG, + LIBETH_SQE_SKB, +}; + +/** + * struct libeth_sqe - represents a Send Queue Element / Tx buffer + * @type: type of the buffer, see the enum above + * @rs_idx: index of the last buffer from the batch this one was sent in + * @raw: slab buffer to free via kfree() + * @skb: &sk_buff to consume + * @dma: DMA address to unmap + * @len: length of the mapped region to unmap + * @nr_frags: number of frags in the frame this buffer belongs to + * @packets: number of physical packets sent for this frame + * @bytes: number of physical bytes sent for this frame + * @priv: driver-private scratchpad + */ +struct libeth_sqe { + enum libeth_sqe_type type:32; + u32 rs_idx; + + union { + void *raw; + struct sk_buff *skb; + }; + + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + + u32 nr_frags; + u32 packets; + u32 bytes; + + unsigned long priv; +} __aligned_largest; + +/** + * LIBETH_SQE_CHECK_PRIV - check the driver's private SQE data + * @p: type or name of the object the driver wants to fit into &libeth_sqe + * + * Make sure the driver's private data fits into libeth_sqe::priv. To be used + * right after its declaration. + */ +#define LIBETH_SQE_CHECK_PRIV(p) \ + static_assert(sizeof(p) <= sizeof_field(struct libeth_sqe, priv)) + +/** + * struct libeth_cq_pp - completion queue poll params + * @dev: &device to perform DMA unmapping + * @ss: onstack NAPI stats to fill + * @napi: whether it's called from the NAPI context + * + * libeth uses this structure to access objects needed for performing full + * Tx complete operation without passing lots of arguments and change the + * prototypes each time a new one is added. + */ +struct libeth_cq_pp { + struct device *dev; + struct libeth_sq_napi_stats *ss; + + bool napi; +}; + +/** + * libeth_tx_complete - perform Tx completion for one SQE + * @sqe: SQE to complete + * @cp: poll params + * + * Do Tx complete for all the types of buffers, incl. freeing, unmapping, + * updating the stats etc. + */ +static inline void libeth_tx_complete(struct libeth_sqe *sqe, + const struct libeth_cq_pp *cp) +{ + switch (sqe->type) { + case LIBETH_SQE_EMPTY: + return; + case LIBETH_SQE_SKB: + case LIBETH_SQE_FRAG: + case LIBETH_SQE_SLAB: + dma_unmap_page(cp->dev, dma_unmap_addr(sqe, dma), + dma_unmap_len(sqe, len), DMA_TO_DEVICE); + break; + default: + break; + } + + switch (sqe->type) { + case LIBETH_SQE_SKB: + cp->ss->packets += sqe->packets; + cp->ss->bytes += sqe->bytes; + + napi_consume_skb(sqe->skb, cp->napi); + break; + case LIBETH_SQE_SLAB: + kfree(sqe->raw); + break; + default: + break; + } + + sqe->type = LIBETH_SQE_EMPTY; +} + +#endif /* __LIBETH_TX_H */ diff --git a/include/net/libeth/types.h b/include/net/libeth/types.h new file mode 100644 index 000000000000..603825e45133 --- /dev/null +++ b/include/net/libeth/types.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBETH_TYPES_H +#define __LIBETH_TYPES_H + +#include <linux/types.h> + +/** + * struct libeth_sq_napi_stats - "hot" counters to update in Tx completion loop + * @packets: completed frames counter + * @bytes: sum of bytes of completed frames above + * @raw: alias to access all the fields as an array + */ +struct libeth_sq_napi_stats { + union { + struct { + u32 packets; + u32 bytes; + }; + DECLARE_FLEX_ARRAY(u32, raw); + }; +}; + +#endif /* __LIBETH_TYPES_H */ diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 1d55ba7c45be..86681f29bda7 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -254,7 +254,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, } /** - * llc_pdu_decode_sa - extracs source address (MAC) of input frame + * llc_pdu_decode_sa - extracts, source address (MAC) of input frame * @skb: input skb that source address must be extracted from it. * @sa: pointer to source address (6 byte array). * diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 0a04eaf5343c..954dff901b69 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -994,8 +994,9 @@ enum mac80211_tx_info_flags { * of their QoS TID or other priority field values. * @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally * for sequence number assignment - * @IEEE80211_TX_CTRL_SCAN_TX: Indicates that this frame is transmitted - * due to scanning, not in normal operation on the interface. + * @IEEE80211_TX_CTRL_DONT_USE_RATE_MASK: Don't use rate mask for this frame + * which is transmitted due to scanning or offchannel TX, not in normal + * operation on the interface. * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this * frame should be transmitted on the specific link. This really is * only relevant for frames that do not have data present, and is @@ -1016,7 +1017,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX = BIT(9), - IEEE80211_TX_CTRL_SCAN_TX = BIT(10), + IEEE80211_TX_CTRL_DONT_USE_RATE_MASK = BIT(10), IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000, }; @@ -2487,7 +2488,7 @@ struct ieee80211_link_sta { * @spp_amsdu: indicates whether the STA uses SPP A-MSDU or not. */ struct ieee80211_sta { - u8 addr[ETH_ALEN]; + u8 addr[ETH_ALEN] __aligned(2); u16 aid; u16 max_rx_aggregation_subframes; bool wme; @@ -3181,6 +3182,19 @@ ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw, void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); /** + * ieee80211_purge_tx_queue - purge TX skb queue + * @hw: the hardware + * @skbs: the skbs + * + * Free a set of transmit skbs. Use this function when device is going to stop + * but some transmit skbs without TX status are still queued. + * This function does not take the list lock and the caller must hold the + * relevant locks to use it. + */ +void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, + struct sk_buff_head *skbs); + +/** * DOC: Hardware crypto acceleration * * mac80211 is capable of taking advantage of many hardware @@ -6242,6 +6256,24 @@ void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw, void (*iterator)(void *data, struct ieee80211_sta *sta), void *data); + +/** + * ieee80211_iterate_stations_mtx - iterate stations + * + * This function iterates over all stations associated with a given + * hardware that are currently uploaded to the driver and calls the callback + * function for them. This version can only be used while holding the wiphy + * mutex. + * + * @hw: the hardware struct of which the interfaces should be iterated over + * @iterator: the iterator function to call + * @data: first argument of the iterator function + */ +void ieee80211_iterate_stations_mtx(struct ieee80211_hw *hw, + void (*iterator)(void *data, + struct ieee80211_sta *sta), + void *data); + /** * ieee80211_queue_work - add work onto the mac80211 workqueue * @@ -6716,8 +6748,11 @@ void ieee80211_cqm_beacon_loss_notify(struct ieee80211_vif *vif, gfp_t gfp); * ieee80211_radar_detected - inform that a radar was detected * * @hw: pointer as obtained from ieee80211_alloc_hw() + * @chanctx_conf: Channel context on which radar is detected. Mandatory to + * pass a valid pointer during MLO. For non-MLO %NULL can be passed */ -void ieee80211_radar_detected(struct ieee80211_hw *hw); +void ieee80211_radar_detected(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *chanctx_conf); /** * ieee80211_chswitch_done - Complete channel switch process diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 4a3a9de9da73..1b5488fa2ff0 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -140,7 +140,7 @@ enum ieee802154_hw_flags { * * xmit_sync: * Handler that 802.15.4 module calls for each transmitted frame. - * skb cntains the buffer starting from the IEEE 802.15.4 header. + * skb contains the buffer starting from the IEEE 802.15.4 header. * The low-level driver should send the frame based on available * configuration. This is called by a workqueue and useful for * synchronous 802.15.4 drivers. @@ -152,7 +152,7 @@ enum ieee802154_hw_flags { * * xmit_async: * Handler that 802.15.4 module calls for each transmitted frame. - * skb cntains the buffer starting from the IEEE 802.15.4 header. + * skb contains the buffer starting from the IEEE 802.15.4 header. * The low-level driver should send the frame based on available * configuration. * This function should return zero or negative errno. diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 7caa334f4888..f2a5200d8a0f 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -38,9 +38,21 @@ enum TRI_STATE { #define COMP_ENTRY_SIZE 64 -#define RX_BUFFERS_PER_QUEUE 512 +/* This Max value for RX buffers is derived from __alloc_page()'s max page + * allocation calculation. It allows maximum 2^(MAX_ORDER -1) pages. RX buffer + * size beyond this value gets rejected by __alloc_page() call. + */ +#define MAX_RX_BUFFERS_PER_QUEUE 8192 +#define DEF_RX_BUFFERS_PER_QUEUE 512 +#define MIN_RX_BUFFERS_PER_QUEUE 128 -#define MAX_SEND_BUFFERS_PER_QUEUE 256 +/* This max value for TX buffers is derived as the maximum allocatable + * pages supported on host per guest through testing. TX buffer size beyond + * this value is rejected by the hardware. + */ +#define MAX_TX_BUFFERS_PER_QUEUE 16384 +#define DEF_TX_BUFFERS_PER_QUEUE 256 +#define MIN_TX_BUFFERS_PER_QUEUE 128 #define EQ_SIZE (8 * MANA_PAGE_SIZE) @@ -98,6 +110,8 @@ struct mana_txq { atomic_t pending_sends; + bool napi_initialized; + struct mana_stats_tx stats; }; @@ -286,7 +300,7 @@ struct mana_recv_buf_oob { void *buf_va; bool from_pool; /* allocated from a page pool */ - /* SGL of the buffer going to be sent has part of the work request. */ + /* SGL of the buffer going to be sent as part of the work request. */ u32 num_sge; struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES]; @@ -438,6 +452,9 @@ struct mana_port_context { unsigned int max_queues; unsigned int num_queues; + unsigned int rx_queue_size; + unsigned int tx_queue_size; + mana_handle_t port_handle; mana_handle_t pf_filter_handle; @@ -473,6 +490,8 @@ struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); void mana_query_gf_stats(struct mana_port_context *apc); +int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues); +void mana_pre_dealloc_rxbufs(struct mana_port_context *apc); extern const struct ethtool_ops mana_ethtool_ops; diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 0bc4ab03f487..814b5f2e3ed5 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -223,6 +223,8 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb) return htonl(0u); } + +void mptcp_active_detect_blackhole(struct sock *sk, bool expired); #else static inline void mptcp_init(void) @@ -307,6 +309,8 @@ static inline struct request_sock *mptcp_subflow_reqsk_alloc(const struct reques } static inline __be32 mptcp_reset_option(const struct sk_buff *skb) { return htonl(0u); } + +static inline void mptcp_active_detect_blackhole(struct sock *sk, bool expired) { } #endif /* CONFIG_MPTCP */ #if IS_ENABLED(CONFIG_MPTCP_IPV6) diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 7a533d5b1d59..3c88d5bc5eed 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -147,11 +147,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * - * int (*is_useropt)(u8 nd_opt_type): - * This function is called when IPv6 decide RA userspace options. if - * this function returns 1 then the option given by nd_opt_type will - * be handled as userspace option additional to the IPv6 options. - * * int (*parse_options)(const struct net_device *dev, * struct nd_opt_hdr *nd_opt, * struct ndisc_options *ndopts): @@ -200,7 +195,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, * addresses. E.g. 802.15.4 6LoWPAN. */ struct ndisc_ops { - int (*is_useropt)(u8 nd_opt_type); int (*parse_options)(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts); @@ -224,15 +218,6 @@ struct ndisc_ops { }; #if IS_ENABLED(CONFIG_IPV6) -static inline int ndisc_ops_is_useropt(const struct net_device *dev, - u8 nd_opt_type) -{ - if (dev->ndisc_ops && dev->ndisc_ops->is_useropt) - return dev->ndisc_ops->is_useropt(nd_opt_type); - else - return 0; -} - static inline int ndisc_ops_parse_options(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 20c34bd7a077..e67b483cc8bb 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -451,8 +451,8 @@ struct pernet_operations { /* Following method is called with RTNL held. */ void (*exit_batch_rtnl)(struct list_head *net_exit_list, struct list_head *dev_kill_list); - unsigned int *id; - size_t size; + unsigned int * const id; + const size_t size; }; /* diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index aa1716fb0e53..596836abf7bf 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -6,6 +6,7 @@ #include <linux/netdevice.h> #include <linux/sysfs.h> #include <net/xdp.h> +#include <net/page_pool/types.h> /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { @@ -25,6 +26,7 @@ struct netdev_rx_queue { * Readers and writers must hold RTNL */ struct napi_struct *napi; + struct pp_memory_provider_params mp_params; } ____cacheline_aligned_in_smp; /* @@ -43,7 +45,6 @@ __netif_get_rx_queue(struct net_device *dev, unsigned int rxq) return dev->_rx + rxq; } -#ifdef CONFIG_SYSFS static inline unsigned int get_netdev_rx_queue_index(struct netdev_rx_queue *queue) { @@ -53,5 +54,7 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue) BUG_ON(index >= dev->num_rx_queues); return index; } -#endif + +int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq); + #endif diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index e227d997fc71..1b58b5b91ff6 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -15,10 +15,8 @@ struct nf_conncount_list { unsigned int count; /* length of list */ }; -struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, - unsigned int keylen); -void nf_conncount_destroy(struct net *net, unsigned int family, - struct nf_conncount_data *data); +struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen); +void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data); unsigned int nf_conncount_count(struct net *net, struct nf_conncount_data *data, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 1bfdd16890fa..49708e7e1339 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -209,6 +209,7 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src, * @family: protocol family * @level: depth of the chains * @report: notify via unicast netlink message + * @reg_inited: bitmap of initialised registers */ struct nft_ctx { struct net *net; @@ -221,6 +222,7 @@ struct nft_ctx { u8 family; u8 level; bool report; + DECLARE_BITMAP(reg_inited, NFT_REG32_NUM); }; enum nft_data_desc_flags { @@ -254,7 +256,8 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); -int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len); +int nft_parse_register_load(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *sreg, u32 len); int nft_parse_register_store(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *dreg, const struct nft_data *data, @@ -311,6 +314,7 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) /** * enum nft_iter_type - nftables set iterator type * + * @NFT_ITER_UNSPEC: unspecified, to catch errors * @NFT_ITER_READ: read-only iteration over set elements * @NFT_ITER_UPDATE: iteration under mutex to update set element state */ @@ -683,9 +687,8 @@ void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); * @NFT_SET_EXT_DATA: mapping data * @NFT_SET_EXT_FLAGS: element flags * @NFT_SET_EXT_TIMEOUT: element timeout - * @NFT_SET_EXT_EXPIRATION: element expiration time * @NFT_SET_EXT_USERDATA: user data associated with the element - * @NFT_SET_EXT_EXPRESSIONS: expressions assiciated with the element + * @NFT_SET_EXT_EXPRESSIONS: expressions associated with the element * @NFT_SET_EXT_OBJREF: stateful object reference associated with element * @NFT_SET_EXT_NUM: number of extension types */ @@ -695,7 +698,6 @@ enum nft_set_extensions { NFT_SET_EXT_DATA, NFT_SET_EXT_FLAGS, NFT_SET_EXT_TIMEOUT, - NFT_SET_EXT_EXPIRATION, NFT_SET_EXT_USERDATA, NFT_SET_EXT_EXPRESSIONS, NFT_SET_EXT_OBJREF, @@ -807,14 +809,14 @@ static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext) return nft_set_ext(ext, NFT_SET_EXT_FLAGS); } -static inline u64 *nft_set_ext_timeout(const struct nft_set_ext *ext) -{ - return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT); -} +struct nft_timeout { + u64 timeout; + u64 expiration; +}; -static inline u64 *nft_set_ext_expiration(const struct nft_set_ext *ext) +static inline struct nft_timeout *nft_set_ext_timeout(const struct nft_set_ext *ext) { - return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION); + return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT); } static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext) @@ -830,8 +832,11 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext, u64 tstamp) { - return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) && - time_after_eq64(tstamp, *nft_set_ext_expiration(ext)); + if (!nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) || + READ_ONCE(nft_set_ext_timeout(ext)->timeout) == 0) + return false; + + return time_after_eq64(tstamp, READ_ONCE(nft_set_ext_timeout(ext)->expiration)); } static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) @@ -959,8 +964,7 @@ struct nft_expr_ops { const struct nft_expr *expr, bool reset); int (*validate)(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data); + const struct nft_expr *expr); bool (*reduce)(struct nft_regs_track *track, const struct nft_expr *expr); bool (*gc)(struct net *net, @@ -1674,6 +1678,7 @@ struct nft_trans_rule { struct nft_trans_set { struct nft_trans_binding nft_trans_binding; + struct list_head list_trans_newset; struct nft_set *set; u32 set_id; u32 gc_int; @@ -1744,10 +1749,18 @@ struct nft_trans_table { #define nft_trans_table_update(trans) \ nft_trans_container_table(trans)->update +enum nft_trans_elem_flags { + NFT_TRANS_UPD_TIMEOUT = (1 << 0), + NFT_TRANS_UPD_EXPIRATION = (1 << 1), +}; + struct nft_trans_elem { struct nft_trans nft_trans; struct nft_set *set; struct nft_elem_priv *elem_priv; + u64 timeout; + u64 expiration; + u8 update_flags; bool bound; }; @@ -1757,6 +1770,12 @@ struct nft_trans_elem { nft_trans_container_elem(trans)->set #define nft_trans_elem_priv(trans) \ nft_trans_container_elem(trans)->elem_priv +#define nft_trans_elem_update_flags(trans) \ + nft_trans_container_elem(trans)->update_flags +#define nft_trans_elem_timeout(trans) \ + nft_trans_container_elem(trans)->timeout +#define nft_trans_elem_expiration(trans) \ + nft_trans_container_elem(trans)->expiration #define nft_trans_elem_set_bound(trans) \ nft_trans_container_elem(trans)->bound @@ -1875,6 +1894,7 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re struct nftables_pernet { struct list_head tables; struct list_head commit_list; + struct list_head commit_set_list; struct list_head binding_list; struct list_head module_list; struct list_head notify_list; diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 60a7d0ce3080..fcf967286e37 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -19,7 +19,7 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt) static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) { struct iphdr *iph, _iph; - u32 len, thoff; + u32 len, thoff, skb_len; iph = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), sizeof(*iph), &_iph); @@ -30,8 +30,10 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) return -1; len = iph_totlen(pkt->skb, iph); - thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4); - if (pkt->skb->len < len) + thoff = iph->ihl * 4; + skb_len = pkt->skb->len - skb_network_offset(pkt->skb); + + if (skb_len < len) return -1; else if (len < thoff) return -1; @@ -40,7 +42,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = iph->protocol; - pkt->thoff = thoff; + pkt->thoff = skb_network_offset(pkt->skb) + thoff; pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; return 0; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 467d59b9e533..a0633eeaec97 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -31,8 +31,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) struct ipv6hdr *ip6h, _ip6h; unsigned int thoff = 0; unsigned short frag_off; + u32 pkt_len, skb_len; int protohdr; - u32 pkt_len; ip6h = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), sizeof(*ip6h), &_ip6h); @@ -43,7 +43,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) return -1; pkt_len = ntohs(ip6h->payload_len); - if (pkt_len + sizeof(*ip6h) > pkt->skb->len) + skb_len = pkt->skb->len - skb_network_offset(pkt->skb); + if (pkt_len + sizeof(*ip6h) > skb_len) return -1; protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h index faa108b1ba67..5adf6fda11e8 100644 --- a/include/net/netfilter/nf_tproxy.h +++ b/include/net/netfilter/nf_tproxy.h @@ -36,6 +36,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr); /** * nf_tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections + * @net: The network namespace. * @skb: The skb being processed. * @laddr: IPv4 address to redirect to or zero. * @lport: TCP port to redirect to or zero. diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index 167640b843ef..38cae7113de4 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -21,9 +21,7 @@ nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in) int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset); int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); -int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nft_data **data); - +int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr); void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index ba1238f12a48..d602263590fe 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -41,8 +41,7 @@ void nft_meta_set_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr); int nft_meta_set_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data); + const struct nft_expr *expr); bool nft_meta_get_reduce(struct nft_regs_track *track, const struct nft_expr *expr); diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h index 6d9ba62efd75..19060212988a 100644 --- a/include/net/netfilter/nft_reject.h +++ b/include/net/netfilter/nft_reject.h @@ -15,8 +15,7 @@ struct nft_reject { extern const struct nla_policy nft_reject_policy[]; int nft_reject_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data); + const struct nft_expr *expr); int nft_reject_init(const struct nft_ctx *ctx, const struct nft_expr *expr, diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 654bc777d2a7..529160f76cac 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -30,7 +30,7 @@ struct calipso_doi; /* * NetLabel - A management interface for maintaining network packet label - * mapping tables for explicit packet labling protocols. + * mapping tables for explicit packet labeling protocols. * * Network protocols such as CIPSO and RIPSO require a label translation layer * to convert the label on the packet into something meaningful on the host diff --git a/include/net/netlink.h b/include/net/netlink.h index e78ce008e07c..db6af207287c 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -827,7 +827,7 @@ nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. @@ -849,7 +849,7 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in liberal mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ @@ -872,7 +872,7 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in strict mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ @@ -887,7 +887,7 @@ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, /** * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct @@ -933,7 +933,7 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ @@ -1034,7 +1034,7 @@ static inline struct sk_buff *nlmsg_new_large(size_t payload) * @skb: socket buffer the message is stored in * @nlh: netlink message header * - * Corrects the netlink message header to include the appeneded + * Corrects the netlink message header to include the appended * attributes. Only necessary if attributes have been added to * the message. */ @@ -1954,7 +1954,7 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) * @start: container attribute * * Corrects the container attribute header to include the all - * appeneded attributes. + * appended attributes. * * Returns the total data length of the skb. */ @@ -1987,7 +1987,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) * * Validates all attributes in the nested attribute stream against the * specified policy. Attributes with a type exceeding maxtype will be - * ignored. See documenation of struct nla_policy for more details. + * ignored. See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ diff --git a/include/net/netmem.h b/include/net/netmem.h index 46cc9b89ac79..8a6e20be4b9d 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -8,6 +8,54 @@ #ifndef _NET_NETMEM_H #define _NET_NETMEM_H +#include <linux/mm.h> +#include <net/net_debug.h> + +/* net_iov */ + +DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers); + +/* We overload the LSB of the struct page pointer to indicate whether it's + * a page or net_iov. + */ +#define NET_IOV 0x01UL + +struct net_iov { + unsigned long __unused_padding; + unsigned long pp_magic; + struct page_pool *pp; + struct dmabuf_genpool_chunk_owner *owner; + unsigned long dma_addr; + atomic_long_t pp_ref_count; +}; + +/* These fields in struct page are used by the page_pool and net stack: + * + * struct { + * unsigned long pp_magic; + * struct page_pool *pp; + * unsigned long _pp_mapping_pad; + * unsigned long dma_addr; + * atomic_long_t pp_ref_count; + * }; + * + * We mirror the page_pool fields here so the page_pool can access these fields + * without worrying whether the underlying fields belong to a page or net_iov. + * + * The non-net stack fields of struct page are private to the mm stack and must + * never be mirrored to net_iov. + */ +#define NET_IOV_ASSERT_OFFSET(pg, iov) \ + static_assert(offsetof(struct page, pg) == \ + offsetof(struct net_iov, iov)) +NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic); +NET_IOV_ASSERT_OFFSET(pp, pp); +NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr); +NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count); +#undef NET_IOV_ASSERT_OFFSET + +/* netmem */ + /** * typedef netmem_ref - a nonexistent type marking a reference to generic * network memory. @@ -19,20 +67,37 @@ */ typedef unsigned long __bitwise netmem_ref; +static inline bool netmem_is_net_iov(const netmem_ref netmem) +{ + return (__force unsigned long)netmem & NET_IOV; +} + /* This conversion fails (returns NULL) if the netmem_ref is not struct page * backed. - * - * Currently struct page is the only possible netmem, and this helper never - * fails. */ static inline struct page *netmem_to_page(netmem_ref netmem) { + if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) + return NULL; + return (__force struct page *)netmem; } -/* Converting from page to netmem is always safe, because a page can always be - * a netmem. - */ +static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return (struct net_iov *)((__force unsigned long)netmem & + ~NET_IOV); + + DEBUG_NET_WARN_ON_ONCE(true); + return NULL; +} + +static inline netmem_ref net_iov_to_netmem(struct net_iov *niov) +{ + return (__force netmem_ref)((unsigned long)niov | NET_IOV); +} + static inline netmem_ref page_to_netmem(struct page *page) { return (__force netmem_ref)page; @@ -40,17 +105,70 @@ static inline netmem_ref page_to_netmem(struct page *page) static inline int netmem_ref_count(netmem_ref netmem) { + /* The non-pp refcount of net_iov is always 1. On net_iov, we only + * support pp refcounting which uses the pp_ref_count field. + */ + if (netmem_is_net_iov(netmem)) + return 1; + return page_ref_count(netmem_to_page(netmem)); } -static inline unsigned long netmem_to_pfn(netmem_ref netmem) +static inline unsigned long netmem_pfn_trace(netmem_ref netmem) { + if (netmem_is_net_iov(netmem)) + return 0; + return page_to_pfn(netmem_to_page(netmem)); } +static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem) +{ + return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); +} + +static inline struct page_pool *netmem_get_pp(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->pp; +} + +static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem) +{ + return &__netmem_clear_lsb(netmem)->pp_ref_count; +} + +static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid) +{ + /* NUMA node preference only makes sense if we're allocating + * system memory. Memory providers (which give us net_iovs) + * choose for us. + */ + if (netmem_is_net_iov(netmem)) + return true; + + return page_to_nid(netmem_to_page(netmem)) == pref_nid; +} + static inline netmem_ref netmem_compound_head(netmem_ref netmem) { + /* niov are never compounded */ + if (netmem_is_net_iov(netmem)) + return netmem; + return page_to_netmem(compound_head(netmem_to_page(netmem))); } +static inline void *netmem_address(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return NULL; + + return page_address(netmem_to_page(netmem)); +} + +static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->dma_addr; +} + #endif /* _NET_NETMEM_H */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 5fcd61ada622..276f622f3516 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -122,7 +122,10 @@ struct netns_ipv4 { u8 sysctl_icmp_errors_use_inbound_ifaddr; int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; - + int sysctl_icmp_msgs_per_sec; + int sysctl_icmp_msgs_burst; + atomic_t icmp_global_credit; + u32 icmp_global_stamp; u32 ip_rt_min_pmtu; int ip_rt_mtu_expires; int ip_rt_min_advmss; diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 7eff3d981b89..d25cd7a9c5ff 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -125,14 +125,14 @@ struct netns_sctp { int pf_expose; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_sndbuf * 1 - do sctp accounting, each asoc may use sk_sndbuf bytes */ int sndbuf_policy; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_rcvbuf * 1 - do sctp accounting, each asoc may use sk_rcvbuf bytes */ diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 68463aebcc05..d9fb44e8b321 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -105,7 +105,7 @@ struct nh_grp_entry_stats { struct nh_grp_entry { struct nexthop *nh; struct nh_grp_entry_stats __percpu *stats; - u8 weight; + u16 weight; union { struct { @@ -192,7 +192,7 @@ struct nh_notifier_single_info { }; struct nh_notifier_grp_entry_info { - u8 weight; + u16 weight; struct nh_notifier_single_info nh; }; diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index e82f55f543bb..dc36519d16aa 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -332,7 +332,7 @@ struct nci_core_init_rsp_1 { __le32 nfcc_features; __u8 num_supported_rf_interfaces; __u8 supported_rf_interfaces[]; /* variable size array */ - /* continuted in nci_core_init_rsp_2 */ + /* continued in nci_core_init_rsp_2 */ } __packed; struct nci_core_init_rsp_2 { diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 3d07abacf08b..3a3781838c67 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -80,7 +80,7 @@ struct nfc_ops { #define NFC_ATR_REQ_GT_OFFSET 14 /** - * struct nfc_target - NFC target descriptiom + * struct nfc_target - NFC target description * * @sens_res: 2 bytes describing the target SENS_RES response, if the target * is a type A one. The %sens_res most significant byte must be byte 2 @@ -230,10 +230,10 @@ static inline void nfc_set_parent_dev(struct nfc_dev *nfc_dev, } /** - * nfc_set_drvdata - set driver specifc data + * nfc_set_drvdata - set driver specific data * * @dev: The nfc device - * @data: Pointer to driver specifc data + * @data: Pointer to driver specific data */ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) { @@ -241,7 +241,7 @@ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) } /** - * nfc_get_drvdata - get driver specifc data + * nfc_get_drvdata - get driver specific data * * @dev: The nfc device */ diff --git a/include/net/nl802154.h b/include/net/nl802154.h index 4c752f799957..a994dea74596 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -192,7 +192,7 @@ enum nl802154_iftype { * @NL802154_CAP_ATTR_TX_POWERS: a nested attribute for * nl802154_wpan_phy_tx_power * @NL802154_CAP_ATTR_MIN_CCA_ED_LEVEL: minimum value for cca_ed_level - * @NL802154_CAP_ATTR_MAX_CCA_ED_LEVEL: maxmimum value for cca_ed_level + * @NL802154_CAP_ATTR_MAX_CCA_ED_LEVEL: maximum value for cca_ed_level * @NL802154_CAP_ATTR_CCA_MODES: nl802154_cca_modes flags * @NL802154_CAP_ATTR_CCA_OPTS: nl802154_cca_opts flags * @NL802154_CAP_ATTR_MIN_MINBE: minimum of minbe value diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 2b43a893c619..793e6fd78bc5 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -216,7 +216,7 @@ page_pool_get_dma_dir(const struct page_pool *pool) static inline void page_pool_fragment_netmem(netmem_ref netmem, long nr) { - atomic_long_set(&netmem_to_page(netmem)->pp_ref_count, nr); + atomic_long_set(netmem_get_pp_ref_count_ref(netmem), nr); } /** @@ -244,7 +244,7 @@ static inline void page_pool_fragment_page(struct page *page, long nr) static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) { - struct page *page = netmem_to_page(netmem); + atomic_long_t *pp_ref_count = netmem_get_pp_ref_count_ref(netmem); long ret; /* If nr == pp_ref_count then we have cleared all remaining @@ -261,19 +261,19 @@ static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) * initially, and only overwrite it when the page is partitioned into * more than one piece. */ - if (atomic_long_read(&page->pp_ref_count) == nr) { + if (atomic_long_read(pp_ref_count) == nr) { /* As we have ensured nr is always one for constant case using * the BUILD_BUG_ON(), only need to handle the non-constant case * here for pp_ref_count draining, which is a rare case. */ BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1); if (!__builtin_constant_p(nr)) - atomic_long_set(&page->pp_ref_count, 1); + atomic_long_set(pp_ref_count, 1); return 0; } - ret = atomic_long_sub_return(nr, &page->pp_ref_count); + ret = atomic_long_sub_return(nr, pp_ref_count); WARN_ON(ret < 0); /* We are the last user here too, reset pp_ref_count back to 1 to @@ -282,7 +282,7 @@ static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) * page_pool_unref_page() currently. */ if (unlikely(!ret)) - atomic_long_set(&page->pp_ref_count, 1); + atomic_long_set(pp_ref_count, 1); return ret; } @@ -401,9 +401,7 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va, static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem) { - struct page *page = netmem_to_page(netmem); - - dma_addr_t ret = page->dma_addr; + dma_addr_t ret = netmem_get_dma_addr(netmem); if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) ret <<= PAGE_SHIFT; @@ -423,24 +421,6 @@ static inline dma_addr_t page_pool_get_dma_addr(const struct page *page) return page_pool_get_dma_addr_netmem(page_to_netmem((struct page *)page)); } -static inline bool page_pool_set_dma_addr_netmem(netmem_ref netmem, - dma_addr_t addr) -{ - struct page *page = netmem_to_page(netmem); - - if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) { - page->dma_addr = addr >> PAGE_SHIFT; - - /* We assume page alignment to shave off bottom bits, - * if this "compression" doesn't work we need to drop. - */ - return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT; - } - - page->dma_addr = addr; - return false; -} - /** * page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW * @pool: &page_pool the @page belongs to @@ -463,11 +443,6 @@ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool, page_pool_get_dma_dir(pool)); } -static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) -{ - return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr); -} - static inline bool page_pool_put(struct page_pool *pool) { return refcount_dec_and_test(&pool->user_cnt); diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 50569fed7868..c022c410abe3 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -20,8 +20,18 @@ * device driver responsibility */ #define PP_FLAG_SYSTEM_POOL BIT(2) /* Global system page_pool */ + +/* Allow unreadable (net_iov backed) netmem in this page_pool. Drivers setting + * this must be able to support unreadable netmem, where netmem_address() would + * return NULL. This flag should not be set for header page_pools. + * + * If the driver sets PP_FLAG_ALLOW_UNREADABLE_NETMEM, it should also set + * page_pool_params.slow.queue_idx. + */ +#define PP_FLAG_ALLOW_UNREADABLE_NETMEM BIT(3) + #define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV | \ - PP_FLAG_SYSTEM_POOL) + PP_FLAG_SYSTEM_POOL | PP_FLAG_ALLOW_UNREADABLE_NETMEM) /* * Fast allocation side cache array/stack @@ -57,7 +67,9 @@ struct pp_alloc_cache { * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV * @slow: params with slowpath access only (initialization and Netlink) * @netdev: netdev this pool will serve (leave as NULL if none or multiple) - * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL + * @queue_idx: queue idx this page_pool is being created for. + * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL, + * PP_FLAG_ALLOW_UNREADABLE_NETMEM. */ struct page_pool_params { struct_group_tagged(page_pool_params_fast, fast, @@ -72,6 +84,7 @@ struct page_pool_params { ); struct_group_tagged(page_pool_params_slow, slow, struct net_device *netdev; + unsigned int queue_idx; unsigned int flags; /* private: used by test code only */ void (*init_callback)(netmem_ref netmem, void *arg); @@ -139,6 +152,10 @@ struct page_pool_stats { */ #define PAGE_POOL_FRAG_GROUP_ALIGN (4 * sizeof(long)) +struct pp_memory_provider_params { + void *mp_priv; +}; + struct page_pool { struct page_pool_params_fast p; @@ -197,6 +214,8 @@ struct page_pool { */ struct ptr_ring ring; + void *mp_priv; + #ifdef CONFIG_PAGE_POOL_STATS /* recycle stats are per-cpu to avoid locking */ struct page_pool_recycle_stats __percpu *recycle_stats; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 41297bd38dff..4880b3a7aced 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -491,7 +491,7 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, struct tcf_pkt_info *); /** - * tcf_em_tree_match - evaulate an ematch tree + * tcf_em_tree_match - evaluate an ematch tree * * @skb: socket buffer of the packet in question * @tree: ematch tree to be used for evaluation diff --git a/include/net/red.h b/include/net/red.h index 802287d52c9e..159a09359fc0 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -40,7 +40,7 @@ max_P should be small (not 1), usually 0.01..0.02 is good value. max_P is chosen as a number, so that max_P/(th_max-th_min) - is a negative power of two in order arithmetics to contain + is a negative power of two in order arithmetic to contain only shifts. @@ -159,7 +159,7 @@ static inline u32 red_maxp(u8 Plog) static inline void red_set_vars(struct red_vars *v) { /* Reset average queue length, the value is strictly bound - * to the parameters below, reseting hurts a bit but leaving + * to the parameters below, resetting hurts a bit but leaving * it might result in an unreasonable qavg for a while. --TGR */ v->qavg = 0; @@ -340,7 +340,7 @@ static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p { /* * NOTE: v->qavg is fixed point number with point at Wlog. - * The formula below is equvalent to floating point + * The formula below is equivalent to floating point * version: * * qavg = qavg*(1-W) + backlog*W; @@ -375,7 +375,7 @@ static inline int red_mark_probability(const struct red_parms *p, OK. qR is random number in the interval (0..1/max_P)*(qth_max-qth_min) i.e. 0..(2^Plog). If we used floating point - arithmetics, it would be: (2^Plog)*rnd_num, + arithmetic, it would be: (2^Plog)*rnd_num, where rnd_num is less 1. Taking into account, that qavg have fixed diff --git a/include/net/regulatory.h b/include/net/regulatory.h index a103f4c8cf75..6633627f6e76 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -121,7 +121,7 @@ struct regulatory_request { * @REGULATORY_DISABLE_BEACON_HINTS: enable this if your driver needs to * ensure that passive scan flags and beaconing flags may not be lifted by * cfg80211 due to regulatory beacon hints. For more information on beacon - * hints read the documenation for regulatory_hint_found_beacon() + * hints read the documentation for regulatory_hint_found_beacon() * @REGULATORY_COUNTRY_IE_FOLLOW_POWER: for devices that have a preference * that even though they may have programmed their own custom power * setting prior to wiphy registration, they want to ensure their channel diff --git a/include/net/route.h b/include/net/route.h index 93833cfe9c96..1789f1e6640b 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -27,6 +27,7 @@ #include <net/ip_fib.h> #include <net/arp.h> #include <net/ndisc.h> +#include <net/inet_dscp.h> #include <linux/in_route.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> @@ -45,7 +46,7 @@ static inline __u8 ip_sock_rt_scope(const struct sock *sk) static inline __u8 ip_sock_rt_tos(const struct sock *sk) { - return RT_TOS(READ_ONCE(inet_sk(sk)->tos)); + return READ_ONCE(inet_sk(sk)->tos) & INET_DSCP_MASK; } struct ip_tunnel_info; @@ -265,8 +266,6 @@ static inline void ip_rt_put(struct rtable *rt) dst_release(&rt->dst); } -#define IPTOS_RT_MASK (IPTOS_TOS_MASK & ~3) - extern const __u8 ip_tos2prio[16]; static inline char rt_tos2priority(u8 tos) diff --git a/include/net/rstreason.h b/include/net/rstreason.h index 2575c85d7f7a..69cb2e52b7da 100644 --- a/include/net/rstreason.h +++ b/include/net/rstreason.h @@ -17,6 +17,12 @@ FN(TCP_ABORT_ON_DATA) \ FN(TCP_TIMEWAIT_SOCKET) \ FN(INVALID_SYN) \ + FN(TCP_ABORT_ON_CLOSE) \ + FN(TCP_ABORT_ON_LINGER) \ + FN(TCP_ABORT_ON_MEMORY) \ + FN(TCP_STATE) \ + FN(TCP_KEEPALIVE_TIMEOUT) \ + FN(TCP_DISCONNECT_WITH_DATA) \ FN(MPTCP_RST_EUNSPEC) \ FN(MPTCP_RST_EMPTCP) \ FN(MPTCP_RST_ERESOURCE) \ @@ -84,6 +90,39 @@ enum sk_rst_reason { * an error, send a reset" */ SK_RST_REASON_INVALID_SYN, + /** + * @SK_RST_REASON_TCP_ABORT_ON_CLOSE: abort on close + * corresponding to LINUX_MIB_TCPABORTONCLOSE + */ + SK_RST_REASON_TCP_ABORT_ON_CLOSE, + /** + * @SK_RST_REASON_TCP_ABORT_ON_LINGER: abort on linger + * corresponding to LINUX_MIB_TCPABORTONLINGER + */ + SK_RST_REASON_TCP_ABORT_ON_LINGER, + /** + * @SK_RST_REASON_TCP_ABORT_ON_MEMORY: abort on memory + * corresponding to LINUX_MIB_TCPABORTONMEMORY + */ + SK_RST_REASON_TCP_ABORT_ON_MEMORY, + /** + * @SK_RST_REASON_TCP_STATE: abort on tcp state + * Please see RFC 9293 for all possible reset conditions + */ + SK_RST_REASON_TCP_STATE, + /** + * @SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT: time to timeout + * When we have already run out of all the chances, which means + * keepalive timeout, we have to reset the connection + */ + SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT, + /** + * @SK_RST_REASON_TCP_DISCONNECT_WITH_DATA: disconnect when write + * queue is not empty + * It means user has written data into the write queue when doing + * disconnecting, so we have to send an RST. + */ + SK_RST_REASON_TCP_DISCONNECT_WITH_DATA, /* Copy from include/uapi/linux/mptcp.h. * These reset fields will not be changed since they adhere to diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a2310fa995f6..84e6b9fd5610 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -28,7 +28,7 @@ #define __net_sctp_h__ /* Header Strategy. - * Start getting some control over the header file depencies: + * Start getting some control over the header file dependencies: * includes * constants * structs diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index f24a1bbcb3ef..31248cfdfb23 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -521,7 +521,7 @@ struct sctp_datamsg { refcount_t refcnt; /* When is this message no longer interesting to the peer? */ unsigned long expires_at; - /* Did the messenge fail to send? */ + /* Did the message fail to send? */ int send_error; u8 send_failed:1, can_delay:1, /* should this message be Nagle delayed */ @@ -792,7 +792,7 @@ struct sctp_transport { */ hb_sent:1, - /* Is the Path MTU update pending on this tranport */ + /* Is the Path MTU update pending on this transport */ pmtu_pending:1, dst_pending_confirm:1, /* need to confirm neighbour */ @@ -1223,7 +1223,7 @@ enum sctp_endpoint_type { }; /* - * A common base class to bridge the implmentation view of a + * A common base class to bridge the implementation view of a * socket (usually listening) endpoint versus an association's * local endpoint. * This common structure is useful for several purposes: @@ -1353,7 +1353,7 @@ struct sctp_endpoint { struct rcu_head rcu; }; -/* Recover the outter endpoint structure. */ +/* Recover the outer endpoint structure. */ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base) { struct sctp_endpoint *ep; @@ -1906,7 +1906,7 @@ struct sctp_association { __u32 rwnd_over; /* Keeps treack of rwnd pressure. This happens when we have - * a window, but not recevie buffer (i.e small packets). This one + * a window, but not receive buffer (i.e small packets). This one * is releases slowly (1 PMTU at a time ). */ __u32 rwnd_press; @@ -1994,7 +1994,7 @@ struct sctp_association { /* ADDIP Section 5.2 Upon reception of an ASCONF Chunk. * - * This is needed to implement itmes E1 - E4 of the updated + * This is needed to implement items E1 - E4 of the updated * spec. Here is the justification: * * Since the peer may bundle multiple ASCONF chunks toward us, @@ -2005,7 +2005,7 @@ struct sctp_association { /* These ASCONF chunks are waiting to be sent. * - * These chunaks can't be pushed to outqueue until receiving + * These chunks can't be pushed to outqueue until receiving * ASCONF_ACK for the previous ASCONF indicated by * addip_last_asconf, so as to guarantee that only one ASCONF * is in flight at any time. @@ -2059,13 +2059,13 @@ struct sctp_association { struct sctp_transport *new_transport; /* SCTP AUTH: list of the endpoint shared keys. These - * keys are provided out of band by the user applicaton + * keys are provided out of band by the user application * and can't change during the lifetime of the association */ struct list_head endpoint_shared_keys; /* SCTP AUTH: - * The current generated assocaition shared key (secret) + * The current generated association shared key (secret) */ struct sctp_auth_bytes *asoc_shared_key; struct sctp_shared_key *shkey; @@ -2121,7 +2121,7 @@ enum { SCTP_ASSOC_EYECATCHER = 0xa550c123, }; -/* Recover the outter association structure. */ +/* Recover the outer association structure. */ static inline struct sctp_association *sctp_assoc(struct sctp_ep_common *base) { struct sctp_association *asoc; diff --git a/include/net/sock.h b/include/net/sock.h index cce23ac4d514..c58ca8dd561b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -337,6 +337,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_user_frags: xarray of pages the user is holding a reference on. */ struct sock { /* @@ -542,6 +543,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct xarray sk_user_frags; }; struct sock_bh_locked { @@ -1624,7 +1626,7 @@ bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); * lock_sock_fast - fast version of lock_sock * @sk: socket * - * This version should be used for very small section, where process wont block + * This version should be used for very small section, where process won't block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled @@ -2546,7 +2548,7 @@ struct sock_skb_cb { /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its - * alignement guarantee. + * alignment guarantee. */ #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 6ec140b0a61b..6e4faf3ee76f 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -26,7 +26,7 @@ struct sock_reuseport { unsigned int bind_inany:1; unsigned int has_conns:1; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ - struct sock *socks[]; /* array of sock pointers */ + struct sock *socks[] __counted_by(max_socks); }; extern int reuseport_alloc(struct sock *sk, bool bind_inany); diff --git a/include/net/tcp.h b/include/net/tcp.h index 2aac11e7e1cc..f77f812bfbe7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1069,7 +1069,8 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to, /* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */ return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from) && - skb_pure_zcopy_same(to, from)); + skb_pure_zcopy_same(to, from) && + skb_frags_readable(to) == skb_frags_readable(from)); } static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to, diff --git a/include/net/udp.h b/include/net/udp.h index c4e05b14b648..61222545ab1c 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -79,7 +79,8 @@ struct udp_table { extern struct udp_table udp_table; void udp_table_init(struct udp_table *, const char *); static inline struct udp_hslot *udp_hashslot(struct udp_table *table, - struct net *net, unsigned int num) + const struct net *net, + unsigned int num) { return &table->hash[udp_hashfn(net, num, table->mask)]; } @@ -231,7 +232,7 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, } /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only upper 16 bits are relevant in the * computation for 16 bit port value. */ @@ -245,7 +246,7 @@ static inline int udp_rqueue_get(struct sock *sk) return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } -static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, +static inline bool udp_sk_bound_dev_eq(const struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) @@ -296,18 +297,19 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); -struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); -struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, + __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); -struct sock *udp6_lib_lookup(struct net *net, +struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif); -struct sock *__udp6_lib_lookup(struct net *net, +struct sock *__udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, diff --git a/include/net/x25.h b/include/net/x25.h index 597eb53c471e..5e833cfc864e 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -81,7 +81,7 @@ enum { #define X25_DEFAULT_WINDOW_SIZE 2 /* Default Window Size */ #define X25_DEFAULT_PACKET_SIZE X25_PS128 /* Default Packet Size */ -#define X25_DEFAULT_THROUGHPUT 0x0A /* Deafult Throughput */ +#define X25_DEFAULT_THROUGHPUT 0x0A /* Default Throughput */ #define X25_DEFAULT_REVERSE 0x00 /* Default Reverse Charging */ #define X25_SMODULUS 8 diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 54cef89f6c1e..b6bfdc6416c7 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -67,27 +67,27 @@ - instance of a transformer, struct xfrm_state (=SA) - template to clone xfrm_state, struct xfrm_tmpl - SPD is plain linear list of xfrm_policy rules, ordered by priority. + SPD is organized as hash table (for policies that meet minimum address prefix + length setting, net->xfrm.policy_hthresh). Other policies are stored in + lists, sorted into rbtree ordered by destination and source address networks. + See net/xfrm/xfrm_policy.c for details. + (To be compatible with existing pfkeyv2 implementations, many rules with priority of 0x7fffffff are allowed to exist and such rules are ordered in an unpredictable way, thanks to bsd folks.) - Lookup is plain linear search until the first match with selector. - If "action" is "block", then we prohibit the flow, otherwise: if "xfrms_nr" is zero, the flow passes untransformed. Otherwise, policy entry has list of up to XFRM_MAX_DEPTH transformations, described by templates xfrm_tmpl. Each template is resolved to a complete xfrm_state (see below) and we pack bundle of transformations - to a dst_entry returned to requestor. + to a dst_entry returned to requester. dst -. xfrm .-> xfrm_state #1 |---. child .-> dst -. xfrm .-> xfrm_state #2 |---. child .-> dst -. xfrm .-> xfrm_state #3 |---. child .-> NULL - Bundles are cached at xrfm_policy struct (field ->bundles). - Resolution of xrfm_tmpl ----------------------- @@ -526,6 +526,36 @@ struct xfrm_policy_queue { unsigned long timeout; }; +/** + * struct xfrm_policy - xfrm policy + * @xp_net: network namespace the policy lives in + * @bydst: hlist node for SPD hash table or rbtree list + * @byidx: hlist node for index hash table + * @lock: serialize changes to policy structure members + * @refcnt: reference count, freed once it reaches 0 + * @pos: kernel internal tie-breaker to determine age of policy + * @timer: timer + * @genid: generation, used to invalidate old policies + * @priority: priority, set by userspace + * @index: policy index (autogenerated) + * @if_id: virtual xfrm interface id + * @mark: packet mark + * @selector: selector + * @lft: liftime configuration data + * @curlft: liftime state + * @walk: list head on pernet policy list + * @polq: queue to hold packets while aqcuire operaion in progress + * @bydst_reinsert: policy tree node needs to be merged + * @type: XFRM_POLICY_TYPE_MAIN or _SUB + * @action: XFRM_POLICY_ALLOW or _BLOCK + * @flags: XFRM_POLICY_LOCALOK, XFRM_POLICY_ICMP + * @xfrm_nr: number of used templates in @xfrm_vec + * @family: protocol family + * @security: SELinux security label + * @xfrm_vec: array of templates to resolve state + * @rcu: rcu head, used to defer memory release + * @xdo: hardware offload state + */ struct xfrm_policy { possible_net_t xp_net; struct hlist_node bydst; @@ -555,7 +585,6 @@ struct xfrm_policy { u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; - struct hlist_node bydst_inexact_list; struct rcu_head rcu; struct xfrm_dev_offload xdo; @@ -1016,7 +1045,7 @@ void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); struct xfrm_if_parms { int link; /* ifindex of underlying L2 interface */ - u32 if_id; /* interface identifyer */ + u32 if_id; /* interface identifier */ bool collect_md; }; |