diff options
Diffstat (limited to 'include/net')
83 files changed, 1291 insertions, 511 deletions
diff --git a/include/net/9p/client.h b/include/net/9p/client.h index 838a94218b59..55c6cb54bd25 100644 --- a/include/net/9p/client.h +++ b/include/net/9p/client.h @@ -192,6 +192,7 @@ struct p9_rdma_opts { * @dfltgid: default numeric groupid to mount hierarchy as * @uid: if %V9FS_ACCESS_SINGLE, the numeric uid which mounted the hierarchy * @session_lock_timeout: retry interval for blocking locks + * @ndentry_timeout_ms: Negative dentry lookup cache retention time in ms * * This strucure holds options which are parsed and will be transferred * to the v9fs_session_info structure when mounted, and therefore largely @@ -203,6 +204,7 @@ struct p9_session_opts { unsigned short debug; unsigned int afid; unsigned int cache; + unsigned int ndentry_timeout_ms; #ifdef CONFIG_9P_FSCACHE char *cachetag; #endif diff --git a/include/net/Space.h b/include/net/Space.h deleted file mode 100644 index 6a0b6674d930..000000000000 --- a/include/net/Space.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* A unified ethernet device probe. This is the easiest way to have every - * ethernet adaptor have the name "eth[0123...]". - */ - -struct net_device *ne_probe(int unit); -struct net_device *cs89x0_probe(int unit); diff --git a/include/net/act_api.h b/include/net/act_api.h index d11b79107930..20d9e55f8564 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -45,6 +45,7 @@ struct tc_action { struct tc_cookie __rcu *user_cookie; struct tcf_chain __rcu *goto_chain; u32 tcfa_flags; + struct rcu_head tcfa_rcu; u8 hw_stats; u8 used_hw_stats; bool used_hw_stats_valid; @@ -241,7 +242,7 @@ static inline void tcf_action_update_bstats(struct tc_action *a, static inline void tcf_action_inc_drop_qstats(struct tc_action *a) { if (likely(a->cpu_qstats)) { - qstats_drop_inc(this_cpu_ptr(a->cpu_qstats)); + qstats_cpu_drop_inc(a->cpu_qstats); return; } atomic_inc(&a->tcfa_drops); @@ -250,7 +251,7 @@ static inline void tcf_action_inc_drop_qstats(struct tc_action *a) static inline void tcf_action_inc_overlimit_qstats(struct tc_action *a) { if (likely(a->cpu_qstats)) { - qstats_overlimit_inc(this_cpu_ptr(a->cpu_qstats)); + qstats_cpu_overlimit_inc(a->cpu_qstats); return; } atomic_inc(&a->tcfa_overlimits); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 9e96776945e5..8ced27a8229b 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -369,8 +369,11 @@ static inline struct inet6_dev *__in6_dev_get_rtnl_net(const struct net_device * static inline struct inet6_dev *__in6_dev_stats_get(const struct net_device *dev, const struct sk_buff *skb) { - if (netif_is_l3_master(dev)) + if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(dev_net(dev), inet6_iif(skb)); + if (!dev) + return NULL; + } return __in6_dev_get(dev); } @@ -443,6 +446,11 @@ static inline void in6_dev_hold(struct inet6_dev *idev) refcount_inc(&idev->refcnt); } +static inline bool in6_dev_hold_safe(struct inet6_dev *idev) +{ + return refcount_inc_not_zero(&idev->refcnt); +} + /* called with rcu_read_lock held */ static inline bool ip6_ignore_linkdown(const struct net_device *dev) { diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 4e40063adab4..30046a3c20f7 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -220,6 +220,7 @@ static inline bool __vsock_in_connected_table(struct vsock_sock *vsk) void vsock_add_pending(struct sock *listener, struct sock *pending); void vsock_remove_pending(struct sock *listener, struct sock *pending); void vsock_enqueue_accept(struct sock *listener, struct sock *connected); +void vsock_pending_to_accept(struct sock *listener, struct sock *pending); void vsock_insert_connected(struct vsock_sock *vsk); void vsock_remove_bound(struct vsock_sock *vsk); void vsock_remove_connected(struct vsock_sock *vsk); diff --git a/include/net/amt.h b/include/net/amt.h index c881bc8b673b..a0255491f5b0 100644 --- a/include/net/amt.h +++ b/include/net/amt.h @@ -331,7 +331,7 @@ struct amt_dev { enum amt_status status; /* Generated key */ siphash_key_t key; - struct socket __rcu *sock; + struct sock __rcu *sk; u32 max_groups; u32 max_sources; u32 hash_buckets; diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 69eed69f7f26..b624da5026f5 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated @@ -5,10 +6,6 @@ Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. @@ -398,6 +395,7 @@ void baswap(bdaddr_t *dst, const bdaddr_t *src); struct bt_sock { struct sock sk; struct list_head accept_q; + spinlock_t accept_q_lock; /* protects accept_q */ struct sock *parent; unsigned long flags; void (*skb_msg_name)(struct sk_buff *, void *, int *); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 572b1c620c5d..50f0eef71fb1 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated @@ -5,10 +6,6 @@ Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. @@ -2486,6 +2483,12 @@ struct hci_rp_le_cs_test { #define HCI_OP_LE_CS_TEST_END 0x2096 +#define HCI_OP_LE_SET_HOST_FEATURE_V2 0x2097 +struct hci_cp_le_set_host_feature_v2 { + __le16 bit_number; + __u8 bit_value; +} __packed; + /* ---- HCI Events ---- */ struct hci_ev_status { __u8 status; @@ -3410,8 +3413,9 @@ static inline struct hci_iso_hdr *hci_iso_hdr(const struct sk_buff *skb) #define hci_iso_flags_pack(pb, ts) ((pb & 0x03) | ((ts & 0x01) << 2)) /* ISO data length and flags pack/unpack */ -#define hci_iso_data_len_pack(h, f) ((__u16) ((h) | ((f) << 14))) -#define hci_iso_data_len(h) ((h) & 0x3fff) +#define hci_iso_data_len_pack(h, f) ((__u16) (((h) & 0x0fff) | \ + (((f) & 0x3) << 14))) +#define hci_iso_data_len(h) ((h) & 0x0fff) #define hci_iso_data_flags(h) ((h) >> 14) /* codec transport types */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a7bffb908c1e..e7133ff87fbf 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. @@ -5,10 +6,6 @@ Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. @@ -988,6 +985,7 @@ enum { HCI_CONN_AUTH_FAILURE, HCI_CONN_PER_ADV, HCI_CONN_BIG_CREATED, + HCI_CONN_CREATE, HCI_CONN_CREATE_CIS, HCI_CONN_CREATE_BIG_SYNC, HCI_CONN_BIG_SYNC, @@ -2432,6 +2430,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent); void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, u8 *name, u8 name_len); +u8 hci_to_mgmt_reason(u8 err); void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 reason, bool mgmt_connected); @@ -2495,7 +2494,7 @@ void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, bdaddr_t *bdaddr, u8 addr_type); int hci_abort_conn(struct hci_conn *conn, u8 reason); -u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, +void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, __u8 ltk[16], __u8 key_size); diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index bbd752494ef9..4b2a0af4ed58 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2011-2012 Intel Corporation - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. diff --git a/include/net/bluetooth/hci_sock.h b/include/net/bluetooth/hci_sock.h index 13e8cd4414a1..16f150b861be 100644 --- a/include/net/bluetooth/hci_sock.h +++ b/include/net/bluetooth/hci_sock.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 5172afee5494..ef6ce1c20a4f 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated @@ -6,10 +7,6 @@ Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. @@ -33,6 +30,7 @@ /* L2CAP defaults */ #define L2CAP_DEFAULT_MTU 672 #define L2CAP_DEFAULT_MIN_MTU 48 +#define L2CAP_SIG_MTU 48 /* BR/EDR signaling MTU */ #define L2CAP_DEFAULT_FLUSH_TO 0xFFFF #define L2CAP_EFS_DEFAULT_FLUSH_TO 0xFFFFFFFF #define L2CAP_DEFAULT_TX_WINDOW 63 @@ -619,7 +617,8 @@ struct l2cap_chan { struct l2cap_ops { char *name; - struct l2cap_chan *(*new_connection) (struct l2cap_chan *chan); + int (*new_connection)(struct l2cap_chan *chan, + struct l2cap_chan *new_chan); int (*recv) (struct l2cap_chan * chan, struct sk_buff *skb); void (*teardown) (struct l2cap_chan *chan, int err); @@ -747,6 +746,7 @@ enum { FLAG_ECRED_CONN_REQ_SENT, FLAG_PENDING_SECURITY, FLAG_HOLD_HCI_CONN, + FLAG_DEL, }; /* Lock nesting levels for L2CAP channels. We need these because lockdep @@ -883,9 +883,10 @@ static inline __u16 __next_seq(struct l2cap_chan *chan, __u16 seq) return (seq + 1) % (chan->tx_win_max + 1); } -static inline struct l2cap_chan *l2cap_chan_no_new_connection(struct l2cap_chan *chan) +static inline int l2cap_chan_no_new_connection(struct l2cap_chan *chan, + struct l2cap_chan *new_chan) { - return NULL; + return -EOPNOTSUPP; } static inline int l2cap_chan_no_recv(struct l2cap_chan *chan, struct sk_buff *skb) @@ -962,7 +963,7 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, void l2cap_chan_busy(struct l2cap_chan *chan, int busy); void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail); int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator); -void l2cap_chan_set_defaults(struct l2cap_chan *chan); +void l2cap_chan_set_defaults(struct l2cap_chan *chan, struct l2cap_chan *pchan); int l2cap_ertm_init(struct l2cap_chan *chan); void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan); void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 8234915854b6..08daed7a96d5 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2010 Nokia Corporation Copyright (C) 2011-2012 Intel Corporation - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h index c05882476900..102c278e3584 100644 --- a/include/net/bluetooth/rfcomm.h +++ b/include/net/bluetooth/rfcomm.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* RFCOMM implementation for Linux Bluetooth stack (BlueZ) Copyright (C) 2002 Maxim Krasnyansky <maxk@qualcomm.com> Copyright (C) 2002 Marcel Holtmann <marcel@holtmann.org> - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. @@ -229,6 +226,9 @@ int rfcomm_send_rpn(struct rfcomm_session *s, int cr, u8 dlci, u8 bit_rate, u8 data_bits, u8 stop_bits, u8 parity, u8 flow_ctrl_settings, u8 xon_char, u8 xoff_char, u16 param_mask); +int rfcomm_dlc_send_rpn(struct rfcomm_dlc *d, u8 bit_rate, u8 data_bits, + u8 stop_bits, u8 parity, u8 flow_ctrl_settings, + u8 xon_char, u8 xoff_char, u16 param_mask); /* ---- RFCOMM DLCs (channels) ---- */ struct rfcomm_dlc *rfcomm_dlc_alloc(gfp_t prio); diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h index f40ddb4264fc..214409527b35 100644 --- a/include/net/bluetooth/sco.h +++ b/include/net/bluetooth/sco.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. diff --git a/include/net/bond_options.h b/include/net/bond_options.h index e6eedf23aea1..52b966e92793 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -79,6 +79,7 @@ enum { BOND_OPT_COUPLED_CONTROL, BOND_OPT_BROADCAST_NEIGH, BOND_OPT_ACTOR_PORT_PRIO, + BOND_OPT_LACP_STRICT, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index edd1942dcd73..2c54a36a8477 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -129,6 +129,7 @@ struct bond_params { int peer_notif_delay; int lacp_active; int lacp_fast; + int lacp_strict; unsigned int min_links; int ad_select; char primary[IFNAMSIZ]; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9d3639ff9c28..f5abf1db7558 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -830,6 +830,8 @@ struct vif_params { * @seq_len: length of @seq. * @vlan_id: vlan_id for VLAN group key (if nonzero) * @mode: key install mode (RX_TX, NO_TX or SET_TX) + * @ltf_keyseed: LTF key seed material + * @ltf_keyseed_len: length of LTF key seed material */ struct key_params { const u8 *key; @@ -839,11 +841,18 @@ struct key_params { u16 vlan_id; u32 cipher; enum nl80211_key_mode mode; + const u8 *ltf_keyseed; + size_t ltf_keyseed_len; }; /** * struct cfg80211_chan_def - channel definition * @chan: the (control) channel + * @npca_chan: the NPCA primary channel + * Note that if DBE is in use, this channel may appear to be + * inside the primary half of the chandef. Implementations + * can use the position of this channel to understand how + * NPCA is used. * @width: channel width * @center_freq1: center frequency of first segment * @center_freq2: center frequency of second segment @@ -856,18 +865,24 @@ struct key_params { * @punctured: mask of the punctured 20 MHz subchannels, with * bits turned on being disabled (punctured); numbered * from lower to higher frequency (like in the spec) + * @npca_punctured: NPCA puncturing bitmap, like @punctured but for + * NPCA transmissions. If NPCA is used (@npca_chan is not %NULL) + * this will be a superset of the @punctured bimap. + * Note that if DBE is used, this bitmap is also shifted to be in + * accordance with the overall chandef bandwidth. * @s1g_primary_2mhz: Indicates if the control channel pointed to * by 'chan' exists as a 1MHz primary subchannel within an * S1G 2MHz primary channel. */ struct cfg80211_chan_def { struct ieee80211_channel *chan; + struct ieee80211_channel *npca_chan; enum nl80211_chan_width width; u32 center_freq1; u32 center_freq2; struct ieee80211_edmg edmg; u16 freq1_offset; - u16 punctured; + u16 punctured, npca_punctured; bool s1g_primary_2mhz; }; @@ -1014,7 +1029,9 @@ cfg80211_chandef_identical(const struct cfg80211_chan_def *chandef1, chandef1->freq1_offset == chandef2->freq1_offset && chandef1->center_freq2 == chandef2->center_freq2 && chandef1->punctured == chandef2->punctured && - chandef1->s1g_primary_2mhz == chandef2->s1g_primary_2mhz); + chandef1->s1g_primary_2mhz == chandef2->s1g_primary_2mhz && + chandef1->npca_chan == chandef2->npca_chan && + chandef1->npca_punctured == chandef2->npca_punctured); } /** @@ -1144,6 +1161,46 @@ int cfg80211_chandef_primary(const struct cfg80211_chan_def *chandef, u16 *punctured); /** + * cfg80211_chandef_npca_valid - check that NPCA information is valid + * @wiphy: the wiphy to check for, for channel pointer lookup + * @chandef: the BSS channel chandef to check against + * @npca: NPCA information, can be %NULL in which case this + * always returns %true + * + * Note that DBE must not have been configured into the chandef yet + * before checking NPCA, i.e. @chandef must represent the BSS channel. + * + * Returns: %true if the NPCA channel and puncturing bitmap are valid + * according to the chandef, %false otherwise + */ +bool cfg80211_chandef_npca_valid(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + const struct ieee80211_uhr_npca_info *npca); + +/** + * cfg80211_chandef_add_npca - parse and add NPCA information to chandef + * @wiphy: the wiphy this will be used for, for channel pointer lookup + * @chandef: the chandef to modify, must be a valid chandef without NPCA + * @npca: the NPCA information, can be %NULL + * + * Returns: 0 if the NPCA information was added and the resulting + * chandef is valid, a negative error code on errors + */ +int cfg80211_chandef_add_npca(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + const struct ieee80211_uhr_npca_info *npca); + +/** + * cfg80211_chandef_add_dbe - parse and add DBE information to chandef + * @chandef: the chandef to expand + * @dbe: the DBE information, must be size-checked if not %NULL + * + * Returns: 0 for success, a negative error code otherwise + */ +int cfg80211_chandef_add_dbe(struct cfg80211_chan_def *chandef, + const struct ieee80211_uhr_dbe_info *dbe); + +/** * nl80211_send_chandef - sends the channel definition. * @msg: the msg to send channel definition * @chandef: the channel definition to check @@ -1396,6 +1453,13 @@ struct cfg80211_rnr_elems { * @he_bss_color: BSS Color settings * @he_bss_color_valid: indicates whether bss color * attribute is present in beacon data or not. + * @ht_required: stations must support HT + * @vht_required: stations must support VHT + * @ht_oper: HT operation element (or %NULL if HT isn't enabled) + * @vht_oper: VHT operation element (or %NULL if VHT isn't enabled) + * @he_oper: HE operation IE (or %NULL if HE isn't enabled) + * @eht_oper: EHT operation IE (or %NULL if EHT isn't enabled) + * @uhr_oper: UHR operation (or %NULL if UHR isn't enabled) */ struct cfg80211_beacon_data { unsigned int link_id; @@ -1420,6 +1484,13 @@ struct cfg80211_beacon_data { size_t civicloc_len; struct cfg80211_he_bss_color he_bss_color; bool he_bss_color_valid; + + bool ht_required, vht_required; + const struct ieee80211_ht_operation *ht_oper; + const struct ieee80211_vht_operation *vht_oper; + const struct ieee80211_he_operation *he_oper; + const struct ieee80211_eht_operation *eht_oper; + const struct ieee80211_uhr_operation *uhr_oper; }; struct mac_address { @@ -1524,16 +1595,9 @@ struct cfg80211_s1g_short_beacon { * @vht_cap: VHT capabilities (or %NULL if VHT isn't enabled) * @he_cap: HE capabilities (or %NULL if HE isn't enabled) * @eht_cap: EHT capabilities (or %NULL if EHT isn't enabled) - * @eht_oper: EHT operation IE (or %NULL if EHT isn't enabled) - * @uhr_oper: UHR operation (or %NULL if UHR isn't enabled) - * @ht_required: stations must support HT - * @vht_required: stations must support VHT * @twt_responder: Enable Target Wait Time - * @he_required: stations must support HE - * @sae_h2e_required: stations must support direct H2E technique in SAE * @flags: flags, as defined in &enum nl80211_ap_settings_flags * @he_obss_pd: OBSS Packet Detection settings - * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters * @mbssid_config: AP settings for multiple bssid @@ -1562,11 +1626,7 @@ struct cfg80211_ap_settings { const struct ieee80211_ht_cap *ht_cap; const struct ieee80211_vht_cap *vht_cap; const struct ieee80211_he_cap_elem *he_cap; - const struct ieee80211_he_operation *he_oper; const struct ieee80211_eht_cap_elem *eht_cap; - const struct ieee80211_eht_operation *eht_oper; - const struct ieee80211_uhr_operation *uhr_oper; - bool ht_required, vht_required, he_required, sae_h2e_required; bool twt_responder; u32 flags; struct ieee80211_he_obss_pd he_obss_pd; @@ -4433,6 +4493,25 @@ struct cfg80211_ftm_responder_stats { * (must have either this or @rtt_avg) * @dist_variance: variance of distances measured (see also @rtt_variance) * @dist_spread: spread of distances measured (see also @rtt_spread) + * @tx_ltf_repetition_count: negotiated value of number of tx ltf repetitions + * in NDP frames + * @rx_ltf_repetition_count: negotiated value of number of rx ltf repetitions + * in NDP frames + * @max_time_between_measurements: the negotiated maximum interval (in units of + * 10 ms) by which the ISTA must complete the next measurement cycle. + * @min_time_between_measurements: the negotiated minimum interval (in units of + * 100 us) between two consecutive range measurements initiated by the + * ISTA. + * @num_tx_spatial_streams: number of Tx space-time streams used in the NDP + * frame during the measurement sounding phase. + * @num_rx_spatial_streams: number of Rx space-time streams used in the NDP + * frame during the measurement sounding phase. + * @nominal_time: negotiated nominal duration between adjacent availability + * windows in units of milliseconds (u32). + * @availability_window: negotiated availability window time used in this + * session in units of milliseconds (u8). + * @chan_width: band width used for measurement. + * @preamble: preamble used for measurement. * @num_ftmr_attempts_valid: @num_ftmr_attempts is valid * @num_ftmr_successes_valid: @num_ftmr_successes is valid * @rssi_avg_valid: @rssi_avg is valid @@ -4445,6 +4524,18 @@ struct cfg80211_ftm_responder_stats { * @dist_avg_valid: @dist_avg is valid * @dist_variance_valid: @dist_variance is valid * @dist_spread_valid: @dist_spread is valid + * @tx_ltf_repetition_count_valid: @tx_ltf_repetition_count is valid + * @rx_ltf_repetition_count_valid: @rx_ltf_repetition_count is valid + * @max_time_between_measurements_valid: @max_time_between_measurements is valid + * @min_time_between_measurements_valid: @min_time_between_measurements is valid + * @num_tx_spatial_streams_valid: @num_tx_spatial_streams is valid + * @num_rx_spatial_streams_valid: @num_rx_spatial_streams is valid + * @nominal_time_valid: @nominal_time is valid + * @availability_window_valid: @availability_window is valid + * @chan_width_valid: @chan_width is valid. + * @preamble_valid: @preamble is valid. + * @is_delayed_lmr: indicates if the reported LMR is of the current burst or the + * previous burst, flag. */ struct cfg80211_pmsr_ftm_result { const u8 *lci; @@ -4468,8 +4559,18 @@ struct cfg80211_pmsr_ftm_result { s64 dist_avg; s64 dist_variance; s64 dist_spread; + u32 tx_ltf_repetition_count; + u32 rx_ltf_repetition_count; + u32 max_time_between_measurements; + u32 min_time_between_measurements; + u8 num_tx_spatial_streams; + u8 num_rx_spatial_streams; + u32 nominal_time; + u8 availability_window; + enum nl80211_chan_width chan_width; + enum nl80211_preamble preamble; - u16 num_ftmr_attempts_valid:1, + u32 num_ftmr_attempts_valid:1, num_ftmr_successes_valid:1, rssi_avg_valid:1, rssi_spread_valid:1, @@ -4480,7 +4581,18 @@ struct cfg80211_pmsr_ftm_result { rtt_spread_valid:1, dist_avg_valid:1, dist_variance_valid:1, - dist_spread_valid:1; + dist_spread_valid:1, + tx_ltf_repetition_count_valid:1, + rx_ltf_repetition_count_valid:1, + max_time_between_measurements_valid:1, + min_time_between_measurements_valid:1, + num_tx_spatial_streams_valid:1, + num_rx_spatial_streams_valid:1, + nominal_time_valid:1, + availability_window_valid:1, + chan_width_valid:1, + preamble_valid:1, + is_delayed_lmr:1; }; /** @@ -4524,7 +4636,8 @@ struct cfg80211_pmsr_result { * @burst_duration: burst duration. If @trigger_based or @non_trigger_based is * set, this is the burst duration in milliseconds, and zero means the * device should pick an appropriate value based on @ftms_per_burst. - * @ftms_per_burst: number of FTMs per burst + * @ftms_per_burst: number of FTMs per burst. If set to 0, the firmware or + * driver can automatically select an appropriate value. * @ftmr_retries: number of retries for FTM request * @request_lci: request LCI information * @request_civicloc: request civic location information @@ -4541,6 +4654,48 @@ struct cfg80211_pmsr_result { * @bss_color: the bss color of the responder. Optional. Set to zero to * indicate the driver should set the BSS color. Only valid if * @non_trigger_based or @trigger_based is set. + * @request_type: ranging request type, one of + * &enum nl80211_peer_measurement_ftm_req_type. Defaults to + * %NL80211_PMSR_FTM_REQ_TYPE_INFRA if not specified. + * @min_time_between_measurements: minimum time between two consecutive range + * measurements in units of 100 microseconds, for non-trigger based + * ranging. Should be set as short as possible to minimize turnaround + * time, since two-way ranging with delayed LMR requires two measurements. + * Only valid if @non_trigger_based is set. + * @max_time_between_measurements: maximum time between two consecutive range + * measurements in units of 10 milliseconds, for non-trigger based + * ranging. Acts as a session timeout; if exceeded, the ranging session + * should be terminated. Only valid if @non_trigger_based is set. + * @availability_window: duration of the availability window (AW) in units of + * 1 millisecond (0-255 ms). Only valid if @non_trigger_based is set. + * If set to 0, the firmware or driver can automatically select an + * appropriate value. + * @nominal_time: Nominal duration between adjacent availability windows + * in units of milli seconds. Only valid if @non_trigger_based is set. + * If set to 0, the firmware or driver can automatically select an + * appropriate value. + * @num_measurements: number of Availability Windows (AWs) to schedule + * for non-trigger-based ranging. Each AW may contain multiple FTM + * exchanges as configured by @ftms_per_burst. Only valid if + * @non_trigger_based is set. If set to 0, the firmware or driver + * can automatically select an appropriate value. + * @ingress_distance: optional ingress threshold in units of mm. When set, + * the measurement result of the peer needs to be indicated if the device + * moves into this range. Measurement results need to be sent on a burst + * index basis in this case. + * @egress_distance: optional egress threshold in units of mm. When set, + * the measurement result of the peer needs to be indicated if the device + * moves out of this range. Measurement results need to be sent on a burst + * index basis in this case. + * If neither or only one of @ingress_distance and @egress_distance + * is set, only the specified threshold is used. If both are set, both + * thresholds are applied. If neither is set, results are reported without + * threshold filtering. + * @pd_suppress_range_results: flag to suppress ranging results for PD + * requests. When set, the device performs ranging measurements to + * provide ranging services to a peer (e.g. in RSTA role) but does + * not report the measurement results to userspace. Only valid when + * @request_type is %NL80211_PMSR_FTM_REQ_TYPE_PD. * * See also nl80211 for the respective attribute documentation. */ @@ -4560,6 +4715,16 @@ struct cfg80211_pmsr_ftm_request_peer { u8 ftms_per_burst; u8 ftmr_retries; u8 bss_color; + + u32 request_type; + u32 min_time_between_measurements; + u32 max_time_between_measurements; + u8 availability_window; + u32 nominal_time; + u32 num_measurements; + u64 ingress_distance; + u64 egress_distance; + u8 pd_suppress_range_results:1; }; /** @@ -5085,6 +5250,9 @@ struct mgmt_frame_regs { * links by calling cfg80211_mlo_reconf_add_done(). When calling * cfg80211_mlo_reconf_add_done() the bss pointer must be given for each * link for which MLO reconfiguration 'add' operation was requested. + * + * @start_pd: Start the PD interface. + * @stop_pd: Stop the PD interface. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -5267,7 +5435,7 @@ struct cfg80211_ops { struct wireless_dev *wdev, struct ieee80211_channel *chan, unsigned int duration, - u64 *cookie); + u64 *cookie, const u8 *rx_addr); int (*cancel_remain_on_channel)(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie); @@ -5461,6 +5629,8 @@ struct cfg80211_ops { struct cfg80211_ml_reconf_req *req); int (*set_epcs)(struct wiphy *wiphy, struct net_device *dev, bool val); + int (*start_pd)(struct wiphy *wiphy, struct wireless_dev *wdev); + void (*stop_pd)(struct wiphy *wiphy, struct wireless_dev *wdev); }; /* @@ -5506,7 +5676,6 @@ struct cfg80211_ops { * responds to probe-requests in hardware. * @WIPHY_FLAG_OFFCHAN_TX: Device supports direct off-channel TX. * @WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL: Device supports remain-on-channel call. - * @WIPHY_FLAG_SUPPORTS_5_10_MHZ: Device supports 5 MHz and 10 MHz channels. * @WIPHY_FLAG_HAS_CHANNEL_SWITCH: Device supports channel switch in * beaconing mode (AP, IBSS, Mesh, ...). * @WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK: The device supports bigger kek and kck keys @@ -5546,7 +5715,6 @@ enum wiphy_flags { WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD = BIT(19), WIPHY_FLAG_OFFCHAN_TX = BIT(20), WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL = BIT(21), - WIPHY_FLAG_SUPPORTS_5_10_MHZ = BIT(22), WIPHY_FLAG_HAS_CHANNEL_SWITCH = BIT(23), WIPHY_FLAG_NOTIFY_REGDOM_BY_DRIVER = BIT(24), WIPHY_FLAG_CHANNEL_CHANGE_ON_BEACON = BIT(25), @@ -5852,6 +6020,7 @@ struct wiphy_vendor_command { * @extended_capabilities_len: length of the extended capabilities * @eml_capabilities: EML capabilities (for MLO) * @mld_capa_and_ops: MLD capabilities and operations (for MLO) + * @ext_mld_capa_and_ops: Extended MLD capabilities and operations (for MLO) */ struct wiphy_iftype_ext_capab { enum nl80211_iftype iftype; @@ -5860,6 +6029,7 @@ struct wiphy_iftype_ext_capab { u8 extended_capabilities_len; u16 eml_capabilities; u16 mld_capa_and_ops; + u16 ext_mld_capa_and_ops; }; /** @@ -5903,7 +6073,53 @@ cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type); * (0 means unknown) * @ftm.max_total_ltf_rx: maximum total number of LTFs that can be received * (0 means unknown) - * @ftm.support_rsta: supports operating as RSTA in PMSR FTM request + * @ftm.ista: initiator role capabilities + * @ftm.ista.support_ntb: supports operating as ISTA in PMSR FTM request for + * NTB ranging. + * @ftm.ista.support_tb: supports operating as ISTA in PMSR FTM request for + * TB ranging. + * @ftm.ista.support_edca: supports operating as ISTA in PMSR FTM request for + * EDCA based ranging. + * @ftm.ista.max_peers: maximum number of peers supported in the ISTA role. + * If zero, no role-specific peer limit applies. + * @ftm.rsta: responder role capabilities + * @ftm.rsta.support_ntb: supports operating as RSTA in PMSR FTM request for + * NTB ranging. + * @ftm.rsta.support_tb: supports operating as RSTA in PMSR FTM request for + * TB ranging. + * @ftm.rsta.support_edca: supports operating as RSTA in PMSR FTM request for + * EDCA based ranging. + * @ftm.rsta.max_peers: maximum number of peers supported in the RSTA role. + * If zero, no role-specific peer limit applies. + * @ftm.max_no_of_tx_antennas: maximum number of transmit antennas supported for + * EDCA based ranging (0 means unknown) + * @ftm.max_no_of_rx_antennas: maximum number of receive antennas supported for + * EDCA based ranging (0 means unknown) + * @ftm.min_allowed_ranging_interval_edca: Minimum EDCA ranging + * interval supported by the device in milli seconds. (0 means unknown). + * Applications can use this value to estimate the burst period to be + * given in the FTM request for the EDCA based ranging case. If + * non-zero, this value will be used to validate the burst period in + * the FTM request. + * @ftm.min_allowed_ranging_interval_ntb: Minimum NTB ranging + * interval supported by the device in milli seconds. (0 means unknown). + * Applications can use this value to estimate the burst period to be + * given in the FTM request for the NTB ranging case. If non-zero, + * this value will be used to validate the nominal time in the FTM + * request. + * @ftm.type: ranging type capabilities + * @ftm.type.infra_support: supports infrastructure ranging (STA-to-AP or + * AP-to-STA) as part of Proximity Detection + * @ftm.type.pd_support: supports peer-to-peer ranging as mentioned in the + * specification "PR Implementation Consideration Draft 1.9 rev 1" where + * PD stands for proximity detection + * @ftm.concurrent_ista_rsta_support: indicates if the device can + * simultaneously act as initiator and responder in a multi-peer + * measurement request. Only valid if @ftm.rsta_support is set. + * @ftm.pd_preambles: bitmap of preambles supported (&enum nl80211_preamble) + * for PD ranging requests. Ignored if @ftm.type.pd_support is not set. + * @ftm.pd_bandwidths: bitmap of bandwidths supported (&enum nl80211_chan_width) + * for PD ranging requests. Ignored if @ftm.type.pd_support is not set. */ struct cfg80211_pmsr_capabilities { unsigned int max_peers; @@ -5929,7 +6145,29 @@ struct cfg80211_pmsr_capabilities { u8 max_rx_sts; u8 max_total_ltf_tx; u8 max_total_ltf_rx; - u8 support_rsta:1; + struct { + u8 support_ntb:1, + support_tb:1, + support_edca:1; + u32 max_peers; + } ista; + struct { + u8 support_ntb:1, + support_tb:1, + support_edca:1; + u32 max_peers; + } rsta; + u8 max_no_of_tx_antennas; + u8 max_no_of_rx_antennas; + u32 min_allowed_ranging_interval_edca; + u32 min_allowed_ranging_interval_ntb; + struct { + u8 infra_support:1, + pd_support:1; + } type; + u8 concurrent_ista_rsta_support:1; + u32 pd_preambles; + u32 pd_bandwidths; } ftm; }; @@ -6024,7 +6262,7 @@ enum wiphy_nan_flags { * nibble indicates the number of TX antennas and upper nibble indicates the * number of RX antennas. Value 0 indicates the information is not * available. - * @max_channel_switch_time: maximum channel switch time in milliseconds. + * @max_channel_switch_time: maximum channel switch time in microseconds. * @dev_capabilities: NAN device capabilities as defined in Wi-Fi Aware (TM) * specification Table 79 (Capabilities field). * @phy: Band-agnostic capabilities for NAN data interfaces. Since NAN @@ -6990,7 +7228,7 @@ struct wireless_dev { enum ieee80211_bss_type conn_bss_type; u32 conn_owner_nlportid; - struct work_struct disconnect_wk; + struct wiphy_work disconnect_wk; u8 disconnect_bssid[ETH_ALEN]; struct list_head event_list; @@ -7027,7 +7265,7 @@ struct wireless_dev { struct list_head pmsr_list; spinlock_t pmsr_lock; - struct work_struct pmsr_free_wk; + struct wiphy_work pmsr_free_wk; unsigned long unprot_beacon_reported; @@ -8302,6 +8540,7 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr); * as the AC bitmap in the QoS info field * @req_ies: information elements from the (Re)Association Request frame * @req_ies_len: length of req_ies data + * @assoc_encrypted: indicate if the (re)association exchange is encrypted. * @ap_mld_addr: AP MLD address (in case of MLO) * @links: per-link information indexed by link ID, use links[0] for * non-MLO connections @@ -8316,6 +8555,7 @@ struct cfg80211_rx_assoc_resp_data { const u8 *req_ies; size_t req_ies_len; int uapsd_queues; + bool assoc_encrypted; const u8 *ap_mld_addr; struct { u8 addr[ETH_ALEN] __aligned(2); @@ -8445,7 +8685,7 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, * cfg80211 then sends a notification to userspace. */ void cfg80211_notify_new_peer_candidate(struct net_device *dev, - const u8 *macaddr, const u8 *ie, u8 ie_len, + const u8 *macaddr, const u8 *ie, size_t ie_len, int sig_dbm, gfp_t gfp); /** @@ -8835,6 +9075,9 @@ struct cfg80211_fils_resp_params { * @links.status: per-link status code, to report a status code that's not * %WLAN_STATUS_SUCCESS for a given link, it must also be in the * @valid_links bitmap and may have a BSS pointer (which is then released) + * @assoc_encrypted: The driver should set this flag to indicate that the + * (Re)Association Request/Response frames are transmitted encrypted over + * the air. */ struct cfg80211_connect_resp_params { int status; @@ -8844,6 +9087,7 @@ struct cfg80211_connect_resp_params { size_t resp_ie_len; struct cfg80211_fils_resp_params fils; enum nl80211_timeout_reason timeout_reason; + bool assoc_encrypted; const u8 *ap_mld_addr; u16 valid_links; diff --git a/include/net/devlink.h b/include/net/devlink.h index bcd31de1f890..dd546dbd57cf 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -433,6 +433,13 @@ enum devlink_param_type { DEVLINK_PARAM_TYPE_U64 = DEVLINK_VAR_ATTR_TYPE_U64, DEVLINK_PARAM_TYPE_STRING = DEVLINK_VAR_ATTR_TYPE_STRING, DEVLINK_PARAM_TYPE_BOOL = DEVLINK_VAR_ATTR_TYPE_FLAG, + DEVLINK_PARAM_TYPE_U64_ARRAY = DEVLINK_VAR_ATTR_TYPE_U64_ARRAY, +}; + +#define __DEVLINK_PARAM_MAX_ARRAY_SIZE 32 +struct devlink_param_u64_array { + u64 size; + u64 val[__DEVLINK_PARAM_MAX_ARRAY_SIZE]; }; union devlink_param_value { @@ -442,6 +449,7 @@ union devlink_param_value { u64 vu64; char vstr[__DEVLINK_PARAM_MAX_STRING_VALUE]; bool vbool; + struct devlink_param_u64_array u64arr; }; struct devlink_param_gset_ctx { @@ -501,7 +509,7 @@ struct devlink_param { struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int (*validate)(struct devlink *devlink, u32 id, - union devlink_param_value val, + union devlink_param_value *val, struct netlink_ext_ack *extack); int (*get_default)(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx, @@ -1923,7 +1931,7 @@ void devlink_params_unregister(struct devlink *devlink, int devl_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *val); void devl_param_driverinit_value_set(struct devlink *devlink, u32 param_id, - union devlink_param_value init_val); + union devlink_param_value *init_val); void devl_param_value_changed(struct devlink *devlink, u32 param_id); struct devlink_region *devl_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index e0ca3904ff8e..2f312d1f67d6 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -99,6 +99,7 @@ FN(FRAG_TOO_FAR) \ FN(TCP_MINTTL) \ FN(IPV6_BAD_EXTHDR) \ + FN(IPV6_TOO_MANY_EXTHDRS) \ FN(IPV6_NDISC_FRAG) \ FN(IPV6_NDISC_HOP_LIMIT) \ FN(IPV6_NDISC_BAD_CODE) \ @@ -494,6 +495,11 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_MINTTL, /** @SKB_DROP_REASON_IPV6_BAD_EXTHDR: Bad IPv6 extension header. */ SKB_DROP_REASON_IPV6_BAD_EXTHDR, + /** + * @SKB_DROP_REASON_IPV6_TOO_MANY_EXTHDRS: Number of IPv6 extension + * headers in the packet exceeds IP6_MAX_EXT_HDRS_CNT. + */ + SKB_DROP_REASON_IPV6_TOO_MANY_EXTHDRS, /** @SKB_DROP_REASON_IPV6_NDISC_FRAG: invalid frag (suppress_frag_ndisc). */ SKB_DROP_REASON_IPV6_NDISC_FRAG, /** @SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT: invalid hop limit. */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 8b6d34e8a6f0..8c16ef23cc10 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -58,6 +58,7 @@ struct tc_action; #define DSA_TAG_PROTO_YT921X_VALUE 30 #define DSA_TAG_PROTO_MXL_GSW1XX_VALUE 31 #define DSA_TAG_PROTO_MXL862_VALUE 32 +#define DSA_TAG_PROTO_NETC_VALUE 33 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -93,6 +94,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_YT921X = DSA_TAG_PROTO_YT921X_VALUE, DSA_TAG_PROTO_MXL_GSW1XX = DSA_TAG_PROTO_MXL_GSW1XX_VALUE, DSA_TAG_PROTO_MXL862 = DSA_TAG_PROTO_MXL862_VALUE, + DSA_TAG_PROTO_NETC = DSA_TAG_PROTO_NETC_VALUE, }; struct dsa_switch; @@ -1122,7 +1124,8 @@ struct dsa_switch_ops { void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, - const struct flow_action_police *policer); + const struct flow_action_police *policer, + struct netlink_ext_ack *extack); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 1fc2fb03ce3f..f45d1e3163f0 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -164,8 +164,11 @@ 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); + /* Copy in two stages to keep the __counted_by happy. */ + new_md->u.tun_info = md_dst->u.tun_info; + memcpy(ip_tunnel_info_opts(&new_md->u.tun_info), + ip_tunnel_info_opts(&md_dst->u.tun_info), md_size); + #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/fib_rules.h b/include/net/fib_rules.h index 6e68e359ad18..7dee0ae616e3 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -111,6 +111,11 @@ static inline void fib_rule_get(struct fib_rule *rule) refcount_inc(&rule->refcnt); } +static inline bool fib_rule_get_safe(struct fib_rule *rule) +{ + return refcount_inc_not_zero(&rule->refcnt); +} + static inline void fib_rule_put(struct fib_rule *rule) { if (refcount_dec_and_test(&rule->refcnt)) diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 7aa2b8e1fb29..856b5e90fbdb 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -47,19 +47,19 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int padattr); int gnet_stats_copy_basic(struct gnet_dump *d, - struct gnet_stats_basic_sync __percpu *cpu, - struct gnet_stats_basic_sync *b, bool running); + const struct gnet_stats_basic_sync __percpu *cpu, + const struct gnet_stats_basic_sync *b, bool running); void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, - struct gnet_stats_basic_sync __percpu *cpu, - struct gnet_stats_basic_sync *b, bool running); + const struct gnet_stats_basic_sync __percpu *cpu, + const struct gnet_stats_basic_sync *b, bool running); int gnet_stats_copy_basic_hw(struct gnet_dump *d, - struct gnet_stats_basic_sync __percpu *cpu, - struct gnet_stats_basic_sync *b, bool running); + const struct gnet_stats_basic_sync __percpu *cpu, + const struct gnet_stats_basic_sync *b, bool running); int gnet_stats_copy_rate_est(struct gnet_dump *d, struct net_rate_estimator __rcu **ptr); int gnet_stats_copy_queue(struct gnet_dump *d, - struct gnet_stats_queue __percpu *cpu_q, - struct gnet_stats_queue *q, __u32 qlen); + const struct gnet_stats_queue __percpu *cpu_q, + const struct gnet_stats_queue *q, __u32 qlen); void gnet_stats_add_queue(struct gnet_stats_queue *qstats, const struct gnet_stats_queue __percpu *cpu_q, const struct gnet_stats_queue *q); diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 7b84f2cef8b1..d70510ac31ab 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -489,8 +489,10 @@ genlmsg_multicast_netns_filtered(const struct genl_family *family, netlink_filter_fn filter, void *filter_data) { - if (WARN_ON_ONCE(group >= family->n_mcgrps)) + if (WARN_ON_ONCE(group >= family->n_mcgrps)) { + nlmsg_free(skb); return -EINVAL; + } group = family->mcgrp_offset + group; return nlmsg_multicast_filtered(net->genl_sock, skb, portid, group, flags, filter, filter_data); diff --git a/include/net/gue.h b/include/net/gue.h index dfca298bec9c..caefd6da8693 100644 --- a/include/net/gue.h +++ b/include/net/gue.h @@ -80,7 +80,7 @@ static inline size_t guehdr_flags_len(__be16 flags) static inline size_t guehdr_priv_flags_len(__be32 flags) { - return 0; + return (flags & GUE_PFLAG_REMCSUM) ? GUE_PLEN_REMCSUM : 0; } /* Validate standard and private flags. Returns non-zero (meaning invalid) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 318593743b6e..c63a3c4967ae 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -269,7 +269,6 @@ struct fib_dump_filter { bool filter_set; bool dump_routes; bool dump_exceptions; - bool rtnl_held; unsigned char protocol; unsigned char rt_type; unsigned int flags; @@ -375,7 +374,7 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; - int err = -ENETUNREACH; + int err = -EAGAIN; flags |= FIB_LOOKUP_NOREF; if (net->ipv4.fib_has_custom_rules) @@ -389,17 +388,16 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp, if (tb) err = fib_table_lookup(tb, flp, res, flags); - if (!err) + if (err != -EAGAIN) goto out; tb = rcu_dereference_rtnl(net->ipv4.fib_default); if (tb) err = fib_table_lookup(tb, flp, res, flags); -out: if (err == -EAGAIN) err = -ENETUNREACH; - +out: rcu_read_unlock(); return err; @@ -629,6 +627,11 @@ static inline void fib_info_hold(struct fib_info *fi) refcount_inc(&fi->fib_clntref); } +static inline bool fib_info_hold_safe(struct fib_info *fi) +{ + return refcount_inc_not_zero(&fi->fib_clntref); +} + static inline void fib_info_put(struct fib_info *fi) { if (refcount_dec_and_test(&fi->fib_clntref)) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 72d325c81313..417ff51f62fc 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -44,6 +44,14 @@ #define IP_VS_CONN_TAB_MAX_BITS 20 #endif +/* conn_max limits */ +#if BITS_PER_LONG > 32 +/* Limit of atomic_t but restricted by roundup_pow_of_two() in ip_vs_core.c */ +#define IP_VS_CONN_MAX (1 << 30) +#else +#define IP_VS_CONN_MAX (1 << 24) +#endif + /* svc_table limits */ #define IP_VS_SVC_TAB_MIN_BITS 4 #define IP_VS_SVC_TAB_MAX_BITS 20 @@ -491,6 +499,7 @@ struct ip_vs_est_kt_data { DECLARE_BITMAP(avail, IPVS_EST_NTICKS); /* tick has space for ests */ unsigned long est_timer; /* estimation timer (jiffies) */ struct ip_vs_stats *calc_stats; /* Used for calculation */ + int needed; /* task is needed */ int tick_len[IPVS_EST_NTICKS]; /* est count */ int id; /* ktid per netns */ int chain_max; /* max ests per tick chain */ @@ -743,7 +752,8 @@ struct ip_vs_protocol { void (*state_transition)(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd); + struct ip_vs_proto_data *pd, + unsigned int iph_len); int (*register_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc); @@ -1185,8 +1195,9 @@ struct netns_ipvs { struct timer_list dest_trash_timer; /* expiration timer */ struct mutex service_mutex; /* service reconfig */ struct rw_semaphore svc_resize_sem; /* svc_table resizing */ + struct rw_semaphore svc_replace_sem; /* svc_table replace */ struct delayed_work svc_resize_work; /* resize svc_table */ - atomic_t svc_table_changes;/* ++ on new table */ + atomic_t svc_table_changes;/* ++ on table changes */ /* Service counters */ atomic_t num_services[IP_VS_AF_MAX]; /* Services */ atomic_t fwm_services[IP_VS_AF_MAX]; /* Services */ @@ -1218,6 +1229,10 @@ struct netns_ipvs { /* sysctl variables */ int sysctl_amemthresh; int sysctl_am_droprate; +#ifdef CONFIG_SYSCTL + int sysctl_conn_max;/* soft limit for conns */ + int conn_max_limit; /* hard limit for conn_max */ +#endif int sysctl_drop_entry; int sysctl_drop_packet; int sysctl_secure_tcp; @@ -1315,6 +1330,11 @@ struct netns_ipvs { #ifdef CONFIG_SYSCTL +static inline int sysctl_conn_max(struct netns_ipvs *ipvs) +{ + return READ_ONCE(ipvs->sysctl_conn_max); +} + static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) { return ipvs->sysctl_sync_threshold[0]; @@ -1411,7 +1431,7 @@ static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) return ipvs->sysctl_run_estimation; } -static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) +static inline const struct cpumask *__sysctl_est_cpulist(struct netns_ipvs *ipvs) { if (ipvs->est_cpulist_valid) return ipvs->sysctl_est_cpulist; @@ -1434,6 +1454,11 @@ static inline int sysctl_est_nice(struct netns_ipvs *ipvs) #else +static inline int sysctl_conn_max(struct netns_ipvs *ipvs) +{ + return IP_VS_CONN_MAX; +} + static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) { return DEFAULT_SYNC_THRESHOLD; @@ -1529,7 +1554,7 @@ static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) return 1; } -static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) +static inline const struct cpumask *__sysctl_est_cpulist(struct netns_ipvs *ipvs) { return housekeeping_cpumask(HK_TYPE_KTHREAD); } @@ -1564,6 +1589,18 @@ static inline int sysctl_svc_lfactor(struct netns_ipvs *ipvs) return READ_ONCE(ipvs->sysctl_svc_lfactor); } +static inline bool sysctl_est_cpulist_empty(struct netns_ipvs *ipvs) +{ + guard(rcu)(); + return cpumask_empty(__sysctl_est_cpulist(ipvs)); +} + +static inline unsigned int sysctl_est_cpulist_weight(struct netns_ipvs *ipvs) +{ + guard(rcu)(); + return cpumask_weight(__sysctl_est_cpulist(ipvs)); +} + /* IPVS core functions * (from ip_vs_core.c) */ @@ -1810,8 +1847,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler); int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler); int ip_vs_bind_scheduler(struct ip_vs_service *svc, struct ip_vs_scheduler *scheduler); -void ip_vs_unbind_scheduler(struct ip_vs_service *svc, - struct ip_vs_scheduler *sched); +void ip_vs_unbind_scheduler(struct ip_vs_service *svc); struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); struct ip_vs_conn * @@ -1884,18 +1920,26 @@ int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_zero_estimator(struct ip_vs_stats *stats); void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats); -void ip_vs_est_reload_start(struct netns_ipvs *ipvs); +void ip_vs_est_reload_start(struct netns_ipvs *ipvs, bool restart); int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, struct ip_vs_est_kt_data *kd); void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd); +static inline void ip_vs_stop_estimator_tot_stats(struct netns_ipvs *ipvs) +{ +#ifdef CONFIG_SYSCTL + ip_vs_stop_estimator(ipvs, &ipvs->tot_stats->s); + ipvs->tot_stats->s.est.ktid = -2; +#endif +} + static inline void ip_vs_est_stopped_recalc(struct netns_ipvs *ipvs) { #ifdef CONFIG_SYSCTL /* Stop tasks while cpulist is empty or if disabled with flag */ ipvs->est_stopped = !sysctl_run_estimation(ipvs) || (ipvs->est_cpulist_valid && - cpumask_empty(sysctl_est_cpulist(ipvs))); + sysctl_est_cpulist_empty(ipvs)); #endif } @@ -1911,7 +1955,7 @@ static inline bool ip_vs_est_stopped(struct netns_ipvs *ipvs) static inline int ip_vs_est_max_threads(struct netns_ipvs *ipvs) { unsigned int limit = IPVS_EST_CPU_KTHREADS * - cpumask_weight(sysctl_est_cpulist(ipvs)); + sysctl_est_cpulist_weight(ipvs); return max(1U, limit); } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d042afe7a245..3de07e738538 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -90,6 +90,9 @@ struct ip_tunnel_info; #define IP6_DEFAULT_MAX_DST_OPTS_LEN INT_MAX /* No limit */ #define IP6_DEFAULT_MAX_HBH_OPTS_LEN INT_MAX /* No limit */ +/* Hard limit on traversed IPv6 extension headers */ +#define IP6_MAX_EXT_HDRS_CNT 12 + /* * Addr type * @@ -952,6 +955,18 @@ static inline u32 ip6_multipath_hash_fields(const struct net *net) } #endif +/* Derive the IPv6 ECMP hash from txhash so a rehash may pick a different path; + * policy 0 only, and only when txhash is set. >> 1 clears the top bit + * (fib6_select_path() uses mp_hash as a signed 31-bit value); ?: 1 keeps the + * result non-zero, since mp_hash 0 falls back to rt6_multipath_hash(). + */ +static inline void ip6_ecmp_set_mp_hash(const struct net *net, + struct flowi6 *fl6, u32 txhash) +{ + if (ip6_multipath_hash_policy(net) == 0 && txhash) + fl6->mp_hash = (txhash >> 1) ?: 1; +} + /* * Header manipulation */ diff --git a/include/net/llc.h b/include/net/llc.h index e250dca03963..029ba8a22319 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_H #define LLC_H /* * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include <linux/if.h> diff --git a/include/net/llc_c_ac.h b/include/net/llc_c_ac.h index 7620a9196922..af31a49bebb0 100644 --- a/include/net/llc_c_ac.h +++ b/include/net/llc_c_ac.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_C_AC_H #define LLC_C_AC_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ /* Connection component state transition actions */ /* diff --git a/include/net/llc_c_ev.h b/include/net/llc_c_ev.h index 241889955157..d45140d4289a 100644 --- a/include/net/llc_c_ev.h +++ b/include/net/llc_c_ev.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_C_EV_H #define LLC_C_EV_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include <net/sock.h> diff --git a/include/net/llc_c_st.h b/include/net/llc_c_st.h index a4bea0f33188..f52a4cc4880d 100644 --- a/include/net/llc_c_st.h +++ b/include/net/llc_c_st.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_C_ST_H #define LLC_C_ST_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include <net/llc_c_ac.h> diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index 374411b3066c..e1a302696723 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_CONN_H #define LLC_CONN_H /* * Copyright (c) 1997 by Procom Technology, Inc. * 2001, 2002 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include <linux/timer.h> #include <net/llc_if.h> diff --git a/include/net/llc_if.h b/include/net/llc_if.h index c72570a21a4f..a333259613ab 100644 --- a/include/net/llc_if.h +++ b/include/net/llc_if.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_IF_H #define LLC_IF_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ /* Defines LLC interface to network layer */ /* Available primitives */ diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 86681f29bda7..f165237a3723 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_PDU_H #define LLC_PDU_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include <linux/if_ether.h> diff --git a/include/net/llc_s_ac.h b/include/net/llc_s_ac.h index f71790305bc9..076adc5217fd 100644 --- a/include/net/llc_s_ac.h +++ b/include/net/llc_s_ac.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_S_AC_H #define LLC_S_AC_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ struct llc_sap; diff --git a/include/net/llc_s_ev.h b/include/net/llc_s_ev.h index fb7df1d70af3..7b9c94093336 100644 --- a/include/net/llc_s_ev.h +++ b/include/net/llc_s_ev.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_S_EV_H #define LLC_S_EV_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include <linux/skbuff.h> diff --git a/include/net/llc_s_st.h b/include/net/llc_s_st.h index fca49d483d20..85ce230fd946 100644 --- a/include/net/llc_s_st.h +++ b/include/net/llc_s_st.h @@ -1,15 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_S_ST_H #define LLC_S_ST_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ #include <linux/types.h> diff --git a/include/net/llc_sap.h b/include/net/llc_sap.h index 1e4df9fd9fb2..b259f5993c46 100644 --- a/include/net/llc_sap.h +++ b/include/net/llc_sap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LLC_SAP_H #define LLC_SAP_H @@ -6,13 +7,6 @@ /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License as published by the Free Software Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License for more details. */ struct llc_sap; struct net_device; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 40cb20d9309c..4f95da023746 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -218,6 +218,8 @@ struct ieee80211_low_level_stats { * bandwidth) OFDMA settings need to be changed * @IEEE80211_CHANCTX_CHANGE_PUNCTURING: The punctured channel(s) bitmap * was changed. + * @IEEE80211_CHANCTX_CHANGE_NPCA: NPCA configuration changed + * @IEEE80211_CHANCTX_CHANGE_NPCA_PUNCT: NPCA puncturing changed */ enum ieee80211_chanctx_change { IEEE80211_CHANCTX_CHANGE_WIDTH = BIT(0), @@ -227,6 +229,8 @@ enum ieee80211_chanctx_change { IEEE80211_CHANCTX_CHANGE_MIN_DEF = BIT(4), IEEE80211_CHANCTX_CHANGE_AP = BIT(5), IEEE80211_CHANCTX_CHANGE_PUNCTURING = BIT(6), + IEEE80211_CHANCTX_CHANGE_NPCA = BIT(7), + IEEE80211_CHANCTX_CHANGE_NPCA_PUNCT = BIT(8), }; /** @@ -234,10 +238,13 @@ enum ieee80211_chanctx_change { * @oper: channel definition to use for operation * @ap: the channel definition of the AP, if any * (otherwise the chan member is %NULL) + * @require_npca: If NPCA is configured, require it to + * remain, this is used by AP interfaces */ struct ieee80211_chan_req { struct cfg80211_chan_def oper; struct cfg80211_chan_def ap; + bool require_npca; }; /** @@ -366,6 +373,7 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_MLD_TTLM: negotiated TID to link mapping was changed * @BSS_CHANGED_TPE: transmit power envelope changed * @BSS_CHANGED_NAN_LOCAL_SCHED: NAN local schedule changed (NAN mode only) + * @BSS_CHANGED_NPCA: NPCA parameters changed */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, @@ -404,6 +412,7 @@ enum ieee80211_bss_change { BSS_CHANGED_MLD_TTLM = BIT_ULL(34), BSS_CHANGED_TPE = BIT_ULL(35), BSS_CHANGED_NAN_LOCAL_SCHED = BIT_ULL(36), + BSS_CHANGED_NPCA = BIT_ULL(37), /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -590,6 +599,26 @@ struct ieee80211_parsed_tpe { }; /** + * struct ieee80211_bss_npca_params - NPCA parameters + * @min_dur_thresh: NPCA minimum duration threshold (512 + 128*n usec) + * @switch_delay: NPCA switch delay (units of 4 usec) + * @switch_back_delay: NPCA switch back delay (units of 4 usec) + * @init_qsrc: initial QSRC value + * @moplen: indicates MOPLEN NPCA is permitted in the BSS + * @enabled: NPCA is enabled for this link + * + * Note: the individual values (except @enabled) are in spec representation. + */ +struct ieee80211_bss_npca_params { + u32 min_dur_thresh:4, + switch_delay:6, + switch_back_delay:6, + init_qsrc:2, + moplen:1, + enabled:1; +}; + +/** * struct ieee80211_bss_conf - holds the BSS's changing parameters * * This structure keeps information about a BSS (and an association @@ -763,6 +792,7 @@ struct ieee80211_parsed_tpe { * (as opposed to hearing its value from another link's beacon). * @s1g_long_beacon_period: number of beacon intervals between each long * beacon transmission. + * @npca: NPCA parameters */ struct ieee80211_bss_conf { struct ieee80211_vif *vif; @@ -866,6 +896,8 @@ struct ieee80211_bss_conf { u8 bss_param_ch_cnt_link_id; u8 s1g_long_beacon_period; + + struct ieee80211_bss_npca_params npca; }; #define IEEE80211_NAN_MAX_CHANNELS 3 @@ -1672,6 +1704,7 @@ enum mac80211_rx_encoding { RX_ENC_HE, RX_ENC_EHT, RX_ENC_UHR, + RX_ENC_S1G, }; /** @@ -1747,18 +1780,18 @@ struct ieee80211_rx_status { u8 he_ru:3; u8 he_gi:2; u8 he_dcm:1; - }; + } __packed; struct { u8 ru:4; u8 gi:2; - } eht; + } __packed eht; struct { u8 ru:4; u8 gi:2; u8 elr:1; u8 im:1; - } uhr; - }; + } __packed uhr; + } __packed; u8 rate_idx; u8 nss; u8 rx_flags; @@ -1771,6 +1804,8 @@ struct ieee80211_rx_status { u8 link_valid:1, link_id:4; }; +static_assert(sizeof(struct ieee80211_rx_status) <= sizeof_field(struct sk_buff, cb)); + static inline u32 ieee80211_rx_status_to_khz(struct ieee80211_rx_status *rx_status) { @@ -1979,12 +2014,16 @@ enum ieee80211_vif_flags { * @IEEE80211_OFFLOAD_DECAP_ENABLED: rx encapsulation offload is enabled * The driver supports passing received 802.11 frames as 802.3 frames to * mac80211. + * @IEEE80211_OFFLOAD_ENCAP_MCAST: tx multicast encapsulation offload is enabled + * The driver supports sending multicast frames passed as 802.3 frames + * by mac80211. */ enum ieee80211_offload_flags { IEEE80211_OFFLOAD_ENCAP_ENABLED = BIT(0), IEEE80211_OFFLOAD_ENCAP_4ADDR = BIT(1), IEEE80211_OFFLOAD_DECAP_ENABLED = BIT(2), + IEEE80211_OFFLOAD_ENCAP_MCAST = BIT(3), }; #define IEEE80211_NAN_AVAIL_BLOB_MAX_LEN 54 @@ -2672,6 +2711,8 @@ struct ieee80211_link_sta { * @epp_peer: indicates that the peer is an EPP peer. * @nmi: For NDI stations, pointer to the NMI station of the peer. * @nan_sched: NAN peer schedule for this station. Valid only for NMI stations. + * @ext_mld_capa_ops: the MLD's extended MLD capabilities and operations + * NOTE: currently only tracked for AP STAs */ struct ieee80211_sta { u8 addr[ETH_ALEN] __aligned(2); @@ -2696,6 +2737,7 @@ struct ieee80211_sta { struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; u16 valid_links; + u16 ext_mld_capa_ops; bool epp_peer; struct ieee80211_link_sta deflink; struct ieee80211_link_sta __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; @@ -7890,6 +7932,35 @@ void ieee80211_nan_func_match(struct ieee80211_vif *vif, void ieee80211_nan_sched_update_done(struct ieee80211_vif *vif); /** + * ieee80211_nan_cluster_joined - notify about NAN cluster join. + * + * This function is used to notify mac80211 about NAN cluster join. + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @cluster_id: the cluster ID that was joined + * @new_cluster: true if this is a new cluster + * @gfp: allocation flags + */ +void ieee80211_nan_cluster_joined(struct ieee80211_vif *vif, + const u8 *cluster_id, bool new_cluster, + gfp_t gfp); + +/** + * ieee80211_nan_try_evacuate - try to evacuate a NAN channel + * + * This function tries to evacuate a NAN channel that is using the given + * channel context, to free up channel context resources. + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @conf: the channel context configuration to try to evacuate. If %NULL, + * the NAN channel that has the fewest slots scheduled will be evacuated. + * + * Return: %true if a channel was evacuated, %false otherwise + */ +bool ieee80211_nan_try_evacuate(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *conf); + +/** * ieee80211_calc_rx_airtime - calculate estimated transmission airtime for RX. * * This function calculates the estimated airtime usage of a frame based on the diff --git a/include/net/macsec.h b/include/net/macsec.h index bc7de5b53e54..d962093ee923 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -9,6 +9,7 @@ #include <linux/u64_stats_sync.h> #include <linux/if_vlan.h> +#include <linux/workqueue.h> #include <uapi/linux/if_link.h> #include <uapi/linux/if_macsec.h> @@ -123,6 +124,7 @@ struct macsec_dev_stats { * @key: key structure * @ssci: short secure channel identifier * @stats: per-SA stats + * @destroy_work: deferred work to free the SA in process context after RCU grace period */ struct macsec_rx_sa { struct macsec_key key; @@ -136,7 +138,7 @@ struct macsec_rx_sa { bool active; struct macsec_rx_sa_stats __percpu *stats; struct macsec_rx_sc *sc; - struct rcu_head rcu; + struct rcu_work destroy_work; }; struct pcpu_rx_sc_stats { @@ -174,6 +176,7 @@ struct macsec_rx_sc { * @key: key structure * @ssci: short secure channel identifier * @stats: per-SA stats + * @destroy_work: deferred work to free the SA in process context after RCU grace period */ struct macsec_tx_sa { struct macsec_key key; @@ -186,7 +189,7 @@ struct macsec_tx_sa { refcount_t refcnt; bool active; struct macsec_tx_sa_stats __percpu *stats; - struct rcu_head rcu; + struct rcu_work destroy_work; }; /** diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 6d836060976a..0c395917b214 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -342,6 +342,7 @@ struct gdma_queue { void *context; unsigned int msix_index; + unsigned int irq; u32 log2_throttle_limit; } eq; @@ -388,6 +389,11 @@ struct gdma_irq_context { spinlock_t lock; struct list_head eq_list; char name[MANA_IRQ_NAME_SZ]; + unsigned int msi; + unsigned int irq; + refcount_t refcount; + unsigned int bitmap_refs; + bool dyn_msix; }; enum gdma_context_flags { @@ -399,8 +405,10 @@ struct gdma_context { struct device *dev; struct dentry *mana_pci_debugfs; - /* Per-vPort max number of queues */ + /* Hardware max number of queues */ unsigned int max_num_queues; + /* Per-vPort max number of queues */ + unsigned int max_num_queues_vport; unsigned int max_num_msix; unsigned int num_msix_usable; struct xarray irq_contexts; @@ -418,6 +426,7 @@ struct gdma_context { u32 test_event_eq_id; bool is_pf; + bool is_pf2; phys_addr_t bar0_pa; void __iomem *bar0_va; @@ -442,10 +451,20 @@ struct gdma_context { struct gdma_dev mana_ib; u64 pf_cap_flags1; + u64 gdma_protocol_ver; struct workqueue_struct *service_wq; unsigned long flags; + + /* Protect access to GIC context */ + struct mutex gic_mutex; + + /* Indicate if this device is sharing MSI for EQs on MANA */ + bool msi_sharing; + + /* Bitmap tracks where MSI is allocated when it is not shared for EQs */ + unsigned long *msi_bitmap; }; static inline bool mana_gd_is_mana(struct gdma_dev *gd) @@ -570,6 +589,7 @@ struct gdma_eqe { #define GDMA_SRIOV_REG_CFG_BASE_OFF 0x108 #define MANA_PF_DEVICE_ID 0x00B9 +#define MANA_PF2_DEVICE_ID 0x00C1 #define MANA_VF_DEVICE_ID 0x00BA struct gdma_posted_wqe_info { @@ -598,6 +618,7 @@ enum { #define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3) #define GDMA_DRV_CAP_FLAG_1_GDMA_PAGES_4MB_1GB_2GB BIT(4) #define GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT BIT(5) +#define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6) /* Driver can handle holes (zeros) in the device list */ #define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11) @@ -614,7 +635,8 @@ enum { /* Driver detects stalled send queues and recovers them */ #define GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY BIT(18) -#define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6) +/* Driver supports separate EQ/MSIs for each vPort */ +#define GDMA_DRV_CAP_FLAG_1_EQ_MSI_UNSHARE_MULTI_VPORT BIT(19) /* Driver supports linearizing the skb when num_sge exceeds hardware limit */ #define GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE BIT(20) @@ -642,7 +664,8 @@ enum { GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE | \ GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY | \ GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY | \ - GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECOVERY) + GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECOVERY | \ + GDMA_DRV_CAP_FLAG_1_EQ_MSI_UNSHARE_MULTI_VPORT) #define GDMA_DRV_CAP_FLAGS2 0 @@ -1018,4 +1041,11 @@ int mana_gd_resume(struct pci_dev *pdev); bool mana_need_log(struct gdma_context *gc, int err); +struct gdma_irq_context *mana_gd_get_gic(struct gdma_context *gc, + bool use_msi_bitmap, + int *msi_requested); +void mana_gd_put_gic(struct gdma_context *gc, bool use_msi_bitmap, int msi); +int mana_gd_query_device_cfg(struct gdma_context *gc, u32 proto_major_ver, + u32 proto_minor_ver, u32 proto_micro_ver, + u16 *max_num_vports, u8 *bm_hostmode); #endif /* _GDMA_H */ diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 8f721cd4e4a7..04acb6791dbd 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -305,6 +305,14 @@ struct mana_recv_buf_oob { void *buf_va; bool from_pool; /* allocated from a page pool */ + /* head page of the page_pool fragment; valid only when + * from_pool && frag_count > 1. + */ + struct page *pp_page; + /* Fragment offset plus rxq->headroom, passed to + * page_pool_dma_sync_for_cpu(). + */ + u32 dma_sync_offset; /* SGL of the buffer going to be sent as part of the work request. */ u32 num_sge; @@ -480,8 +488,6 @@ struct mana_context { u8 bm_hostmode; struct mana_ethtool_hc_stats hc_stats; - struct mana_eq *eqs; - struct dentry *mana_eqs_debugfs; struct workqueue_struct *per_port_queue_reset_wq; /* Workqueue for querying hardware stats */ struct delayed_work gf_stats_work; @@ -501,13 +507,16 @@ struct mana_port_context { u8 mac_addr[ETH_ALEN]; + struct mana_eq *eqs; + struct dentry *mana_eqs_debugfs; + enum TRI_STATE rss_state; mana_handle_t default_rxobj; bool tx_shortform_allowed; u16 tx_vp_offset; - struct mana_tx_qp *tx_qp; + struct mana_tx_qp **tx_qp; /* Indirection Table for RX & TX. The values are queue indexes */ u32 *indir_table; @@ -547,6 +556,12 @@ struct mana_port_context { struct mutex vport_mutex; int vport_use_count; + /* Set by mana_set_channels() under vport_mutex to block RDMA + * from grabbing the vport during the detach/attach window. + * Checked by mana_cfg_vport() when called from the RDMA path. + */ + bool channel_changing; + /* Net shaper handle*/ struct net_shaper_handle handle; @@ -555,6 +570,10 @@ struct mana_port_context { u32 speed; /* Maximum speed supported by the SKU (mbps) */ u32 max_speed; + /* 1 = not queried, 0 = cached success, negative = permanent error. + * Protected by the netdev instance lock. + */ + int link_cfg_error; bool port_is_up; bool port_st_save; /* Saved port state */ @@ -568,6 +587,14 @@ struct mana_port_context { /* Debugfs */ struct dentry *mana_port_debugfs; + + /* Cached vport/steering config for debugfs */ + u32 vport_max_sq; + u32 vport_max_rq; + u32 steer_rx; + u32 steer_rss; + bool steer_update_tab; + u32 steer_cqe_coalescing; }; netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); @@ -1032,8 +1059,10 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, mana_handle_t wq_obj); int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, - u32 doorbell_pg_id); + u32 doorbell_pg_id, bool check_channel_changing); void mana_uncfg_vport(struct mana_port_context *apc); +int mana_create_eq(struct mana_port_context *apc); +void mana_destroy_eq(struct mana_port_context *apc); struct net_device *mana_get_primary_netdev(struct mana_context *ac, u32 port_index, diff --git a/include/net/mana/shm_channel.h b/include/net/mana/shm_channel.h index 5199b41497ff..dbabcfb95daf 100644 --- a/include/net/mana/shm_channel.h +++ b/include/net/mana/shm_channel.h @@ -4,6 +4,12 @@ #ifndef _SHM_CHANNEL_H #define _SHM_CHANNEL_H +#define SMC_APERTURE_BITS 256 +#define SMC_BASIC_UNIT (sizeof(u32)) +#define SMC_APERTURE_DWORDS (SMC_APERTURE_BITS / (SMC_BASIC_UNIT * 8)) +#define SMC_LAST_DWORD (SMC_APERTURE_DWORDS - 1) +#define SMC_APERTURE_SIZE (SMC_APERTURE_BITS / 8) + struct shm_channel { struct device *dev; void __iomem *base; diff --git a/include/net/mld.h b/include/net/mld.h index c07359808493..23255cc47ced 100644 --- a/include/net/mld.h +++ b/include/net/mld.h @@ -89,29 +89,196 @@ struct mld2_query { #define MLDV2_QQIC_EXP(value) (((value) >> 4) & 0x07) #define MLDV2_QQIC_MAN(value) ((value) & 0x0f) -#define MLD_EXP_MIN_LIMIT 32768UL -#define MLDV1_MRD_MAX_COMPAT (MLD_EXP_MIN_LIMIT - 1) +/* MLDv2 QQIC floating-point exponential field min threshold */ +#define MLD_QQIC_MIN_THRESHOLD 128 +/* MLDv2 QQIC FP max threshold (mant = 0xF, exp = 7) -> 31744 */ +#define MLD_QQIC_MAX_THRESHOLD 31744 +/* MLDv2 MRC floating-point exponential field min threshold */ +#define MLD_MRC_MIN_THRESHOLD 32768UL +/* MLDv2 MRC FP max threshold (mant = 0xFFF, exp = 7) -> 8387584 */ +#define MLD_MRC_MAX_THRESHOLD 8387584 +#define MLDV1_MRD_MAX_COMPAT (MLD_MRC_MIN_THRESHOLD - 1) #define MLD_MAX_QUEUE 8 #define MLD_MAX_SKBS 32 -static inline unsigned long mldv2_mrc(const struct mld2_query *mlh2) +/* V2 exponential field encoding */ + +/* + * Calculate Maximum Response Code from Maximum Response Delay + * + * MRC represents the 16-bit encoded form of Maximum Response Delay (MRD); + * once decoded, the resulting value is in milliseconds. + * + * RFC3810, 5.1.3. defines only the decoding formula: + * Maximum Response Delay = (mant | 0x1000) << (exp + 3) + * + * but does NOT define the encoding procedure. To derive exponent: + * + * For the 16-bit MRC, the "hidden bit" (0x1000) is left shifted by 12 to + * sit above the 12-bit mantissa. The RFC then shifts this entire block + * left by (exp + 3) to reconstruct the value. So, 'hidden bit' is the + * MSB which is shifted by (12 + exp + 3). + * + * Total left shift of the hidden bit = 12 + (exp + 3) = exp + 15. + * This is the MSB at the 0-based bit position: (exp + 15). + * Since fls() is 1-based, fls(value) - 1 = exp + 15. + * + * Therefore: + * exp = fls(value) - 16 + * mant = (value >> (exp + 3)) & 0x0FFF + * + * Final encoding formula: + * 0x8000 | (exp << 12) | mant + * + * Example (value = 1311744): + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 0 1 2 3 4 5 6 7 0 1 2 3 4 5 6 7 0 1 2 3 4 5 6 7 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |0 0 0 0 0 0 0 0 0 0 0 1 0 1 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0| 1311744 + * | ^-^--------mant---------^ ^...(exp+3)...^| exp=5 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Encoded: + * 0x8000 | (5 << 12) | 0x404 = 0xD404 + */ +static inline u16 mldv2_mrc(unsigned long mrd) +{ + u16 mc_man, mc_exp; + + /* MRC < 32768 is literal */ + if (mrd < MLD_MRC_MIN_THRESHOLD) + return mrd; + + /* Saturate at max representable (mant = 0xFFF, exp = 7) -> 8387584 */ + if (mrd >= MLD_MRC_MAX_THRESHOLD) + return 0xFFFF; + + mc_exp = fls(mrd) - 16; + mc_man = (mrd >> (mc_exp + 3)) & 0x0FFF; + + return 0x8000 | (mc_exp << 12) | mc_man; +} + +/* + * Calculate Querier's Query Interval Code from Querier's Query Interval + * + * QQIC represents the 8-bit encoded form of Querier's Query Interval (QQI); + * once decoded, the resulting value is in seconds. + * + * RFC3810, 5.1.9. defines only the decoding formula: + * QQI = (mant | 0x10) << (exp + 3) + * + * but does NOT define the encoding procedure. To derive exponent: + * + * For any value of mantissa and exponent, the decoding formula indicates + * that the "hidden bit" (0x10) is shifted 4 bits left to sit above the + * 4-bit mantissa. The RFC again shifts this entire block left by (exp + 3) + * to reconstruct the value. So, 'hidden bit' is the MSB which is shifted + * by (4 + exp + 3). + * + * Total left shift of the 'hidden bit' = 4 + (exp + 3) = exp + 7. + * This is the MSB at the 0-based bit position: (exp + 7). + * Since fls() is 1-based, fls(value) - 1 = exp + 7. + * + * Therefore: + * exp = fls(value) - 8 + * mant = (value >> (exp + 3)) & 0x0F + * + * Final encoding formula: + * 0x80 | (exp << 4) | mant + * + * Example (value = 3200): + * 0 1 + * 0 1 2 3 4 5 6 7 0 1 2 3 4 5 6 7 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |0 0 0 0 1 1 0 0 1 0 0 0 0 0 0 0| (value = 3200) + * | ^-^-mant^ ^..(exp+3)..^| exp = 4, mant = 9 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Encoded: + * 0x80 | (4 << 4) | 9 = 0xC9 + */ +static inline u8 mldv2_qqic(unsigned long value) +{ + u8 mc_man, mc_exp; + + /* QQIC < 128 is literal */ + if (value < MLD_QQIC_MIN_THRESHOLD) + return value; + + /* Saturate at max representable (mant = 0xF, exp = 7) -> 31744 */ + if (value >= MLD_QQIC_MAX_THRESHOLD) + return 0xFF; + + mc_exp = fls(value) - 8; + mc_man = (value >> (mc_exp + 3)) & 0x0F; + + return 0x80 | (mc_exp << 4) | mc_man; +} + +/* V2 exponential field decoding */ + +/* Calculate Maximum Response Delay from Maximum Response Code + * + * RFC3810, relevant sections: + * - 5.1.3. Maximum Response Code defines the decoding formula: + * 0 1 2 3 4 5 6 7 8 9 A B C D E F + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |1| exp | mant | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * Maximum Response Delay = (mant | 0x1000) << (exp+3) + * - 9.3. Query Response Interval + * + * After decode, MRC represents the Maximum Response Delay (MRD) in + * units of milliseconds. + */ +static inline unsigned long mldv2_mrd(const struct mld2_query *mlh2) { - /* RFC3810, 5.1.3. Maximum Response Code */ - unsigned long ret, mc_mrc = ntohs(mlh2->mld2q_mrc); + unsigned long mc_mrc = ntohs(mlh2->mld2q_mrc); - if (mc_mrc < MLD_EXP_MIN_LIMIT) { - ret = mc_mrc; + if (mc_mrc < MLD_MRC_MIN_THRESHOLD) { + return mc_mrc; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_MRC_EXP(mc_mrc); mc_man = MLDV2_MRC_MAN(mc_mrc); - ret = (mc_man | 0x1000) << (mc_exp + 3); + return (mc_man | 0x1000) << (mc_exp + 3); } +} - return ret; +/* Calculate Querier's Query Interval from Querier's Query Interval Code + * + * RFC3810, relevant sections: + * - 5.1.9. QQIC (Querier's Query Interval Code) defines the decoding formula: + * 0 1 2 3 4 5 6 7 + * +-+-+-+-+-+-+-+-+ + * |1| exp | mant | + * +-+-+-+-+-+-+-+-+ + * QQI = (mant | 0x10) << (exp + 3) + * - 9.2. Query Interval + * - 9.12. Older Version Querier Present Timeout + * (the [Query Interval] in the last Query received) + * + * After decode, QQIC represents the Querier's Query Interval in units + * of seconds. + */ +static inline unsigned long mldv2_qqi(const struct mld2_query *mlh2) +{ + unsigned long qqic = mlh2->mld2q_qqic; + + if (qqic < MLD_QQIC_MIN_THRESHOLD) { + return qqic; + } else { + unsigned long mc_man, mc_exp; + + mc_exp = MLDV2_QQIC_EXP(qqic); + mc_man = MLDV2_QQIC_MAN(qqic); + + return (mc_man | 0x10) << (mc_exp + 3); + } } #endif diff --git a/include/net/mptcp.h b/include/net/mptcp.h index f7263fe2a2e4..71b9fc5a5796 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -27,7 +27,9 @@ struct mptcp_ext { u32 subflow_seq; u16 data_len; __sum16 csum; - u8 use_map:1, + + struct_group(flags, + u8 use_map:1, dsn64:1, data_fin:1, use_ack:1, @@ -35,9 +37,10 @@ struct mptcp_ext { mpc_map:1, frozen:1, reset_transient:1; - u8 reset_reason:4, + u8 reset_reason:4, csum_reqd:1, infinite_map:1; + ); /* end of flags group */ }; #define MPTCPOPT_HMAC_LEN 20 @@ -69,7 +72,8 @@ struct mptcp_out_options { u8 reset_reason:4, reset_transient:1, csum_reqd:1, - allow_join_id0:1; + allow_join_id0:1, + drop_ts:1; union { struct { u64 sndr_key; @@ -149,9 +153,9 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, unsigned int *size, struct mptcp_out_options *opts); bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, struct mptcp_out_options *opts); -bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, - unsigned int *size, unsigned int remaining, - struct mptcp_out_options *opts); +int mptcp_established_options(struct sock *sk, struct sk_buff *skb, + unsigned int remaining, bool has_ts, + struct mptcp_out_options *opts); bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, @@ -266,15 +270,6 @@ static inline bool mptcp_synack_options(const struct request_sock *req, return false; } -static inline bool mptcp_established_options(struct sock *sk, - struct sk_buff *skb, - unsigned int *size, - unsigned int remaining, - struct mptcp_out_options *opts) -{ - return false; -} - static inline bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { diff --git a/include/net/ncsi.h b/include/net/ncsi.h index 08a50d9acb0a..e886358207aa 100644 --- a/include/net/ncsi.h +++ b/include/net/ncsi.h @@ -60,7 +60,7 @@ static inline int ncsi_start_dev(struct ncsi_dev *nd) return -ENOTTY; } -static void ncsi_stop_dev(struct ncsi_dev *nd) +static inline void ncsi_stop_dev(struct ncsi_dev *nd) { } diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 2dfee6d4258a..8860cc2175fc 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -489,11 +489,15 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) { - unsigned int seq, hh_alen; + unsigned int seq, hh_alen = HH_DATA_ALIGN(ETH_HLEN); + int err; + + err = skb_cow_head(skb, hh_alen); + if (err) + return err; do { seq = read_seqbegin(&hh->hh_lock); - hh_alen = HH_DATA_ALIGN(ETH_HLEN); memcpy(skb->data - hh_alen, hh->hh_data, ETH_ALEN + hh_alen - ETH_HLEN); } while (read_seqretry(&hh->hh_lock, seq)); return 0; diff --git a/include/net/net_shaper.h b/include/net/net_shaper.h index 5c3f49b52fe9..3939b816b001 100644 --- a/include/net/net_shaper.h +++ b/include/net/net_shaper.h @@ -53,6 +53,7 @@ struct net_shaper { /* private: */ u32 leaves; /* accounted only for NODE scope */ + bool valid; struct rcu_head rcu; }; diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h index 3d3aef80beac..9fb3e93857c3 100644 --- a/include/net/netdev_lock.h +++ b/include/net/netdev_lock.h @@ -64,7 +64,7 @@ static inline void netdev_unlock_full_to_ops(struct net_device *dev) netdev_unlock(dev); } -static inline void netdev_ops_assert_locked(const struct net_device *dev) +static inline void netdev_assert_locked_ops_compat(const struct net_device *dev) { if (netdev_need_ops_lock(dev)) lockdep_assert_held(&dev->lock); @@ -73,11 +73,17 @@ static inline void netdev_ops_assert_locked(const struct net_device *dev) } static inline void -netdev_ops_assert_locked_or_invisible(const struct net_device *dev) +netdev_assert_locked_ops_compat_or_invisible(const struct net_device *dev) { if (dev->reg_state == NETREG_REGISTERED || dev->reg_state == NETREG_UNREGISTERING) - netdev_ops_assert_locked(dev); + netdev_assert_locked_ops_compat(dev); +} + +static inline void netdev_assert_locked_ops(const struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_assert_locked(dev); } static inline void netdev_lock_ops_compat(struct net_device *dev) @@ -96,6 +102,14 @@ static inline void netdev_unlock_ops_compat(struct net_device *dev) rtnl_unlock(); } +/* Matching "ops protected" category from netdevice.h */ +static inline int netdev_is_locked_ops_compat(const struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + return lockdep_is_held(&dev->lock); + return lockdep_rtnl_is_held(); +} + static inline int netdev_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b) { @@ -132,6 +146,9 @@ static inline int netdev_lock_cmp_fn(const struct lockdep_map *a, #define netdev_lock_dereference(p, dev) \ rcu_dereference_protected(p, lockdep_is_held(&(dev)->lock)) +#define netdev_ops_lock_dereference(p, dev) \ + rcu_dereference_protected(p, netdev_is_locked_ops_compat(dev)) + int netdev_debug_event(struct notifier_block *nb, unsigned long event, void *ptr); diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h index b39417ad955e..0b07d5e69c15 100644 --- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h +++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h @@ -20,4 +20,8 @@ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp; extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre; #endif +#if IS_ENABLED(CONFIG_NF_CONNTRACK_PPTP) +void gre_pptp_destroy_siblings(struct nf_conn *ct); +#endif + #endif /*_NF_CONNTRACK_IPV4_H*/ diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index e9a8350e7ccf..c024345c9bd8 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -26,6 +26,7 @@ struct nf_conntrack_expect { possible_net_t net; /* We expect this tuple, with the following mask */ + struct nf_conntrack_tuple master_tuple; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_mask mask; @@ -45,14 +46,17 @@ struct nf_conntrack_expect { void (*expectfn)(struct nf_conn *new, struct nf_conntrack_expect *this); - /* Helper to assign to new connection */ + /* Helper that created this expectation */ struct nf_conntrack_helper __rcu *helper; + /* Helper to assign to new connection */ + struct nf_conntrack_helper __rcu *assign_helper; + /* The conntrack of the master connection */ struct nf_conn *master; - /* Timer function; deletes the expectation. */ - struct timer_list timeout; + /* jiffies32 when this expectation expires */ + u32 timeout; #if IS_ENABLED(CONFIG_NF_NAT) union nf_inet_addr saved_addr; @@ -66,6 +70,14 @@ struct nf_conntrack_expect { struct rcu_head rcu; }; +static inline bool nf_ct_exp_is_expired(const struct nf_conntrack_expect *exp) +{ + if (READ_ONCE(exp->flags) & NF_CT_EXPECT_DEAD) + return true; + + return (__s32)(READ_ONCE(exp->timeout) - nfct_time_stamp) <= 0; +} + static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp) { return read_pnet(&exp->net); @@ -127,7 +139,6 @@ static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) void nf_ct_remove_expectations(struct nf_conn *ct); void nf_ct_unexpect_related(struct nf_conntrack_expect *exp); -bool nf_ct_remove_expect(struct nf_conntrack_expect *exp); void nf_ct_expect_iterate_destroy(bool (*iter)(struct nf_conntrack_expect *e, void *data), void *data); void nf_ct_expect_iterate_net(struct net *net, @@ -150,5 +161,8 @@ static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect, return nf_ct_expect_related_report(expect, 0, 0, flags); } +struct nf_conn_help; +void nf_ct_expectation_gc(struct nf_conn_help *master_help); + #endif /*_NF_CONNTRACK_EXPECT_H*/ diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 0b247248b032..fd5c4dbf72ca 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -38,7 +38,6 @@ enum nf_ct_ext_id { struct nf_ct_ext { u8 offset[NF_CT_EXT_NUM]; u8 len; - unsigned int gen_id; char data[] __aligned(8); }; @@ -52,8 +51,6 @@ static inline bool nf_ct_ext_exist(const struct nf_conn *ct, u8 id) return (ct->ext && __nf_ct_ext_exist(ct->ext, id)); } -void *__nf_ct_ext_find(const struct nf_ct_ext *ext, u8 id); - static inline void *nf_ct_ext_find(const struct nf_conn *ct, u8 id) { struct nf_ct_ext *ext = ct->ext; @@ -61,19 +58,10 @@ static inline void *nf_ct_ext_find(const struct nf_conn *ct, u8 id) if (!ext || !__nf_ct_ext_exist(ext, id)) return NULL; - if (unlikely(ext->gen_id)) - return __nf_ct_ext_find(ext, id); - return (void *)ct->ext + ct->ext->offset[id]; } /* Add this type, returns pointer to data or NULL. */ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp); -/* ext genid. if ext->id != ext_genid, extensions cannot be used - * anymore unless conntrack has CONFIRMED bit set. - */ -extern atomic_t nf_conntrack_ext_genid; -void nf_ct_ext_bump_genid(void); - #endif /* _NF_CONNTRACK_EXTEND_H */ diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index de2f956abf34..c761cd8158b2 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -29,23 +29,28 @@ enum nf_ct_helper_flags { #define NF_CT_HELPER_NAME_LEN 16 +/* Must be kept in sync with the classes defined by helpers */ +#define NF_CT_MAX_EXPECT_CLASSES 4 + struct nf_conntrack_helper { struct hlist_node hnode; /* Internal use. */ + struct rcu_head rcu; + char name[NF_CT_HELPER_NAME_LEN]; /* name of the module */ - refcount_t refcnt; struct module *me; /* pointer to self */ - const struct nf_conntrack_expect_policy *expect_policy; + struct nf_conntrack_expect_policy expect_policy[NF_CT_MAX_EXPECT_CLASSES]; + + refcount_t ct_refcnt; /* Tuple of things we will help (compared against server response) */ struct nf_conntrack_tuple tuple; /* Function to call when data passes; return verdict, or -1 to invalidate. */ - int (*help)(struct sk_buff *skb, - unsigned int protoff, - struct nf_conn *ct, - enum ip_conntrack_info conntrackinfo); + int __rcu (*help)(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info conntrackinfo); void (*destroy)(struct nf_conn *ct); @@ -63,9 +68,6 @@ struct nf_conntrack_helper { char nat_mod_name[NF_CT_HELPER_NAME_LEN]; }; -/* Must be kept in sync with the classes defined by helpers */ -#define NF_CT_MAX_EXPECT_CLASSES 4 - /* nf_conn feature for connections that have a helper */ struct nf_conn_help { /* Helper. if any */ @@ -103,13 +105,19 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper, struct nf_conn *ct), struct module *module); -int nf_conntrack_helper_register(struct nf_conntrack_helper *); +int nf_conntrack_helper_register(struct nf_conntrack_helper *, struct nf_conntrack_helper **); +int __nf_conntrack_helper_register(struct nf_conntrack_helper *); void nf_conntrack_helper_unregister(struct nf_conntrack_helper *); -int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int); -void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *, +int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int, + struct nf_conntrack_helper **); +void nf_conntrack_helpers_unregister(struct nf_conntrack_helper **, unsigned int); +#define nf_conntrack_helper_deprecated(name) \ + pr_warn("The %s conntrack helper is scheduled for removal.\n" \ + "Please contact the netfilter-devel mailing list if you still need this.\n", name) + struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp); int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, @@ -132,10 +140,26 @@ static inline void *nfct_help_data(const struct nf_conn *ct) struct nf_conn_help *help; help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); + if (!help) + return NULL; return (void *)help->data; } +static inline void nf_ct_help_put(const struct nf_conn *ct) +{ + struct nf_conntrack_helper *helper; + struct nf_conn_help *help; + + help = nfct_help(ct); + if (!help) + return; + + helper = rcu_dereference(help->helper); + if (helper && refcount_dec_and_test(&helper->ct_refcnt)) + kfree_rcu(helper, rcu); +} + int nf_conntrack_helper_init(void); void nf_conntrack_helper_fini(void); @@ -155,6 +179,7 @@ void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct, void nf_ct_helper_expectfn_register(struct nf_ct_helper_expectfn *n); void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n); +void nf_ct_helper_expectfn_destroy(const struct nf_ct_helper_expectfn *n); struct nf_ct_helper_expectfn * nf_ct_helper_expectfn_find_by_name(const char *name); struct nf_ct_helper_expectfn * diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 3a66d4abb6d6..d60aa86be019 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -12,6 +12,7 @@ #define CTNL_TIMEOUT_NAME_MAX 32 struct nf_ct_timeout { + refcount_t refcnt; __u16 l3num; const struct nf_conntrack_l4proto *l4proto; struct rcu_head rcu; @@ -22,6 +23,22 @@ struct nf_conn_timeout { struct nf_ct_timeout __rcu *timeout; }; +static inline void nf_ct_timeout_put(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + struct nf_conn_timeout *timeout_ext; + struct nf_ct_timeout *timeout; + + timeout_ext = nf_ct_ext_find(ct, NF_CT_EXT_TIMEOUT); + if (!timeout_ext) + return; + + timeout = rcu_dereference(timeout_ext->timeout); + if (timeout && refcount_dec_and_test(&timeout->refcnt)) + kfree_rcu(timeout, rcu); +#endif +} + static inline unsigned int * nf_ct_timeout_data(const struct nf_conn_timeout *t) { @@ -56,8 +73,14 @@ struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct, #ifdef CONFIG_NF_CONNTRACK_TIMEOUT struct nf_conn_timeout *timeout_ext; + if (!timeout) + return NULL; + timeout_ext = nf_ct_ext_add(ct, NF_CT_EXT_TIMEOUT, gfp); - if (timeout_ext == NULL) + if (!timeout_ext || timeout_ext->timeout) + return NULL; + + if (!refcount_inc_not_zero(&timeout->refcnt)) return NULL; rcu_assign_pointer(timeout_ext->timeout, timeout); @@ -75,7 +98,7 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct) struct nf_conn_timeout *timeout_ext; timeout_ext = nf_ct_timeout_find(ct); - if (timeout_ext) + if (timeout_ext && rcu_access_pointer(timeout_ext->timeout)) timeouts = nf_ct_timeout_data(timeout_ext); #endif return timeouts; diff --git a/include/net/netfilter/nf_dup_netdev.h b/include/net/netfilter/nf_dup_netdev.h index b175d271aec9..f6b05bd80c3f 100644 --- a/include/net/netfilter/nf_dup_netdev.h +++ b/include/net/netfilter/nf_dup_netdev.h @@ -3,10 +3,47 @@ #define _NF_DUP_NETDEV_H_ #include <net/netfilter/nf_tables.h> +#include <linux/netdevice.h> +#include <linux/sched.h> void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif); void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif); +#define NF_RECURSION_LIMIT 2 + +#ifndef CONFIG_PREEMPT_RT +static inline bool nf_dev_xmit_recursion(void) +{ + return unlikely(__this_cpu_read(softnet_data.xmit.nf_dup_skb_recursion) > + NF_RECURSION_LIMIT); +} + +static inline void nf_dev_xmit_recursion_inc(void) +{ + __this_cpu_inc(softnet_data.xmit.nf_dup_skb_recursion); +} + +static inline void nf_dev_xmit_recursion_dec(void) +{ + __this_cpu_dec(softnet_data.xmit.nf_dup_skb_recursion); +} +#else +static inline bool nf_dev_xmit_recursion(void) +{ + return unlikely(current->net_xmit.nf_dup_skb_recursion > NF_RECURSION_LIMIT); +} + +static inline void nf_dev_xmit_recursion_inc(void) +{ + current->net_xmit.nf_dup_skb_recursion++; +} + +static inline void nf_dev_xmit_recursion_dec(void) +{ + current->net_xmit.nf_dup_skb_recursion--; +} +#endif + struct nft_offload_ctx; struct nft_flow_rule; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index b09c11c048d5..ce414118962f 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -148,17 +148,19 @@ struct flow_offload_tuple { /* All members above are keys for lookups, see flow_offload_hash(). */ struct { } __hash; - u8 dir:2, + u16 dir:2, xmit_type:3, encap_num:2, + needs_gso_segment:1, tun_num:2, in_vlan_ingress:2; u16 mtu; + u32 dst_cookie; + struct dst_entry *dst_cache; + union { struct { - struct dst_entry *dst_cache; u32 ifidx; - u32 dst_cookie; }; struct { u32 ifidx; @@ -232,6 +234,7 @@ struct nf_flow_route { u32 hw_ifindex; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; + u8 needs_gso_segment:1; } out; enum flow_offload_xmit_type xmit_type; } tuple[FLOW_OFFLOAD_DIR_MAX]; @@ -355,6 +358,8 @@ static inline int nf_flow_register_bpf(void) void nf_flow_offload_add(struct nf_flowtable *flowtable, struct flow_offload *flow); +void nf_flow_offload_refresh(struct nf_flowtable *flowtable, + struct flow_offload *flow); void nf_flow_offload_del(struct nf_flowtable *flowtable, struct flow_offload *flow); void nf_flow_offload_stats(struct nf_flowtable *flowtable, diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index d17035d14d96..fc3e81c07364 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -14,9 +14,11 @@ struct nf_queue_entry { struct list_head list; struct rhash_head hash_node; struct sk_buff *skb; + struct net_device *skb_dev; unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + struct net_device *bridge_dev; struct net_device *physin; struct net_device *physout; #endif diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index cff7b773e972..9d844354c4d9 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -180,6 +180,13 @@ static inline u64 nft_reg_load64(const u32 *sreg) return get_unaligned((u64 *)sreg); } +static inline bool nft_reg_overlap(u8 src, u8 dst, u32 len) +{ + unsigned int n = DIV_ROUND_UP(len, sizeof(u32)); + + return src != dst && src < dst + n && dst < src + n; +} + static inline void nft_data_copy(u32 *dst, const struct nft_data *src, unsigned int len) { diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index f74e63290603..6cf1d910bbf8 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -40,6 +40,8 @@ void nft_meta_set_eval(const struct nft_expr *expr, void nft_meta_set_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr); +int nft_meta_get_validate(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); diff --git a/include/net/netlink.h b/include/net/netlink.h index 546d10586576..b5048dd1d511 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -2260,7 +2260,10 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) */ static inline int nla_nest_end(struct sk_buff *skb, struct nlattr *start) { - start->nla_len = skb_tail_pointer(skb) - (unsigned char *)start; + unsigned long diff = skb_tail_pointer(skb) - (unsigned char *)start; + + DEBUG_NET_WARN_ON_ONCE(diff > U16_MAX); + start->nla_len = diff; return skb->len; } diff --git a/include/net/netmem.h b/include/net/netmem.h index 78fe51e5756b..bccacd21b6c3 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -94,20 +94,10 @@ enum net_iov_type { */ struct net_iov { struct netmem_desc desc; - unsigned int page_type; enum net_iov_type type; struct net_iov_area *owner; }; -/* Make sure 'the offset of page_type in struct page == the offset of - * type in struct net_iov'. - */ -#define NET_IOV_ASSERT_OFFSET(pg, iov) \ - static_assert(offsetof(struct page, pg) == \ - offsetof(struct net_iov, iov)) -NET_IOV_ASSERT_OFFSET(page_type, page_type); -#undef NET_IOV_ASSERT_OFFSET - struct net_iov_area { /* Array of net_iovs for this area. */ struct net_iov *niovs; @@ -127,11 +117,7 @@ static inline unsigned int net_iov_idx(const struct net_iov *niov) return niov - net_iov_owner(niov)->niovs; } -/* Initialize a niov: stamp the owning area, the memory provider type, - * and the page_type "no type" sentinel expected by the page-type API - * (see PAGE_TYPE_OPS in <linux/page-flags.h>) so that - * page_pool_set_pp_info() can later call __SetPageNetpp() on a niov - * cast to struct page. +/* Initialize a niov: stamp the owning area, the memory provider type. */ static inline void net_iov_init(struct net_iov *niov, struct net_iov_area *owner, @@ -139,7 +125,6 @@ static inline void net_iov_init(struct net_iov *niov, { niov->owner = owner; niov->type = type; - niov->page_type = UINT_MAX; } /* netmem */ @@ -245,7 +230,7 @@ static inline unsigned long netmem_pfn_trace(netmem_ref netmem) */ #define pp_page_to_nmdesc(p) \ ({ \ - DEBUG_NET_WARN_ON_ONCE(!PageNetpp(p)); \ + DEBUG_NET_WARN_ON_ONCE(!page_pool_page_is_pp(p)); \ __pp_page_to_nmdesc(p); \ }) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 80ccd4dda8e0..6e27c56514df 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -275,7 +275,7 @@ struct netns_ipv4 { #ifdef CONFIG_IP_MROUTE #ifndef CONFIG_IP_MROUTE_MULTIPLE_TABLES - struct mr_table *mrt; + struct mr_table __rcu *mrt; #else struct list_head mr_tables; struct fib_rules_ops *mr_rules_ops; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 499e4288170f..ffda15318be5 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -112,13 +112,15 @@ struct netns_ipv6 { struct list_head mr6_tables; struct fib_rules_ops *mr6_rules_ops; #endif + struct fib_notifier_ops *ip6mr_notifier_ops; + atomic_t ipmr_seq; + struct mutex mfc_mutex; #endif atomic_t dev_addr_genid; atomic_t fib6_sernum; struct seg6_pernet_data *seg6_data; struct fib_notifier_ops *notifier_ops; - struct fib_notifier_ops *ip6mr_notifier_ops; - atomic_t ipmr_seq; + int flowlabel_count; struct { struct hlist_head head; spinlock_t lock; diff --git a/include/net/nsh.h b/include/net/nsh.h index 16a751093896..15a26c590815 100644 --- a/include/net/nsh.h +++ b/include/net/nsh.h @@ -247,10 +247,10 @@ struct nshhdr { #define NSH_M_TYPE1_LEN 24 /* NSH header maximum Length. */ -#define NSH_HDR_MAX_LEN 256 +#define NSH_HDR_MAX_LEN ((NSH_LEN_MASK >> NSH_LEN_SHIFT) * 4) /* NSH context headers maximum Length. */ -#define NSH_CTX_HDRS_MAX_LEN 248 +#define NSH_CTX_HDRS_MAX_LEN (NSH_HDR_MAX_LEN - NSH_BASE_HDR_LEN) static inline struct nshhdr *nsh_hdr(struct sk_buff *skb) { diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 3247026e096a..e2730dd273b2 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -64,7 +64,7 @@ int page_pool_ethtool_stats_get_count(void); u8 *page_pool_ethtool_stats_get_strings(u8 *data); u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats); -bool page_pool_get_stats(const struct page_pool *pool, +void page_pool_get_stats(const struct page_pool *pool, struct page_pool_stats *stats); #else static inline int page_pool_ethtool_stats_get_count(void) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 99ac747b7906..5f5cb36439fe 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -156,8 +156,20 @@ static inline int tcf_classify(struct sk_buff *skb, { return TC_ACT_UNSPEC; } - #endif +static inline int tcf_classify_qdisc(struct sk_buff *skb, + const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ + int ret = tcf_classify(skb, NULL, tp, res, compat_mode); + + /* TC_ACT_REDIRECT from qdisc filter chains is not supported. + * Use BPF via tcx or mirred redirect instead. + */ + if (unlikely(ret == TC_ACT_REDIRECT)) + ret = TC_ACT_SHOT; + return ret; +} static inline unsigned long __cls_set_class(unsigned long *clp, unsigned long cl) @@ -1046,6 +1058,7 @@ struct tc_tbf_qopt_offload_replace_params { }; struct tc_tbf_qopt_offload { + struct netlink_ext_ack *extack; enum tc_tbf_command command; u32 handle; u32 parent; diff --git a/include/net/psp/types.h b/include/net/psp/types.h index 25a9096d4e7d..87991a1ea02d 100644 --- a/include/net/psp/types.h +++ b/include/net/psp/types.h @@ -5,6 +5,7 @@ #include <linux/mutex.h> #include <linux/refcount.h> +#include <net/net_trackers.h> struct netlink_ext_ack; @@ -43,9 +44,29 @@ struct psp_dev_config { u32 versions; }; +/* Max number of devices that can be associated with a single PSP device. + * Each entry consumes ~24 bytes in the netlink dev-get response, and the + * response must fit in GENLMSG_DEFAULT_SIZE (~3.7KB). + */ +#define PSP_ASSOC_DEV_MAX 128 + +/** + * struct psp_assoc_dev - wrapper for associated net_device + * @dev_list: list node for psp_dev::assoc_dev_list + * @assoc_dev: the associated net_device + * @dev_tracker: tracker for the net_device reference + */ +struct psp_assoc_dev { + struct list_head dev_list; + struct net_device *assoc_dev; + netdevice_tracker dev_tracker; +}; + /** * struct psp_dev - PSP device struct * @main_netdev: original netdevice of this PSP device + * @assoc_dev_list: list of psp_assoc_dev entries associated with this PSP device + * @assoc_dev_cnt: number of entries in @assoc_dev_list * @ops: driver callbacks * @caps: device capabilities * @drv_priv: driver priv pointer @@ -67,6 +88,8 @@ struct psp_dev_config { */ struct psp_dev { struct net_device *main_netdev; + struct list_head assoc_dev_list; + int assoc_dev_cnt; struct psp_dev_ops *ops; struct psp_dev_caps *caps; diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index ec65a8cebb99..2bff41aacc98 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -256,6 +256,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm, int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, struct netlink_ext_ack *exterr); struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid); +bool rtnl_dev_link_net_capable(const struct net_device *dev, + const struct net *link_net); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 11159a50d6a1..45a1e8c78222 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -86,7 +86,7 @@ struct Qdisc { #define TCQ_F_WARN_NONWC (1 << 16) #define TCQ_F_CPUSTATS 0x20 /* run using percpu statistics */ #define TCQ_F_NOPARENT 0x40 /* root of its hierarchy : - * qdisc_tree_decrease_qlen() should stop. + * qdisc_tree_reduce_backlog() should stop. */ #define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */ #define TCQ_F_NOLOCK 0x100 /* qdisc does not require locking */ @@ -542,6 +542,21 @@ static inline int qdisc_qlen(const struct Qdisc *q) return q->q.qlen; } +static inline int qdisc_qlen_lockless(const struct Qdisc *q) +{ + return READ_ONCE(q->q.qlen); +} + +static inline void qdisc_qlen_inc(struct Qdisc *q) +{ + WRITE_ONCE(q->q.qlen, q->q.qlen + 1); +} + +static inline void qdisc_qlen_dec(struct Qdisc *q) +{ + WRITE_ONCE(q->q.qlen, q->q.qlen - 1); +} + static inline int qdisc_qlen_sum(const struct Qdisc *q) { __u32 qlen = q->qstats.qlen; @@ -549,9 +564,9 @@ static inline int qdisc_qlen_sum(const struct Qdisc *q) if (qdisc_is_percpu_stats(q)) { for_each_possible_cpu(i) - qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen; + qlen += READ_ONCE(per_cpu_ptr(q->cpu_qstats, i)->qlen); } else { - qlen += q->q.qlen; + qlen += qdisc_qlen_lockless(q); } return qlen; @@ -937,6 +952,15 @@ static inline void _bstats_update(struct gnet_stats_basic_sync *bstats, u64_stats_update_end(&bstats->syncp); } +static inline void _bstats_set(struct gnet_stats_basic_sync *bstats, + u64 bytes, u64 packets) +{ + u64_stats_update_begin(&bstats->syncp); + u64_stats_set(&bstats->bytes, bytes); + u64_stats_set(&bstats->packets, packets); + u64_stats_update_end(&bstats->syncp); +} + static inline void bstats_update(struct gnet_stats_basic_sync *bstats, const struct sk_buff *skb) { @@ -955,10 +979,15 @@ static inline void qdisc_bstats_update(struct Qdisc *sch, bstats_update(&sch->bstats, skb); } +static inline void qstats_backlog_sub(struct Qdisc *sch, u32 val) +{ + WRITE_ONCE(sch->qstats.backlog, sch->qstats.backlog - val); +} + static inline void qdisc_qstats_backlog_dec(struct Qdisc *sch, const struct sk_buff *skb) { - sch->qstats.backlog -= qdisc_pkt_len(skb); + qstats_backlog_sub(sch, qdisc_pkt_len(skb)); } static inline void qdisc_qstats_cpu_backlog_dec(struct Qdisc *sch, @@ -967,10 +996,15 @@ static inline void qdisc_qstats_cpu_backlog_dec(struct Qdisc *sch, this_cpu_sub(sch->cpu_qstats->backlog, qdisc_pkt_len(skb)); } +static inline void qstats_backlog_add(struct Qdisc *sch, u32 val) +{ + WRITE_ONCE(sch->qstats.backlog, sch->qstats.backlog + val); +} + static inline void qdisc_qstats_backlog_inc(struct Qdisc *sch, const struct sk_buff *skb) { - sch->qstats.backlog += qdisc_pkt_len(skb); + qstats_backlog_add(sch, qdisc_pkt_len(skb)); } static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch, @@ -996,17 +1030,22 @@ static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch) static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count) { - sch->qstats.drops += count; + WRITE_ONCE(sch->qstats.drops, sch->qstats.drops + count); } static inline void qstats_drop_inc(struct gnet_stats_queue *qstats) { - qstats->drops++; + WRITE_ONCE(qstats->drops, qstats->drops + 1); +} + +static inline void qstats_cpu_drop_inc(struct gnet_stats_queue __percpu *qstats) +{ + this_cpu_inc(qstats->drops); } -static inline void qstats_overlimit_inc(struct gnet_stats_queue *qstats) +static inline void qstats_cpu_overlimit_inc(struct gnet_stats_queue __percpu *qstats) { - qstats->overlimits++; + this_cpu_inc(qstats->overlimits); } static inline void qdisc_qstats_drop(struct Qdisc *sch) @@ -1021,23 +1060,23 @@ static inline void qdisc_qstats_cpu_drop(struct Qdisc *sch) static inline void qdisc_qstats_overlimit(struct Qdisc *sch) { - sch->qstats.overlimits++; + WRITE_ONCE(sch->qstats.overlimits, sch->qstats.overlimits + 1); } -static inline int qdisc_qstats_copy(struct gnet_dump *d, struct Qdisc *sch) +static inline int qdisc_qstats_copy(struct gnet_dump *d, const struct Qdisc *sch) { __u32 qlen = qdisc_qlen_sum(sch); return gnet_stats_copy_queue(d, sch->cpu_qstats, &sch->qstats, qlen); } -static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen, - __u32 *backlog) +static inline void qdisc_qstats_qlen_backlog(const struct Qdisc *sch, + u32 *qlen, u32 *backlog) { struct gnet_stats_queue qstats = { 0 }; gnet_stats_add_queue(&qstats, sch->cpu_qstats, &sch->qstats); - *qlen = qstats.qlen + qdisc_qlen(sch); + *qlen = qstats.qlen + qdisc_qlen_lockless(sch); *backlog = qstats.backlog; } @@ -1063,7 +1102,7 @@ static inline void __qdisc_enqueue_tail(struct sk_buff *skb, qh->tail = skb; qh->head = skb; } - qh->qlen++; + WRITE_ONCE(qh->qlen, qh->qlen + 1); } static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) @@ -1081,7 +1120,7 @@ static inline void __qdisc_enqueue_head(struct sk_buff *skb, if (!qh->head) qh->tail = skb; qh->head = skb; - qh->qlen++; + WRITE_ONCE(qh->qlen, qh->qlen + 1); } static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) @@ -1090,7 +1129,7 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) if (likely(skb != NULL)) { qh->head = skb->next; - qh->qlen--; + WRITE_ONCE(qh->qlen, qh->qlen - 1); if (qh->head == NULL) qh->tail = NULL; skb->next = NULL; @@ -1105,7 +1144,7 @@ static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool dir skb = __skb_dequeue(&sch->gso_skb); if (skb) { - sch->q.qlen--; + qdisc_qlen_dec(sch); qdisc_qstats_backlog_dec(sch, skb); return skb; } @@ -1261,7 +1300,7 @@ static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch) __skb_queue_head(&sch->gso_skb, skb); /* it's still part of the queue */ qdisc_qstats_backlog_inc(sch, skb); - sch->q.qlen++; + qdisc_qlen_inc(sch); } } @@ -1278,7 +1317,7 @@ static inline void qdisc_update_stats_at_dequeue(struct Qdisc *sch, } else { qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); - sch->q.qlen--; + qdisc_qlen_dec(sch); } } @@ -1289,8 +1328,8 @@ static inline void qdisc_update_stats_at_enqueue(struct Qdisc *sch, qdisc_qstats_cpu_qlen_inc(sch); this_cpu_add(sch->cpu_qstats->backlog, pkt_len); } else { - sch->qstats.backlog += pkt_len; - sch->q.qlen++; + qstats_backlog_add(sch, pkt_len); + qdisc_qlen_inc(sch); } } @@ -1306,7 +1345,7 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch) qdisc_qstats_cpu_qlen_dec(sch); } else { qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; + qdisc_qlen_dec(sch); } } else { skb = sch->dequeue(sch); @@ -1327,7 +1366,7 @@ static inline void __qdisc_reset_queue(struct qdisc_skb_head *qh) qh->head = NULL; qh->tail = NULL; - qh->qlen = 0; + WRITE_ONCE(qh->qlen, 0); } } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 58242b37b47a..d50c27812504 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -111,7 +111,8 @@ int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net, const union sctp_addr *paddr, void *p, int dif); int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done, struct net *net, int *pos, void *p); -int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p); +int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), + struct net *net, int *pos, void *p); int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, struct sctp_info *info); @@ -303,7 +304,7 @@ void sctp_dbg_objcnt_init(struct net *); static inline void sctp_dbg_objcnt_init(struct net *net) { return; } -#endif /* CONFIG_SCTP_DBG_OBJCOUNT */ +#endif /* CONFIG_SCTP_DBG_OBJCNT */ #if defined CONFIG_SYSCTL void sctp_sysctl_register(void); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index affee44bd38e..cccc662561aa 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -312,7 +312,8 @@ struct sctp_cookie { __u8 auth_random[sizeof(struct sctp_paramhdr) + SCTP_AUTH_RANDOM_LENGTH]; - __u8 auth_hmacs[SCTP_AUTH_NUM_HMACS * sizeof(__u16) + 2]; + __u8 auth_hmacs[sizeof(struct sctp_paramhdr) + + SCTP_AUTH_NUM_HMACS * sizeof(__u16)]; __u8 auth_chunks[sizeof(struct sctp_paramhdr) + SCTP_AUTH_MAX_CHUNKS]; /* This is a shim for my peer's INIT packet, followed by diff --git a/include/net/smc.h b/include/net/smc.h index bfdc4c41f019..a2bc3ab88075 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -40,7 +40,6 @@ struct smcd_dev { struct dibs_dev *dibs; struct list_head list; spinlock_t lock; - struct smc_connection **conn; struct list_head vlan; struct workqueue_struct *event_wq; u8 pnetid[SMC_MAX_PNETID_LEN]; @@ -50,6 +49,7 @@ struct smcd_dev { atomic_t lgr_cnt; wait_queue_head_t lgrs_deleted; u8 going_away : 1; + struct smc_connection *conn[]; }; #define SMC_HS_CTRL_NAME_MAX 16 diff --git a/include/net/sock.h b/include/net/sock.h index dccd3738c368..51185222aac2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1850,12 +1850,22 @@ static inline struct sock *sk_clone_lock(const struct sock *sk, const gfp_t prio struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); -void __sock_wfree(struct sk_buff *skb); void sock_wfree(struct sk_buff *skb); +void __sock_wfree(struct sk_buff *skb); +void tcp_wfree(struct sk_buff *skb); + +static inline bool is_skb_wmem(const struct sk_buff *skb) +{ + return skb->destructor == sock_wfree || + (IS_ENABLED(CONFIG_INET) && skb->destructor == __sock_wfree) || + (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree); +} + struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority); void skb_orphan_partial(struct sk_buff *skb); void sock_rfree(struct sk_buff *skb); +void sock_rmem_free(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); @@ -2252,6 +2262,20 @@ sk_dst_reset(struct sock *sk) sk_dst_set(sk, NULL); } +/* Re-roll the socket txhash. On a rehash, IPv6 also drops the cached route + * so the next transmit re-selects an ECMP path; IPv4 keeps its route, since + * IPv4 ECMP path selection does not use sk_txhash. + */ +static inline bool __sk_rethink_txhash_reset_dst(struct sock *sk) +{ + if (sk_rethink_txhash(sk)) { + if (sk->sk_family == AF_INET6) + __sk_dst_reset(sk); + return true; + } + return false; +} + struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index f58ee15cd858..97754ea0a827 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -15,7 +15,6 @@ struct tcf_pedit_parms { struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; int action; - u32 tcfp_off_max_hint; unsigned char tcfp_nkeys; unsigned char tcfp_flags; struct rcu_head rcu; @@ -38,17 +37,15 @@ static inline bool is_tcf_pedit(const struct tc_action *a) return false; } -static inline int tcf_pedit_nkeys(const struct tc_action *a) +/* Must be called with act->tcfa_lock held to ensure consistency of parallel + * reads of the same action's pedit keys (e.g. flow_offload count vs fill). + * Note, this is only used for pedit offload. + */ +static inline int tcf_pedit_nkeys_locked(const struct tc_action *a) { - struct tcf_pedit_parms *parms; - int nkeys; - - rcu_read_lock(); - parms = to_pedit_parms(a); - nkeys = parms->tcfp_nkeys; - rcu_read_unlock(); - - return nkeys; + lockdep_assert_held(&a->tcfa_lock); + return rcu_dereference_protected(to_pedit(a)->parms, + lockdep_is_held(&a->tcfa_lock))->tcfp_nkeys; } static inline u32 tcf_pedit_htype(const struct tc_action *a, int index) diff --git a/include/net/tcp.h b/include/net/tcp.h index ecbadcb3a744..2c5b889530b5 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -65,8 +65,6 @@ static inline void tcp_orphan_count_dec(void) this_cpu_dec(tcp_orphan_count); } -DECLARE_PER_CPU(u32, tcp_tw_isn); - void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) @@ -390,7 +388,6 @@ static inline bool tcp_release_cb_cond(struct sock *sk) return false; } -void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, int *karg); @@ -1015,6 +1012,16 @@ static inline u32 tcp_time_stamp_ts(const struct tcp_sock *tp) return tcp_time_stamp_ms(tp); } +/* Refresh clocks of a TCP socket, + * ensuring monotically increasing values. + */ +static inline void tcp_mstamp_refresh_inline(struct tcp_sock *tp) +{ + u64 val = tcp_clock_ns(); + + tp->tcp_clock_cache = val; + tp->tcp_mstamp = div_u64(val, NSEC_PER_USEC); +} void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) @@ -1102,10 +1109,13 @@ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { - /* Note : + /* Notes : + * tcp_tw_isn is used in input path only + * (isn chosen by tcp_timewait_state_process()) * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ + u32 tcp_tw_isn; struct { u16 tcp_gso_segs; u16 tcp_gso_size; @@ -1964,6 +1974,8 @@ static inline void tcp_fast_path_check(struct sock *sk) bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, int mib_idx, u32 *last_oow_ack_time); +void tcp_reqsk_send_challenge_ack(struct sock *sk, struct sk_buff *skb, + struct request_sock *req); static inline void tcp_mib_init(struct net *net) { @@ -2017,40 +2029,6 @@ struct tcp6_pseudohdr { __be32 protocol; /* including padding */ }; -/* - * struct tcp_sigpool - per-CPU pool of ahash_requests - * @scratch: per-CPU temporary area, that can be used between - * tcp_sigpool_start() and tcp_sigpool_end() to perform - * crypto request - * @req: pre-allocated ahash request - */ -struct tcp_sigpool { - void *scratch; - struct ahash_request *req; -}; - -int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size); -void tcp_sigpool_get(unsigned int id); -void tcp_sigpool_release(unsigned int id); -int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp, - const struct sk_buff *skb, - unsigned int header_len); - -/** - * tcp_sigpool_start - disable bh and start using tcp_sigpool_ahash - * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() - * @c: returned tcp_sigpool for usage (uninitialized on failure) - * - * Returns: 0 on success, error otherwise. - */ -int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c); -/** - * tcp_sigpool_end - enable bh and stop using tcp_sigpool - * @c: tcp_sigpool context that was returned by tcp_sigpool_start() - */ -void tcp_sigpool_end(struct tcp_sigpool *c); -size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len); -/* - functions */ void tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, @@ -2510,9 +2488,9 @@ struct tcp_sock_af_ops { struct tcp_ao_key *(*ao_lookup)(const struct sock *sk, struct sock *addr_sk, int sndid, int rcvid); - int (*ao_calc_key_sk)(struct tcp_ao_key *mkt, u8 *key, - const struct sock *sk, - __be32 sisn, __be32 disn, bool send); + void (*ao_calc_key_sk)(struct tcp_ao_key *mkt, u8 *key, + const struct sock *sk, + __be32 sisn, __be32 disn, bool send); int (*calc_ao_hash)(char *location, struct tcp_ao_key *ao, const struct sock *sk, const struct sk_buff *skb, const u8 *tkey, int hash_offset, u32 sne); @@ -2533,7 +2511,7 @@ struct tcp_request_sock_ops { struct tcp_ao_key *(*ao_lookup)(const struct sock *sk, struct request_sock *req, int sndid, int rcvid); - int (*ao_calc_key)(struct tcp_ao_key *mkt, u8 *key, struct request_sock *sk); + void (*ao_calc_key)(struct tcp_ao_key *mkt, u8 *key, struct request_sock *sk); int (*ao_synack_hash)(char *ao_hash, struct tcp_ao_key *mkt, struct request_sock *req, const struct sk_buff *skb, int hash_offset, u32 sne); @@ -2564,22 +2542,30 @@ extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops; #ifdef CONFIG_SYN_COOKIES static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, - const struct sock *sk, struct sk_buff *skb, - __u16 *mss) + struct sk_buff *skb, __u16 *mss) { - tcp_synq_overflow(sk); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); return ops->cookie_init_seq(skb, mss); } #else static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, - const struct sock *sk, struct sk_buff *skb, - __u16 *mss) + struct sk_buff *skb, __u16 *mss) { return 0; } #endif +#ifdef CONFIG_SYN_COOKIES +static inline void cookie_record_sent(const struct sock *sk) +{ + tcp_synq_overflow(sk); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); +} +#else +static inline void cookie_record_sent(const struct sock *sk) +{ +} +#endif + struct tcp_key { union { struct { @@ -2941,6 +2927,11 @@ static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, return tcp_call_bpf(sk, op, 3, args); } +static inline void tcp_clear_sock_ops_cb_flags(struct sock *sk) +{ + tcp_sk(sk)->bpf_sock_ops_cb_flags = 0; +} + #else static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { @@ -2958,6 +2949,10 @@ static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, return -EPERM; } +static inline void tcp_clear_sock_ops_cb_flags(struct sock *sk) +{ +} + #endif static inline u32 tcp_timeout_init(struct sock *sk) diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 1e9e27d6e06b..9a2333e62e99 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -2,8 +2,7 @@ #ifndef _TCP_AO_H #define _TCP_AO_H -#define TCP_AO_KEY_ALIGN 1 -#define __tcp_ao_key_align __aligned(TCP_AO_KEY_ALIGN) +#include <crypto/sha2.h> /* for SHA256_DIGEST_SIZE */ union tcp_ao_addr { struct in_addr a4; @@ -32,11 +31,27 @@ struct tcp_ao_counters { atomic64_t dropped_icmp; }; +enum tcp_ao_algo_id { + TCP_AO_ALGO_HMAC_SHA1 = 1, /* specified by RFC 5926 */ + TCP_AO_ALGO_HMAC_SHA256, /* Linux extension */ + TCP_AO_ALGO_AES_128_CMAC, /* specified by RFC 5926 */ +}; + +/* + * This is the maximum untruncated MAC length, in bytes. Note that the MACs + * actually get truncated to 20 or fewer bytes to fit in the TCP options space. + */ +#define TCP_AO_MAX_MAC_LEN SHA256_DIGEST_SIZE + +#define TCP_AO_MAX_TRAFFIC_KEY_LEN SHA256_DIGEST_SIZE + +struct tcp_ao_mac_ctx; + struct tcp_ao_key { struct hlist_node node; union tcp_ao_addr addr; - u8 key[TCP_AO_MAXKEYLEN] __tcp_ao_key_align; - unsigned int tcp_sigpool_id; + u8 key[TCP_AO_MAXKEYLEN]; + enum tcp_ao_algo_id algo; unsigned int digest_size; int l3index; u8 prefixlen; @@ -130,6 +145,7 @@ struct tcp_ao_info { u32 snd_sne; u32 rcv_sne; refcount_t refcnt; /* Protects twsk destruction */ + struct rcu_head rcu; }; #ifdef CONFIG_TCP_MD5SIG @@ -168,14 +184,15 @@ struct tcp6_ao_context { __be32 disn; }; -struct tcp_sigpool; /* Established states are fast-path and there always is current_key/rnext_key */ #define TCP_AO_ESTABLISHED (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | \ TCPF_CLOSE_WAIT | TCPF_LAST_ACK | TCPF_CLOSING) -int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, - struct tcp_ao_key *key, struct tcphdr *th, - __u8 *hash_location); +void tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, + struct tcp_ao_key *key, struct tcphdr *th, + __u8 *hash_location); +void tcp_ao_mac_update(struct tcp_ao_mac_ctx *mac_ctx, const void *data, + size_t data_len); int tcp_ao_hash_skb(unsigned short int family, char *ao_hash, struct tcp_ao_key *key, const struct sock *sk, const struct sk_buff *skb, @@ -188,8 +205,8 @@ struct tcp_ao_key *tcp_ao_established_key(const struct sock *sk, int tcp_ao_copy_all_matching(const struct sock *sk, struct sock *newsk, struct request_sock *req, struct sk_buff *skb, int family); -int tcp_ao_calc_traffic_key(struct tcp_ao_key *mkt, u8 *key, void *ctx, - unsigned int len, struct tcp_sigpool *hp); +void tcp_ao_calc_traffic_key(const struct tcp_ao_key *mkt, u8 *traffic_key, + const void *input, unsigned int input_len); void tcp_ao_destroy_sock(struct sock *sk, bool twsk); void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp); bool tcp_ao_ignore_icmp(const struct sock *sk, int family, int type, int code); @@ -222,11 +239,11 @@ struct tcp_ao_key *tcp_v4_ao_lookup(const struct sock *sk, struct sock *addr_sk, int tcp_v4_ao_synack_hash(char *ao_hash, struct tcp_ao_key *mkt, struct request_sock *req, const struct sk_buff *skb, int hash_offset, u32 sne); -int tcp_v4_ao_calc_key_sk(struct tcp_ao_key *mkt, u8 *key, - const struct sock *sk, - __be32 sisn, __be32 disn, bool send); -int tcp_v4_ao_calc_key_rsk(struct tcp_ao_key *mkt, u8 *key, - struct request_sock *req); +void tcp_v4_ao_calc_key_sk(struct tcp_ao_key *mkt, u8 *key, + const struct sock *sk, + __be32 sisn, __be32 disn, bool send); +void tcp_v4_ao_calc_key_rsk(struct tcp_ao_key *mkt, u8 *key, + struct request_sock *req); struct tcp_ao_key *tcp_v4_ao_lookup_rsk(const struct sock *sk, struct request_sock *req, int sndid, int rcvid); @@ -234,16 +251,17 @@ int tcp_v4_ao_hash_skb(char *ao_hash, struct tcp_ao_key *key, const struct sock *sk, const struct sk_buff *skb, const u8 *tkey, int hash_offset, u32 sne); /* ipv6 specific functions */ -int tcp_v6_ao_hash_pseudoheader(struct tcp_sigpool *hp, - const struct in6_addr *daddr, - const struct in6_addr *saddr, int nbytes); -int tcp_v6_ao_calc_key_skb(struct tcp_ao_key *mkt, u8 *key, - const struct sk_buff *skb, __be32 sisn, __be32 disn); -int tcp_v6_ao_calc_key_sk(struct tcp_ao_key *mkt, u8 *key, - const struct sock *sk, __be32 sisn, - __be32 disn, bool send); -int tcp_v6_ao_calc_key_rsk(struct tcp_ao_key *mkt, u8 *key, - struct request_sock *req); +void tcp_v6_ao_hash_pseudoheader(struct tcp_ao_mac_ctx *mac_ctx, + const struct in6_addr *daddr, + const struct in6_addr *saddr, int nbytes); +void tcp_v6_ao_calc_key_skb(struct tcp_ao_key *mkt, u8 *key, + const struct sk_buff *skb, __be32 sisn, + __be32 disn); +void tcp_v6_ao_calc_key_sk(struct tcp_ao_key *mkt, u8 *key, + const struct sock *sk, __be32 sisn, + __be32 disn, bool send); +void tcp_v6_ao_calc_key_rsk(struct tcp_ao_key *mkt, u8 *key, + struct request_sock *req); struct tcp_ao_key *tcp_v6_ao_lookup(const struct sock *sk, struct sock *addr_sk, int sndid, int rcvid); struct tcp_ao_key *tcp_v6_ao_lookup_rsk(const struct sock *sk, @@ -263,11 +281,10 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, struct request_sock *req, unsigned short int family); #else /* CONFIG_TCP_AO */ -static inline int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, - struct tcp_ao_key *key, struct tcphdr *th, - __u8 *hash_location) +static inline void tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, + struct tcp_ao_key *key, + struct tcphdr *th, __u8 *hash_location) { - return 0; } static inline void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, diff --git a/include/net/tls.h b/include/net/tls.h index ebd2550280ae..e57bef58851e 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -85,7 +85,6 @@ enum { TLS_BASE, TLS_SW, TLS_HW, - TLS_HW_RECORD, TLS_NUM_CONFIG, }; @@ -111,11 +110,16 @@ struct tls_sw_context_tx { struct tls_strparser { struct sock *sk; + /* Bitfield word and msg_ready are serialized by the lower + * socket lock; BH and worker contexts both acquire it. + */ u32 mark : 8; u32 stopped : 1; u32 copy_mode : 1; u32 mixed_decrypted : 1; + u32 msg_announced : 1; + bool msg_ready; struct strp_msg stm; diff --git a/include/net/tls_toe.h b/include/net/tls_toe.h deleted file mode 100644 index b3aa7593ce2c..000000000000 --- a/include/net/tls_toe.h +++ /dev/null @@ -1,77 +0,0 @@ -/* - * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. - * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include <linux/kref.h> -#include <linux/list.h> - -struct sock; - -#define TLS_TOE_DEVICE_NAME_MAX 32 - -/* - * This structure defines the routines for Inline TLS driver. - * The following routines are optional and filled with a - * null pointer if not defined. - * - * @name: Its the name of registered Inline tls device - * @dev_list: Inline tls device list - * int (*feature)(struct tls_toe_device *device); - * Called to return Inline TLS driver capability - * - * int (*hash)(struct tls_toe_device *device, struct sock *sk); - * This function sets Inline driver for listen and program - * device specific functioanlity as required - * - * void (*unhash)(struct tls_toe_device *device, struct sock *sk); - * This function cleans listen state set by Inline TLS driver - * - * void (*release)(struct kref *kref); - * Release the registered device and allocated resources - * @kref: Number of reference to tls_toe_device - */ -struct tls_toe_device { - char name[TLS_TOE_DEVICE_NAME_MAX]; - struct list_head dev_list; - int (*feature)(struct tls_toe_device *device); - int (*hash)(struct tls_toe_device *device, struct sock *sk); - void (*unhash)(struct tls_toe_device *device, struct sock *sk); - void (*release)(struct kref *kref); - struct kref kref; -}; - -int tls_toe_bypass(struct sock *sk); -int tls_toe_hash(struct sock *sk); -void tls_toe_unhash(struct sock *sk); - -void tls_toe_register_device(struct tls_toe_device *device); -void tls_toe_unregister_device(struct tls_toe_device *device); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 47c23d4a1740..498b7b262fa9 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -94,7 +94,7 @@ struct udp_tunnel_sock_cfg { }; /* Setup the given (UDP) sock to receive UDP encapsulated packets */ -void setup_udp_tunnel_sock(struct net *net, struct socket *sock, +void setup_udp_tunnel_sock(struct net *net, struct sock *sk, struct udp_tunnel_sock_cfg *sock_cfg); /* -- List of parsable UDP tunnel types -- @@ -127,12 +127,12 @@ struct udp_tunnel_info { }; /* Notify network devices of offloadable types */ -void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, +void udp_tunnel_push_rx_port(struct net_device *dev, struct sock *sk, unsigned short type); -void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, +void udp_tunnel_drop_rx_port(struct net_device *dev, struct sock *sk, unsigned short type); -void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); -void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); +void udp_tunnel_notify_add_rx_port(struct sock *sk, unsigned short type); +void udp_tunnel_notify_del_rx_port(struct sock *sk, unsigned short type); /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, @@ -176,7 +176,7 @@ static inline void udp_tunnel_set_inner_protocol(struct sk_buff *skb, skb_set_inner_protocol(skb, inner_proto); } -void udp_tunnel_sock_release(struct socket *sock); +void udp_tunnel_sock_release(struct sock *sk); struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, struct net_device *dev, @@ -188,7 +188,7 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, - struct socket *sock, int oif, + struct sock *sk, int oif, struct in6_addr *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 dsfield, diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 0ee50785f4f1..dfba89695efc 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -185,7 +185,8 @@ struct vxlan_metadata { /* per UDP socket information */ struct vxlan_sock { struct hlist_node hlist; - struct socket *sock; + struct sock *sk; + struct rcu_head rcu; struct hlist_head vni_list[VNI_HASH_SIZE]; refcount_t refcnt; u32 flags; @@ -448,7 +449,7 @@ static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset) static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs) { - return vs->sock->sk->sk_family; + return vs->sk->sk_family; } #if IS_ENABLED(CONFIG_IPV6) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 10d3edde6b2f..a6d69aaa6cd2 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -162,6 +162,8 @@ struct xfrm_dev_offload { */ struct net_device *real_dev; unsigned long offload_handle; + /* Snapshot the attached device index for dump paths. */ + int ifindex; u8 dir : 2; u8 type : 2; u8 flags : 2; @@ -682,12 +684,22 @@ struct xfrm_migrate { xfrm_address_t old_saddr; xfrm_address_t new_daddr; xfrm_address_t new_saddr; + struct xfrm_encap_tmpl *encap; + struct xfrm_user_offload *xuo; + struct xfrm_mark old_mark; + const struct xfrm_mark *new_mark; + struct xfrm_mark smark; u8 proto; u8 mode; - u16 reserved; - u32 reqid; + u16 msg_type; /* XFRM_MSG_MIGRATE or XFRM_MSG_MIGRATE_STATE */ + u32 flags; + u32 old_reqid; + u32 new_reqid; + u32 nat_keepalive_interval; + u32 mapping_maxage; u16 old_family; u16 new_family; + const struct xfrm_selector *new_sel; }; #define XFRM_KM_TIMEOUT 30 @@ -715,6 +727,7 @@ struct xfrm_mgr { const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, + struct net *net, const struct xfrm_encap_tmpl *encap); bool (*is_alive)(const struct km_event *c); }; @@ -942,6 +955,9 @@ static inline bool addr_match(const void *token1, const void *token2, unsigned int pdw; unsigned int pbi; + if (prefixlen > 128) + return false; + pdw = prefixlen >> 5; /* num of whole u32 in prefix */ pbi = prefixlen & 0x1f; /* num of bits in incomplete u32 in prefix */ @@ -966,6 +982,10 @@ static inline bool addr4_match(__be32 a1, __be32 a2, u8 prefixlen) /* C99 6.5.7 (3): u32 << 32 is undefined behaviour */ if (sizeof(long) == 4 && prefixlen == 0) return true; + + if (prefixlen > 32) + return false; + return !((a1 ^ a2) & htonl(~0UL << (32 - prefixlen))); } @@ -1249,8 +1269,8 @@ int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb, static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb, int dir) { - if (!net->xfrm.policy_count[dir] && !secpath_exists(skb)) - return net->xfrm.policy_default[dir] == XFRM_USERPOLICY_ACCEPT; + if (!READ_ONCE(net->xfrm.policy_count[dir]) && !secpath_exists(skb)) + return READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_ACCEPT; return false; } @@ -1350,8 +1370,8 @@ static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); - if (!net->xfrm.policy_count[XFRM_POLICY_OUT] && - net->xfrm.policy_default[XFRM_POLICY_OUT] == XFRM_USERPOLICY_ACCEPT) + if (!READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT]) && + READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT]) == XFRM_USERPOLICY_ACCEPT) return true; return (skb_dst(skb)->flags & DST_NOXFRM) || @@ -1774,7 +1794,7 @@ u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x, struct netlink_ext_ack *extack); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack); -int xfrm_init_state(struct xfrm_state *x); +int xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm_input_resume(struct sk_buff *skb, int nexthdr); int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, @@ -1891,15 +1911,21 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, - const struct xfrm_kmaddress *k, + const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap); struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, u32 if_id); +struct xfrm_state *xfrm_state_migrate_create(struct xfrm_state *x, + const struct xfrm_migrate *m, + struct net *net, + struct netlink_ext_ack *extack); +int xfrm_state_migrate_install(const struct xfrm_state *x, + struct xfrm_state *xc, + const struct xfrm_migrate *m, + struct netlink_ext_ack *extack); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, - struct xfrm_encap_tmpl *encap, struct net *net, - struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack); int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, @@ -2013,23 +2039,51 @@ static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_es #ifdef CONFIG_XFRM_MIGRATE static inline int xfrm_replay_clone(struct xfrm_state *x, - struct xfrm_state *orig) + const struct xfrm_state *orig) { + /* Counters synced later in xfrm_replay_sync() */ + + x->replay = orig->replay; + x->preplay = orig->preplay; - x->replay_esn = kmemdup(orig->replay_esn, + if (orig->replay_esn) { + x->replay_esn = kmemdup(orig->replay_esn, xfrm_replay_state_esn_len(orig->replay_esn), GFP_KERNEL); - if (!x->replay_esn) - return -ENOMEM; - x->preplay_esn = kmemdup(orig->preplay_esn, - xfrm_replay_state_esn_len(orig->preplay_esn), - GFP_KERNEL); - if (!x->preplay_esn) - return -ENOMEM; + if (!x->replay_esn) + return -ENOMEM; + x->preplay_esn = kmemdup(orig->preplay_esn, + xfrm_replay_state_esn_len(orig->preplay_esn), + GFP_KERNEL); + if (!x->preplay_esn) + return -ENOMEM; + } return 0; } +static inline void xfrm_replay_sync(struct xfrm_state *x, const struct xfrm_state *orig) +{ + x->replay = orig->replay; + x->preplay = orig->preplay; + + if (orig->replay_esn) { + memcpy(x->replay_esn, orig->replay_esn, + xfrm_replay_state_esn_len(orig->replay_esn)); + + memcpy(x->preplay_esn, orig->preplay_esn, + xfrm_replay_state_esn_len(orig->preplay_esn)); + } +} + +static inline void xfrm_migrate_sync(struct xfrm_state *x, + const struct xfrm_state *orig) +{ + /* called under lock so no race conditions or mallocs allowed */ + memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft)); + xfrm_replay_sync(x, orig); +} + static inline struct xfrm_algo_aead *xfrm_algo_aead_clone(struct xfrm_algo_aead *orig) { return kmemdup(orig, aead_len(orig), GFP_KERNEL); @@ -2068,7 +2122,7 @@ void xfrm_dev_resume(struct sk_buff *skb); void xfrm_dev_backlog(struct softnet_data *sd); struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, - struct xfrm_user_offload *xuo, + const struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack); int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, @@ -2139,7 +2193,9 @@ static inline struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_fea return skb; } -static inline int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) +static inline int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, + const struct xfrm_user_offload *xuo, + struct netlink_ext_ack *extack) { return 0; } |