diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-07 22:03:58 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-07 22:03:58 -0700 |
| commit | 80f232121b69cc69a31ccb2b38c1665d770b0710 (patch) | |
| tree | 106263eac4ff03b899df695e00dd11e593e74fe2 /include/net | |
| parent | 82efe439599439a5e1e225ce5740e6cfb777a7dd (diff) | |
| parent | a9e41a529681b38087c91ebc0bb91e12f510ca2d (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.
2) Add fib_sync_mem to control the amount of dirty memory we allow to
queue up between synchronize RCU calls, from David Ahern.
3) Make flow classifier more lockless, from Vlad Buslov.
4) Add PHY downshift support to aquantia driver, from Heiner
Kallweit.
5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
contention on SLAB spinlocks in heavy RPC workloads.
6) Partial GSO offload support in XFRM, from Boris Pismenny.
7) Add fast link down support to ethtool, from Heiner Kallweit.
8) Use siphash for IP ID generator, from Eric Dumazet.
9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
entries, from David Ahern.
10) Move skb->xmit_more into a per-cpu variable, from Florian
Westphal.
11) Improve eBPF verifier speed and increase maximum program size,
from Alexei Starovoitov.
12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
spinlocks. From Neil Brown.
13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.
14) Improve link partner cap detection in generic PHY code, from
Heiner Kallweit.
15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
Maguire.
16) Remove SKB list implementation assumptions in SCTP, your's truly.
17) Various cleanups, optimizations, and simplifications in r8169
driver. From Heiner Kallweit.
18) Add memory accounting on TX and RX path of SCTP, from Xin Long.
19) Switch PHY drivers over to use dynamic featue detection, from
Heiner Kallweit.
20) Support flow steering without masking in dpaa2-eth, from Ioana
Ciocoi.
21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
Pirko.
22) Increase the strict parsing of current and future netlink
attributes, also export such policies to userspace. From Johannes
Berg.
23) Allow DSA tag drivers to be modular, from Andrew Lunn.
24) Remove legacy DSA probing support, also from Andrew Lunn.
25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
Haabendal.
26) Add a generic tracepoint for TX queue timeouts to ease debugging,
from Cong Wang.
27) More indirect call optimizations, from Paolo Abeni"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
cxgb4: Fix error path in cxgb4_init_module
net: phy: improve pause mode reporting in phy_print_status
dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
net: macb: Change interrupt and napi enable order in open
net: ll_temac: Improve error message on error IRQ
net/sched: remove block pointer from common offload structure
net: ethernet: support of_get_mac_address new ERR_PTR error
net: usb: smsc: fix warning reported by kbuild test robot
staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
net: dsa: support of_get_mac_address new ERR_PTR error
net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
vrf: sit mtu should not be updated when vrf netdev is the link
net: dsa: Fix error cleanup path in dsa_init_module
l2tp: Fix possible NULL pointer dereference
taprio: add null check on sched_nest to avoid potential null pointer dereference
net: mvpp2: cls: fix less than zero check on a u32 variable
net_sched: sch_fq: handle non connected flows
net_sched: sch_fq: do not assume EDT packets are ordered
net: hns3: use devm_kcalloc when allocating desc_cb
net: hns3: some cleanup for struct hns3_enet_ring
...
Diffstat (limited to 'include/net')
58 files changed, 1415 insertions, 960 deletions
diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 269ec27385e9..2f67ae854ff0 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -238,53 +238,6 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, void ipv6_mc_dad_complete(struct inet6_dev *idev); -/* A stub used by vxlan module. This is ugly, ideally these - * symbols should be built into the core kernel. - */ -struct ipv6_stub { - int (*ipv6_sock_mc_join)(struct sock *sk, int ifindex, - const struct in6_addr *addr); - int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex, - const struct in6_addr *addr); - int (*ipv6_dst_lookup)(struct net *net, struct sock *sk, - struct dst_entry **dst, struct flowi6 *fl6); - int (*ipv6_route_input)(struct sk_buff *skb); - - struct fib6_table *(*fib6_get_table)(struct net *net, u32 id); - struct fib6_info *(*fib6_lookup)(struct net *net, int oif, - struct flowi6 *fl6, int flags); - struct fib6_info *(*fib6_table_lookup)(struct net *net, - struct fib6_table *table, - int oif, struct flowi6 *fl6, - int flags); - struct fib6_info *(*fib6_multipath_select)(const struct net *net, - struct fib6_info *f6i, - struct flowi6 *fl6, int oif, - const struct sk_buff *skb, - int strict); - u32 (*ip6_mtu_from_fib6)(struct fib6_info *f6i, struct in6_addr *daddr, - struct in6_addr *saddr); - - void (*udpv6_encap_enable)(void); - void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, - const struct in6_addr *solicited_addr, - bool router, bool solicited, bool override, bool inc_opt); - struct neigh_table *nd_tbl; -}; -extern const struct ipv6_stub *ipv6_stub __read_mostly; - -/* A stub used by bpf helpers. Similarly ugly as ipv6_stub */ -struct ipv6_bpf_stub { - int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len, - bool force_bind_address_no_port, bool with_lock); - struct sock *(*udp6_lib_lookup)(struct net *net, - const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, __be16 dport, - int dif, int sdif, struct udp_table *tbl, - struct sk_buff *skb); -}; -extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; - /* * identify MLD packets for MLD filter exceptions */ @@ -425,6 +378,14 @@ static inline void in6_dev_hold(struct inet6_dev *idev) refcount_inc(&idev->refcnt); } +/* called with rcu_read_lock held */ +static inline bool ip6_ignore_linkdown(const struct net_device *dev) +{ + const struct inet6_dev *idev = __in6_dev_get(dev); + + return !!idev->cnf.ignore_routes_with_linkdown; +} + void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp); static inline void in6_ifa_put(struct inet6_ifaddr *ifp) diff --git a/include/net/arp.h b/include/net/arp.h index 977aabfcdc03..c8f580a0e6b1 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -18,6 +18,7 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 return val * hash_rnd[0]; } +#ifdef CONFIG_INET static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) @@ -25,6 +26,13 @@ static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } +#else +static inline +struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) +{ + return NULL; +} +#endif static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key) { diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index fbba43e9bef5..9a5330eed794 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -282,6 +282,7 @@ enum { HCI_FORCE_BREDR_SMP, HCI_FORCE_STATIC_ADDR, HCI_LL_RPA_RESOLUTION, + HCI_CMD_PENDING, __HCI_NUM_FLAGS, }; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 094e61e07030..05b1b96f4d9e 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -190,6 +190,9 @@ struct adv_info { #define HCI_MAX_SHORT_NAME_LENGTH 10 +/* Min encryption key size to match with SMP */ +#define HCI_MIN_ENC_KEY_SIZE 7 + /* Default LE RPA expiry time, 15 minutes */ #define HCI_DEFAULT_RPA_TIMEOUT (15 * 60) diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h new file mode 100644 index 000000000000..b9dcb02e756b --- /dev/null +++ b/include/net/bpf_sk_storage.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Facebook */ +#ifndef _BPF_SK_STORAGE_H +#define _BPF_SK_STORAGE_H + +struct sock; + +void bpf_sk_storage_free(struct sock *sk); + +extern const struct bpf_func_proto bpf_sk_storage_get_proto; +extern const struct bpf_func_proto bpf_sk_storage_delete_proto; + +#endif /* _BPF_SK_STORAGE_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 13bfeb712d36..87dae868707e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -485,6 +485,7 @@ struct vif_params { * with the get_key() callback, must be in little endian, * length given by @seq_len. * @seq_len: length of @seq. + * @mode: key install mode (RX_TX, NO_TX or SET_TX) */ struct key_params { const u8 *key; @@ -492,6 +493,7 @@ struct key_params { int key_len; int seq_len; u32 cipher; + enum nl80211_key_mode mode; }; /** @@ -973,6 +975,27 @@ enum station_parameters_apply_mask { STATION_PARAM_APPLY_UAPSD = BIT(0), STATION_PARAM_APPLY_CAPABILITY = BIT(1), STATION_PARAM_APPLY_PLINK_STATE = BIT(2), + STATION_PARAM_APPLY_STA_TXPOWER = BIT(3), +}; + +/** + * struct sta_txpwr - station txpower configuration + * + * Used to configure txpower for station. + * + * @power: tx power (in dBm) to be used for sending data traffic. If tx power + * is not provided, the default per-interface tx power setting will be + * overriding. Driver should be picking up the lowest tx power, either tx + * power per-interface or per-station. + * @type: In particular if TPC %type is NL80211_TX_POWER_LIMITED then tx power + * will be less than or equal to specified from userspace, whereas if TPC + * %type is NL80211_TX_POWER_AUTOMATIC then it indicates default tx power. + * NL80211_TX_POWER_FIXED is not a valid configuration option for + * per peer TPC. + */ +struct sta_txpwr { + s16 power; + enum nl80211_tx_power_setting type; }; /** @@ -1047,6 +1070,7 @@ struct station_parameters { const struct ieee80211_he_cap_elem *he_capa; u8 he_capa_len; u16 airtime_weight; + struct sta_txpwr txpwr; }; /** @@ -1327,6 +1351,7 @@ struct cfg80211_tid_stats { * @fcs_err_count: number of packets (MPDUs) received from this station with * an FCS error. This counter should be incremented only when TA of the * received packet with an FCS error matches the peer MAC address. + * @airtime_link_metric: mesh airtime link metric. */ struct station_info { u64 filled; @@ -1381,6 +1406,8 @@ struct station_info { u32 rx_mpdu_count; u32 fcs_err_count; + + u32 airtime_link_metric; }; #if IS_ENABLED(CONFIG_CFG80211) @@ -1832,11 +1859,19 @@ static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask) * @bssid: BSSID to be matched; may be all-zero BSSID in case of SSID match * or no match (RSSI only) * @rssi_thold: don't report scan results below this threshold (in s32 dBm) + * @per_band_rssi_thold: Minimum rssi threshold for each band to be applied + * for filtering out scan results received. Drivers advertize this support + * of band specific rssi based filtering through the feature capability + * %NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD. These band + * specific rssi thresholds take precedence over rssi_thold, if specified. + * If not specified for any band, it will be assigned with rssi_thold of + * corresponding matchset. */ struct cfg80211_match_set { struct cfg80211_ssid ssid; u8 bssid[ETH_ALEN]; s32 rssi_thold; + s32 per_band_rssi_thold[NUM_NL80211_BANDS]; }; /** @@ -3100,6 +3135,32 @@ struct cfg80211_pmsr_request { }; /** + * struct cfg80211_update_owe_info - OWE Information + * + * This structure provides information needed for the drivers to offload OWE + * (Opportunistic Wireless Encryption) processing to the user space. + * + * Commonly used across update_owe_info request and event interfaces. + * + * @peer: MAC address of the peer device for which the OWE processing + * has to be done. + * @status: status code, %WLAN_STATUS_SUCCESS for successful OWE info + * processing, use %WLAN_STATUS_UNSPECIFIED_FAILURE if user space + * cannot give you the real status code for failures. Used only for + * OWE update request command interface (user space to driver). + * @ie: IEs obtained from the peer or constructed by the user space. These are + * the IEs of the remote peer in the event from the host driver and + * the constructed IEs by the user space in the request interface. + * @ie_len: Length of IEs in octets. + */ +struct cfg80211_update_owe_info { + u8 peer[ETH_ALEN] __aligned(2); + u16 status; + const u8 *ie; + size_t ie_len; +}; + +/** * struct cfg80211_ops - backend description for wireless configuration * * This struct is registered by fullmac card drivers and/or wireless stacks @@ -3436,6 +3497,13 @@ struct cfg80211_pmsr_request { * Statistics should be cumulative, currently no way to reset is provided. * @start_pmsr: start peer measurement (e.g. FTM) * @abort_pmsr: abort peer measurement + * + * @update_owe_info: Provide updated OWE info to driver. Driver implementing SME + * but offloading OWE processing to the user space will get the updated + * DH IE through this interface. + * + * @probe_mesh_link: Probe direct Mesh peer's link quality by sending data frame + * and overrule HWMP path selection algorithm. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -3750,6 +3818,10 @@ struct cfg80211_ops { struct cfg80211_pmsr_request *request); void (*abort_pmsr)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_pmsr_request *request); + int (*update_owe_info)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_update_owe_info *owe_info); + int (*probe_mesh_link)(struct wiphy *wiphy, struct net_device *dev, + const u8 *buf, size_t len); }; /* @@ -5492,6 +5564,28 @@ static inline void cfg80211_gen_new_bssid(const u8 *bssid, u8 max_bssid, } /** + * cfg80211_is_element_inherited - returns if element ID should be inherited + * @element: element to check + * @non_inherit_element: non inheritance element + */ +bool cfg80211_is_element_inherited(const struct element *element, + const struct element *non_inherit_element); + +/** + * cfg80211_merge_profile - merges a MBSSID profile if it is split between IEs + * @ie: ies + * @ielen: length of IEs + * @mbssid_elem: current MBSSID element + * @sub_elem: current MBSSID subelement (profile) + * @merged_ie: location of the merged profile + * @max_copy_len: max merged profile length + */ +size_t cfg80211_merge_profile(const u8 *ie, size_t ielen, + const struct element *mbssid_elem, + const struct element *sub_elem, + u8 *merged_ie, size_t max_copy_len); + +/** * enum cfg80211_bss_frame_type - frame type that the BSS data came from * @CFG80211_BSS_FTYPE_UNKNOWN: driver doesn't know whether the data is * from a beacon or probe response @@ -7213,4 +7307,14 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, #define wiphy_WARN(wiphy, format, args...) \ WARN(1, "wiphy: %s\n" format, wiphy_name(wiphy), ##args); +/** + * cfg80211_update_owe_info_event - Notify the peer's OWE info to user space + * @netdev: network device + * @owe_info: peer's owe info + * @gfp: allocation flags + */ +void cfg80211_update_owe_info_event(struct net_device *netdev, + struct cfg80211_update_owe_info *owe_info, + gfp_t gfp); + #endif /* __NET_CFG80211_H */ diff --git a/include/net/compat.h b/include/net/compat.h index 4c6d75612b6c..f277653c7e17 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -30,9 +30,6 @@ struct compat_cmsghdr { compat_int_t cmsg_type; }; -int compat_sock_get_timestamp(struct sock *, struct timeval __user *); -int compat_sock_get_timestampns(struct sock *, struct timespec __user *); - #else /* defined(CONFIG_COMPAT) */ /* * To avoid compiler warnings: diff --git a/include/net/devlink.h b/include/net/devlink.h index 63de99e09f04..1c4adfb4195a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -16,6 +16,7 @@ #include <linux/gfp.h> #include <linux/list.h> #include <linux/netdevice.h> +#include <linux/spinlock.h> #include <net/net_namespace.h> #include <uapi/linux/devlink.h> @@ -31,6 +32,7 @@ struct devlink { struct list_head region_list; u32 snapshot_id; struct list_head reporter_list; + struct mutex reporters_lock; /* protects reporter_list */ struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; @@ -40,11 +42,13 @@ struct devlink { }; struct devlink_port_attrs { - bool set; + u8 set:1, + split:1, + switch_port:1; enum devlink_port_flavour flavour; u32 port_number; /* same value as "split group" */ - bool split; u32 split_subport_number; + struct netdev_phys_item_id switch_id; }; struct devlink_port { @@ -53,6 +57,9 @@ struct devlink_port { struct devlink *devlink; unsigned index; bool registered; + spinlock_t type_lock; /* Protects type and type_dev + * pointer consistency. + */ enum devlink_port_type type; enum devlink_port_type desired_type; void *type_dev; @@ -485,13 +492,14 @@ struct devlink_ops { struct devlink_sb_pool_info *pool_info); int (*sb_pool_set)(struct devlink *devlink, unsigned int sb_index, u16 pool_index, u32 size, - enum devlink_sb_threshold_type threshold_type); + enum devlink_sb_threshold_type threshold_type, + struct netlink_ext_ack *extack); int (*sb_port_pool_get)(struct devlink_port *devlink_port, unsigned int sb_index, u16 pool_index, u32 *p_threshold); int (*sb_port_pool_set)(struct devlink_port *devlink_port, unsigned int sb_index, u16 pool_index, - u32 threshold); + u32 threshold, struct netlink_ext_ack *extack); int (*sb_tc_pool_bind_get)(struct devlink_port *devlink_port, unsigned int sb_index, u16 tc_index, @@ -501,7 +509,8 @@ struct devlink_ops { unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, - u16 pool_index, u32 threshold); + u16 pool_index, u32 threshold, + struct netlink_ext_ack *extack); int (*sb_occ_snapshot)(struct devlink *devlink, unsigned int sb_index); int (*sb_occ_max_clear)(struct devlink *devlink, @@ -543,19 +552,25 @@ static inline struct devlink *priv_to_devlink(void *priv) return container_of(priv, struct devlink, priv); } +static inline struct devlink_port * +netdev_to_devlink_port(struct net_device *dev) +{ + if (dev->netdev_ops->ndo_get_devlink_port) + return dev->netdev_ops->ndo_get_devlink_port(dev); + return NULL; +} + static inline struct devlink *netdev_to_devlink(struct net_device *dev) { -#if IS_ENABLED(CONFIG_NET_DEVLINK) - if (dev->netdev_ops->ndo_get_devlink) - return dev->netdev_ops->ndo_get_devlink(dev); -#endif + struct devlink_port *devlink_port = netdev_to_devlink_port(dev); + + if (devlink_port) + return devlink_port->devlink; return NULL; } struct ib_device; -#if IS_ENABLED(CONFIG_NET_DEVLINK) - struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); int devlink_register(struct devlink *devlink, struct device *dev); void devlink_unregister(struct devlink *devlink); @@ -572,9 +587,9 @@ void devlink_port_type_clear(struct devlink_port *devlink_port); void devlink_port_attrs_set(struct devlink_port *devlink_port, enum devlink_port_flavour flavour, u32 port_number, bool split, - u32 split_subport_number); -int devlink_port_get_phys_port_name(struct devlink_port *devlink_port, - char *name, size_t len); + u32 split_subport_number, + const unsigned char *switch_id, + unsigned char switch_id_len); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, @@ -724,510 +739,43 @@ void devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, enum devlink_health_reporter_state state); +#if IS_ENABLED(CONFIG_NET_DEVLINK) + void devlink_compat_running_version(struct net_device *dev, char *buf, size_t len); int devlink_compat_flash_update(struct net_device *dev, const char *file_name); +int devlink_compat_phys_port_name_get(struct net_device *dev, + char *name, size_t len); +int devlink_compat_switch_id_get(struct net_device *dev, + struct netdev_phys_item_id *ppid); #else -static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, - size_t priv_size) -{ - return kzalloc(sizeof(struct devlink) + priv_size, GFP_KERNEL); -} - -static inline int devlink_register(struct devlink *devlink, struct device *dev) -{ - return 0; -} - -static inline void devlink_unregister(struct devlink *devlink) -{ -} - -static inline void devlink_params_publish(struct devlink *devlink) -{ -} - -static inline void devlink_params_unpublish(struct devlink *devlink) -{ -} - -static inline void devlink_free(struct devlink *devlink) -{ - kfree(devlink); -} - -static inline int devlink_port_register(struct devlink *devlink, - struct devlink_port *devlink_port, - unsigned int port_index) -{ - return 0; -} - -static inline void devlink_port_unregister(struct devlink_port *devlink_port) -{ -} - -static inline void devlink_port_type_eth_set(struct devlink_port *devlink_port, - struct net_device *netdev) -{ -} - -static inline void devlink_port_type_ib_set(struct devlink_port *devlink_port, - struct ib_device *ibdev) -{ -} - -static inline void devlink_port_type_clear(struct devlink_port *devlink_port) -{ -} - -static inline void devlink_port_attrs_set(struct devlink_port *devlink_port, - enum devlink_port_flavour flavour, - u32 port_number, bool split, - u32 split_subport_number) -{ -} - -static inline int -devlink_port_get_phys_port_name(struct devlink_port *devlink_port, - char *name, size_t len) -{ - return -EOPNOTSUPP; -} - -static inline int devlink_sb_register(struct devlink *devlink, - unsigned int sb_index, u32 size, - u16 ingress_pools_count, - u16 egress_pools_count, - u16 ingress_tc_count, - u16 egress_tc_count) -{ - return 0; -} - -static inline void devlink_sb_unregister(struct devlink *devlink, - unsigned int sb_index) -{ -} - -static inline int -devlink_dpipe_table_register(struct devlink *devlink, - const char *table_name, - struct devlink_dpipe_table_ops *table_ops, - void *priv, bool counter_control_extern) -{ - return 0; -} - -static inline void devlink_dpipe_table_unregister(struct devlink *devlink, - const char *table_name) -{ -} - -static inline int devlink_dpipe_headers_register(struct devlink *devlink, - struct devlink_dpipe_headers * - dpipe_headers) -{ - return 0; -} - -static inline void devlink_dpipe_headers_unregister(struct devlink *devlink) -{ -} - -static inline bool devlink_dpipe_table_counter_enabled(struct devlink *devlink, - const char *table_name) -{ - return false; -} - -static inline int -devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx) -{ - return 0; -} - -static inline int -devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx, - struct devlink_dpipe_entry *entry) -{ - return 0; -} - -static inline int -devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx) -{ - return 0; -} - -static inline void -devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry) -{ -} - -static inline int -devlink_dpipe_action_put(struct sk_buff *skb, - struct devlink_dpipe_action *action) -{ - return 0; -} - -static inline int -devlink_dpipe_match_put(struct sk_buff *skb, - struct devlink_dpipe_match *match) -{ - return 0; -} - -static inline int -devlink_resource_register(struct devlink *devlink, - const char *resource_name, - u64 resource_size, - u64 resource_id, - u64 parent_resource_id, - const struct devlink_resource_size_params *size_params) -{ - return 0; -} - static inline void -devlink_resources_unregister(struct devlink *devlink, - struct devlink_resource *resource) -{ -} - -static inline int -devlink_resource_size_get(struct devlink *devlink, u64 resource_id, - u64 *p_resource_size) -{ - return -EOPNOTSUPP; -} - -static inline int -devlink_dpipe_table_resource_set(struct devlink *devlink, - const char *table_name, u64 resource_id, - u64 resource_units) -{ - return -EOPNOTSUPP; -} - -static inline void -devlink_resource_occ_get_register(struct devlink *devlink, - u64 resource_id, - devlink_resource_occ_get_t *occ_get, - void *occ_get_priv) -{ -} - -static inline void -devlink_resource_occ_get_unregister(struct devlink *devlink, - u64 resource_id) -{ -} - -static inline int -devlink_params_register(struct devlink *devlink, - const struct devlink_param *params, - size_t params_count) -{ - return 0; -} - -static inline void -devlink_params_unregister(struct devlink *devlink, - const struct devlink_param *params, - size_t params_count) -{ - -} - -static inline int -devlink_port_params_register(struct devlink_port *devlink_port, - const struct devlink_param *params, - size_t params_count) -{ - return 0; -} - -static inline void -devlink_port_params_unregister(struct devlink_port *devlink_port, - const struct devlink_param *params, - size_t params_count) -{ -} - -static inline int -devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, - union devlink_param_value *init_val) +devlink_compat_running_version(struct net_device *dev, char *buf, size_t len) { - return -EOPNOTSUPP; } static inline int -devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, - union devlink_param_value init_val) +devlink_compat_flash_update(struct net_device *dev, const char *file_name) { return -EOPNOTSUPP; } static inline int -devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, - u32 param_id, - union devlink_param_value *init_val) +devlink_compat_phys_port_name_get(struct net_device *dev, + char *name, size_t len) { return -EOPNOTSUPP; } static inline int -devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, - u32 param_id, - union devlink_param_value init_val) +devlink_compat_switch_id_get(struct net_device *dev, + struct netdev_phys_item_id *ppid) { return -EOPNOTSUPP; } -static inline void -devlink_param_value_changed(struct devlink *devlink, u32 param_id) -{ -} - -static inline void -devlink_port_param_value_changed(struct devlink_port *devlink_port, - u32 param_id) -{ -} - -static inline void -devlink_param_value_str_fill(union devlink_param_value *dst_val, - const char *src) -{ -} - -static inline struct devlink_region * -devlink_region_create(struct devlink *devlink, - const char *region_name, - u32 region_max_snapshots, - u64 region_size) -{ - return NULL; -} - -static inline void -devlink_region_destroy(struct devlink_region *region) -{ -} - -static inline u32 -devlink_region_shapshot_id_get(struct devlink *devlink) -{ - return 0; -} - -static inline int -devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, - u8 *data, u32 snapshot_id, - devlink_snapshot_data_dest_t *data_destructor) -{ - return 0; -} - -static inline int -devlink_info_driver_name_put(struct devlink_info_req *req, const char *name) -{ - return 0; -} - -static inline int -devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) -{ - return 0; -} - -static inline int -devlink_info_version_fixed_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return 0; -} - -static inline int -devlink_info_version_stored_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return 0; -} - -static inline int -devlink_info_version_running_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return 0; -} - -static inline int -devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) -{ - return 0; -} - -static inline int -devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) -{ - return 0; -} - -static inline int -devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) -{ - return 0; -} - -static inline int -devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) -{ - return 0; -} - -static inline int -devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, - const char *name) -{ - return 0; -} - -static inline int -devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) -{ - return 0; -} - -static inline int -devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) -{ - return 0; -} - -static inline int -devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) -{ - return 0; -} - -static inline int -devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) -{ - return 0; -} - -static inline int -devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) -{ - return 0; -} - -static inline int -devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) -{ - return 0; -} - -static inline int -devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len) -{ - return 0; -} - -static inline int -devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, - bool value) -{ - return 0; -} - -static inline int -devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, - u8 value) -{ - return 0; -} - -static inline int -devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, - u32 value) -{ - return 0; -} - -static inline int -devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, - u64 value) -{ - return 0; -} - -static inline int -devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, - const char *value) -{ - return 0; -} - -static inline int -devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, - const void *value, u16 value_len) -{ - return 0; -} - -static inline struct devlink_health_reporter * -devlink_health_reporter_create(struct devlink *devlink, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, bool auto_recover, - void *priv) -{ - return NULL; -} - -static inline void -devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) -{ -} - -static inline void * -devlink_health_reporter_priv(struct devlink_health_reporter *reporter) -{ - return NULL; -} - -static inline int -devlink_health_report(struct devlink_health_reporter *reporter, - const char *msg, void *priv_ctx) -{ - return 0; -} - -static inline void -devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, - enum devlink_health_reporter_state state) -{ -} - -static inline void -devlink_compat_running_version(struct net_device *dev, char *buf, size_t len) -{ -} - -static inline int -devlink_compat_flash_update(struct net_device *dev, const char *file_name) -{ - return -EOPNOTSUPP; -} #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/net/dsa.h b/include/net/dsa.h index ae480bba11f5..6aaaadd6a413 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -30,20 +30,36 @@ struct phy_device; struct fixed_phy_status; struct phylink_link_state; +#define DSA_TAG_PROTO_NONE_VALUE 0 +#define DSA_TAG_PROTO_BRCM_VALUE 1 +#define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2 +#define DSA_TAG_PROTO_DSA_VALUE 3 +#define DSA_TAG_PROTO_EDSA_VALUE 4 +#define DSA_TAG_PROTO_GSWIP_VALUE 5 +#define DSA_TAG_PROTO_KSZ9477_VALUE 6 +#define DSA_TAG_PROTO_KSZ9893_VALUE 7 +#define DSA_TAG_PROTO_LAN9303_VALUE 8 +#define DSA_TAG_PROTO_MTK_VALUE 9 +#define DSA_TAG_PROTO_QCA_VALUE 10 +#define DSA_TAG_PROTO_TRAILER_VALUE 11 +#define DSA_TAG_PROTO_8021Q_VALUE 12 +#define DSA_TAG_PROTO_SJA1105_VALUE 13 + enum dsa_tag_protocol { - DSA_TAG_PROTO_NONE = 0, - DSA_TAG_PROTO_BRCM, - DSA_TAG_PROTO_BRCM_PREPEND, - DSA_TAG_PROTO_DSA, - DSA_TAG_PROTO_EDSA, - DSA_TAG_PROTO_GSWIP, - DSA_TAG_PROTO_KSZ9477, - DSA_TAG_PROTO_KSZ9893, - DSA_TAG_PROTO_LAN9303, - DSA_TAG_PROTO_MTK, - DSA_TAG_PROTO_QCA, - DSA_TAG_PROTO_TRAILER, - DSA_TAG_LAST, /* MUST BE LAST */ + DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, + DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, + DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, + DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, + DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, + DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE, + DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE, + DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE, + DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE, + DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, + DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, + DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, + DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, + DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, }; struct packet_type; @@ -55,9 +71,52 @@ struct dsa_device_ops { struct packet_type *pt); int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); + /* Used to determine which traffic should match the DSA filter in + * eth_type_trans, and which, if any, should bypass it and be processed + * as regular on the master net device. + */ + bool (*filter)(const struct sk_buff *skb, struct net_device *dev); unsigned int overhead; + const char *name; + enum dsa_tag_protocol proto; +}; + +#define DSA_TAG_DRIVER_ALIAS "dsa_tag-" +#define MODULE_ALIAS_DSA_TAG_DRIVER(__proto) \ + MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __stringify(__proto##_VALUE)) + +struct dsa_skb_cb { + struct sk_buff *clone; + bool deferred_xmit; +}; + +struct __dsa_skb_cb { + struct dsa_skb_cb cb; + u8 priv[48 - sizeof(struct dsa_skb_cb)]; }; +#define __DSA_SKB_CB(skb) ((struct __dsa_skb_cb *)((skb)->cb)) + +#define DSA_SKB_CB(skb) ((struct dsa_skb_cb *)((skb)->cb)) + +#define DSA_SKB_CB_COPY(nskb, skb) \ + { *__DSA_SKB_CB(nskb) = *__DSA_SKB_CB(skb); } + +#define DSA_SKB_CB_ZERO(skb) \ + { *__DSA_SKB_CB(skb) = (struct __dsa_skb_cb) {0}; } + +#define DSA_SKB_CB_PRIV(skb) \ + ((void *)(skb)->cb + offsetof(struct __dsa_skb_cb, priv)) + +#define DSA_SKB_CB_CLONE(_clone, _skb) \ + { \ + struct sk_buff *clone = _clone; \ + struct sk_buff *skb = _skb; \ + \ + DSA_SKB_CB_COPY(clone, skb); \ + DSA_SKB_CB(skb)->clone = clone; \ + } + struct dsa_switch_tree { struct list_head list; @@ -128,6 +187,7 @@ struct dsa_port { struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt); + bool (*filter)(const struct sk_buff *skb, struct net_device *dev); enum { DSA_PORT_TYPE_UNUSED = 0, @@ -140,12 +200,24 @@ struct dsa_port { unsigned int index; const char *name; const struct dsa_port *cpu_dp; + const char *mac; struct device_node *dn; unsigned int ageing_time; + bool vlan_filtering; u8 stp_state; struct net_device *bridge_dev; struct devlink_port devlink_port; struct phylink *pl; + + struct work_struct xmit_work; + struct sk_buff_head xmit_queue; + + /* + * Give the switch driver somewhere to hang its per-port private data + * structures (accessible from the tagger). + */ + void *priv; + /* * Original copy of the master netdev ethtool_ops */ @@ -208,6 +280,16 @@ struct dsa_switch { /* Number of switch port queues */ unsigned int num_tx_queues; + /* Disallow bridge core from requesting different VLAN awareness + * settings on ports if not hardware-supported + */ + bool vlan_filtering_is_global; + + /* In case vlan_filtering_is_global is set, the VLAN awareness state + * should be retrieved from here and not from the per-port settings. + */ + bool vlan_filtering; + unsigned long *bitmap; unsigned long _bitmap; @@ -275,18 +357,19 @@ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } +static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) +{ + const struct dsa_switch *ds = dp->ds; + + if (ds->vlan_filtering_is_global) + return ds->vlan_filtering; + else + return dp->vlan_filtering; +} + typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { -#if IS_ENABLED(CONFIG_NET_DSA_LEGACY) - /* - * Legacy probing. - */ - const char *(*probe)(struct device *dsa_dev, - struct device *host_dev, int sw_addr, - void **priv); -#endif - enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port); @@ -469,6 +552,12 @@ struct dsa_switch_ops { struct sk_buff *clone, unsigned int type); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); + + /* + * Deferred frame Tx + */ + netdev_tx_t (*port_deferred_xmit)(struct dsa_switch *ds, int port, + struct sk_buff *skb); }; struct dsa_switch_driver { @@ -476,20 +565,6 @@ struct dsa_switch_driver { const struct dsa_switch_ops *ops; }; -#if IS_ENABLED(CONFIG_NET_DSA_LEGACY) -/* Legacy driver registration */ -void register_switch_driver(struct dsa_switch_driver *type); -void unregister_switch_driver(struct dsa_switch_driver *type); -struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev); - -#else -static inline void register_switch_driver(struct dsa_switch_driver *type) { } -static inline void unregister_switch_driver(struct dsa_switch_driver *type) { } -static inline struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev) -{ - return NULL; -} -#endif struct net_device *dsa_dev_to_net_device(struct device *dev); /* Keep inline for faster access in hot path */ @@ -501,6 +576,15 @@ static inline bool netdev_uses_dsa(struct net_device *dev) return false; } +static inline bool dsa_can_decode(const struct sk_buff *skb, + struct net_device *dev) +{ +#if IS_ENABLED(CONFIG_NET_DSA) + return !dev->dsa_ptr->filter || dev->dsa_ptr->filter(skb, dev); +#endif + return false; +} + struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n); void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); @@ -569,9 +653,76 @@ static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev, #define BRCM_TAG_GET_QUEUE(v) ((v) & 0xff) +netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data); int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data); int dsa_port_get_phy_sset_count(struct dsa_port *dp); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); +struct dsa_tag_driver { + const struct dsa_device_ops *ops; + struct list_head list; + struct module *owner; +}; + +void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count, + struct module *owner); +void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count); + +#define dsa_tag_driver_module_drivers(__dsa_tag_drivers_array, __count) \ +static int __init dsa_tag_driver_module_init(void) \ +{ \ + dsa_tag_drivers_register(__dsa_tag_drivers_array, __count, \ + THIS_MODULE); \ + return 0; \ +} \ +module_init(dsa_tag_driver_module_init); \ + \ +static void __exit dsa_tag_driver_module_exit(void) \ +{ \ + dsa_tag_drivers_unregister(__dsa_tag_drivers_array, __count); \ +} \ +module_exit(dsa_tag_driver_module_exit) + +/** + * module_dsa_tag_drivers() - Helper macro for registering DSA tag + * drivers + * @__ops_array: Array of tag driver strucutres + * + * Helper macro for DSA tag drivers which do not do anything special + * in module init/exit. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit(). + */ +#define module_dsa_tag_drivers(__ops_array) \ +dsa_tag_driver_module_drivers(__ops_array, ARRAY_SIZE(__ops_array)) + +#define DSA_TAG_DRIVER_NAME(__ops) dsa_tag_driver ## _ ## __ops + +/* Create a static structure we can build a linked list of dsa_tag + * drivers + */ +#define DSA_TAG_DRIVER(__ops) \ +static struct dsa_tag_driver DSA_TAG_DRIVER_NAME(__ops) = { \ + .ops = &__ops, \ +} + +/** + * module_dsa_tag_driver() - Helper macro for registering a single DSA tag + * driver + * @__ops: Single tag driver structures + * + * Helper macro for DSA tag drivers which do not do anything special + * in module init/exit. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit(). + */ +#define module_dsa_tag_driver(__ops) \ +DSA_TAG_DRIVER(__ops); \ + \ +static struct dsa_tag_driver *dsa_tag_driver_array[] = { \ + &DSA_TAG_DRIVER_NAME(__ops) \ +}; \ +module_dsa_tag_drivers(dsa_tag_driver_array) #endif + diff --git a/include/net/dst.h b/include/net/dst.h index 6cf0870414c7..12b31c602cb0 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -19,17 +19,6 @@ #include <net/neighbour.h> #include <asm/processor.h> -#define DST_GC_MIN (HZ/10) -#define DST_GC_INC (HZ/2) -#define DST_GC_MAX (120*HZ) - -/* Each dst_entry has reference count and sits in some parent list(s). - * When it is removed from parent list, it is "freed" (dst_free). - * After this it enters dead state (dst->obsolete > 0) and if its refcnt - * is zero, it can be destroyed immediately, otherwise it is added - * to gc list and garbage collector periodically checks the refcnt. - */ - struct sk_buff; struct dst_entry { diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h index c91ec732afd6..c49d7bfb5c30 100644 --- a/include/net/fib_notifier.h +++ b/include/net/fib_notifier.h @@ -2,10 +2,11 @@ #define __NET_FIB_NOTIFIER_H #include <linux/types.h> -#include <linux/module.h> #include <linux/notifier.h> #include <net/net_namespace.h> +struct module; + struct fib_notifier_info { struct net *net; int family; diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 2b26979efb48..7c5a8d9a8d2a 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -305,4 +305,11 @@ static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissec return ((char *)target_container) + flow_dissector->offset[key_id]; } +struct bpf_flow_dissector { + struct bpf_flow_keys *flow_keys; + const struct sk_buff *skb; + void *data; + void *data_end; +}; + #endif diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index d035183c8d03..6200900434e1 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -118,6 +118,8 @@ enum flow_action_id { FLOW_ACTION_MARK, FLOW_ACTION_WAKE, FLOW_ACTION_QUEUE, + FLOW_ACTION_SAMPLE, + FLOW_ACTION_POLICE, }; /* This is mirroring enum pedit_header_type definition for easy mapping between @@ -157,6 +159,16 @@ struct flow_action_entry { u32 index; u8 vf; } queue; + struct { /* FLOW_ACTION_SAMPLE */ + struct psample_group *psample_group; + u32 rate; + u32 trunc_size; + bool truncate; + } sample; + struct { /* FLOW_ACTION_POLICE */ + s64 burst; + u64 rate_bytes_ps; + } police; }; }; @@ -170,6 +182,17 @@ static inline bool flow_action_has_entries(const struct flow_action *action) return action->num_entries; } +/** + * flow_action_has_one_action() - check if exactly one action is present + * @action: tc filter flow offload action + * + * Returns true if exactly one action is present. + */ +static inline bool flow_offload_has_one_action(const struct flow_action *action) +{ + return action->num_entries == 1; +} + #define flow_action_for_each(__i, __act, __actions) \ for (__i = 0, __act = &(__actions)->entries[0]; __i < (__actions)->num_entries; __act = &(__actions)->entries[++__i]) diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index be7c0fab3478..2caa86660ab0 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -107,21 +107,23 @@ begin: return skb; } +static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb) +{ + u32 hash = skb_get_hash_perturb(skb, fq->perturbation); + + return reciprocal_scale(hash, fq->flows_cnt); +} + static struct fq_flow *fq_flow_classify(struct fq *fq, - struct fq_tin *tin, + struct fq_tin *tin, u32 idx, struct sk_buff *skb, fq_flow_get_default_t get_default_func) { struct fq_flow *flow; - u32 hash; - u32 idx; lockdep_assert_held(&fq->lock); - hash = skb_get_hash_perturb(skb, fq->perturbation); - idx = reciprocal_scale(hash, fq->flows_cnt); flow = &fq->flows[idx]; - if (flow->tin && flow->tin != tin) { flow = get_default_func(fq, tin, idx, skb); tin->collisions++; @@ -153,7 +155,7 @@ static void fq_recalc_backlog(struct fq *fq, } static void fq_tin_enqueue(struct fq *fq, - struct fq_tin *tin, + struct fq_tin *tin, u32 idx, struct sk_buff *skb, fq_skb_free_t free_func, fq_flow_get_default_t get_default_func) @@ -163,7 +165,7 @@ static void fq_tin_enqueue(struct fq *fq, lockdep_assert_held(&fq->lock); - flow = fq_flow_classify(fq, tin, skb, get_default_func); + flow = fq_flow_classify(fq, tin, idx, skb, get_default_func); flow->tin = tin; flow->backlog += skb->len; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index aa2e5888f18d..9292f1c588b7 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -26,6 +26,7 @@ struct genl_info; * @name: name of family * @version: protocol version * @maxattr: maximum number of attributes supported + * @policy: netlink policy * @netnsok: set to true if the family can handle network * namespaces and should be presented in all of them * @parallel_ops: operations can be called in parallel and aren't @@ -56,6 +57,7 @@ struct genl_family { unsigned int maxattr; bool netnsok; bool parallel_ops; + const struct nla_policy *policy; int (*pre_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); @@ -119,19 +121,23 @@ static inline int genl_err_attr(struct genl_info *info, int err, return err; } +enum genl_validate_flags { + GENL_DONT_VALIDATE_STRICT = BIT(0), + GENL_DONT_VALIDATE_DUMP = BIT(1), + GENL_DONT_VALIDATE_DUMP_STRICT = BIT(2), +}; + /** * struct genl_ops - generic netlink operations * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags - * @policy: attribute validation policy * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps */ struct genl_ops { - const struct nla_policy *policy; int (*doit)(struct sk_buff *skb, struct genl_info *info); int (*start)(struct netlink_callback *cb); @@ -141,6 +147,7 @@ struct genl_ops { u8 cmd; u8 internal_flags; u8 flags; + u8 validate; }; int genl_register_family(struct genl_family *family); @@ -165,6 +172,25 @@ static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr) } /** + * genlmsg_parse_deprecated - parse attributes of a genetlink message + * @nlh: netlink message header + * @family: genetlink message family + * @tb: destination array with maxtype+1 elements + * @maxtype: maximum attribute type to be expected + * @policy: validation policy + * @extack: extended ACK report struct + */ +static inline int genlmsg_parse_deprecated(const struct nlmsghdr *nlh, + const struct genl_family *family, + struct nlattr *tb[], int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, + policy, NL_VALIDATE_LIBERAL, extack); +} + +/** * genlmsg_parse - parse attributes of a genetlink message * @nlh: netlink message header * @family: genetlink message family @@ -179,8 +205,8 @@ static inline int genlmsg_parse(const struct nlmsghdr *nlh, const struct nla_policy *policy, struct netlink_ext_ack *extack) { - return nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, - policy, extack); + return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, + policy, NL_VALIDATE_STRICT, extack); } /** diff --git a/include/net/geneve.h b/include/net/geneve.h index fc6a7e0a874a..bced0b1d9fe4 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -4,6 +4,8 @@ #include <net/udp_tunnel.h> +#define GENEVE_UDP_PORT 6081 + /* Geneve Header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |Ver| Opt Len |O|C| Rsvd. | Protocol Type | diff --git a/include/net/ife.h b/include/net/ife.h index e117617e3c34..7e2538d8585b 100644 --- a/include/net/ife.h +++ b/include/net/ife.h @@ -4,7 +4,6 @@ #include <linux/etherdevice.h> #include <linux/rtnetlink.h> -#include <linux/module.h> #include <uapi/linux/ife.h> #if IS_ENABLED(CONFIG_NET_IFE) diff --git a/include/net/ip.h b/include/net/ip.h index 583526aad1d0..2d3cce7c3e8a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -38,6 +38,10 @@ #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ #define IPV4_MIN_MTU 68 /* RFC 791 */ +extern unsigned int sysctl_fib_sync_mem; +extern unsigned int sysctl_fib_sync_mem_min; +extern unsigned int sysctl_fib_sync_mem_max; + struct sock; struct inet_skb_parm { diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 84097010237c..40105738e2f6 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -19,6 +19,7 @@ #include <linux/notifier.h> #include <net/dst.h> #include <net/flow.h> +#include <net/ip_fib.h> #include <net/netlink.h> #include <net/inetpeer.h> #include <net/fib_notifier.h> @@ -50,7 +51,8 @@ struct fib6_config { u32 fc_protocol; u16 fc_type; /* only 8 bits are used */ u16 fc_delete_all_nh : 1, - __unused : 15; + fc_ignore_dev_down:1, + __unused : 14; struct in6_addr fc_dst; struct in6_addr fc_src; @@ -124,13 +126,11 @@ struct rt6_exception { #define FIB6_MAX_DEPTH 5 struct fib6_nh { - struct in6_addr nh_gw; - struct net_device *nh_dev; - struct lwtunnel_state *nh_lwtstate; + struct fib_nh_common nh_common; - unsigned int nh_flags; - atomic_t nh_upper_bound; - int nh_weight; +#ifdef CONFIG_IPV6_ROUTER_PREF + unsigned long last_probe; +#endif }; struct fib6_info { @@ -146,7 +146,7 @@ struct fib6_info { struct list_head fib6_siblings; unsigned int fib6_nsiblings; - atomic_t fib6_ref; + refcount_t fib6_ref; unsigned long expires; struct dst_metrics *fib6_metrics; #define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] @@ -159,10 +159,6 @@ struct fib6_info { struct rt6_info * __percpu *rt6i_pcpu; struct rt6_exception_bucket __rcu *rt6i_exception_bucket; -#ifdef CONFIG_IPV6_ROUTER_PREF - unsigned long last_probe; -#endif - u32 fib6_metric; u8 fib6_protocol; u8 fib6_type; @@ -194,6 +190,14 @@ struct rt6_info { unsigned short rt6i_nfheader_len; }; +struct fib6_result { + struct fib6_nh *nh; + struct fib6_info *f6i; + u32 fib6_flags; + u8 fib6_type; + struct rt6_info *rt6; +}; + #define for_each_fib6_node_rt_rcu(fn) \ for (rt = rcu_dereference((fn)->leaf); rt; \ rt = rcu_dereference(rt->fib6_next)) @@ -281,17 +285,17 @@ void fib6_info_destroy_rcu(struct rcu_head *head); static inline void fib6_info_hold(struct fib6_info *f6i) { - atomic_inc(&f6i->fib6_ref); + refcount_inc(&f6i->fib6_ref); } static inline bool fib6_info_hold_safe(struct fib6_info *f6i) { - return atomic_inc_not_zero(&f6i->fib6_ref); + return refcount_inc_not_zero(&f6i->fib6_ref); } static inline void fib6_info_release(struct fib6_info *f6i) { - if (f6i && atomic_dec_and_test(&f6i->fib6_ref)) + if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) call_rcu(&f6i->rcu, fib6_info_destroy_rcu); } @@ -388,18 +392,17 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, /* called with rcu lock held; can return error pointer * caller needs to select path */ -struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, - int flags); +int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, + struct fib6_result *res, int flags); /* called with rcu lock held; caller needs to select path */ -struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table, - int oif, struct flowi6 *fl6, int strict); - -struct fib6_info *fib6_multipath_select(const struct net *net, - struct fib6_info *match, - struct flowi6 *fl6, int oif, - const struct sk_buff *skb, int strict); +int fib6_table_lookup(struct net *net, struct fib6_table *table, + int oif, struct flowi6 *fl6, struct fib6_result *res, + int strict); +void fib6_select_path(const struct net *net, struct fib6_result *res, + struct flowi6 *fl6, int oif, bool have_oif_match, + const struct sk_buff *skb, int strict); struct fib6_node *fib6_node_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr); @@ -440,14 +443,13 @@ void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i) { - return f6i->fib6_nh.nh_dev; + return f6i->fib6_nh.fib_nh_dev; } -static inline -struct lwtunnel_state *fib6_info_nh_lwt(const struct fib6_info *f6i) -{ - return f6i->fib6_nh.nh_lwtstate; -} +int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, + struct fib6_config *cfg, gfp_t gfp_flags, + struct netlink_ext_ack *extack); +void fib6_nh_release(struct fib6_nh *fib6_nh); void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 7ab119936e69..4790beaa86e0 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -68,8 +68,9 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) { - return (f6i->fib6_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == - RTF_GATEWAY; + /* the RTF_ADDRCONF flag filters out RA's */ + return !(f6i->fib6_flags & RTF_ADDRCONF) && + f6i->fib6_nh.fib_nh_gw_family; } void ip6_route_input(struct sk_buff *skb); @@ -181,7 +182,7 @@ int rt6_dump_route(struct fib6_info *f6i, void *p_arg); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); -void rt6_sync_up(struct net_device *dev, unsigned int nh_flags); +void rt6_sync_up(struct net_device *dev, unsigned char nh_flags); void rt6_disable_ip(struct net_device *dev, unsigned long event); void rt6_sync_down_dev(struct net_device *dev, unsigned long event); void rt6_multipath_rebalance(struct fib6_info *f6i); @@ -274,9 +275,11 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b) { - return a->fib6_nh.nh_dev == b->fib6_nh.nh_dev && - ipv6_addr_equal(&a->fib6_nh.nh_gw, &b->fib6_nh.nh_gw) && - !lwtunnel_cmp_encap(a->fib6_nh.nh_lwtstate, b->fib6_nh.nh_lwtstate); + struct fib6_nh *nha = &a->fib6_nh, *nhb = &b->fib6_nh; + + return nha->fib_nh_dev == nhb->fib_nh_dev && + ipv6_addr_equal(&nha->fib_nh_gw6, &nhb->fib_nh_gw6) && + !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws); } static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) @@ -300,8 +303,9 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) return mtu; } -u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr, - struct in6_addr *saddr); +u32 ip6_mtu_from_fib6(const struct fib6_result *res, + const struct in6_addr *daddr, + const struct in6_addr *saddr); struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 9c8214d2116d..d0e28f4ab099 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -32,10 +32,14 @@ struct fib_config { u8 fc_protocol; u8 fc_scope; u8 fc_type; - /* 3 bytes unused */ + u8 fc_gw_family; + /* 2 bytes unused */ u32 fc_table; __be32 fc_dst; - __be32 fc_gw; + union { + __be32 fc_gw4; + struct in6_addr fc_gw6; + }; int fc_oif; u32 fc_flags; u32 fc_priority; @@ -76,27 +80,49 @@ struct fnhe_hash_bucket { #define FNHE_HASH_SIZE (1 << FNHE_HASH_SHIFT) #define FNHE_RECLAIM_DEPTH 5 +struct fib_nh_common { + struct net_device *nhc_dev; + int nhc_oif; + unsigned char nhc_scope; + u8 nhc_family; + u8 nhc_gw_family; + unsigned char nhc_flags; + struct lwtunnel_state *nhc_lwtstate; + + union { + __be32 ipv4; + struct in6_addr ipv6; + } nhc_gw; + + int nhc_weight; + atomic_t nhc_upper_bound; + + /* v4 specific, but allows fib6_nh with v4 routes */ + struct rtable __rcu * __percpu *nhc_pcpu_rth_output; + struct rtable __rcu *nhc_rth_input; + struct fnhe_hash_bucket __rcu *nhc_exceptions; +}; + struct fib_nh { - struct net_device *nh_dev; + struct fib_nh_common nh_common; struct hlist_node nh_hash; struct fib_info *nh_parent; - unsigned int nh_flags; - unsigned char nh_scope; -#ifdef CONFIG_IP_ROUTE_MULTIPATH - int nh_weight; - atomic_t nh_upper_bound; -#endif #ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif - int nh_oif; - __be32 nh_gw; __be32 nh_saddr; int nh_saddr_genid; - struct rtable __rcu * __percpu *nh_pcpu_rth_output; - struct rtable __rcu *nh_rth_input; - struct fnhe_hash_bucket __rcu *nh_exceptions; - struct lwtunnel_state *nh_lwtstate; +#define fib_nh_family nh_common.nhc_family +#define fib_nh_dev nh_common.nhc_dev +#define fib_nh_oif nh_common.nhc_oif +#define fib_nh_flags nh_common.nhc_flags +#define fib_nh_lws nh_common.nhc_lwtstate +#define fib_nh_scope nh_common.nhc_scope +#define fib_nh_gw_family nh_common.nhc_gw_family +#define fib_nh_gw4 nh_common.nhc_gw.ipv4 +#define fib_nh_gw6 nh_common.nhc_gw.ipv6 +#define fib_nh_weight nh_common.nhc_weight +#define fib_nh_upper_bound nh_common.nhc_upper_bound }; /* @@ -123,9 +149,10 @@ struct fib_info { #define fib_rtt fib_metrics->metrics[RTAX_RTT-1] #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; + bool fib_nh_is_v6; struct rcu_head rcu; struct fib_nh fib_nh[0]; -#define fib_dev fib_nh[0].nh_dev +#define fib_dev fib_nh[0].fib_nh_dev }; @@ -135,15 +162,16 @@ struct fib_rule; struct fib_table; struct fib_result { - __be32 prefix; - unsigned char prefixlen; - unsigned char nh_sel; - unsigned char type; - unsigned char scope; - u32 tclassid; - struct fib_info *fi; - struct fib_table *table; - struct hlist_head *fa_head; + __be32 prefix; + unsigned char prefixlen; + unsigned char nh_sel; + unsigned char type; + unsigned char scope; + u32 tclassid; + struct fib_nh_common *nhc; + struct fib_info *fi; + struct fib_table *table; + struct hlist_head *fa_head; }; struct fib_result_nl { @@ -161,11 +189,10 @@ struct fib_result_nl { int err; }; -#ifdef CONFIG_IP_ROUTE_MULTIPATH -#define FIB_RES_NH(res) ((res).fi->fib_nh[(res).nh_sel]) -#else /* CONFIG_IP_ROUTE_MULTIPATH */ -#define FIB_RES_NH(res) ((res).fi->fib_nh[0]) -#endif /* CONFIG_IP_ROUTE_MULTIPATH */ +static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) +{ + return &fi->fib_nh[nhsel].nh_common; +} #ifdef CONFIG_IP_MULTIPLE_TABLES #define FIB_TABLE_HASHSZ 256 @@ -174,18 +201,11 @@ struct fib_result_nl { #endif __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh); +__be32 fib_result_prefsrc(struct net *net, struct fib_result *res); -#define FIB_RES_SADDR(net, res) \ - ((FIB_RES_NH(res).nh_saddr_genid == \ - atomic_read(&(net)->ipv4.dev_addr_genid)) ? \ - FIB_RES_NH(res).nh_saddr : \ - fib_info_update_nh_saddr((net), &FIB_RES_NH(res))) -#define FIB_RES_GW(res) (FIB_RES_NH(res).nh_gw) -#define FIB_RES_DEV(res) (FIB_RES_NH(res).nh_dev) -#define FIB_RES_OIF(res) (FIB_RES_NH(res).nh_oif) - -#define FIB_RES_PREFSRC(net, res) ((res).fi->fib_prefsrc ? : \ - FIB_RES_SADDR(net, res)) +#define FIB_RES_NHC(res) ((res).nhc) +#define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev) +#define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif) struct fib_entry_notifier_info { struct fib_notifier_info info; /* must be first */ @@ -383,6 +403,8 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net, /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); +int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, + struct netlink_ext_ack *extack); __be32 fib_compute_spec_dst(struct sk_buff *skb); bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, @@ -405,7 +427,7 @@ int fib_unmerge(struct net *net); int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); -int fib_sync_up(struct net_device *dev, unsigned int nh_flags); +int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -416,6 +438,15 @@ void fib_select_multipath(struct fib_result *res, int hash); void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb); +int fib_nh_init(struct net *net, struct fib_nh *fib_nh, + struct fib_config *cfg, int nh_weight, + struct netlink_ext_ack *extack); +void fib_nh_release(struct net *net, struct fib_nh *fib_nh); +int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *fc_encap, + u16 fc_encap_type, void *cfg, gfp_t gfp_flags, + struct netlink_ext_ack *extack); +void fib_nh_common_release(struct fib_nh_common *nhc); + /* Exported by fib_trie.c */ void fib_trie_init(void); struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); @@ -423,10 +454,12 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { #ifdef CONFIG_IP_ROUTE_CLASSID + struct fib_nh_common *nhc = res->nhc; + struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common); #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif - *itag = FIB_RES_NH(*res).nh_tclassid<<16; + *itag = nh->nh_tclassid << 16; #ifdef CONFIG_IP_MULTIPLE_TABLES rtag = res->tclassid; if (*itag == 0) @@ -467,4 +500,9 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr); int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb); + +int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, + unsigned char *flags, bool skip_oif); +int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, + int nh_weight); #endif /* _NET_FIB_H */ diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 047f9a5ccaad..2ac40135b576 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -600,6 +600,9 @@ struct ip_vs_dest_user_kern { /* Address family of addr */ u16 af; + + u16 tun_type; /* tunnel type */ + __be16 tun_port; /* tunnel port */ }; @@ -660,6 +663,8 @@ struct ip_vs_dest { atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ atomic_t last_weight; /* server latest weight */ + __u16 tun_type; /* tunnel type */ + __be16 tun_port; /* tunnel port */ refcount_t refcnt; /* reference counter */ struct ip_vs_stats stats; /* statistics */ diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 28aa9b30aece..1f77fb4dc79d 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -94,7 +94,6 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) goto out; head->dev = dev; - skb_get(head); spin_unlock(&fq->q.lock); icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h new file mode 100644 index 000000000000..6c0c4fde16f8 --- /dev/null +++ b/include/net/ipv6_stubs.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _IPV6_STUBS_H +#define _IPV6_STUBS_H + +#include <linux/in6.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <net/dst.h> +#include <net/flow.h> +#include <net/neighbour.h> +#include <net/sock.h> + +/* structs from net/ip6_fib.h */ +struct fib6_info; +struct fib6_nh; +struct fib6_config; +struct fib6_result; + +/* This is ugly, ideally these symbols should be built + * into the core kernel. + */ +struct ipv6_stub { + int (*ipv6_sock_mc_join)(struct sock *sk, int ifindex, + const struct in6_addr *addr); + int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex, + const struct in6_addr *addr); + int (*ipv6_dst_lookup)(struct net *net, struct sock *sk, + struct dst_entry **dst, struct flowi6 *fl6); + int (*ipv6_route_input)(struct sk_buff *skb); + + struct fib6_table *(*fib6_get_table)(struct net *net, u32 id); + int (*fib6_lookup)(struct net *net, int oif, struct flowi6 *fl6, + struct fib6_result *res, int flags); + int (*fib6_table_lookup)(struct net *net, struct fib6_table *table, + int oif, struct flowi6 *fl6, + struct fib6_result *res, int flags); + void (*fib6_select_path)(const struct net *net, struct fib6_result *res, + struct flowi6 *fl6, int oif, bool oif_match, + const struct sk_buff *skb, int strict); + u32 (*ip6_mtu_from_fib6)(const struct fib6_result *res, + const struct in6_addr *daddr, + const struct in6_addr *saddr); + + int (*fib6_nh_init)(struct net *net, struct fib6_nh *fib6_nh, + struct fib6_config *cfg, gfp_t gfp_flags, + struct netlink_ext_ack *extack); + void (*fib6_nh_release)(struct fib6_nh *fib6_nh); + void (*udpv6_encap_enable)(void); + void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, + const struct in6_addr *solicited_addr, + bool router, bool solicited, bool override, bool inc_opt); + struct neigh_table *nd_tbl; +}; +extern const struct ipv6_stub *ipv6_stub __read_mostly; + +/* A stub used by bpf helpers. Similarly ugly as ipv6_stub */ +struct ipv6_bpf_stub { + int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len, + bool force_bind_address_no_port, bool with_lock); + struct sock *(*udp6_lib_lookup)(struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, + int dif, int sdif, struct udp_table *tbl, + struct sk_buff *skb); +}; +extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; + +#endif diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 671113bcb2cc..5d6c5b1fc695 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -118,8 +118,8 @@ int lwtunnel_build_state(u16 encap_type, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack); -int lwtunnel_fill_encap(struct sk_buff *skb, - struct lwtunnel_state *lwtstate); +int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, + int encap_attr, int encap_type_attr); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate); struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b); @@ -219,7 +219,8 @@ static inline int lwtunnel_build_state(u16 encap_type, } static inline int lwtunnel_fill_encap(struct sk_buff *skb, - struct lwtunnel_state *lwtstate) + struct lwtunnel_state *lwtstate, + int encap_attr, int encap_type_attr) { return 0; } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 112dc18c658f..72080d9d617e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -807,6 +807,7 @@ enum mac80211_tx_info_flags { * @IEEE80211_TX_CTRL_RATE_INJECT: This frame is injected with rate information * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path + * @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup * * These flags are used in tx_info->control.flags. */ @@ -816,6 +817,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_RATE_INJECT = BIT(2), IEEE80211_TX_CTRL_AMSDU = BIT(3), IEEE80211_TX_CTRL_FAST_XMIT = BIT(4), + IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5), }; /* @@ -1697,6 +1699,7 @@ struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); * @IEEE80211_KEY_FLAG_PUT_MIC_SPACE: This flag should be set by the driver for * a TKIP key if it only requires MIC space. Do not set together with * @IEEE80211_KEY_FLAG_GENERATE_MMIC on the same key. + * @IEEE80211_KEY_FLAG_NO_AUTO_TX: Key needs explicit Tx activation. */ enum ieee80211_key_flags { IEEE80211_KEY_FLAG_GENERATE_IV_MGMT = BIT(0), @@ -1708,6 +1711,7 @@ enum ieee80211_key_flags { IEEE80211_KEY_FLAG_RX_MGMT = BIT(6), IEEE80211_KEY_FLAG_RESERVE_TAILROOM = BIT(7), IEEE80211_KEY_FLAG_PUT_MIC_SPACE = BIT(8), + IEEE80211_KEY_FLAG_NO_AUTO_TX = BIT(9), }; /** @@ -1888,6 +1892,24 @@ struct ieee80211_sta_rates { }; /** + * struct ieee80211_sta_txpwr - station txpower configuration + * + * Used to configure txpower for station. + * + * @power: indicates the tx power, in dBm, to be used when sending data frames + * to the STA. + * @type: In particular if TPC %type is NL80211_TX_POWER_LIMITED then tx power + * will be less than or equal to specified from userspace, whereas if TPC + * %type is NL80211_TX_POWER_AUTOMATIC then it indicates default tx power. + * NL80211_TX_POWER_FIXED is not a valid configuration option for + * per peer TPC. + */ +struct ieee80211_sta_txpwr { + s16 power; + enum nl80211_tx_power_setting type; +}; + +/** * struct ieee80211_sta - station table entry * * A station table entry represents a station we are possibly @@ -1973,6 +1995,7 @@ struct ieee80211_sta { bool support_p2p_ps; u16 max_rc_amsdu_len; u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS]; + struct ieee80211_sta_txpwr txpwr; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; @@ -2243,6 +2266,9 @@ struct ieee80211_txq { * @IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID: Hardware supports multi BSSID * only for HE APs. Applies if @IEEE80211_HW_SUPPORTS_MULTI_BSSID is set. * + * @IEEE80211_HW_EXT_KEY_ID_NATIVE: Driver and hardware are supporting Extended + * Key ID and can handle two unicast keys per station for Rx and Tx. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2294,6 +2320,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN, IEEE80211_HW_SUPPORTS_MULTI_BSSID, IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID, + IEEE80211_HW_EXT_KEY_ID_NATIVE, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -3794,6 +3821,9 @@ struct ieee80211_ops { #endif void (*sta_notify)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum sta_notify_cmd, struct ieee80211_sta *sta); + int (*sta_set_txpwr)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta); int (*sta_state)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, enum ieee80211_sta_state old_state, diff --git a/include/net/ndisc.h b/include/net/ndisc.h index ddfbb591e2c5..366150053043 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -2,6 +2,8 @@ #ifndef _NDISC_H #define _NDISC_H +#include <net/ipv6_stubs.h> + /* * ICMP codes for neighbour discovery messages */ @@ -379,6 +381,14 @@ static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev); } +static inline +struct neighbour *__ipv6_neigh_lookup_noref_stub(struct net_device *dev, + const void *pkey) +{ + return ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128, + ndisc_hashfn, pkey, dev); +} + static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey) { struct neighbour *n; @@ -409,6 +419,36 @@ static inline void __ipv6_confirm_neigh(struct net_device *dev, rcu_read_unlock_bh(); } +static inline void __ipv6_confirm_neigh_stub(struct net_device *dev, + const void *pkey) +{ + struct neighbour *n; + + rcu_read_lock_bh(); + n = __ipv6_neigh_lookup_noref_stub(dev, pkey); + if (n) { + unsigned long now = jiffies; + + /* avoid dirtying neighbour */ + if (n->confirmed != now) + n->confirmed = now; + } + rcu_read_unlock_bh(); +} + +/* uses ipv6_stub and is meant for use outside of IPv6 core */ +static inline struct neighbour *ip_neigh_gw6(struct net_device *dev, + const void *addr) +{ + struct neighbour *neigh; + + neigh = __ipv6_neigh_lookup_noref_stub(dev, addr); + if (unlikely(!neigh)) + neigh = __neigh_create(ipv6_stub->nd_tbl, addr, dev, false); + + return neigh; +} + int ndisc_init(void); int ndisc_late_init(void); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 7c1ab9edba03..50a67bd6a434 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -205,6 +205,8 @@ struct neigh_table { int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); void (*proxy_redo)(struct sk_buff *skb); + bool (*allow_add)(const struct net_device *dev, + struct netlink_ext_ack *extack); char *id; struct neigh_parms parms; struct list_head parms_list; @@ -498,11 +500,12 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb return dev_queue_xmit(skb); } -static inline int neigh_output(struct neighbour *n, struct sk_buff *skb) +static inline int neigh_output(struct neighbour *n, struct sk_buff *skb, + bool skip_cache) { const struct hh_cache *hh = &n->hh; - if ((n->nud_state & NUD_CONNECTED) && hh->hh_len) + if ((n->nud_state & NUD_CONNECTED) && hh->hh_len && !skip_cache) return neigh_hh_output(hh, skb); else return n->output(n, skb); diff --git a/include/net/netfilter/ipv4/nf_nat_masquerade.h b/include/net/netfilter/ipv4/nf_nat_masquerade.h deleted file mode 100644 index 13d55206bb9f..000000000000 --- a/include/net/netfilter/ipv4/nf_nat_masquerade.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NF_NAT_MASQUERADE_IPV4_H_ -#define _NF_NAT_MASQUERADE_IPV4_H_ - -#include <net/netfilter/nf_nat.h> - -unsigned int -nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, - const struct nf_nat_range2 *range, - const struct net_device *out); - -int nf_nat_masquerade_ipv4_register_notifier(void); -void nf_nat_masquerade_ipv4_unregister_notifier(void); - -#endif /*_NF_NAT_MASQUERADE_IPV4_H_ */ diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h deleted file mode 100644 index 2917bf95c437..000000000000 --- a/include/net/netfilter/ipv6/nf_nat_masquerade.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NF_NAT_MASQUERADE_IPV6_H_ -#define _NF_NAT_MASQUERADE_IPV6_H_ - -unsigned int -nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, - const struct net_device *out); -int nf_nat_masquerade_ipv6_register_notifier(void); -void nf_nat_masquerade_ipv6_unregister_notifier(void); - -#endif /* _NF_NAT_MASQUERADE_IPV6_H_ */ diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 006e430d1cdf..93ce6b0daaba 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -48,7 +48,7 @@ struct nf_conntrack_expect { /* Expectation class */ unsigned int class; -#ifdef CONFIG_NF_NAT_NEEDED +#if IS_ENABLED(CONFIG_NF_NAT) union nf_inet_addr saved_addr; /* This is the original per-proto part, used to map the * expected connection the way the recipient expects. */ diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index ec52a8dc32fd..44b5a00a9c64 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -15,6 +15,11 @@ #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_expect.h> +#define NF_NAT_HELPER_PREFIX "ip_nat_" +#define NF_NAT_HELPER_NAME(name) NF_NAT_HELPER_PREFIX name +#define MODULE_ALIAS_NF_NAT_HELPER(name) \ + MODULE_ALIAS(NF_NAT_HELPER_NAME(name)) + struct module; enum nf_ct_helper_flags { @@ -54,6 +59,8 @@ struct nf_conntrack_helper { unsigned int queue_num; /* length of userspace private data stored in nf_conn_help->data */ u16 data_len; + /* name of NAT helper module */ + char nat_mod_name[NF_CT_HELPER_NAME_LEN]; }; /* Must be kept in sync with the classes defined by helpers */ @@ -153,4 +160,21 @@ nf_ct_helper_expectfn_find_by_symbol(const void *symbol); extern struct hlist_head *nf_ct_helper_hash; extern unsigned int nf_ct_helper_hsize; +struct nf_conntrack_nat_helper { + struct list_head list; + char mod_name[NF_CT_HELPER_NAME_LEN]; /* module name */ + struct module *module; /* pointer to self */ +}; + +#define NF_CT_NAT_HELPER_INIT(name) \ + { \ + .mod_name = NF_NAT_HELPER_NAME(name), \ + .module = THIS_MODULE \ + } + +void nf_nat_helper_register(struct nf_conntrack_nat_helper *nat); +void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat); +int nf_nat_helper_try_module_get(const char *name, u16 l3num, + u8 protonum); +void nf_nat_helper_put(struct nf_conntrack_helper *helper); #endif /*_NF_CONNTRACK_HELPER_H*/ diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 3394d75e1c80..00a8fbb2d735 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -88,6 +88,9 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct) int nf_conntrack_timeout_init(void); void nf_conntrack_timeout_fini(void); void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout); +int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, u8 l3num, u8 l4num, + const char *timeout_name); +void nf_ct_destroy_timeout(struct nf_conn *ct); #else static inline int nf_conntrack_timeout_init(void) { @@ -98,6 +101,18 @@ static inline void nf_conntrack_timeout_fini(void) { return; } + +static inline int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, + u8 l3num, u8 l4num, + const char *timeout_name) +{ + return -EOPNOTSUPP; +} + +static inline void nf_ct_destroy_timeout(struct nf_conn *ct) +{ + return; +} #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_NF_CONNTRACK_TIMEOUT diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index cf332c4e0b32..423cda2c6542 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -69,9 +69,9 @@ static inline bool nf_nat_oif_changed(unsigned int hooknum, #endif } -int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops, +int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, const struct nf_hook_ops *nat_ops, unsigned int ops_count); -void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops, +void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, unsigned int ops_count); unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, @@ -98,6 +98,9 @@ void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops); int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops); void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops); +int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops); +void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops); + unsigned int nf_nat_inet_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/include/net/netfilter/nf_nat_masquerade.h b/include/net/netfilter/nf_nat_masquerade.h new file mode 100644 index 000000000000..54a14d643c34 --- /dev/null +++ b/include/net/netfilter/nf_nat_masquerade.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NF_NAT_MASQUERADE_H_ +#define _NF_NAT_MASQUERADE_H_ + +#include <net/netfilter/nf_nat.h> + +unsigned int +nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, + const struct nf_nat_range2 *range, + const struct net_device *out); + +int nf_nat_masquerade_inet_register_notifiers(void); +void nf_nat_masquerade_inet_unregister_notifiers(void); + +unsigned int +nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, + const struct net_device *out); + +#endif /*_NF_NAT_MASQUERADE_H_ */ diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index a50a69f5334c..7239105d9d2e 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -119,4 +119,7 @@ nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family, return queue; } +int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, + const struct nf_hook_entries *entries, unsigned int index, + unsigned int verdict); #endif /* _NF_QUEUE_H */ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3e9ab643eedf..5b8624ae4a27 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -2,7 +2,6 @@ #ifndef _NET_NF_TABLES_H #define _NET_NF_TABLES_H -#include <linux/module.h> #include <linux/list.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> @@ -13,6 +12,8 @@ #include <net/netfilter/nf_flow_table.h> #include <net/netlink.h> +struct module; + #define NFT_JUMP_STACK_SIZE 16 struct nft_pktinfo { @@ -475,8 +476,6 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, enum nft_trans_phase phase); int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); -void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding, bool commit); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); /** @@ -808,23 +807,6 @@ void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr); -static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) -{ - int err; - - if (src->ops->clone) { - dst->ops = src->ops; - err = src->ops->clone(dst, src); - if (err < 0) - return err; - } else { - memcpy(dst, src, src->ops->size); - } - - __module_get(src->ops->type->owner); - return 0; -} - /** * struct nft_rule - nf_tables rule * @@ -1411,4 +1393,6 @@ struct nft_trans_flowtable { int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); +void __init nft_chain_route_init(void); +void nft_chain_route_fini(void); #endif /* _NET_NF_TABLES_H */ diff --git a/include/net/netlink.h b/include/net/netlink.h index 23f27b0b3cef..395b4406f4b0 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -183,6 +183,7 @@ enum { NLA_REJECT, NLA_EXACT_LEN, NLA_EXACT_LEN_WARN, + NLA_MIN_LEN, __NLA_TYPE_MAX, }; @@ -212,6 +213,7 @@ enum nla_policy_validation { * NLA_NUL_STRING Maximum length of string (excluding NUL) * NLA_FLAG Unused * NLA_BINARY Maximum length of attribute payload + * NLA_MIN_LEN Minimum length of attribute payload * NLA_NESTED, * NLA_NESTED_ARRAY Length verification is done by checking len of * nested header (or empty); len field is used if @@ -230,6 +232,7 @@ enum nla_policy_validation { * it is rejected. * NLA_EXACT_LEN_WARN Attribute should have exactly this length, a warning * is logged if it is longer, shorter is rejected. + * NLA_MIN_LEN Minimum length of attribute payload * All other Minimum length of attribute payload * * Meaning of `validation_data' field: @@ -281,7 +284,7 @@ enum nla_policy_validation { * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, - * [ATTR_BAZ] = { .len = sizeof(struct mystruct) }, + * [ATTR_BAZ] = { .type = NLA_EXACT_LEN, .len = sizeof(struct mystruct) }, * [ATTR_GOO] = { .type = NLA_BITFIELD32, .validation_data = &myvalidflags }, * }; */ @@ -296,12 +299,31 @@ struct nla_policy { }; int (*validate)(const struct nlattr *attr, struct netlink_ext_ack *extack); + /* This entry is special, and used for the attribute at index 0 + * only, and specifies special data about the policy, namely it + * specifies the "boundary type" where strict length validation + * starts for any attribute types >= this value, also, strict + * nesting validation starts here. + * + * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT + * for any types >= this, so need to use NLA_MIN_LEN to get the + * previous pure { .len = xyz } behaviour. The advantage of this + * is that types not specified in the policy will be rejected. + * + * For completely new families it should be set to 1 so that the + * validation is enforced for all attributes. For existing ones + * it should be set at least when new attributes are added to + * the enum used by the policy, and be set to the new value that + * was added to enforce strict validation from thereon. + */ + u16 strict_start_type; }; }; #define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len } #define NLA_POLICY_EXACT_LEN_WARN(_len) { .type = NLA_EXACT_LEN_WARN, \ .len = _len } +#define NLA_POLICY_MIN_LEN(_len) { .type = NLA_MIN_LEN, .len = _len } #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) @@ -365,21 +387,52 @@ struct nl_info { bool skip_notify; }; +/** + * enum netlink_validation - netlink message/attribute validation levels + * @NL_VALIDATE_LIBERAL: Old-style "be liberal" validation, not caring about + * extra data at the end of the message, attributes being longer than + * they should be, or unknown attributes being present. + * @NL_VALIDATE_TRAILING: Reject junk data encountered after attribute parsing. + * @NL_VALIDATE_MAXTYPE: Reject attributes > max type; Together with _TRAILING + * this is equivalent to the old nla_parse_strict()/nlmsg_parse_strict(). + * @NL_VALIDATE_UNSPEC: Reject attributes with NLA_UNSPEC in the policy. + * This can safely be set by the kernel when the given policy has no + * NLA_UNSPEC anymore, and can thus be used to ensure policy entries + * are enforced going forward. + * @NL_VALIDATE_STRICT_ATTRS: strict attribute policy parsing (e.g. + * U8, U16, U32 must have exact size, etc.) + * @NL_VALIDATE_NESTED: Check that NLA_F_NESTED is set for NLA_NESTED(_ARRAY) + * and unset for other policies. + */ +enum netlink_validation { + NL_VALIDATE_LIBERAL = 0, + NL_VALIDATE_TRAILING = BIT(0), + NL_VALIDATE_MAXTYPE = BIT(1), + NL_VALIDATE_UNSPEC = BIT(2), + NL_VALIDATE_STRICT_ATTRS = BIT(3), + NL_VALIDATE_NESTED = BIT(4), +}; + +#define NL_VALIDATE_DEPRECATED_STRICT (NL_VALIDATE_TRAILING |\ + NL_VALIDATE_MAXTYPE) +#define NL_VALIDATE_STRICT (NL_VALIDATE_TRAILING |\ + NL_VALIDATE_MAXTYPE |\ + NL_VALIDATE_UNSPEC |\ + NL_VALIDATE_STRICT_ATTRS |\ + NL_VALIDATE_NESTED) + int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)); int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags); -int nla_validate(const struct nlattr *head, int len, int maxtype, - const struct nla_policy *policy, - struct netlink_ext_ack *extack); -int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, - int len, const struct nla_policy *policy, - struct netlink_ext_ack *extack); -int nla_parse_strict(struct nlattr **tb, int maxtype, const struct nlattr *head, - int len, const struct nla_policy *policy, - struct netlink_ext_ack *extack); +int __nla_validate(const struct nlattr *head, int len, int maxtype, + const struct nla_policy *policy, unsigned int validate, + struct netlink_ext_ack *extack); +int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, + int len, const struct nla_policy *policy, unsigned int validate, + struct netlink_ext_ack *extack); int nla_policy_len(const struct nla_policy *, int); struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype); size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize); @@ -508,42 +561,167 @@ nlmsg_next(const struct nlmsghdr *nlh, int *remaining) } /** - * nlmsg_parse - parse attributes of a netlink message + * nla_parse - Parse a stream of attributes into a tb buffer + * @tb: destination array with maxtype+1 elements + * @maxtype: maximum attribute type to be expected + * @head: head of attribute stream + * @len: length of attribute stream + * @policy: validation policy + * @extack: extended ACK pointer + * + * Parses a stream of attributes and stores a pointer to each attribute in + * the tb array accessible via the attribute type. Attributes with a type + * exceeding maxtype will be rejected, policy must be specified, attributes + * will be validated in the strictest way possible. + * + * Returns 0 on success or a negative error code. + */ +static inline int nla_parse(struct nlattr **tb, int maxtype, + const struct nlattr *head, int len, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nla_parse(tb, maxtype, head, len, policy, + NL_VALIDATE_STRICT, extack); +} + +/** + * nla_parse_deprecated - Parse a stream of attributes into a tb buffer + * @tb: destination array with maxtype+1 elements + * @maxtype: maximum attribute type to be expected + * @head: head of attribute stream + * @len: length of attribute stream + * @policy: validation policy + * @extack: extended ACK pointer + * + * Parses a stream of attributes and stores a pointer to each attribute in + * the tb array accessible via the attribute type. Attributes with a type + * exceeding maxtype will be ignored and attributes from the policy are not + * always strictly validated (only for new attributes). + * + * Returns 0 on success or a negative error code. + */ +static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype, + const struct nlattr *head, int len, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nla_parse(tb, maxtype, head, len, policy, + NL_VALIDATE_LIBERAL, extack); +} + +/** + * nla_parse_deprecated_strict - Parse a stream of attributes into a tb buffer + * @tb: destination array with maxtype+1 elements + * @maxtype: maximum attribute type to be expected + * @head: head of attribute stream + * @len: length of attribute stream + * @policy: validation policy + * @extack: extended ACK pointer + * + * Parses a stream of attributes and stores a pointer to each attribute in + * the tb array accessible via the attribute type. Attributes with a type + * exceeding maxtype will be rejected as well as trailing data, but the + * policy is not completely strictly validated (only for new attributes). + * + * Returns 0 on success or a negative error code. + */ +static inline int nla_parse_deprecated_strict(struct nlattr **tb, int maxtype, + const struct nlattr *head, + int len, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nla_parse(tb, maxtype, head, len, policy, + NL_VALIDATE_DEPRECATED_STRICT, extack); +} + +/** + * __nlmsg_parse - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy + * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() */ -static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, - struct nlattr *tb[], int maxtype, - const struct nla_policy *policy, - struct netlink_ext_ack *extack) +static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, + struct nlattr *tb[], int maxtype, + const struct nla_policy *policy, + unsigned int validate, + struct netlink_ext_ack *extack) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) { NL_SET_ERR_MSG(extack, "Invalid header length"); return -EINVAL; } - return nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen), - nlmsg_attrlen(nlh, hdrlen), policy, extack); + return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen), + nlmsg_attrlen(nlh, hdrlen), policy, validate, + extack); } -static inline int nlmsg_parse_strict(const struct nlmsghdr *nlh, int hdrlen, - struct nlattr *tb[], int maxtype, - const struct nla_policy *policy, - struct netlink_ext_ack *extack) +/** + * nlmsg_parse - parse attributes of a netlink message + * @nlh: netlink message header + * @hdrlen: length of family specific header + * @tb: destination array with maxtype+1 elements + * @maxtype: maximum attribute type to be expected + * @validate: validation strictness + * @extack: extended ACK report struct + * + * See nla_parse() + */ +static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, + struct nlattr *tb[], int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) { - if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) { - NL_SET_ERR_MSG(extack, "Invalid header length"); - return -EINVAL; - } + return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen), + nlmsg_attrlen(nlh, hdrlen), policy, + NL_VALIDATE_STRICT, extack); +} - return nla_parse_strict(tb, maxtype, nlmsg_attrdata(nlh, hdrlen), - nlmsg_attrlen(nlh, hdrlen), policy, extack); +/** + * nlmsg_parse_deprecated - parse attributes of a netlink message + * @nlh: netlink message header + * @hdrlen: length of family specific header + * @tb: destination array with maxtype+1 elements + * @maxtype: maximum attribute type to be expected + * @extack: extended ACK report struct + * + * See nla_parse_deprecated() + */ +static inline int nlmsg_parse_deprecated(const struct nlmsghdr *nlh, int hdrlen, + struct nlattr *tb[], int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, + NL_VALIDATE_LIBERAL, extack); +} + +/** + * nlmsg_parse_deprecated_strict - parse attributes of a netlink message + * @nlh: netlink message header + * @hdrlen: length of family specific header + * @tb: destination array with maxtype+1 elements + * @maxtype: maximum attribute type to be expected + * @extack: extended ACK report struct + * + * See nla_parse_deprecated_strict() + */ +static inline int +nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, + struct nlattr *tb[], int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, + NL_VALIDATE_DEPRECATED_STRICT, extack); } /** @@ -562,26 +740,75 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, } /** - * nlmsg_validate - validate a netlink message including attributes + * nla_validate_deprecated - Validate a stream of attributes + * @head: head of attribute stream + * @len: length of attribute stream + * @maxtype: maximum attribute type to be expected + * @policy: validation policy + * @validate: validation strictness + * @extack: extended ACK report struct + * + * Validates all attributes in the specified attribute stream against the + * specified policy. Validation is done in liberal mode. + * See documenation of struct nla_policy for more details. + * + * Returns 0 on success or a negative error code. + */ +static inline int nla_validate_deprecated(const struct nlattr *head, int len, + int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_LIBERAL, + extack); +} + +/** + * nla_validate - Validate a stream of attributes + * @head: head of attribute stream + * @len: length of attribute stream + * @maxtype: maximum attribute type to be expected + * @policy: validation policy + * @validate: validation strictness + * @extack: extended ACK report struct + * + * Validates all attributes in the specified attribute stream against the + * specified policy. Validation is done in strict mode. + * See documenation of struct nla_policy for more details. + * + * Returns 0 on success or a negative error code. + */ +static inline int nla_validate(const struct nlattr *head, int len, int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_STRICT, + extack); +} + +/** + * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header * @hdrlen: length of familiy specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ -static inline int nlmsg_validate(const struct nlmsghdr *nlh, - int hdrlen, int maxtype, - const struct nla_policy *policy, - struct netlink_ext_ack *extack) +static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh, + int hdrlen, int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; - return nla_validate(nlmsg_attrdata(nlh, hdrlen), - nlmsg_attrlen(nlh, hdrlen), maxtype, policy, - extack); + return __nla_validate(nlmsg_attrdata(nlh, hdrlen), + nlmsg_attrlen(nlh, hdrlen), maxtype, + policy, NL_VALIDATE_LIBERAL, extack); } + + /** * nlmsg_report - need to report back to application? * @nlh: netlink message header @@ -909,8 +1136,32 @@ static inline int nla_parse_nested(struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { - return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, - extack); + if (!(nla->nla_type & NLA_F_NESTED)) { + NL_SET_ERR_MSG_ATTR(extack, nla, "NLA_F_NESTED is missing"); + return -EINVAL; + } + + return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, + NL_VALIDATE_STRICT, extack); +} + +/** + * nla_parse_nested_deprecated - parse nested attributes + * @tb: destination array with maxtype+1 elements + * @maxtype: maximum attribute type to be expected + * @nla: attribute containing the nested attributes + * @policy: validation policy + * @extack: extended ACK report struct + * + * See nla_parse_deprecated() + */ +static inline int nla_parse_nested_deprecated(struct nlattr *tb[], int maxtype, + const struct nlattr *nla, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, + NL_VALIDATE_LIBERAL, extack); } /** @@ -1415,13 +1666,18 @@ static inline void *nla_memdup(const struct nlattr *src, gfp_t gfp) } /** - * nla_nest_start - Start a new level of nested attributes + * nla_nest_start_noflag - Start a new level of nested attributes * @skb: socket buffer to add attributes to * @attrtype: attribute type of container * - * Returns the container attribute + * This function exists for backward compatibility to use in APIs which never + * marked their nest attributes with NLA_F_NESTED flag. New APIs should use + * nla_nest_start() which sets the flag. + * + * Returns the container attribute or NULL on error */ -static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) +static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb, + int attrtype) { struct nlattr *start = (struct nlattr *)skb_tail_pointer(skb); @@ -1432,6 +1688,21 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) } /** + * nla_nest_start - Start a new level of nested attributes, with NLA_F_NESTED + * @skb: socket buffer to add attributes to + * @attrtype: attribute type of container + * + * Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED + * flag. This is the preferred function to use in new code. + * + * Returns the container attribute or NULL on error + */ +static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) +{ + return nla_nest_start_noflag(skb, attrtype | NLA_F_NESTED); +} + +/** * nla_nest_end - Finalize nesting of attributes * @skb: socket buffer the attributes are stored in * @start: container attribute @@ -1465,6 +1736,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) * @start: container attribute * @maxtype: maximum attribute type to be expected * @policy: validation policy + * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the nested attribute stream against the @@ -1473,12 +1745,22 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) * * Returns 0 on success or a negative error code. */ -static inline int nla_validate_nested(const struct nlattr *start, int maxtype, - const struct nla_policy *policy, - struct netlink_ext_ack *extack) +static inline int __nla_validate_nested(const struct nlattr *start, int maxtype, + const struct nla_policy *policy, + unsigned int validate, + struct netlink_ext_ack *extack) +{ + return __nla_validate(nla_data(start), nla_len(start), maxtype, policy, + validate, extack); +} + +static inline int +nla_validate_nested_deprecated(const struct nlattr *start, int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) { - return nla_validate(nla_data(start), nla_len(start), maxtype, policy, - extack); + return __nla_validate_nested(start, maxtype, policy, + NL_VALIDATE_LIBERAL, extack); } /** diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index f19b53130bf7..806454e767bf 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -24,9 +24,9 @@ struct nf_generic_net { struct nf_tcp_net { unsigned int timeouts[TCP_CONNTRACK_TIMEOUT_MAX]; - unsigned int tcp_loose; - unsigned int tcp_be_liberal; - unsigned int tcp_max_retrans; + int tcp_loose; + int tcp_be_liberal; + int tcp_max_retrans; }; enum udp_conntrack { diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 104a6669e344..7698460a3dd1 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -9,6 +9,7 @@ #include <linux/uidgid.h> #include <net/inet_frag.h> #include <linux/rcupdate.h> +#include <linux/siphash.h> struct tcpm_hash_bucket; struct ctl_table_header; @@ -217,5 +218,6 @@ struct netns_ipv4 { unsigned int ipmr_seq; /* protected by rtnl_mutex */ atomic_t rt_genid; + siphash_key_t ip_id_key; }; #endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index b028a1dc150d..5e61b5a8635d 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -8,6 +8,7 @@ #ifndef __NETNS_IPV6_H__ #define __NETNS_IPV6_H__ #include <net/dst_ops.h> +#include <uapi/linux/icmpv6.h> struct ctl_table_header; @@ -33,6 +34,10 @@ struct netns_sysctl_ipv6 { int auto_flowlabels; int icmpv6_time; int icmpv6_echo_ignore_all; + int icmpv6_echo_ignore_multicast; + int icmpv6_echo_ignore_anycast; + DECLARE_BITMAP(icmpv6_ratemask, ICMPV6_MSG_MAX + 1); + unsigned long *icmpv6_ratemask_ptr; int anycast_src_echo_reply; int ip_nonlocal_bind; int fwmark_reflect; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index d5e7a1af346f..514e3c80ecc1 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -100,6 +100,11 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); #else +static inline bool tcf_block_shared(struct tcf_block *block) +{ + return false; +} + static inline int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, @@ -372,30 +377,6 @@ static inline bool tcf_exts_has_actions(struct tcf_exts *exts) } /** - * tcf_exts_has_one_action - check if exactly one action is present - * @exts: tc filter extensions handle - * - * Returns true if exactly one action is present. - */ -static inline bool tcf_exts_has_one_action(struct tcf_exts *exts) -{ -#ifdef CONFIG_NET_CLS_ACT - return exts->nr_actions == 1; -#else - return false; -#endif -} - -static inline struct tc_action *tcf_exts_first_action(struct tcf_exts *exts) -{ -#ifdef CONFIG_NET_CLS_ACT - return exts->actions[0]; -#else - return NULL; -#endif -} - -/** * tcf_exts_exec - execute tc filter extensions * @skb: socket buffer * @exts: tc filter extensions handle @@ -784,12 +765,14 @@ tc_cls_flower_offload_flow_rule(struct tc_cls_flower_offload *tc_flow_cmd) enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, + TC_CLSMATCHALL_STATS, }; struct tc_cls_matchall_offload { struct tc_cls_common_offload common; enum tc_matchall_command command; - struct tcf_exts *exts; + struct flow_rule *rule; + struct flow_stats stats; unsigned long cookie; }; diff --git a/include/net/psample.h b/include/net/psample.h index 9b80f814ab04..37a4df2325b2 100644 --- a/include/net/psample.h +++ b/include/net/psample.h @@ -3,7 +3,6 @@ #define __NET_PSAMPLE_H #include <uapi/linux/psample.h> -#include <linux/module.h> #include <linux/list.h> struct psample_group { diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 21a5243fecd1..9dfd7960d90a 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -106,10 +106,8 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, return req; } -static inline void reqsk_free(struct request_sock *req) +static inline void __reqsk_free(struct request_sock *req) { - WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0); - req->rsk_ops->destructor(req); if (req->rsk_listener) sock_put(req->rsk_listener); @@ -117,6 +115,12 @@ static inline void reqsk_free(struct request_sock *req) kmem_cache_free(req->rsk_ops->slab, req); } +static inline void reqsk_free(struct request_sock *req) +{ + WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0); + __reqsk_free(req); +} + static inline void reqsk_put(struct request_sock *req) { if (refcount_dec_and_test(&req->rsk_refcnt)) diff --git a/include/net/route.h b/include/net/route.h index 9883dc82f723..96f6c9ae33c2 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -29,6 +29,8 @@ #include <net/flow.h> #include <net/inet_sock.h> #include <net/ip_fib.h> +#include <net/arp.h> +#include <net/ndisc.h> #include <linux/in_route.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> @@ -55,12 +57,15 @@ struct rtable { unsigned int rt_flags; __u16 rt_type; __u8 rt_is_input; - __u8 rt_uses_gateway; + u8 rt_gw_family; int rt_iif; /* Info on neighbour */ - __be32 rt_gateway; + union { + __be32 rt_gw4; + struct in6_addr rt_gw6; + }; /* Miscellaneous cached information */ u32 rt_mtu_locked:1, @@ -82,8 +87,8 @@ static inline bool rt_is_output_route(const struct rtable *rt) static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr) { - if (rt->rt_gateway) - return rt->rt_gateway; + if (rt->rt_gw_family == AF_INET) + return rt->rt_gw4; return daddr; } @@ -347,4 +352,34 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst) return hoplimit; } +static inline struct neighbour *ip_neigh_gw4(struct net_device *dev, + __be32 daddr) +{ + struct neighbour *neigh; + + neigh = __ipv4_neigh_lookup_noref(dev, daddr); + if (unlikely(!neigh)) + neigh = __neigh_create(&arp_tbl, &daddr, dev, false); + + return neigh; +} + +static inline struct neighbour *ip_neigh_for_gw(struct rtable *rt, + struct sk_buff *skb, + bool *is_v6gw) +{ + struct net_device *dev = rt->dst.dev; + struct neighbour *neigh; + + if (likely(rt->rt_gw_family == AF_INET)) { + neigh = ip_neigh_gw4(dev, rt->rt_gw4); + } else if (rt->rt_gw_family == AF_INET6) { + neigh = ip_neigh_gw6(dev, &rt->rt_gw6); + *is_v6gw = true; + } else { + neigh = ip_neigh_gw4(dev, ip_hdr(skb)->daddr); + } + return neigh; +} + #endif /* _ROUTE_H */ diff --git a/include/net/nexthop.h b/include/net/rtnh.h index 902ff382a6dc..aa2cfc508f7c 100644 --- a/include/net/nexthop.h +++ b/include/net/rtnh.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NET_NEXTHOP_H -#define __NET_NEXTHOP_H +#ifndef __NET_RTNH_H +#define __NET_RTNH_H #include <linux/rtnetlink.h> #include <net/netlink.h> diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index a2b38b3deeca..21f434f3ac9e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -52,10 +52,7 @@ struct qdisc_size_table { struct qdisc_skb_head { struct sk_buff *head; struct sk_buff *tail; - union { - u32 qlen; - atomic_t atomic_qlen; - }; + __u32 qlen; spinlock_t lock; }; @@ -113,6 +110,9 @@ struct Qdisc { spinlock_t busylock ____cacheline_aligned_in_smp; spinlock_t seqlock; + + /* for NOLOCK qdisc, true if there are no enqueued skbs */ + bool empty; struct rcu_head rcu; }; @@ -143,11 +143,24 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc) return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; } +static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) +{ + return q->flags & TCQ_F_CPUSTATS; +} + +static inline bool qdisc_is_empty(const struct Qdisc *qdisc) +{ + if (qdisc_is_percpu_stats(qdisc)) + return qdisc->empty; + return !qdisc->q.qlen; +} + static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { if (!spin_trylock(&qdisc->seqlock)) return false; + qdisc->empty = false; } else if (qdisc_is_running(qdisc)) { return false; } @@ -351,13 +364,10 @@ struct tcf_proto { }; struct qdisc_skb_cb { - union { - struct { - unsigned int pkt_len; - u16 slave_dev_queue_mapping; - u16 tc_classid; - }; - struct bpf_flow_keys *flow_keys; + struct { + unsigned int pkt_len; + u16 slave_dev_queue_mapping; + u16 tc_classid; }; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; @@ -470,19 +480,27 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) BUILD_BUG_ON(sizeof(qcb->data) < sz); } +static inline int qdisc_qlen_cpu(const struct Qdisc *q) +{ + return this_cpu_ptr(q->cpu_qstats)->qlen; +} + static inline int qdisc_qlen(const struct Qdisc *q) { return q->q.qlen; } -static inline u32 qdisc_qlen_sum(const struct Qdisc *q) +static inline int qdisc_qlen_sum(const struct Qdisc *q) { - u32 qlen = q->qstats.qlen; + __u32 qlen = q->qstats.qlen; + int i; - if (q->flags & TCQ_F_NOLOCK) - qlen += atomic_read(&q->q.atomic_qlen); - else + if (qdisc_is_percpu_stats(q)) { + for_each_possible_cpu(i) + qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen; + } else { qlen += q->q.qlen; + } return qlen; } @@ -736,7 +754,7 @@ static inline bool qdisc_all_tx_empty(const struct net_device *dev) struct netdev_queue *txq = netdev_get_tx_queue(dev, i); const struct Qdisc *q = rcu_dereference(txq->qdisc); - if (q->q.qlen) { + if (!qdisc_is_empty(q)) { rcu_read_unlock(); return false; } @@ -806,11 +824,6 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, return sch->enqueue(skb, sch, to_free); } -static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) -{ - return q->flags & TCQ_F_CPUSTATS; -} - static inline void _bstats_update(struct gnet_stats_basic_packed *bstats, __u64 bytes, __u32 packets) { @@ -878,14 +891,14 @@ static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch, this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb)); } -static inline void qdisc_qstats_atomic_qlen_inc(struct Qdisc *sch) +static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch) { - atomic_inc(&sch->q.atomic_qlen); + this_cpu_inc(sch->cpu_qstats->qlen); } -static inline void qdisc_qstats_atomic_qlen_dec(struct Qdisc *sch) +static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch) { - atomic_dec(&sch->q.atomic_qlen); + this_cpu_dec(sch->cpu_qstats->qlen); } static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch) @@ -1095,6 +1108,32 @@ static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch) return skb; } +static inline void qdisc_update_stats_at_dequeue(struct Qdisc *sch, + struct sk_buff *skb) +{ + if (qdisc_is_percpu_stats(sch)) { + qdisc_qstats_cpu_backlog_dec(sch, skb); + qdisc_bstats_cpu_update(sch, skb); + qdisc_qstats_cpu_qlen_dec(sch); + } else { + qdisc_qstats_backlog_dec(sch, skb); + qdisc_bstats_update(sch, skb); + sch->q.qlen--; + } +} + +static inline void qdisc_update_stats_at_enqueue(struct Qdisc *sch, + unsigned int pkt_len) +{ + if (qdisc_is_percpu_stats(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++; + } +} + /* use instead of qdisc->dequeue() for all qdiscs queried with ->peek() */ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch) { @@ -1102,8 +1141,13 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch) if (skb) { skb = __skb_dequeue(&sch->gso_skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; + if (qdisc_is_percpu_stats(sch)) { + qdisc_qstats_cpu_backlog_dec(sch, skb); + qdisc_qstats_cpu_qlen_dec(sch); + } else { + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + } } else { skb = sch->dequeue(sch); } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 1d13ec3f2707..eefdfa5abf6e 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -421,7 +421,7 @@ static inline void sctp_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) /* * This mimics the behavior of skb_set_owner_r */ - sk->sk_forward_alloc -= event->rmem_len; + sk_mem_charge(sk, event->rmem_len); } /* Tests if the list has one and only one entry. */ diff --git a/include/net/sctp/ulpqueue.h b/include/net/sctp/ulpqueue.h index bb0ecba3db2b..f4ac7117ff29 100644 --- a/include/net/sctp/ulpqueue.h +++ b/include/net/sctp/ulpqueue.h @@ -59,7 +59,7 @@ void sctp_ulpq_free(struct sctp_ulpq *); int sctp_ulpq_tail_data(struct sctp_ulpq *, struct sctp_chunk *, gfp_t); /* Add a new event for propagation to the ULP. */ -int sctp_ulpq_tail_event(struct sctp_ulpq *, struct sctp_ulpevent *ev); +int sctp_ulpq_tail_event(struct sctp_ulpq *, struct sk_buff_head *skb_list); /* Renege previously received chunks. */ void sctp_ulpq_renege(struct sctp_ulpq *, struct sctp_chunk *, gfp_t); diff --git a/include/net/sock.h b/include/net/sock.h index 341f8bafa0cf..4d208c0f9c14 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -236,6 +236,8 @@ struct sock_common { /* public: */ }; +struct bpf_sk_storage; + /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock @@ -368,6 +370,7 @@ struct sock { atomic_t sk_drops; int sk_rcvlowat; struct sk_buff_head sk_error_queue; + struct sk_buff *sk_rx_skb_cache; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with @@ -414,6 +417,7 @@ struct sock { struct sk_buff *sk_send_head; struct rb_root tcp_rtx_queue; }; + struct sk_buff *sk_tx_skb_cache; struct sk_buff_head sk_write_queue; __s32 sk_peek_off; int sk_write_pending; @@ -508,6 +512,9 @@ struct sock { #endif void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; +#ifdef CONFIG_BPF_SYSCALL + struct bpf_sk_storage __rcu *sk_bpf_storage; +#endif struct rcu_head sk_rcu; }; @@ -966,7 +973,7 @@ static inline void sock_rps_record_flow_hash(__u32 hash) static inline void sock_rps_record_flow(const struct sock *sk) { #ifdef CONFIG_RPS - if (static_key_false(&rfs_needed)) { + if (static_branch_unlikely(&rfs_needed)) { /* Reading sk->sk_rxhash might incur an expensive cache line * miss. * @@ -1466,6 +1473,11 @@ static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) sock_set_flag(sk, SOCK_QUEUE_SHRUNK); sk->sk_wmem_queued -= skb->truesize; sk_mem_uncharge(sk, skb->truesize); + if (!sk->sk_tx_skb_cache) { + skb_zcopy_clear(skb, true); + sk->sk_tx_skb_cache = skb; + return; + } __kfree_skb(skb); } @@ -1607,6 +1619,8 @@ int sock_setsockopt(struct socket *sock, int level, int op, int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, int __user *optlen); +int sock_gettstamp(struct socket *sock, void __user *userstamp, + bool timeval, bool time32); struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, @@ -2427,6 +2441,15 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); + if ( +#ifdef CONFIG_RPS + !static_branch_unlikely(&rps_needed) && +#endif + !sk->sk_rx_skb_cache) { + sk->sk_rx_skb_cache = skb; + skb_orphan(skb); + return; + } __kfree_skb(skb); } @@ -2487,8 +2510,6 @@ static inline bool sk_listener(const struct sock *sk) } void sock_enable_timestamp(struct sock *sk, int flag); -int sock_get_timestamp(struct sock *, struct timeval __user *); -int sock_get_timestampns(struct sock *, struct timespec __user *); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index 86d13b01b39d..c7f24a2da1ca 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -5,7 +5,8 @@ #include <net/act_api.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> -#include <linux/module.h> + +struct module; struct tcf_ife_params { u8 eth_dst[ETH_ALEN]; diff --git a/include/net/tc_act/tc_police.h b/include/net/tc_act/tc_police.h new file mode 100644 index 000000000000..8b9ef3664262 --- /dev/null +++ b/include/net/tc_act/tc_police.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_TC_POLICE_H +#define __NET_TC_POLICE_H + +#include <net/act_api.h> + +struct tcf_police_params { + int tcfp_result; + u32 tcfp_ewma_rate; + s64 tcfp_burst; + u32 tcfp_mtu; + s64 tcfp_mtu_ptoks; + struct psched_ratecfg rate; + bool rate_present; + struct psched_ratecfg peak; + bool peak_present; + struct rcu_head rcu; +}; + +struct tcf_police { + struct tc_action common; + struct tcf_police_params __rcu *params; + + spinlock_t tcfp_lock ____cacheline_aligned_in_smp; + s64 tcfp_toks; + s64 tcfp_ptoks; + s64 tcfp_t_c; +}; + +#define to_police(pc) ((struct tcf_police *)pc) + +/* old policer structure from before tc actions */ +struct tc_police_compat { + u32 index; + int action; + u32 limit; + u32 burst; + u32 mtu; + struct tc_ratespec rate; + struct tc_ratespec peakrate; +}; + +static inline bool is_tcf_police(const struct tc_action *act) +{ +#ifdef CONFIG_NET_CLS_ACT + if (act->ops && act->ops->id == TCA_ID_POLICE) + return true; +#endif + return false; +} + +static inline u64 tcf_police_rate_bytes_ps(const struct tc_action *act) +{ + struct tcf_police *police = to_police(act); + struct tcf_police_params *params; + + params = rcu_dereference_bh(police->params); + return params->rate.rate_bytes_ps; +} + +static inline s64 tcf_police_tcfp_burst(const struct tc_action *act) +{ + struct tcf_police *police = to_police(act); + struct tcf_police_params *params; + + params = rcu_dereference_bh(police->params); + return params->tcfp_burst; +} + +#endif /* __NET_TC_POLICE_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 68ee02523b87..7cf1181630a3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1314,7 +1314,7 @@ static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq) static inline __sum16 tcp_v4_check(int len, __be32 saddr, __be32 daddr, __wsum base) { - return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base); + return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_TCP, base); } static inline bool tcp_checksum_complete(struct sk_buff *skb) diff --git a/include/net/tls.h b/include/net/tls.h index 5934246b2c6f..39ea62f0c1f6 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -60,6 +60,17 @@ #define TLS_AAD_SPACE_SIZE 13 #define TLS_DEVICE_NAME_MAX 32 +#define MAX_IV_SIZE 16 + +/* For AES-CCM, the full 16-bytes of IV is made of '4' fields of given sizes. + * + * IV[16] = b0[1] || implicit nonce[4] || explicit nonce[8] || length[3] + * + * The field 'length' is encoded in field 'b0' as '(length width - 1)'. + * Hence b0 contains (3 - 1) = 2. + */ +#define TLS_AES_CCM_IV_B0_BYTE 2 + /* * This structure defines the routines for Inline TLS driver. * The following routines are optional and filled with a @@ -123,8 +134,7 @@ struct tls_rec { struct scatterlist sg_content_type; char aad_space[TLS_AAD_SPACE_SIZE]; - u8 iv_data[TLS_CIPHER_AES_GCM_128_IV_SIZE + - TLS_CIPHER_AES_GCM_128_SALT_SIZE]; + u8 iv_data[MAX_IV_SIZE]; struct aead_request aead_req; u8 aead_req_ctx[]; }; @@ -219,6 +229,7 @@ struct tls_prot_info { u16 tag_size; u16 overhead_size; u16 iv_size; + u16 salt_size; u16 rec_seq_size; u16 aad_size; u16 tail_size; @@ -266,6 +277,23 @@ struct tls_context { void (*unhash)(struct sock *sk); }; +enum tls_offload_ctx_dir { + TLS_OFFLOAD_CTX_DIR_RX, + TLS_OFFLOAD_CTX_DIR_TX, +}; + +struct tlsdev_ops { + int (*tls_dev_add)(struct net_device *netdev, struct sock *sk, + enum tls_offload_ctx_dir direction, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn); + void (*tls_dev_del)(struct net_device *netdev, + struct tls_context *ctx, + enum tls_offload_ctx_dir direction); + void (*tls_dev_resync_rx)(struct net_device *netdev, + struct sock *sk, u32 seq, u64 rcd_sn); +}; + struct tls_offload_context_rx { /* sw must be the first member of tls_offload_context_rx */ struct tls_sw_context_rx sw; @@ -306,7 +334,6 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx); int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); -void tls_device_sk_destruct(struct sock *sk); void tls_device_free_resources_tx(struct sock *sk); void tls_device_init(void); void tls_device_cleanup(void); @@ -325,7 +352,6 @@ static inline u32 tls_record_start_seq(struct tls_record_info *rec) return rec->end_seq - rec->len; } -void tls_sk_destruct(struct sock *sk, struct tls_context *ctx); int tls_push_sg(struct sock *sk, struct tls_context *ctx, struct scatterlist *sg, u16 first_offset, int flags); @@ -536,7 +562,7 @@ static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); - atomic64_set(&rx_ctx->resync_req, ((((uint64_t)seq) << 32) | 1)); + atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | 1); } diff --git a/include/net/udp.h b/include/net/udp.h index fd6d948755c8..d8ce937bc395 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -269,13 +269,13 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, - int noblock, int *peeked, int *off, int *err); + int noblock, int *off, int *err); static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *err) { - int peeked, off = 0; + int off = 0; - return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err); + return __skb_recv_udp(sk, flags, noblock, &off, err); } int udp_v4_early_demux(struct sk_buff *skb); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index b8137953fea3..4b1f95e08307 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -7,7 +7,7 @@ #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> -#include <net/addrconf.h> +#include <net/ipv6_stubs.h> #endif struct udp_port_cfg { diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 00254a58824b..83b5999a2587 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -8,6 +8,8 @@ #include <net/rtnetlink.h> #include <net/switchdev.h> +#define IANA_VXLAN_UDP_PORT 4789 + /* VXLAN protocol (RFC 7348) header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |R|R|R|R|I|R|R|R| Reserved | diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 99f722c4d804..a2907873ed56 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -132,6 +132,17 @@ struct xfrm_state_offload { u8 flags; }; +struct xfrm_mode { + u8 encap; + u8 family; + u8 flags; +}; + +/* Flags for xfrm_mode. */ +enum { + XFRM_MODE_FLAG_TUNNEL = 1, +}; + /* Full description of state of transformer. */ struct xfrm_state { possible_net_t xs_net; @@ -234,9 +245,9 @@ struct xfrm_state { /* Reference to data common to all the instances of this * transformer. */ const struct xfrm_type *type; - struct xfrm_mode *inner_mode; - struct xfrm_mode *inner_mode_iaf; - struct xfrm_mode *outer_mode; + struct xfrm_mode inner_mode; + struct xfrm_mode inner_mode_iaf; + struct xfrm_mode outer_mode; const struct xfrm_type_offload *type_offload; @@ -316,13 +327,6 @@ struct xfrm_policy_afinfo { xfrm_address_t *saddr, xfrm_address_t *daddr, u32 mark); - void (*decode_session)(struct sk_buff *skb, - struct flowi *fl, - int reverse); - int (*get_tos)(const struct flowi *fl); - int (*init_path)(struct xfrm_dst *path, - struct dst_entry *dst, - int nfheader_len); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl); @@ -348,7 +352,6 @@ struct xfrm_state_afinfo { struct module *owner; const struct xfrm_type *type_map[IPPROTO_MAX]; const struct xfrm_type_offload *type_offload_map[IPPROTO_MAX]; - struct xfrm_mode *mode_map[XFRM_MODE_MAX]; int (*init_flags)(struct xfrm_state *x); void (*init_tempsel)(struct xfrm_selector *sel, @@ -423,78 +426,6 @@ struct xfrm_type_offload { int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); -struct xfrm_mode { - /* - * Remove encapsulation header. - * - * The IP header will be moved over the top of the encapsulation - * header. - * - * On entry, the transport header shall point to where the IP header - * should be and the network header shall be set to where the IP - * header currently is. skb->data shall point to the start of the - * payload. - */ - int (*input2)(struct xfrm_state *x, struct sk_buff *skb); - - /* - * This is the actual input entry point. - * - * For transport mode and equivalent this would be identical to - * input2 (which does not need to be set). While tunnel mode - * and equivalent would set this to the tunnel encapsulation function - * xfrm4_prepare_input that would in turn call input2. - */ - int (*input)(struct xfrm_state *x, struct sk_buff *skb); - - /* - * Add encapsulation header. - * - * On exit, the transport header will be set to the start of the - * encapsulation header to be filled in by x->type->output and - * the mac header will be set to the nextheader (protocol for - * IPv4) field of the extension header directly preceding the - * encapsulation header, or in its absence, that of the top IP - * header. The value of the network header will always point - * to the top IP header while skb->data will point to the payload. - */ - int (*output2)(struct xfrm_state *x,struct sk_buff *skb); - - /* - * This is the actual output entry point. - * - * For transport mode and equivalent this would be identical to - * output2 (which does not need to be set). While tunnel mode - * and equivalent would set this to a tunnel encapsulation function - * (xfrm4_prepare_output or xfrm6_prepare_output) that would in turn - * call output2. - */ - int (*output)(struct xfrm_state *x, struct sk_buff *skb); - - /* - * Adjust pointers into the packet and do GSO segmentation. - */ - struct sk_buff *(*gso_segment)(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features); - - /* - * Adjust pointers into the packet when IPsec is done at layer2. - */ - void (*xmit)(struct xfrm_state *x, struct sk_buff *skb); - - struct xfrm_state_afinfo *afinfo; - struct module *owner; - unsigned int encap; - int flags; -}; - -/* Flags for xfrm_mode. */ -enum { - XFRM_MODE_FLAG_TUNNEL = 1, -}; - -int xfrm_register_mode(struct xfrm_mode *mode, int family); -int xfrm_unregister_mode(struct xfrm_mode *mode, int family); - static inline int xfrm_af2proto(unsigned int family) { switch(family) { @@ -507,13 +438,13 @@ static inline int xfrm_af2proto(unsigned int family) } } -static inline struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto) +static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto) { if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6)) - return x->inner_mode; + return &x->inner_mode; else - return x->inner_mode_iaf; + return &x->inner_mode_iaf; } struct xfrm_tmpl { @@ -1623,7 +1554,6 @@ int xfrm_init_replay(struct xfrm_state *x); int xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload); int xfrm_init_state(struct xfrm_state *x); -int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb); 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(struct sk_buff *skb, @@ -1631,7 +1561,11 @@ int xfrm_trans_queue(struct sk_buff *skb, struct sk_buff *)); int xfrm_output_resume(struct sk_buff *skb, int err); int xfrm_output(struct sock *sk, struct sk_buff *skb); -int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb); + +#if IS_ENABLED(CONFIG_NET_PKTGEN) +int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb); +#endif + void xfrm_local_error(struct sk_buff *skb, int mtu); int xfrm4_extract_header(struct sk_buff *skb); int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb); @@ -1650,10 +1584,8 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) } int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb); -int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb); -int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err); int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); @@ -1669,7 +1601,6 @@ int xfrm6_rcv(struct sk_buff *skb); int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto); void xfrm6_local_error(struct sk_buff *skb, u32 mtu); -int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err); int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol); int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol); int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family); @@ -1677,7 +1608,6 @@ int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family) __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr); __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr); int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb); -int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, @@ -2069,7 +1999,7 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, tunnel = true; break; } - if (tunnel && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)) + if (tunnel && !(x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL)) return -EINVAL; return 0; |