diff options
Diffstat (limited to 'include/net')
32 files changed, 720 insertions, 231 deletions
diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index da84cf9..5ab4c99 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -141,6 +141,16 @@ struct lowpan_dev { u8 priv[0] __aligned(sizeof(void *)); }; +struct lowpan_802154_neigh { + __le16 short_addr; +}; + +static inline +struct lowpan_802154_neigh *lowpan_802154_neigh(void *neigh_priv) +{ + return neigh_priv; +} + static inline struct lowpan_dev *lowpan_dev(const struct net_device *dev) { @@ -244,6 +254,12 @@ static inline bool lowpan_fetch_skb(struct sk_buff *skb, void *data, return false; } +static inline bool lowpan_802154_is_valid_src_short_addr(__le16 addr) +{ + /* First bit of addr is multicast, reserved or 802.15.4 specific */ + return !(addr & cpu_to_le16(0x8000)); +} + static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, const size_t len) { diff --git a/include/net/act_api.h b/include/net/act_api.h index 9a9a8ed..fb82b5b 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -2,8 +2,8 @@ #define __NET_ACT_API_H /* - * Public police action API for classifiers/qdiscs - */ + * Public action API for classifiers/qdiscs +*/ #include <net/sch_generic.h> #include <net/pkt_sched.h> @@ -76,6 +76,16 @@ static inline void tcf_lastuse_update(struct tcf_t *tm) if (tm->lastuse != now) tm->lastuse = now; + if (unlikely(!tm->firstuse)) + tm->firstuse = now; +} + +static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm) +{ + dtm->install = jiffies_to_clock_t(jiffies - stm->install); + dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse); + dtm->firstuse = jiffies_to_clock_t(jiffies - stm->firstuse); + dtm->expires = jiffies_to_clock_t(stm->expires); } struct tc_action { @@ -97,7 +107,8 @@ struct tc_action_ops { char kind[IFNAMSIZ]; __u32 type; /* TBD to match kind */ struct module *owner; - int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *); + int (*act)(struct sk_buff *, const struct tc_action *, + struct tcf_result *); int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *, int bind); int (*lookup)(struct net *, struct tc_action *, u32); @@ -115,8 +126,8 @@ struct tc_action_net { }; static inline -int tc_action_net_init(struct tc_action_net *tn, const struct tc_action_ops *ops, - unsigned int mask) +int tc_action_net_init(struct tc_action_net *tn, + const struct tc_action_ops *ops, unsigned int mask) { int err = 0; @@ -144,8 +155,8 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct tc_action *a); int tcf_hash_search(struct tc_action_net *tn, struct tc_action *a, u32 index); u32 tcf_hash_new_index(struct tc_action_net *tn); -int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a, - int bind); +bool tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a, + int bind); int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action *a, int size, int bind, bool cpustats); void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est); @@ -159,7 +170,8 @@ static inline int tcf_hash_release(struct tc_action *a, bool bind) } int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops); -int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops); +int tcf_unregister_action(struct tc_action_ops *a, + struct pernet_operations *ops); int tcf_action_destroy(struct list_head *actions, int bind); int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, struct tcf_result *res); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 730d856..9826d3a 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -94,6 +94,16 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr); +void addrconf_add_linklocal(struct inet6_dev *idev, + const struct in6_addr *addr, u32 flags); + +int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, + const struct prefix_info *pinfo, + struct inet6_dev *in6_dev, + const struct in6_addr *addr, int addr_type, + u32 addr_flags, bool sllao, bool tokenized, + __u32 valid_lft, u32 prefered_lft); + static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) { if (dev->addr_len != ETH_ALEN) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6392167..7bbb00d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2367,19 +2367,23 @@ struct cfg80211_qos_map { * (invoked with the wireless_dev mutex held) * * @connect: Connect to the ESS with the specified parameters. When connected, - * call cfg80211_connect_result() with status code %WLAN_STATUS_SUCCESS. - * If the connection fails for some reason, call cfg80211_connect_result() - * with the status from the AP. The driver is allowed to roam to other - * BSSes within the ESS when the other BSS matches the connect parameters. - * When such roaming is initiated by the driver, the driver is expected to - * verify that the target matches the configured security parameters and - * to use Reassociation Request frame instead of Association Request frame. - * The connect function can also be used to request the driver to perform - * a specific roam when connected to an ESS. In that case, the prev_bssid + * call cfg80211_connect_result()/cfg80211_connect_bss() with status code + * %WLAN_STATUS_SUCCESS. If the connection fails for some reason, call + * cfg80211_connect_result()/cfg80211_connect_bss() with the status code + * from the AP or cfg80211_connect_timeout() if no frame with status code + * was received. + * The driver is allowed to roam to other BSSes within the ESS when the + * other BSS matches the connect parameters. When such roaming is initiated + * by the driver, the driver is expected to verify that the target matches + * the configured security parameters and to use Reassociation Request + * frame instead of Association Request frame. + * The connect function can also be used to request the driver to perform a + * specific roam when connected to an ESS. In that case, the prev_bssid * parameter is set to the BSSID of the currently associated BSS as an - * indication of requesting reassociation. In both the driver-initiated and - * new connect() call initiated roaming cases, the result of roaming is - * indicated with a call to cfg80211_roamed() or cfg80211_roamed_bss(). + * indication of requesting reassociation. + * In both the driver-initiated and new connect() call initiated roaming + * cases, the result of roaming is indicated with a call to + * cfg80211_roamed() or cfg80211_roamed_bss(). * (invoked with the wireless_dev mutex held) * @disconnect: Disconnect from the BSS/ESS. * (invoked with the wireless_dev mutex held) @@ -3080,6 +3084,24 @@ struct wiphy_vendor_command { }; /** + * struct wiphy_iftype_ext_capab - extended capabilities per interface type + * @iftype: interface type + * @extended_capabilities: extended capabilities supported by the driver, + * additional capabilities might be supported by userspace; these are the + * 802.11 extended capabilities ("Extended Capabilities element") and are + * in the same format as in the information element. See IEEE Std + * 802.11-2012 8.4.2.29 for the defined fields. + * @extended_capabilities_mask: mask of the valid values + * @extended_capabilities_len: length of the extended capabilities + */ +struct wiphy_iftype_ext_capab { + enum nl80211_iftype iftype; + const u8 *extended_capabilities; + const u8 *extended_capabilities_mask; + u8 extended_capabilities_len; +}; + +/** * struct wiphy - wireless hardware description * @reg_notifier: the driver's regulatory notification callback, * note that if your driver uses wiphy_apply_custom_regulatory() @@ -3199,9 +3221,14 @@ struct wiphy_vendor_command { * additional capabilities might be supported by userspace; these are * the 802.11 extended capabilities ("Extended Capabilities element") * and are in the same format as in the information element. See - * 802.11-2012 8.4.2.29 for the defined fields. + * 802.11-2012 8.4.2.29 for the defined fields. These are the default + * extended capabilities to be used if the capabilities are not specified + * for a specific interface type in iftype_ext_capab. * @extended_capabilities_mask: mask of the valid values * @extended_capabilities_len: length of the extended capabilities + * @iftype_ext_capab: array of extended capabilities per interface type + * @num_iftype_ext_capab: number of interface types for which extended + * capabilities are specified separately. * @coalesce: packet coalescing support information * * @vendor_commands: array of vendor commands supported by the hardware @@ -3301,6 +3328,9 @@ struct wiphy { const u8 *extended_capabilities, *extended_capabilities_mask; u8 extended_capabilities_len; + const struct wiphy_iftype_ext_capab *iftype_ext_capab; + unsigned int num_iftype_ext_capab; + /* If multiple wiphys are registered and you're handed e.g. * a regular netdev with assigned ieee80211_ptr, you won't * know whether it points to a wiphy your driver has registered @@ -4680,7 +4710,7 @@ static inline void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp) void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid, struct cfg80211_bss *bss, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, - size_t resp_ie_len, u16 status, gfp_t gfp); + size_t resp_ie_len, int status, gfp_t gfp); /** * cfg80211_connect_result - notify cfg80211 of connection result @@ -4710,6 +4740,29 @@ cfg80211_connect_result(struct net_device *dev, const u8 *bssid, } /** + * cfg80211_connect_timeout - notify cfg80211 of connection timeout + * + * @dev: network device + * @bssid: the BSSID of the AP + * @req_ie: association request IEs (maybe be %NULL) + * @req_ie_len: association request IEs length + * @gfp: allocation flags + * + * It should be called by the underlying driver whenever connect() has failed + * in a sequence where no explicit authentication/association rejection was + * received from the AP. This could happen, e.g., due to not being able to send + * out the Authentication or Association Request frame or timing out while + * waiting for the response. + */ +static inline void +cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, + const u8 *req_ie, size_t req_ie_len, gfp_t gfp) +{ + cfg80211_connect_bss(dev, bssid, NULL, req_ie, req_ie_len, NULL, 0, -1, + gfp); +} + +/** * cfg80211_roamed - notify cfg80211 of roaming * * @dev: network device diff --git a/include/net/codel_qdisc.h b/include/net/codel_qdisc.h index 8144d9c..098630f 100644 --- a/include/net/codel_qdisc.h +++ b/include/net/codel_qdisc.h @@ -52,6 +52,7 @@ /* Qdiscs using codel plugin must use codel_skb_cb in their own cb[] */ struct codel_skb_cb { codel_time_t enqueue_time; + unsigned int mem_usage; }; static struct codel_skb_cb *get_codel_cb(const struct sk_buff *skb) diff --git a/include/net/devlink.h b/include/net/devlink.h index 1d45b61..c99ffe8 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -90,6 +90,9 @@ struct devlink_ops { u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); + + int (*eswitch_mode_get)(struct devlink *devlink, u16 *p_mode); + int (*eswitch_mode_set)(struct devlink *devlink, u16 mode); }; static inline void *devlink_priv(struct devlink *devlink) diff --git a/include/net/dsa.h b/include/net/dsa.h index 17c3d37..20b3087 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -26,6 +26,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_TRAILER, DSA_TAG_PROTO_EDSA, DSA_TAG_PROTO_BRCM, + DSA_TAG_LAST, /* MUST BE LAST */ }; #define DSA_MAX_SWITCHES 4 @@ -58,12 +59,11 @@ struct dsa_chip_data { struct device_node *port_dn[DSA_MAX_PORTS]; /* - * An array (with nr_chips elements) of which element [a] - * indicates which port on this switch should be used to - * send packets to that are destined for switch a. Can be - * NULL if there is only one switch chip. + * An array of which element [a] indicates which port on this + * switch should be used to send packets to that are destined + * for switch a. Can be NULL if there is only one switch chip. */ - s8 *rtable; + s8 rtable[DSA_MAX_SWITCHES]; }; struct dsa_platform_data { @@ -85,6 +85,17 @@ struct dsa_platform_data { struct packet_type; struct dsa_switch_tree { + struct list_head list; + + /* Tree identifier */ + u32 tree; + + /* Number of switches attached to this tree */ + struct kref refcount; + + /* Has this tree been applied to the hardware? */ + bool applied; + /* * Configuration data for the platform device that owns * this dsa switch tree instance. @@ -100,12 +111,12 @@ struct dsa_switch_tree { struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); - enum dsa_tag_protocol tag_protocol; /* * Original copy of the master netdev ethtool_ops */ struct ethtool_ops master_ethtool_ops; + const struct ethtool_ops *master_orig_ethtool_ops; /* * The switch and port to which the CPU is attached. @@ -117,6 +128,17 @@ struct dsa_switch_tree { * Data for the individual switch chips. */ struct dsa_switch *ds[DSA_MAX_SWITCHES]; + + /* + * Tagging protocol operations for adding and removing an + * encapsulation tag. + */ + const struct dsa_device_ops *tag_ops; +}; + +struct dsa_port { + struct net_device *netdev; + struct device_node *dn; }; struct dsa_switch { @@ -144,6 +166,13 @@ struct dsa_switch { */ struct dsa_switch_driver *drv; + /* + * An array of which element [a] indicates which port on this + * switch should be used to send packets to that are destined + * for switch a. Can be NULL if there is only one switch chip. + */ + s8 rtable[DSA_MAX_SWITCHES]; + #ifdef CONFIG_NET_DSA_HWMON /* * Hardware monitoring information @@ -153,13 +182,19 @@ struct dsa_switch { #endif /* + * The lower device this switch uses to talk to the host + */ + struct net_device *master_netdev; + + /* * Slave mii_bus and devices for the individual ports. */ u32 dsa_port_mask; + u32 cpu_port_mask; u32 enabled_port_mask; u32 phys_mii_mask; + struct dsa_port ports[DSA_MAX_PORTS]; struct mii_bus *slave_mii_bus; - struct net_device *ports[DSA_MAX_PORTS]; }; static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) @@ -174,7 +209,7 @@ static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p) { - return ds->enabled_port_mask & (1 << p) && ds->ports[p]; + return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev; } static inline u8 dsa_upstream_port(struct dsa_switch *ds) @@ -190,7 +225,7 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) if (dst->cpu_switch == ds->index) return dst->cpu_port; else - return ds->cd->rtable[dst->cpu_switch]; + return ds->rtable[dst->cpu_switch]; } struct switchdev_trans; @@ -344,4 +379,7 @@ static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) { return dst->rcv != NULL; } + +void dsa_unregister_switch(struct dsa_switch *ds); +int dsa_register_switch(struct dsa_switch *ds, struct device_node *np); #endif diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 59160de..456e4a6 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -17,7 +17,8 @@ struct fib_rule { u32 flags; u32 table; u8 action; - /* 3 bytes hole, try to use */ + u8 l3mdev; + /* 2 bytes hole, try to use */ u32 target; __be64 tun_id; struct fib_rule __rcu *ctarget; @@ -36,6 +37,7 @@ struct fib_lookup_arg { void *lookup_ptr; void *result; struct fib_rule *rule; + u32 table; int flags; #define FIB_LOOKUP_NOREF 1 #define FIB_LOOKUP_IGNORE_LINKSTATE 2 @@ -89,7 +91,8 @@ struct fib_rules_ops { [FRA_TABLE] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \ - [FRA_GOTO] = { .type = NLA_U32 } + [FRA_GOTO] = { .type = NLA_U32 }, \ + [FRA_L3MDEV] = { .type = NLA_U8 } static inline void fib_rule_get(struct fib_rule *rule) { @@ -102,6 +105,20 @@ static inline void fib_rule_put(struct fib_rule *rule) kfree_rcu(rule, rcu); } +#ifdef CONFIG_NET_L3_MASTER_DEV +static inline u32 fib_rule_get_table(struct fib_rule *rule, + struct fib_lookup_arg *arg) +{ + return rule->l3mdev ? arg->table : rule->table; +} +#else +static inline u32 fib_rule_get_table(struct fib_rule *rule, + struct fib_lookup_arg *arg) +{ + return rule->table; +} +#endif + static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) { if (nla[FRA_TABLE]) @@ -117,4 +134,7 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags, struct fib_lookup_arg *); int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); + +int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh); +int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh); #endif diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 610cd39..231e121 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -33,10 +33,12 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); -int gnet_stats_copy_basic(struct gnet_dump *d, +int gnet_stats_copy_basic(const seqcount_t *running, + struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); -void __gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats, +void __gnet_stats_copy_basic(const seqcount_t *running, + struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); int gnet_stats_copy_rate_est(struct gnet_dump *d, @@ -52,13 +54,15 @@ int gnet_stats_finish_copy(struct gnet_dump *d); int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct gnet_stats_rate_est64 *rate_est, - spinlock_t *stats_lock, struct nlattr *opt); + spinlock_t *stats_lock, + seqcount_t *running, struct nlattr *opt); void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est64 *rate_est); int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct gnet_stats_rate_est64 *rate_est, - spinlock_t *stats_lock, struct nlattr *opt); + spinlock_t *stats_lock, + seqcount_t *running, struct nlattr *opt); bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, const struct gnet_stats_rate_est64 *rate_est); #endif diff --git a/include/net/geneve.h b/include/net/geneve.h index cb544a5..ec0327d 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -1,10 +1,7 @@ #ifndef __NET_GENEVE_H #define __NET_GENEVE_H 1 -#ifdef CONFIG_INET #include <net/udp_tunnel.h> -#endif - /* Geneve Header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ @@ -62,12 +59,6 @@ struct genevehdr { struct geneve_opt options[]; }; -static inline void geneve_get_rx_port(struct net_device *netdev) -{ - ASSERT_RTNL(); - call_netdevice_notifiers(NETDEV_OFFLOAD_PUSH_GENEVE, netdev); -} - #ifdef CONFIG_INET struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 54c7794..d97305d 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -18,6 +18,7 @@ struct route_info { __u8 prefix[0]; /* 0,8 or 16 */ }; +#include <net/addrconf.h> #include <net/flow.h> #include <net/ip6_fib.h> #include <net/sock.h> @@ -76,6 +77,8 @@ static inline struct dst_entry *ip6_route_output(struct net *net, struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, int flags); +struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, + int ifindex, struct flowi6 *fl6, int flags); int ip6_route_init(void); void ip6_route_cleanup(void); @@ -86,9 +89,23 @@ int ip6_route_add(struct fib6_config *cfg); int ip6_ins_rt(struct rt6_info *); int ip6_del_rt(struct rt6_info *); -int ip6_route_get_saddr(struct net *net, struct rt6_info *rt, - const struct in6_addr *daddr, unsigned int prefs, - struct in6_addr *saddr); +static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt, + const struct in6_addr *daddr, + unsigned int prefs, + struct in6_addr *saddr) +{ + struct inet6_dev *idev = + rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL; + int err = 0; + + if (rt && rt->rt6i_prefsrc.plen) + *saddr = rt->rt6i_prefsrc.addr; + else + err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, + daddr, prefs, saddr); + + return err; +} struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, int flags); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index dbf4444..a5e7035 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -132,6 +132,7 @@ struct ip_tunnel { int ip_tnl_net_id; struct gro_cells gro_cells; bool collect_md; + bool ignore_df; }; #define TUNNEL_CSUM __cpu_to_be16(0x01) @@ -156,6 +157,7 @@ struct tnl_ptk_info { __be16 proto; __be32 key; __be32 seq; + int hdr_len; }; #define PACKET_RCVD 0 diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 374388d..e900950 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -11,6 +11,8 @@ #ifndef _NET_L3MDEV_H_ #define _NET_L3MDEV_H_ +#include <net/fib_rules.h> + /** * struct l3mdev_ops - l3mdev operations * @@ -36,11 +38,17 @@ struct l3mdev_ops { /* IPv6 ops */ struct dst_entry * (*l3mdev_get_rt6_dst)(const struct net_device *dev, - const struct flowi6 *fl6); + struct flowi6 *fl6); + int (*l3mdev_get_saddr6)(struct net_device *dev, + const struct sock *sk, + struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV +int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, + struct fib_lookup_arg *arg); + int l3mdev_master_ifindex_rcu(const struct net_device *dev); static inline int l3mdev_master_ifindex(struct net_device *dev) { @@ -71,6 +79,31 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) return rc; } +static inline +const struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) +{ + /* netdev_master_upper_dev_get_rcu calls + * list_first_or_null_rcu to walk the upper dev list. + * list_first_or_null_rcu does not handle a const arg. We aren't + * making changes, just want the master device from that list so + * typecast to remove the const + */ + struct net_device *dev = (struct net_device *)_dev; + const struct net_device *master; + + if (!dev) + return NULL; + + if (netif_is_l3_master(dev)) + master = dev; + else if (netif_is_l3_slave(dev)) + master = netdev_master_upper_dev_get_rcu(dev); + else + master = NULL; + + return master; +} + /* get index of an interface to use for FIB lookups. For devices * enslaved to an L3 master device FIB lookups are based on the * master index @@ -134,7 +167,9 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4); -struct dst_entry *l3mdev_get_rt6_dst(struct net *net, const struct flowi6 *fl6); +struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6); +int l3mdev_get_saddr6(struct net *net, const struct sock *sk, + struct flowi6 *fl6); static inline struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) @@ -180,6 +215,12 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) return 0; } +static inline +const struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) +{ + return NULL; +} + static inline int l3mdev_fib_oif_rcu(struct net_device *dev) { return dev ? dev->ifindex : 0; @@ -220,11 +261,17 @@ static inline int l3mdev_get_saddr(struct net *net, int ifindex, } static inline -struct dst_entry *l3mdev_get_rt6_dst(struct net *net, const struct flowi6 *fl6) +struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6) { return NULL; } +static inline int l3mdev_get_saddr6(struct net *net, const struct sock *sk, + struct flowi6 *fl6) +{ + return 0; +} + static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { @@ -236,6 +283,13 @@ struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return skb; } + +static inline +int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, + struct fib_lookup_arg *arg) +{ + return 1; +} #endif #endif /* _NET_L3MDEV_H_ */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index be30b05..a52009f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -21,6 +21,7 @@ #include <linux/skbuff.h> #include <linux/ieee80211.h> #include <net/cfg80211.h> +#include <net/codel.h> #include <asm/unaligned.h> /** @@ -895,7 +896,18 @@ struct ieee80211_tx_info { unsigned long jiffies; }; /* NB: vif can be NULL for injected frames */ - struct ieee80211_vif *vif; + union { + /* NB: vif can be NULL for injected frames */ + struct ieee80211_vif *vif; + + /* When packets are enqueued on txq it's easy + * to re-construct the vif pointer. There's no + * more space in tx_info so it can be used to + * store the necessary enqueue time for packet + * sojourn time computation. + */ + codel_time_t enqueue_time; + }; struct ieee80211_key_conf *hw_key; u32 flags; /* 4 bytes free */ @@ -2147,9 +2159,6 @@ enum ieee80211_hw_flags { * @n_cipher_schemes: a size of an array of cipher schemes definitions. * @cipher_schemes: a pointer to an array of cipher scheme definitions * supported by HW. - * - * @txq_ac_max_pending: maximum number of frames per AC pending in all txq - * entries for a vif. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -2180,7 +2189,6 @@ struct ieee80211_hw { u8 uapsd_max_sp_len; u8 n_cipher_schemes; const struct ieee80211_cipher_scheme *cipher_schemes; - int txq_ac_max_pending; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 2d8edaa..be1fe228 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -35,6 +35,7 @@ enum { ND_OPT_ROUTE_INFO = 24, /* RFC4191 */ ND_OPT_RDNSS = 25, /* RFC5006 */ ND_OPT_DNSSL = 31, /* RFC6106 */ + ND_OPT_6CO = 34, /* RFC6775 */ __ND_OPT_MAX }; @@ -53,11 +54,21 @@ enum { #include <net/neighbour.h> +/* Set to 3 to get tracing... */ +#define ND_DEBUG 1 + +#define ND_PRINTK(val, level, fmt, ...) \ +do { \ + if (val <= ND_DEBUG) \ + net_##level##_ratelimited(fmt, ##__VA_ARGS__); \ +} while (0) + struct ctl_table; struct inet6_dev; struct net_device; struct net_proto_family; struct sk_buff; +struct prefix_info; extern struct neigh_table nd_tbl; @@ -99,20 +110,201 @@ struct ndisc_options { #endif struct nd_opt_hdr *nd_useropts; struct nd_opt_hdr *nd_useropts_end; +#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) + struct nd_opt_hdr *nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR + 1]; +#endif }; -#define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] -#define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] -#define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] -#define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] -#define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] -#define nd_opts_mtu nd_opt_array[ND_OPT_MTU] +#define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] +#define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] +#define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] +#define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] +#define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] +#define nd_opts_mtu nd_opt_array[ND_OPT_MTU] +#define nd_802154_opts_src_lladdr nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR] +#define nd_802154_opts_tgt_lladdr nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR] #define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) -struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, +struct ndisc_options *ndisc_parse_options(const struct net_device *dev, + u8 *opt, int opt_len, struct ndisc_options *ndopts); +void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, + int data_len, int pad); + +#define NDISC_OPS_REDIRECT_DATA_SPACE 2 + +/* + * This structure defines the hooks for IPv6 neighbour discovery. + * The following hooks can be defined; unless noted otherwise, they are + * optional and can be filled with a null pointer. + * + * int (*is_useropt)(u8 nd_opt_type): + * This function is called when IPv6 decide RA userspace options. if + * this function returns 1 then the option given by nd_opt_type will + * be handled as userspace option additional to the IPv6 options. + * + * int (*parse_options)(const struct net_device *dev, + * struct nd_opt_hdr *nd_opt, + * struct ndisc_options *ndopts): + * This function is called while parsing ndisc ops and put each position + * as pointer into ndopts. If this function return unequal 0, then this + * function took care about the ndisc option, if 0 then the IPv6 ndisc + * option parser will take care about that option. + * + * void (*update)(const struct net_device *dev, struct neighbour *n, + * u32 flags, u8 icmp6_type, + * const struct ndisc_options *ndopts): + * This function is called when IPv6 ndisc updates the neighbour cache + * entry. Additional options which can be updated may be previously + * parsed by parse_opts callback and accessible over ndopts parameter. + * + * int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, + * struct neighbour *neigh, u8 *ha_buf, + * u8 **ha): + * This function is called when the necessary option space will be + * calculated before allocating a skb. The parameters neigh, ha_buf + * abd ha are available on NDISC_REDIRECT messages only. + * + * void (*fill_addr_option)(const struct net_device *dev, + * struct sk_buff *skb, u8 icmp6_type, + * const u8 *ha): + * This function is called when the skb will finally fill the option + * fields inside skb. NOTE: this callback should fill the option + * fields to the skb which are previously indicated by opt_space + * parameter. That means the decision to add such option should + * not lost between these two callbacks, e.g. protected by interface + * up state. + * + * void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, + * const struct prefix_info *pinfo, + * struct inet6_dev *in6_dev, + * struct in6_addr *addr, + * int addr_type, u32 addr_flags, + * bool sllao, bool tokenized, + * __u32 valid_lft, u32 prefered_lft, + * bool dev_addr_generated): + * This function is called when a RA messages is received with valid + * PIO option fields and an IPv6 address will be added to the interface + * for autoconfiguration. The parameter dev_addr_generated reports about + * if the address was based on dev->dev_addr or not. This can be used + * to add a second address if link-layer operates with two link layer + * addresses. E.g. 802.15.4 6LoWPAN. + */ +struct ndisc_ops { + int (*is_useropt)(u8 nd_opt_type); + int (*parse_options)(const struct net_device *dev, + struct nd_opt_hdr *nd_opt, + struct ndisc_options *ndopts); + void (*update)(const struct net_device *dev, struct neighbour *n, + u32 flags, u8 icmp6_type, + const struct ndisc_options *ndopts); + int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, + struct neighbour *neigh, u8 *ha_buf, + u8 **ha); + void (*fill_addr_option)(const struct net_device *dev, + struct sk_buff *skb, u8 icmp6_type, + const u8 *ha); + void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, + const struct prefix_info *pinfo, + struct inet6_dev *in6_dev, + struct in6_addr *addr, + int addr_type, u32 addr_flags, + bool sllao, bool tokenized, + __u32 valid_lft, u32 prefered_lft, + bool dev_addr_generated); +}; + +#if IS_ENABLED(CONFIG_IPV6) +static inline int ndisc_ops_is_useropt(const struct net_device *dev, + u8 nd_opt_type) +{ + if (dev->ndisc_ops && dev->ndisc_ops->is_useropt) + return dev->ndisc_ops->is_useropt(nd_opt_type); + else + return 0; +} + +static inline int ndisc_ops_parse_options(const struct net_device *dev, + struct nd_opt_hdr *nd_opt, + struct ndisc_options *ndopts) +{ + if (dev->ndisc_ops && dev->ndisc_ops->parse_options) + return dev->ndisc_ops->parse_options(dev, nd_opt, ndopts); + else + return 0; +} + +static inline void ndisc_ops_update(const struct net_device *dev, + struct neighbour *n, u32 flags, + u8 icmp6_type, + const struct ndisc_options *ndopts) +{ + if (dev->ndisc_ops && dev->ndisc_ops->update) + dev->ndisc_ops->update(dev, n, flags, icmp6_type, ndopts); +} + +static inline int ndisc_ops_opt_addr_space(const struct net_device *dev, + u8 icmp6_type) +{ + if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space && + icmp6_type != NDISC_REDIRECT) + return dev->ndisc_ops->opt_addr_space(dev, icmp6_type, NULL, + NULL, NULL); + else + return 0; +} + +static inline int ndisc_ops_redirect_opt_addr_space(const struct net_device *dev, + struct neighbour *neigh, + u8 *ha_buf, u8 **ha) +{ + if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space) + return dev->ndisc_ops->opt_addr_space(dev, NDISC_REDIRECT, + neigh, ha_buf, ha); + else + return 0; +} + +static inline void ndisc_ops_fill_addr_option(const struct net_device *dev, + struct sk_buff *skb, + u8 icmp6_type) +{ + if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option && + icmp6_type != NDISC_REDIRECT) + dev->ndisc_ops->fill_addr_option(dev, skb, icmp6_type, NULL); +} + +static inline void ndisc_ops_fill_redirect_addr_option(const struct net_device *dev, + struct sk_buff *skb, + const u8 *ha) +{ + if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option) + dev->ndisc_ops->fill_addr_option(dev, skb, NDISC_REDIRECT, ha); +} + +static inline void ndisc_ops_prefix_rcv_add_addr(struct net *net, + struct net_device *dev, + const struct prefix_info *pinfo, + struct inet6_dev *in6_dev, + struct in6_addr *addr, + int addr_type, u32 addr_flags, + bool sllao, bool tokenized, + __u32 valid_lft, + u32 prefered_lft, + bool dev_addr_generated) +{ + if (dev->ndisc_ops && dev->ndisc_ops->prefix_rcv_add_addr) + dev->ndisc_ops->prefix_rcv_add_addr(net, dev, pinfo, in6_dev, + addr, addr_type, + addr_flags, sllao, + tokenized, valid_lft, + prefered_lft, + dev_addr_generated); +} +#endif + /* * Return the padding between the option length and the start of the * link addr. Currently only IP-over-InfiniBand needs this, although @@ -127,23 +319,48 @@ static inline int ndisc_addr_option_pad(unsigned short type) } } -static inline int ndisc_opt_addr_space(struct net_device *dev) +static inline int __ndisc_opt_addr_space(unsigned char addr_len, int pad) { - return NDISC_OPT_SPACE(dev->addr_len + - ndisc_addr_option_pad(dev->type)); + return NDISC_OPT_SPACE(addr_len + pad); } -static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, - struct net_device *dev) +#if IS_ENABLED(CONFIG_IPV6) +static inline int ndisc_opt_addr_space(struct net_device *dev, u8 icmp6_type) +{ + return __ndisc_opt_addr_space(dev->addr_len, + ndisc_addr_option_pad(dev->type)) + + ndisc_ops_opt_addr_space(dev, icmp6_type); +} + +static inline int ndisc_redirect_opt_addr_space(struct net_device *dev, + struct neighbour *neigh, + u8 *ops_data_buf, + u8 **ops_data) +{ + return __ndisc_opt_addr_space(dev->addr_len, + ndisc_addr_option_pad(dev->type)) + + ndisc_ops_redirect_opt_addr_space(dev, neigh, ops_data_buf, + ops_data); +} +#endif + +static inline u8 *__ndisc_opt_addr_data(struct nd_opt_hdr *p, + unsigned char addr_len, int prepad) { u8 *lladdr = (u8 *)(p + 1); int lladdrlen = p->nd_opt_len << 3; - int prepad = ndisc_addr_option_pad(dev->type); - if (lladdrlen != ndisc_opt_addr_space(dev)) + if (lladdrlen != __ndisc_opt_addr_space(addr_len, prepad)) return NULL; return lladdr + prepad; } +static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, + struct net_device *dev) +{ + return __ndisc_opt_addr_data(p, dev->addr_len, + ndisc_addr_option_pad(dev->type)); +} + static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { const u32 *p32 = pkey; @@ -194,6 +411,9 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target); int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir); +void ndisc_update(const struct net_device *dev, struct neighbour *neigh, + const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, + struct ndisc_options *ndopts); /* * IGMP diff --git a/include/net/netevent.h b/include/net/netevent.h index d8bbb38..f440df1 100644 --- a/include/net/netevent.h +++ b/include/net/netevent.h @@ -24,6 +24,7 @@ struct netevent_redirect { enum netevent_notif_type { NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */ NETEVENT_REDIRECT, /* arg is struct netevent_redirect ptr */ + NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */ }; int register_netevent_notifier(struct notifier_block *nb); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index dd78bea..5d3397f 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -85,6 +85,9 @@ struct nf_conn { spinlock_t lock; u16 cpu; +#ifdef CONFIG_NF_CONNTRACK_ZONES + struct nf_conntrack_zone zone; +#endif /* XXX should I move this to the tail ? - Y.K */ /* These are my tuples; original and reply */ struct nf_conntrack_tuple_hash tuplehash[IP_CT_DIR_MAX]; @@ -287,6 +290,7 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb) struct kernel_param; int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); +int nf_conntrack_hash_resize(unsigned int hashsize); extern unsigned int nf_conntrack_htable_size; extern unsigned int nf_conntrack_max; diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 55d1504..b925395 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -15,9 +15,6 @@ enum nf_ct_ext_id { #ifdef CONFIG_NF_CONNTRACK_EVENTS NF_CT_EXT_ECACHE, #endif -#ifdef CONFIG_NF_CONNTRACK_ZONES - NF_CT_EXT_ZONE, -#endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP NF_CT_EXT_TSTAMP, #endif @@ -38,7 +35,6 @@ enum nf_ct_ext_id { #define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj #define NF_CT_EXT_ACCT_TYPE struct nf_conn_acct #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache -#define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone #define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp #define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout #define NF_CT_EXT_LABELS_TYPE struct nf_conn_labels diff --git a/include/net/netfilter/nf_conntrack_zones.h b/include/net/netfilter/nf_conntrack_zones.h index 4e32512..64a718b 100644 --- a/include/net/netfilter/nf_conntrack_zones.h +++ b/include/net/netfilter/nf_conntrack_zones.h @@ -9,12 +9,11 @@ static inline const struct nf_conntrack_zone * nf_ct_zone(const struct nf_conn *ct) { - const struct nf_conntrack_zone *nf_ct_zone = NULL; - #ifdef CONFIG_NF_CONNTRACK_ZONES - nf_ct_zone = nf_ct_ext_find(ct, NF_CT_EXT_ZONE); + return &ct->zone; +#else + return &nf_ct_zone_dflt; #endif - return nf_ct_zone ? nf_ct_zone : &nf_ct_zone_dflt; } static inline const struct nf_conntrack_zone * @@ -31,32 +30,22 @@ static inline const struct nf_conntrack_zone * nf_ct_zone_tmpl(const struct nf_conn *tmpl, const struct sk_buff *skb, struct nf_conntrack_zone *tmp) { - const struct nf_conntrack_zone *zone; - +#ifdef CONFIG_NF_CONNTRACK_ZONES if (!tmpl) return &nf_ct_zone_dflt; - zone = nf_ct_zone(tmpl); - if (zone->flags & NF_CT_FLAG_MARK) - zone = nf_ct_zone_init(tmp, skb->mark, zone->dir, 0); - - return zone; + if (tmpl->zone.flags & NF_CT_FLAG_MARK) + return nf_ct_zone_init(tmp, skb->mark, tmpl->zone.dir, 0); +#endif + return nf_ct_zone(tmpl); } -static inline int nf_ct_zone_add(struct nf_conn *ct, gfp_t flags, - const struct nf_conntrack_zone *info) +static inline void nf_ct_zone_add(struct nf_conn *ct, + const struct nf_conntrack_zone *zone) { #ifdef CONFIG_NF_CONNTRACK_ZONES - struct nf_conntrack_zone *nf_ct_zone; - - nf_ct_zone = nf_ct_ext_add(ct, NF_CT_EXT_ZONE, flags); - if (!nf_ct_zone) - return -ENOMEM; - - nf_ct_zone_init(nf_ct_zone, info->id, info->dir, - info->flags); + ct->zone = *zone; #endif - return 0; } static inline bool nf_ct_zone_matches_dir(const struct nf_conntrack_zone *zone, @@ -68,22 +57,34 @@ static inline bool nf_ct_zone_matches_dir(const struct nf_conntrack_zone *zone, static inline u16 nf_ct_zone_id(const struct nf_conntrack_zone *zone, enum ip_conntrack_dir dir) { +#ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone_matches_dir(zone, dir) ? zone->id : NF_CT_DEFAULT_ZONE_ID; +#else + return NF_CT_DEFAULT_ZONE_ID; +#endif } static inline bool nf_ct_zone_equal(const struct nf_conn *a, const struct nf_conntrack_zone *b, enum ip_conntrack_dir dir) { +#ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone_id(nf_ct_zone(a), dir) == nf_ct_zone_id(b, dir); +#else + return true; +#endif } static inline bool nf_ct_zone_equal_any(const struct nf_conn *a, const struct nf_conntrack_zone *b) { +#ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone(a)->id == b->id; +#else + return true; +#endif } #endif /* IS_ENABLED(CONFIG_NF_CONNTRACK) */ #endif /* _NF_CONNTRACK_ZONES_H */ diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index 57639fc..83d855b 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -12,6 +12,9 @@ #define NF_LOG_UID 0x08 /* Log UID owning local socket */ #define NF_LOG_MASK 0x0f +/* This flag indicates that copy_len field in nf_loginfo is set */ +#define NF_LOG_F_COPY_LEN 0x1 + enum nf_log_type { NF_LOG_TYPE_LOG = 0, NF_LOG_TYPE_ULOG, @@ -22,9 +25,13 @@ struct nf_loginfo { u_int8_t type; union { struct { + /* copy_len will be used iff you set + * NF_LOG_F_COPY_LEN in flags + */ u_int32_t copy_len; u_int16_t group; u_int16_t qthreshold; + u_int16_t flags; } ulog; struct { u_int8_t level; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f7c291f..30c1d94 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -297,6 +297,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @ops: set ops * @pnet: network namespace * @flags: set flags + * @genmask: generation mask * @klen: key length * @dlen: data length * @data: private set data @@ -318,7 +319,8 @@ struct nft_set { /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; possible_net_t pnet; - u16 flags; + u16 flags:14, + genmask:2; u8 klen; u8 dlen; unsigned char data[] @@ -336,9 +338,9 @@ static inline struct nft_set *nft_set_container_of(const void *priv) } struct nft_set *nf_tables_set_lookup(const struct nft_table *table, - const struct nlattr *nla); + const struct nlattr *nla, u8 genmask); struct nft_set *nf_tables_set_lookup_byid(const struct net *net, - const struct nlattr *nla); + const struct nlattr *nla, u8 genmask); static inline unsigned long nft_set_gc_interval(const struct nft_set *set) { @@ -733,7 +735,6 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) enum nft_chain_flags { NFT_BASE_CHAIN = 0x1, - NFT_CHAIN_INACTIVE = 0x2, }; /** @@ -755,7 +756,8 @@ struct nft_chain { u64 handle; u32 use; u16 level; - u8 flags; + u8 flags:6, + genmask:2; char name[NFT_CHAIN_MAXNAMELEN]; }; @@ -797,7 +799,6 @@ struct nft_stats { }; #define NFT_HOOK_OPS_MAX 2 -#define NFT_BASECHAIN_DISABLED (1 << 0) /** * struct nft_base_chain - nf_tables base chain @@ -839,6 +840,7 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); * @hgenerator: handle generator state * @use: number of chain references to this table * @flags: table flag (see enum nft_table_flags) + * @genmask: generation mask * @name: name of the table */ struct nft_table { @@ -847,7 +849,8 @@ struct nft_table { struct list_head sets; u64 hgenerator; u32 use; - u16 flags; + u16 flags:14, + genmask:2; char name[NFT_TABLE_MAXNAMELEN]; }; @@ -971,6 +974,32 @@ static inline u8 nft_genmask_cur(const struct net *net) #define NFT_GENMASK_ANY ((1 << 0) | (1 << 1)) /* + * Generic transaction helpers + */ + +/* Check if this object is currently active. */ +#define nft_is_active(__net, __obj) \ + (((__obj)->genmask & nft_genmask_cur(__net)) == 0) + +/* Check if this object is active in the next generation. */ +#define nft_is_active_next(__net, __obj) \ + (((__obj)->genmask & nft_genmask_next(__net)) == 0) + +/* This object becomes active in the next generation. */ +#define nft_activate_next(__net, __obj) \ + (__obj)->genmask = nft_genmask_cur(__net) + +/* This object becomes inactive in the next generation. */ +#define nft_deactivate_next(__net, __obj) \ + (__obj)->genmask = nft_genmask_next(__net) + +/* After committing the ruleset, clear the stale generation bit. */ +#define nft_clear(__net, __obj) \ + (__obj)->genmask &= ~nft_genmask_next(__net) +#define nft_active_genmask(__obj, __genmask) \ + !((__obj)->genmask & __genmask) + +/* * Set element transaction helpers */ diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index fea53f4..7caa99b 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -67,12 +67,12 @@ struct qdisc_watchdog { }; void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc); -void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool throttle); +void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires); static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) { - qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires), true); + qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires)); } void qdisc_watchdog_cancel(struct qdisc_watchdog *wd); diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 006a7b8..4113916 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -98,10 +98,11 @@ struct rtnl_link_ops { const struct net_device *dev, const struct net_device *slave_dev); struct net *(*get_link_net)(const struct net_device *dev); - size_t (*get_linkxstats_size)(const struct net_device *dev); + size_t (*get_linkxstats_size)(const struct net_device *dev, + int attr); int (*fill_linkxstats)(struct sk_buff *skb, const struct net_device *dev, - int *prividx); + int *prividx, int attr); }; int __rtnl_link_register(struct rtnl_link_ops *ops); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 62d5531..909aff2 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -26,14 +26,6 @@ struct qdisc_rate_table { enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, - __QDISC_STATE_THROTTLED, -}; - -/* - * following bits are only changed while qdisc lock is held - */ -enum qdisc___state_t { - __QDISC___STATE_RUNNING = 1, }; struct qdisc_size_table { @@ -45,8 +37,10 @@ struct qdisc_size_table { }; struct Qdisc { - int (*enqueue)(struct sk_buff *skb, struct Qdisc *dev); - struct sk_buff * (*dequeue)(struct Qdisc *dev); + int (*enqueue)(struct sk_buff *skb, + struct Qdisc *sch, + struct sk_buff **to_free); + struct sk_buff * (*dequeue)(struct Qdisc *sch); unsigned int flags; #define TCQ_F_BUILTIN 1 #define TCQ_F_INGRESS 2 @@ -70,31 +64,25 @@ struct Qdisc { struct list_head list; u32 handle; u32 parent; - int (*reshape_fail)(struct sk_buff *skb, - struct Qdisc *q); - void *u32_node; - /* This field is deprecated, but it is still used by CBQ - * and it will live until better solution will be invented. - */ - struct Qdisc *__parent; struct netdev_queue *dev_queue; struct gnet_stats_rate_est64 rate_est; struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; - struct Qdisc *next_sched; - struct sk_buff *gso_skb; /* * For performance sake on SMP, we put highly modified fields at the end */ - unsigned long state; + struct sk_buff *gso_skb ____cacheline_aligned_in_smp; struct sk_buff_head q; struct gnet_stats_basic_packed bstats; - unsigned int __state; + seqcount_t running; struct gnet_stats_queue qstats; + unsigned long state; + struct Qdisc *next_sched; + struct sk_buff *skb_bad_txq; struct rcu_head rcu_head; int padded; atomic_t refcnt; @@ -104,20 +92,24 @@ struct Qdisc { static inline bool qdisc_is_running(const struct Qdisc *qdisc) { - return (qdisc->__state & __QDISC___STATE_RUNNING) ? true : false; + return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; } static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc_is_running(qdisc)) return false; - qdisc->__state |= __QDISC___STATE_RUNNING; + /* Variant of write_seqcount_begin() telling lockdep a trylock + * was attempted. + */ + raw_write_seqcount_begin(&qdisc->running); + seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_); return true; } static inline void qdisc_run_end(struct Qdisc *qdisc) { - qdisc->__state &= ~__QDISC___STATE_RUNNING; + write_seqcount_end(&qdisc->running); } static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) @@ -135,21 +127,6 @@ static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq) #endif } -static inline bool qdisc_is_throttled(const struct Qdisc *qdisc) -{ - return test_bit(__QDISC_STATE_THROTTLED, &qdisc->state) ? true : false; -} - -static inline void qdisc_throttled(struct Qdisc *qdisc) -{ - set_bit(__QDISC_STATE_THROTTLED, &qdisc->state); -} - -static inline void qdisc_unthrottled(struct Qdisc *qdisc) -{ - clear_bit(__QDISC_STATE_THROTTLED, &qdisc->state); -} - struct Qdisc_class_ops { /* Child qdisc manipulation */ struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *); @@ -186,10 +163,11 @@ struct Qdisc_ops { char id[IFNAMSIZ]; int priv_size; - int (*enqueue)(struct sk_buff *, struct Qdisc *); + int (*enqueue)(struct sk_buff *skb, + struct Qdisc *sch, + struct sk_buff **to_free); struct sk_buff * (*dequeue)(struct Qdisc *); struct sk_buff * (*peek)(struct Qdisc *); - unsigned int (*drop)(struct Qdisc *); int (*init)(struct Qdisc *, struct nlattr *arg); void (*reset)(struct Qdisc *); @@ -322,6 +300,14 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) return qdisc_lock(root); } +static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) +{ + struct Qdisc *root = qdisc_root_sleeping(qdisc); + + ASSERT_RTNL(); + return &root->running; +} + static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc) { return qdisc->dev_queue->dev; @@ -517,10 +503,11 @@ static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, #endif } -static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) { qdisc_calculate_pkt_len(skb, sch); - return sch->enqueue(skb, sch); + return sch->enqueue(skb, sch, to_free); } static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) @@ -645,40 +632,36 @@ static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) return __qdisc_dequeue_head(sch, &sch->q); } +/* Instead of calling kfree_skb() while root qdisc lock is held, + * queue the skb for future freeing at end of __dev_xmit_skb() + */ +static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free) +{ + skb->next = *to_free; + *to_free = skb; +} + static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, - struct sk_buff_head *list) + struct sk_buff_head *list, + struct sk_buff **to_free) { struct sk_buff *skb = __skb_dequeue(list); if (likely(skb != NULL)) { unsigned int len = qdisc_pkt_len(skb); + qdisc_qstats_backlog_dec(sch, skb); - kfree_skb(skb); + __qdisc_drop(skb, to_free); return len; } return 0; } -static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch) -{ - return __qdisc_queue_drop_head(sch, &sch->q); -} - -static inline struct sk_buff *__qdisc_dequeue_tail(struct Qdisc *sch, - struct sk_buff_head *list) -{ - struct sk_buff *skb = __skb_dequeue_tail(list); - - if (likely(skb != NULL)) - qdisc_qstats_backlog_dec(sch, skb); - - return skb; -} - -static inline struct sk_buff *qdisc_dequeue_tail(struct Qdisc *sch) +static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch, + struct sk_buff **to_free) { - return __qdisc_dequeue_tail(sch, &sch->q); + return __qdisc_queue_drop_head(sch, &sch->q, to_free); } static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) @@ -718,19 +701,21 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch) return skb; } -static inline void __qdisc_reset_queue(struct Qdisc *sch, - struct sk_buff_head *list) +static inline void __qdisc_reset_queue(struct sk_buff_head *list) { /* * We do not know the backlog in bytes of this list, it * is up to the caller to correct it */ - __skb_queue_purge(list); + if (!skb_queue_empty(list)) { + rtnl_kfree_skbs(list->next, list->prev); + __skb_queue_head_init(list); + } } static inline void qdisc_reset_queue(struct Qdisc *sch) { - __qdisc_reset_queue(sch, &sch->q); + __qdisc_reset_queue(&sch->q); sch->qstats.backlog = 0; } @@ -751,46 +736,19 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, return old; } -static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch, - struct sk_buff_head *list) +static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) { - struct sk_buff *skb = __qdisc_dequeue_tail(sch, list); - - if (likely(skb != NULL)) { - unsigned int len = qdisc_pkt_len(skb); - kfree_skb(skb); - return len; - } - - return 0; -} - -static inline unsigned int qdisc_queue_drop(struct Qdisc *sch) -{ - return __qdisc_queue_drop(sch, &sch->q); -} - -static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) -{ - kfree_skb(skb); + rtnl_kfree_skbs(skb, skb); qdisc_qstats_drop(sch); - - return NET_XMIT_DROP; } -static inline int qdisc_reshape_fail(struct sk_buff *skb, struct Qdisc *sch) + +static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) { + __qdisc_drop(skb, to_free); qdisc_qstats_drop(sch); -#ifdef CONFIG_NET_CLS_ACT - if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch)) - goto drop; - - return NET_XMIT_SUCCESS; - -drop: -#endif - kfree_skb(skb); return NET_XMIT_DROP; } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index b392ac8..632e205 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -186,6 +186,10 @@ void sctp_assocs_proc_exit(struct net *net); int sctp_remaddr_proc_init(struct net *net); void sctp_remaddr_proc_exit(struct net *net); +/* + * sctp/offload.c + */ +int sctp_offload_init(void); /* * Module global variables diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 16b013a..83c5ec5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -566,6 +566,9 @@ struct sctp_chunk { /* This points to the sk_buff containing the actual data. */ struct sk_buff *skb; + /* In case of GSO packets, this will store the head one */ + struct sk_buff *head_skb; + /* These are the SCTP headers by reverse order in a packet. * Note that some of these may happen more than once. In that * case, we point at the "current" one, whatever that means @@ -696,6 +699,8 @@ struct sctp_packet { size_t overhead; /* This is the total size of all chunks INCLUDING padding. */ size_t size; + /* This is the maximum size this packet may have */ + size_t max_size; /* The packet is destined for this transport address. * The function we finally use to pass down to the next lower diff --git a/include/net/tc_act/tc_defact.h b/include/net/tc_act/tc_defact.h index 9763dcb..ab9b5d6 100644 --- a/include/net/tc_act/tc_defact.h +++ b/include/net/tc_act/tc_defact.h @@ -5,8 +5,8 @@ struct tcf_defact { struct tcf_common common; - u32 tcfd_datalen; - void *tcfd_defdata; + u32 tcfd_datalen; + void *tcfd_defdata; }; #define to_defact(a) \ container_of(a->priv, struct tcf_defact, common) diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index b496d5a..d01a5d4 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -24,11 +24,11 @@ struct tcf_skbedit { struct tcf_common common; - u32 flags; - u32 priority; - u32 mark; - u16 queue_mapping; - /* XXX: 16-bit pad here? */ + u32 flags; + u32 priority; + u32 mark; + u16 queue_mapping; + u16 ptype; }; #define to_skbedit(a) \ container_of(a->priv, struct tcf_skbedit, common) diff --git a/include/net/tcp.h b/include/net/tcp.h index 0bcc70f..c00e7d5 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -589,7 +589,7 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) * On the other hand, for extremely large MSS devices, handling * smaller than MSS windows in this way does make sense. */ - if (tp->max_window >= 512) + if (tp->max_window > TCP_MSS_DEFAULT) cutoff = (tp->max_window >> 1); else cutoff = tp->max_window; @@ -767,6 +767,7 @@ struct tcp_skb_cb { union { struct { /* There is space for up to 20 bytes */ + __u32 in_flight;/* Bytes in flight when packet sent */ } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; @@ -859,6 +860,7 @@ union tcp_cc_info; struct ack_sample { u32 pkts_acked; s32 rtt_us; + u32 in_flight; }; struct tcp_congestion_ops { @@ -1382,7 +1384,7 @@ union tcp_md5sum_block { /* - pool: digest algorithm, hash description and scratch buffer */ struct tcp_md5sig_pool { struct ahash_request *md5_req; - union tcp_md5sum_block md5_blk; + void *scratch; }; /* - functions */ @@ -1418,7 +1420,6 @@ static inline void tcp_put_md5sig_pool(void) local_bh_enable(); } -int tcp_md5_hash_header(struct tcp_md5sig_pool *, const struct tcphdr *); int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *, unsigned int header_len); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, diff --git a/include/net/udp.h b/include/net/udp.h index ae07f37..8894d71 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -160,8 +160,8 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, static inline void udp_csum_pull_header(struct sk_buff *skb) { - if (skb->ip_summed == CHECKSUM_NONE) - skb->csum = csum_partial(udp_hdr(skb), sizeof(struct udphdr), + if (!skb->csum_valid && skb->ip_summed == CHECKSUM_NONE) + skb->csum = csum_partial(skb->data, sizeof(struct udphdr), skb->csum); skb_pull_rcsum(skb, sizeof(struct udphdr)); UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 9d14f70..02c5be0 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -84,6 +84,46 @@ struct udp_tunnel_sock_cfg { void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); +/* -- List of parsable UDP tunnel types -- + * + * Adding to this list will result in serious debate. The main issue is + * that this list is essentially a list of workarounds for either poorly + * designed tunnels, or poorly designed device offloads. + * + * The parsing supported via these types should really be used for Rx + * traffic only as the network stack will have already inserted offsets for + * the location of the headers in the skb. In addition any ports that are + * pushed should be kept within the namespace without leaking to other + * devices such as VFs or other ports on the same device. + * + * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the + * need to use this for Rx checksum offload. It should not be necessary to + * call this function to perform Tx offloads on outgoing traffic. + */ +enum udp_parsable_tunnel_type { + UDP_TUNNEL_TYPE_VXLAN, /* RFC 7348 */ + UDP_TUNNEL_TYPE_GENEVE, /* draft-ietf-nvo3-geneve */ + UDP_TUNNEL_TYPE_VXLAN_GPE, /* draft-ietf-nvo3-vxlan-gpe */ +}; + +struct udp_tunnel_info { + unsigned short type; + sa_family_t sa_family; + __be16 port; +}; + +/* Notify network devices of offloadable types */ +void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, + unsigned short type); +void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); +void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); + +static inline void udp_tunnel_get_rx_info(struct net_device *dev) +{ + ASSERT_RTNL(); + call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); +} + /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, @@ -105,12 +145,14 @@ struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, __be16 flags, __be64 tunnel_id, int md_size); +#ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; return iptunnel_handle_offloads(skb, type); } +#endif static inline void udp_tunnel_encap_enable(struct socket *sock) { diff --git a/include/net/vxlan.h b/include/net/vxlan.h index b880316..b96d036 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -1,13 +1,10 @@ #ifndef __NET_VXLAN_H #define __NET_VXLAN_H 1 -#include <linux/ip.h> -#include <linux/ipv6.h> #include <linux/if_vlan.h> -#include <linux/skbuff.h> -#include <linux/netdevice.h> -#include <linux/udp.h> +#include <net/udp_tunnel.h> #include <net/dst_metadata.h> +#include <net/udp_tunnel.h> /* VXLAN protocol (RFC 7348) header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ @@ -392,12 +389,6 @@ static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset) return vni_field; } -static inline void vxlan_get_rx_port(struct net_device *netdev) -{ - ASSERT_RTNL(); - call_netdevice_notifiers(NETDEV_OFFLOAD_PUSH_VXLAN, netdev); -} - static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs) { return vs->sock->sk->sk_family; |