diff options
Diffstat (limited to 'include/net')
59 files changed, 908 insertions, 267 deletions
diff --git a/include/net/addrconf.h b/include/net/addrconf.h index cbc6bb0a6838..f68dce2d8d88 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -151,7 +151,8 @@ extern int ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *src_addr); extern int ipv6_is_mld(struct sk_buff *skb, int nexthdr); -extern void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len); +extern void addrconf_prefix_rcv(struct net_device *dev, + u8 *opt, int len, bool sllao); /* * anycast prototypes (anycast.c) diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 91ab5b01678a..5a4e29b168c9 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -11,10 +11,13 @@ extern void unix_notinflight(struct file *fp); extern void unix_gc(void); extern void wait_for_unix_gc(void); extern struct sock *unix_get_socket(struct file *filp); +extern struct sock *unix_peer_get(struct sock *); #define UNIX_HASH_SIZE 256 extern unsigned int unix_tot_inflight; +extern spinlock_t unix_table_lock; +extern struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1]; struct unix_address { atomic_t refcnt; @@ -63,6 +66,9 @@ struct unix_sock { #define peer_wait peer_wq.wait +long unix_inq_len(struct sock *sk); +long unix_outq_len(struct sock *sk); + #ifdef CONFIG_SYSCTL extern int unix_sysctl_register(struct net *net); extern void unix_sysctl_unregister(struct net *net); diff --git a/include/net/arp.h b/include/net/arp.h index 4979af8b1559..0013dc87940b 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -23,7 +23,7 @@ static inline struct neighbour *__ipv4_neigh_lookup(struct neigh_table *tbl, str rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - hash_val = arp_hashfn(key, dev, nht->hash_rnd) >> (32 - nht->hash_shift); + hash_val = arp_hashfn(key, dev, nht->hash_rnd[0]) >> (32 - nht->hash_shift); for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); n != NULL; n = rcu_dereference_bh(n->next)) { diff --git a/include/net/atmclip.h b/include/net/atmclip.h index 497ef6444a7a..5865924d4aac 100644 --- a/include/net/atmclip.h +++ b/include/net/atmclip.h @@ -15,7 +15,6 @@ #define CLIP_VCC(vcc) ((struct clip_vcc *) ((vcc)->user_back)) -#define NEIGH2ENTRY(neigh) ((struct atmarp_entry *) (neigh)->primary_key) struct sk_buff; @@ -36,24 +35,18 @@ struct clip_vcc { struct atmarp_entry { - __be32 ip; /* IP address */ struct clip_vcc *vccs; /* active VCCs; NULL if resolution is pending */ unsigned long expires; /* entry expiration time */ struct neighbour *neigh; /* neighbour back-pointer */ }; - #define PRIV(dev) ((struct clip_priv *) netdev_priv(dev)) - struct clip_priv { int number; /* for convenience ... */ spinlock_t xoff_lock; /* ensures that pop is atomic (SMP) */ struct net_device *next; /* next CLIP interface */ }; - -extern struct neigh_table *clip_tbl_hook; - #endif diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 9572cbd12a7a..68f589150692 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -820,7 +820,7 @@ static inline __u8 __ctrl_size(struct l2cap_chan *chan) return L2CAP_ENH_HDR_SIZE - L2CAP_HDR_SIZE; } -extern int disable_ertm; +extern bool disable_ertm; int l2cap_init_sockets(void); void l2cap_cleanup_sockets(void); diff --git a/include/net/caif/caif_dev.h b/include/net/caif/caif_dev.h index c011281d92c0..ef2dd9438bb1 100644 --- a/include/net/caif/caif_dev.h +++ b/include/net/caif/caif_dev.h @@ -9,6 +9,7 @@ #include <net/caif/caif_layer.h> #include <net/caif/cfcnfg.h> +#include <net/caif/caif_device.h> #include <linux/caif/caif_socket.h> #include <linux/if.h> #include <linux/net.h> @@ -104,4 +105,24 @@ void caif_client_register_refcnt(struct cflayer *adapt_layer, */ void caif_free_client(struct cflayer *adap_layer); +/** + * struct caif_enroll_dev - Enroll a net-device as a CAIF Link layer + * @dev: Network device to enroll. + * @caifdev: Configuration information from CAIF Link Layer + * @link_support: Link layer support layer + * @head_room: Head room needed by link support layer + * @layer: Lowest layer in CAIF stack + * @rcv_fun: Receive function for CAIF stack. + * + * This function enroll a CAIF link layer into CAIF Stack and + * expects the interface to be able to handle CAIF payload. + * The link_support layer is used to add any Link Layer specific + * framing. + */ +void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, + struct cflayer *link_support, int head_room, + struct cflayer **layer, int (**rcv_func)( + struct sk_buff *, struct net_device *, + struct packet_type *, struct net_device *)); + #endif /* CAIF_DEV_H_ */ diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h index 35bc7883cf97..0f3a39125f90 100644 --- a/include/net/caif/caif_layer.h +++ b/include/net/caif/caif_layer.h @@ -121,9 +121,7 @@ enum caif_direction { * @transmit: Packet transmit funciton. * @ctrlcmd: Used for control signalling upwards in the stack. * @modemcmd: Used for control signaling downwards in the stack. - * @prio: Priority of this layer. * @id: The identity of this layer - * @type: The type of this layer * @name: Name of the layer. * * This structure defines the layered structure in CAIF. @@ -230,9 +228,7 @@ struct cflayer { */ int (*modemcmd) (struct cflayer *layr, enum caif_modemcmd ctrl); - unsigned short prio; unsigned int id; - unsigned int type; char name[CAIF_LAYER_NAME_SZ]; }; diff --git a/include/net/caif/caif_spi.h b/include/net/caif/caif_spi.h index 87c3d11b8e55..aa6a485b0545 100644 --- a/include/net/caif/caif_spi.h +++ b/include/net/caif/caif_spi.h @@ -55,8 +55,8 @@ struct cfspi_xfer { u16 tx_dma_len; u16 rx_dma_len; - void *va_tx; - dma_addr_t pa_tx; + void *va_tx[2]; + dma_addr_t pa_tx[2]; void *va_rx; dma_addr_t pa_rx; }; diff --git a/include/net/caif/cfcnfg.h b/include/net/caif/cfcnfg.h index 3e93a4a4b677..90b4ff8bad83 100644 --- a/include/net/caif/cfcnfg.h +++ b/include/net/caif/cfcnfg.h @@ -14,18 +14,6 @@ struct cfcnfg; /** - * enum cfcnfg_phy_type - Types of physical layers defined in CAIF Stack - * - * @CFPHYTYPE_FRAG: Fragmented frames physical interface. - * @CFPHYTYPE_CAIF: Generic CAIF physical interface - */ -enum cfcnfg_phy_type { - CFPHYTYPE_FRAG = 1, - CFPHYTYPE_CAIF, - CFPHYTYPE_MAX -}; - -/** * enum cfcnfg_phy_preference - Physical preference HW Abstraction * * @CFPHYPREF_UNSPECIFIED: Default physical interface @@ -66,21 +54,20 @@ void cfcnfg_remove(struct cfcnfg *cfg); * cfcnfg_add_phy_layer() - Adds a physical layer to the CAIF stack. * @cnfg: Pointer to a CAIF configuration object, created by * cfcnfg_create(). - * @phy_type: Specifies the type of physical interface, e.g. - * CFPHYTYPE_FRAG. * @dev: Pointer to link layer device * @phy_layer: Specify the physical layer. The transmit function * MUST be set in the structure. * @pref: The phy (link layer) preference. + * @link_support: Protocol implementation for link layer specific protocol. * @fcs: Specify if checksum is used in CAIF Framing Layer. - * @stx: Specify if Start Of Frame eXtention is used. + * @head_room: Head space needed by link specific protocol. */ - void -cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type, +cfcnfg_add_phy_layer(struct cfcnfg *cnfg, struct net_device *dev, struct cflayer *phy_layer, enum cfcnfg_phy_preference pref, - bool fcs, bool stx); + struct cflayer *link_support, + bool fcs, int head_room); /** * cfcnfg_del_phy_layer - Deletes an phy layer from the CAIF stack. diff --git a/include/net/caif/cfserl.h b/include/net/caif/cfserl.h index b8374321b362..f121299a3427 100644 --- a/include/net/caif/cfserl.h +++ b/include/net/caif/cfserl.h @@ -8,5 +8,5 @@ #define CFSERL_H_ #include <net/caif/caif_layer.h> -struct cflayer *cfserl_create(int type, int instance, bool use_stx); -#endif /* CFSERL_H_ */ +struct cflayer *cfserl_create(int instance, bool use_stx); +#endif diff --git a/include/net/dsa.h b/include/net/dsa.h index 839f768f9e35..7828ebf99ee1 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -11,6 +11,11 @@ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H +#include <linux/if_ether.h> +#include <linux/list.h> +#include <linux/timer.h> +#include <linux/workqueue.h> + #define DSA_MAX_SWITCHES 4 #define DSA_MAX_PORTS 12 @@ -54,8 +59,143 @@ struct dsa_platform_data { struct dsa_chip_data *chip; }; -extern bool dsa_uses_dsa_tags(void *dsa_ptr); -extern bool dsa_uses_trailer_tags(void *dsa_ptr); +struct dsa_switch_tree { + /* + * Configuration data for the platform device that owns + * this dsa switch tree instance. + */ + struct dsa_platform_data *pd; + + /* + * Reference to network device to use, and which tagging + * protocol to use. + */ + struct net_device *master_netdev; + __be16 tag_protocol; + + /* + * The switch and port to which the CPU is attached. + */ + s8 cpu_switch; + s8 cpu_port; + + /* + * Link state polling. + */ + int link_poll_needed; + struct work_struct link_poll_work; + struct timer_list link_poll_timer; + + /* + * Data for the individual switch chips. + */ + struct dsa_switch *ds[DSA_MAX_SWITCHES]; +}; + +struct dsa_switch { + /* + * Parent switch tree, and switch index. + */ + struct dsa_switch_tree *dst; + int index; + + /* + * Configuration data for this switch. + */ + struct dsa_chip_data *pd; + + /* + * The used switch driver. + */ + struct dsa_switch_driver *drv; + + /* + * Reference to mii bus to use. + */ + struct mii_bus *master_mii_bus; + + /* + * Slave mii_bus and devices for the individual ports. + */ + u32 dsa_port_mask; + u32 phys_port_mask; + 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) +{ + return !!(ds->index == ds->dst->cpu_switch && p == ds->dst->cpu_port); +} + +static inline u8 dsa_upstream_port(struct dsa_switch *ds) +{ + struct dsa_switch_tree *dst = ds->dst; + + /* + * If this is the root switch (i.e. the switch that connects + * to the CPU), return the cpu port number on this switch. + * Else return the (DSA) port number that connects to the + * switch that is one hop closer to the cpu. + */ + if (dst->cpu_switch == ds->index) + return dst->cpu_port; + else + return ds->pd->rtable[dst->cpu_switch]; +} + +struct dsa_switch_driver { + struct list_head list; + + __be16 tag_protocol; + int priv_size; + + /* + * Probing and setup. + */ + char *(*probe)(struct mii_bus *bus, int sw_addr); + int (*setup)(struct dsa_switch *ds); + int (*set_addr)(struct dsa_switch *ds, u8 *addr); + + /* + * Access to the switch's PHY registers. + */ + int (*phy_read)(struct dsa_switch *ds, int port, int regnum); + int (*phy_write)(struct dsa_switch *ds, int port, + int regnum, u16 val); + + /* + * Link state polling and IRQ handling. + */ + void (*poll_link)(struct dsa_switch *ds); + + /* + * ethtool hardware statistics. + */ + void (*get_strings)(struct dsa_switch *ds, int port, uint8_t *data); + void (*get_ethtool_stats)(struct dsa_switch *ds, + int port, uint64_t *data); + int (*get_sset_count)(struct dsa_switch *ds); +}; + +void register_switch_driver(struct dsa_switch_driver *type); +void unregister_switch_driver(struct dsa_switch_driver *type); + +/* + * The original DSA tag format and some other tag formats have no + * ethertype, which means that we need to add a little hack to the + * networking receive path to make sure that received frames get + * the right ->protocol assigned to them when one of those tag + * formats is in use. + */ +static inline bool dsa_uses_dsa_tags(struct dsa_switch_tree *dst) +{ + return !!(dst->tag_protocol == htons(ETH_P_DSA)); +} +static inline bool dsa_uses_trailer_tags(struct dsa_switch_tree *dst) +{ + return !!(dst->tag_protocol == htons(ETH_P_TRAILER)); +} #endif diff --git a/include/net/dst.h b/include/net/dst.h index 4fb6c4381791..344c8dd02874 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -53,6 +53,7 @@ struct dst_entry { #define DST_NOHASH 0x0008 #define DST_NOCACHE 0x0010 #define DST_NOCOUNT 0x0020 +#define DST_NOPEER 0x0040 short error; short obsolete; @@ -86,12 +87,12 @@ struct dst_entry { }; }; -static inline struct neighbour *dst_get_neighbour(struct dst_entry *dst) +static inline struct neighbour *dst_get_neighbour_noref(struct dst_entry *dst) { return rcu_dereference(dst->_neighbour); } -static inline struct neighbour *dst_get_neighbour_raw(struct dst_entry *dst) +static inline struct neighbour *dst_get_neighbour_noref_raw(struct dst_entry *dst) { return rcu_dereference_raw(dst->_neighbour); } @@ -205,12 +206,7 @@ dst_feature(const struct dst_entry *dst, u32 feature) static inline u32 dst_mtu(const struct dst_entry *dst) { - u32 mtu = dst_metric_raw(dst, RTAX_MTU); - - if (!mtu) - mtu = dst->ops->default_mtu(dst); - - return mtu; + return dst->ops->mtu(dst); } /* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */ @@ -397,7 +393,7 @@ static inline void dst_confirm(struct dst_entry *dst) struct neighbour *n; rcu_read_lock(); - n = dst_get_neighbour(dst); + n = dst_get_neighbour_noref(dst); neigh_confirm(n); rcu_read_unlock(); } diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 9adb99845a56..e1c2ee0eef47 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -17,7 +17,7 @@ struct dst_ops { int (*gc)(struct dst_ops *ops); struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); - unsigned int (*default_mtu)(const struct dst_entry *); + unsigned int (*mtu)(const struct dst_entry *); u32 * (*cow_metrics)(struct dst_entry *, unsigned long); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, diff --git a/include/net/flow.h b/include/net/flow.h index a09447749e2d..da1f064a81b3 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -59,8 +59,11 @@ struct flowi4 { #define flowi4_proto __fl_common.flowic_proto #define flowi4_flags __fl_common.flowic_flags #define flowi4_secid __fl_common.flowic_secid - __be32 daddr; + + /* (saddr,daddr) must be grouped, same order as in IP header */ __be32 saddr; + __be32 daddr; + union flowi_uli uli; #define fl4_sport uli.ports.sport #define fl4_dport uli.ports.dport @@ -207,6 +210,7 @@ extern struct flow_cache_object *flow_cache_lookup( u8 dir, flow_resolve_t resolver, void *ctx); extern void flow_cache_flush(void); +extern void flow_cache_flush_deferred(void); extern atomic_t flow_cache_genid; #endif diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h new file mode 100644 index 000000000000..80461c1ae9ef --- /dev/null +++ b/include/net/flow_keys.h @@ -0,0 +1,16 @@ +#ifndef _NET_FLOW_KEYS_H +#define _NET_FLOW_KEYS_H + +struct flow_keys { + /* (src,dst) must be grouped, in the same way than in IP header */ + __be32 src; + __be32 dst; + union { + __be32 ports; + __be16 port16[2]; + }; + u8 ip_proto; +}; + +extern bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow); +#endif diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 82d8d09faa44..7db32995ccd3 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -128,6 +128,8 @@ extern int genl_register_mc_group(struct genl_family *family, struct genl_multicast_group *grp); extern void genl_unregister_mc_group(struct genl_family *family, struct genl_multicast_group *grp); +extern void genl_notify(struct sk_buff *skb, struct net *net, u32 pid, + u32 group, struct nlmsghdr *nlh, gfp_t flags); /** * genlmsg_put - Add generic netlink header to netlink message diff --git a/include/net/icmp.h b/include/net/icmp.h index f0698b955b73..75d615649071 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -31,8 +31,8 @@ struct icmp_err { extern const struct icmp_err icmp_err_convert[]; #define ICMP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define ICMP_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.icmp_statistics, field) -#define ICMPMSGOUT_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmpmsg_statistics, field+256) -#define ICMPMSGIN_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.icmpmsg_statistics, field) +#define ICMPMSGOUT_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field+256) +#define ICMPMSGIN_INC_STATS_BH(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field) struct dst_entry; struct net_proto_family; diff --git a/include/net/ieee802154.h b/include/net/ieee802154.h index d52685defb11..ee59f8b188dd 100644 --- a/include/net/ieee802154.h +++ b/include/net/ieee802154.h @@ -21,11 +21,14 @@ * Maxim Gorbachyov <maxim.gorbachev@siemens.com> * Maxim Osipov <maxim.osipov@siemens.com> * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #ifndef NET_IEEE802154_H #define NET_IEEE802154_H +#define IEEE802154_MTU 127 + #define IEEE802154_FC_TYPE_BEACON 0x0 /* Frame is beacon */ #define IEEE802154_FC_TYPE_DATA 0x1 /* Frame is data */ #define IEEE802154_FC_TYPE_ACK 0x2 /* Frame is acknowledgment */ @@ -56,6 +59,9 @@ (((x) & IEEE802154_FC_DAMODE_MASK) >> IEEE802154_FC_DAMODE_SHIFT) +/* MAC footer size */ +#define IEEE802154_MFR_SIZE 2 /* 2 octets */ + /* MAC's Command Frames Identifiers */ #define IEEE802154_CMD_ASSOCIATION_REQ 0x01 #define IEEE802154_CMD_ASSOCIATION_RESP 0x02 diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index e46674d5daea..00cbb4384c79 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -15,7 +15,7 @@ #define _INET6_HASHTABLES_H -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/types.h> @@ -110,5 +110,5 @@ extern struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif); -#endif /* defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) */ +#endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _INET6_HASHTABLES_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index e6db62e756dc..dbf9aab34c82 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -143,9 +143,9 @@ static inline void *inet_csk_ca(const struct sock *sk) return (void *)inet_csk(sk)->icsk_ca_priv; } -extern struct sock *inet_csk_clone(struct sock *sk, - const struct request_sock *req, - const gfp_t priority); +extern struct sock *inet_csk_clone_lock(const struct sock *sk, + const struct request_sock *req, + const gfp_t priority); enum inet_csk_ack_state_t { ICSK_ACK_SCHED = 1, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index b897d6e6d0a5..e3e405106afe 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -31,6 +31,7 @@ /** struct ip_options - IP Options * * @faddr - Saved first hop address + * @nexthop - Saved nexthop address in LSRR and SSRR * @is_data - Options in __data, rather than skb * @is_strictroute - Strict source route * @srr_is_hit - Packet destination addr was our one @@ -41,6 +42,7 @@ */ struct ip_options { __be32 faddr; + __be32 nexthop; unsigned char optlen; unsigned char srr; unsigned char rr; @@ -69,7 +71,7 @@ struct ip_options_data { struct inet_request_sock { struct request_sock req; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) u16 inet6_rsk_offset; #endif __be16 loc_port; @@ -137,7 +139,7 @@ struct rtable; struct inet_sock { /* sk and pinet6 has to be the first two members of inet_sock */ struct sock sk; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *pinet6; #endif /* Socket demultiplex comparisons on incoming packets. */ @@ -186,7 +188,7 @@ static inline void __inet_sk_copy_descendant(struct sock *sk_to, memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, sk_from->sk_prot->obj_size - ancestor_size); } -#if !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) +#if !(IS_ENABLED(CONFIG_IPV6)) static inline void inet_sk_copy_descendant(struct sock *sk_to, const struct sock *sk_from) { diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index e8c25b981205..ba52c830a7a5 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -218,20 +218,12 @@ extern void inet_twsk_purge(struct inet_hashinfo *hashinfo, static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { -#ifdef CONFIG_NET_NS - return rcu_dereference_raw(twsk->tw_net); /* protected by locking, */ - /* reference counting, */ - /* initialization, or RCU. */ -#else - return &init_net; -#endif + return read_pnet(&twsk->tw_net); } static inline void twsk_net_set(struct inet_timewait_sock *twsk, struct net *net) { -#ifdef CONFIG_NET_NS - rcu_assign_pointer(twsk->tw_net, net); -#endif + write_pnet(&twsk->tw_net, net); } #endif /* _INET_TIMEWAIT_SOCK_ */ diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 78c83e62218f..06b795dd5906 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -35,6 +35,7 @@ struct inet_peer { u32 metrics[RTAX_MAX]; u32 rate_tokens; /* rate limiting for ICMP */ + int redirect_genid; unsigned long rate_last; unsigned long pmtu_expires; u32 pmtu_orig; @@ -86,7 +87,7 @@ static inline struct inet_peer *inet_getpeer_v6(const struct in6_addr *v6daddr, { struct inetpeer_addr daddr; - ipv6_addr_copy((struct in6_addr *)daddr.addr.a6, v6daddr); + *(struct in6_addr *)daddr.addr.a6 = *v6daddr; daddr.family = AF_INET6; return inet_getpeer(&daddr, create); } diff --git a/include/net/ip.h b/include/net/ip.h index eca0ef7a495e..775009f9eaba 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -353,14 +353,14 @@ static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, memcpy(buf, &naddr, sizeof(naddr)); } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) #include <linux/ipv6.h> #endif static __inline__ void inet_reset_saddr(struct sock *sk) { inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); @@ -379,7 +379,7 @@ static inline int sk_mc_loop(struct sock *sk) switch (sk->sk_family) { case AF_INET: return inet_sk(sk)->mc_loop; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return inet6_sk(sk)->mc_loop; #endif @@ -450,7 +450,7 @@ extern int ip_options_rcv_srr(struct sk_buff *skb); * Functions provided by ip_sockglue.c */ -extern int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); +extern void ipv4_pktinfo_prepare(struct sk_buff *skb); extern void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb); extern int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 5735a0f979c3..b26bb8101981 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -86,9 +86,6 @@ struct fib6_table; struct rt6_info { struct dst_entry dst; -#define rt6i_dev dst.dev -#define rt6i_expires dst.expires - /* * Tail elements of dst_entry (__refcnt etc.) * and these elements (rarely used in hot path) are in @@ -202,6 +199,10 @@ struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, const struct in6_addr *saddr, int src_len); +extern void fib6_clean_all_ro(struct net *net, + int (*func)(struct rt6_info *, void *arg), + int prune, void *arg); + extern void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), int prune, void *arg); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 5e91b72fc718..2ad92ca4e6f3 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -70,6 +70,8 @@ extern void ip6_route_input(struct sk_buff *skb); extern struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk, struct flowi6 *fl6); +extern struct dst_entry * ip6_route_lookup(struct net *net, + struct flowi6 *fl6, int flags); extern int ip6_route_init(void); extern void ip6_route_cleanup(void); @@ -95,14 +97,14 @@ extern struct rt6_info *rt6_lookup(struct net *net, extern struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *addr); + struct flowi6 *fl6); extern int icmp6_dst_gc(void); extern void fib6_force_start_gc(struct net *net); extern struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, const struct in6_addr *addr, - int anycast); + bool anycast); extern int ip6_dst_hoplimit(struct dst_entry *dst); diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 873d5be7926c..ebe517f2da9f 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -21,7 +21,7 @@ #include <linux/netfilter.h> /* for union nf_inet_addr */ #include <linux/ip.h> #include <linux/ipv6.h> /* for struct ipv6hdr */ -#include <net/ipv6.h> /* for ipv6_addr_copy */ +#include <net/ipv6.h> #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netfilter/nf_conntrack.h> #endif @@ -119,8 +119,8 @@ ip_vs_fill_iphdr(int af, const void *nh, struct ip_vs_iphdr *iphdr) const struct ipv6hdr *iph = nh; iphdr->len = sizeof(struct ipv6hdr); iphdr->protocol = iph->nexthdr; - ipv6_addr_copy(&iphdr->saddr.in6, &iph->saddr); - ipv6_addr_copy(&iphdr->daddr.in6, &iph->daddr); + iphdr->saddr.in6 = iph->saddr; + iphdr->daddr.in6 = iph->daddr; } else #endif { @@ -137,7 +137,7 @@ static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst, { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) - ipv6_addr_copy(&dst->in6, &src->in6); + dst->in6 = src->in6; else #endif dst->ip = src->ip; @@ -1207,7 +1207,7 @@ extern void ip_vs_control_cleanup(void); extern struct ip_vs_dest * ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, - __u16 protocol, __u32 fwmark); + __u16 protocol, __u32 fwmark, __u32 flags); extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index a366a8a1fe23..e4170a22fc6f 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -132,6 +132,15 @@ extern struct ctl_path net_ipv6_ctl_path[]; SNMP_INC_STATS##modifier((net)->mib.statname##_statistics, (field));\ }) +/* per device and per net counters are atomic_long_t */ +#define _DEVINC_ATOMIC_ATOMIC(net, statname, idev, field) \ +({ \ + struct inet6_dev *_idev = (idev); \ + if (likely(_idev != NULL)) \ + SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ + SNMP_INC_STATS_ATOMIC_LONG((net)->mib.statname##_statistics, (field));\ +}) + #define _DEVADD(net, statname, modifier, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ @@ -168,11 +177,11 @@ extern struct ctl_path net_ipv6_ctl_path[]; _DEVINCATOMIC(net, icmpv6, _BH, idev, field) #define ICMP6MSGOUT_INC_STATS(net, idev, field) \ - _DEVINCATOMIC(net, icmpv6msg, , idev, field +256) + _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256) #define ICMP6MSGOUT_INC_STATS_BH(net, idev, field) \ - _DEVINCATOMIC(net, icmpv6msg, _BH, idev, field +256) + _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256) #define ICMP6MSGIN_INC_STATS_BH(net, idev, field) \ - _DEVINCATOMIC(net, icmpv6msg, _BH, idev, field) + _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field) struct ip6_ra_chain { struct ip6_ra_chain *next; @@ -300,11 +309,6 @@ ipv6_masked_addr_cmp(const struct in6_addr *a1, const struct in6_addr *m, ((a1->s6_addr32[3] ^ a2->s6_addr32[3]) & m->s6_addr32[3])); } -static inline void ipv6_addr_copy(struct in6_addr *a1, const struct in6_addr *a2) -{ - memcpy(a1, a2, sizeof(struct in6_addr)); -} - static inline void ipv6_addr_prefix(struct in6_addr *pfx, const struct in6_addr *addr, int plen) @@ -554,7 +558,7 @@ extern void ipv6_push_frag_opts(struct sk_buff *skb, u8 *proto); extern int ipv6_skip_exthdr(const struct sk_buff *, int start, - u8 *nexthdrp); + u8 *nexthdrp, __be16 *frag_offp); extern int ipv6_ext_hdr(u8 nexthdr); diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h index f2419cf44cef..0954ec959159 100644 --- a/include/net/iucv/af_iucv.h +++ b/include/net/iucv/af_iucv.h @@ -27,7 +27,6 @@ enum { IUCV_OPEN, IUCV_BOUND, IUCV_LISTEN, - IUCV_SEVERED, IUCV_DISCONN, IUCV_CLOSING, IUCV_CLOSED @@ -146,7 +145,6 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock, poll_table *wait); void iucv_sock_link(struct iucv_sock_list *l, struct sock *s); void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s); -int iucv_sock_wait_cnt(struct sock *sk, unsigned long timeo); void iucv_accept_enqueue(struct sock *parent, struct sock *sk); void iucv_accept_unlink(struct sock *sk); struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock); diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 62beeb97c4b1..e3133c23980e 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -79,6 +79,42 @@ struct nd_opt_hdr { __u8 nd_opt_len; } __packed; +static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) +{ + const u32 *p32 = pkey; + + return (((p32[0] ^ dev->ifindex) * hash_rnd[0]) + + (p32[1] * hash_rnd[1]) + + (p32[2] * hash_rnd[2]) + + (p32[3] * hash_rnd[3])); +} + +static inline struct neighbour *__ipv6_neigh_lookup(struct neigh_table *tbl, struct net_device *dev, const void *pkey) +{ + struct neigh_hash_table *nht; + const u32 *p32 = pkey; + struct neighbour *n; + u32 hash_val; + + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + hash_val = ndisc_hashfn(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); + for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); + n != NULL; + n = rcu_dereference_bh(n->next)) { + u32 *n32 = (u32 *) n->primary_key; + if (n->dev == dev && + ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) | + (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0) { + if (!atomic_inc_not_zero(&n->refcnt)) + n = NULL; + break; + } + } + rcu_read_unlock_bh(); + + return n; +} extern int ndisc_init(void); @@ -145,13 +181,4 @@ int ndisc_ifinfo_sysctl_strategy(ctl_table *ctl, extern void inet6_ifinfo_notify(int event, struct inet6_dev *idev); -static inline struct neighbour * ndisc_get_neigh(struct net_device *dev, const struct in6_addr *addr) -{ - - if (dev) - return __neigh_lookup_errno(&nd_tbl, addr, dev); - - return ERR_PTR(-ENODEV); -} - #endif diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 2720884287c3..34c996f46181 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -59,7 +59,7 @@ struct neigh_parms { int reachable_time; int delay_probe_time; - int queue_len; + int queue_len_bytes; int ucast_probes; int app_probes; int mcast_probes; @@ -99,6 +99,7 @@ struct neighbour { rwlock_t lock; atomic_t refcnt; struct sk_buff_head arp_queue; + unsigned int arp_queue_len_bytes; struct timer_list timer; unsigned long used; atomic_t probes; @@ -138,10 +139,12 @@ struct pneigh_entry { * neighbour table manipulation */ +#define NEIGH_NUM_HASH_RND 4 + struct neigh_hash_table { struct neighbour __rcu **hash_buckets; unsigned int hash_shift; - __u32 hash_rnd; + __u32 hash_rnd[NEIGH_NUM_HASH_RND]; struct rcu_head rcu; }; @@ -153,7 +156,7 @@ struct neigh_table { int key_len; __u32 (*hash)(const void *pkey, const struct net_device *dev, - __u32 hash_rnd); + __u32 *hash_rnd); int (*constructor)(struct neighbour *); int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); @@ -172,12 +175,18 @@ struct neigh_table { atomic_t entries; rwlock_t lock; unsigned long last_rand; - struct kmem_cache *kmem_cachep; struct neigh_statistics __percpu *stats; struct neigh_hash_table __rcu *nht; struct pneigh_entry **phash_buckets; }; +#define NEIGH_PRIV_ALIGN sizeof(long long) + +static inline void *neighbour_priv(const struct neighbour *n) +{ + return (char *)n + ALIGN(sizeof(*n) + n->tbl->key_len, NEIGH_PRIV_ALIGN); +} + /* flags for neigh_update() */ #define NEIGH_UPDATE_F_OVERRIDE 0x00000001 #define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002 diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 3bb6fa0eace0..ee547c149810 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -77,7 +77,7 @@ struct net { struct netns_packet packet; struct netns_unix unx; struct netns_ipv4 ipv4; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct netns_ipv6 ipv6; #endif #if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE) diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h index 4e9c63a20db2..463ae8e16696 100644 --- a/include/net/netfilter/nf_conntrack_acct.h +++ b/include/net/netfilter/nf_conntrack_acct.h @@ -15,8 +15,8 @@ #include <net/netfilter/nf_conntrack_extend.h> struct nf_conn_counter { - u_int64_t packets; - u_int64_t bytes; + atomic64_t packets; + atomic64_t bytes; }; static inline diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 4283508b3e18..a88fb6939387 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -67,18 +67,18 @@ struct nf_ct_event_notifier { int (*fcn)(unsigned int events, struct nf_ct_event *item); }; -extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; -extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb); -extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb); +extern int nf_conntrack_register_notifier(struct net *net, struct nf_ct_event_notifier *nb); +extern void nf_conntrack_unregister_notifier(struct net *net, struct nf_ct_event_notifier *nb); extern void nf_ct_deliver_cached_events(struct nf_conn *ct); static inline void nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) { + struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *e; - if (nf_conntrack_event_cb == NULL) + if (net->ct.nf_conntrack_event_cb == NULL) return; e = nf_ct_ecache_find(ct); @@ -95,11 +95,12 @@ nf_conntrack_eventmask_report(unsigned int eventmask, int report) { int ret = 0; + struct net *net = nf_ct_net(ct); struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; rcu_read_lock(); - notify = rcu_dereference(nf_conntrack_event_cb); + notify = rcu_dereference(net->ct.nf_conntrack_event_cb); if (notify == NULL) goto out_unlock; @@ -164,9 +165,8 @@ struct nf_exp_event_notifier { int (*fcn)(unsigned int events, struct nf_exp_event *item); }; -extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb; -extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb); -extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb); +extern int nf_ct_expect_register_notifier(struct net *net, struct nf_exp_event_notifier *nb); +extern void nf_ct_expect_unregister_notifier(struct net *net, struct nf_exp_event_notifier *nb); static inline void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, @@ -174,11 +174,12 @@ nf_ct_expect_event_report(enum ip_conntrack_expect_events event, u32 pid, int report) { + struct net *net = nf_ct_exp_net(exp); struct nf_exp_event_notifier *notify; struct nf_conntrack_ecache *e; rcu_read_lock(); - notify = rcu_dereference(nf_expect_event_cb); + notify = rcu_dereference(net->ct.nf_expect_event_cb); if (notify == NULL) goto out_unlock; diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 0f8a8c587532..4619caadd9d1 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -91,7 +91,6 @@ static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) void nf_ct_remove_expectations(struct nf_conn *ct); void nf_ct_unexpect_related(struct nf_conntrack_expect *exp); -void nf_ct_remove_userspace_expectations(void); /* Allocate space for an expectation: this is mandatory before calling nf_ct_expect_related. You will have to call put afterwards. */ diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h index 2f8fb77bfdd1..aea3f8221be0 100644 --- a/include/net/netfilter/nf_conntrack_tuple.h +++ b/include/net/netfilter/nf_conntrack_tuple.h @@ -12,7 +12,6 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> -#include <linux/netfilter_ipv4/nf_nat.h> #include <linux/list_nulls.h> /* A `tuple' is a structure containing the information to uniquely diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index b8872df7285f..b4de990b55f1 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -1,14 +1,12 @@ #ifndef _NF_NAT_H #define _NF_NAT_H #include <linux/netfilter_ipv4.h> -#include <linux/netfilter_ipv4/nf_nat.h> +#include <linux/netfilter/nf_nat.h> #include <net/netfilter/nf_conntrack_tuple.h> -#define NF_NAT_MAPPING_TYPE_MAX_NAMELEN 16 - enum nf_nat_manip_type { - IP_NAT_MANIP_SRC, - IP_NAT_MANIP_DST + NF_NAT_MANIP_SRC, + NF_NAT_MANIP_DST }; /* SRC manip occurs POST_ROUTING or LOCAL_IN */ @@ -52,7 +50,7 @@ struct nf_conn_nat { /* Set up the info structure to map into this range. */ extern unsigned int nf_nat_setup_info(struct nf_conn *ct, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype); /* Is this tuple already taken? (not by us)*/ diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h index 3dc7b98effeb..b13d8d18d595 100644 --- a/include/net/netfilter/nf_nat_core.h +++ b/include/net/netfilter/nf_nat_core.h @@ -20,7 +20,7 @@ extern int nf_nat_icmp_reply_translation(struct nf_conn *ct, static inline int nf_nat_initialized(struct nf_conn *ct, enum nf_nat_manip_type manip) { - if (manip == IP_NAT_MANIP_SRC) + if (manip == NF_NAT_MANIP_SRC) return ct->status & IPS_SRC_NAT_DONE; else return ct->status & IPS_DST_NAT_DONE; diff --git a/include/net/netfilter/nf_nat_protocol.h b/include/net/netfilter/nf_nat_protocol.h index 93cc90d28e66..7b0b51165f70 100644 --- a/include/net/netfilter/nf_nat_protocol.h +++ b/include/net/netfilter/nf_nat_protocol.h @@ -4,14 +4,12 @@ #include <net/netfilter/nf_nat.h> #include <linux/netfilter/nfnetlink_conntrack.h> -struct nf_nat_range; +struct nf_nat_ipv4_range; struct nf_nat_protocol { /* Protocol number. */ unsigned int protonum; - struct module *me; - /* Translate a packet to the target according to manip type. Return true if succeeded. */ bool (*manip_pkt)(struct sk_buff *skb, @@ -30,15 +28,12 @@ struct nf_nat_protocol { possible. Per-protocol part of tuple is initialized to the incoming packet. */ void (*unique_tuple)(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct); - int (*range_to_nlattr)(struct sk_buff *skb, - const struct nf_nat_range *range); - int (*nlattr_to_range)(struct nlattr *tb[], - struct nf_nat_range *range); + struct nf_nat_ipv4_range *range); }; /* Protocol registration. */ @@ -61,14 +56,12 @@ extern bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple, const union nf_conntrack_man_proto *max); extern void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct, u_int16_t *rover); -extern int nf_nat_proto_range_to_nlattr(struct sk_buff *skb, - const struct nf_nat_range *range); extern int nf_nat_proto_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range *range); + struct nf_nat_ipv4_range *range); #endif /*_NF_NAT_PROTO_H*/ diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h index e505358d8999..75ca9291cf2c 100644 --- a/include/net/netfilter/nf_tproxy_core.h +++ b/include/net/netfilter/nf_tproxy_core.h @@ -131,7 +131,7 @@ nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, return sk; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) static inline struct sock * nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, const struct in6_addr *saddr, const struct in6_addr *daddr, diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 0249399e51a7..7a911eca0f18 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -18,6 +18,8 @@ struct netns_ct { struct hlist_nulls_head unconfirmed; struct hlist_nulls_head dying; struct ip_conntrack_stat __percpu *stat; + struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; + struct nf_exp_event_notifier __rcu *nf_expect_event_cb; int sysctl_events; unsigned int sysctl_events_retry_timeout; int sysctl_acct; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d786b4fc02a4..bbd023a1c9b9 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -55,6 +55,7 @@ struct netns_ipv4 { int current_rt_cache_rebuild_count; unsigned int sysctl_ping_group_range[2]; + long sysctl_tcp_mem[3]; atomic_t rt_genid; atomic_t dev_addr_genid; diff --git a/include/net/netns/mib.h b/include/net/netns/mib.h index 0b44112e2366..d542a4b28cca 100644 --- a/include/net/netns/mib.h +++ b/include/net/netns/mib.h @@ -10,15 +10,15 @@ struct netns_mib { DEFINE_SNMP_STAT(struct udp_mib, udp_statistics); DEFINE_SNMP_STAT(struct udp_mib, udplite_statistics); DEFINE_SNMP_STAT(struct icmp_mib, icmp_statistics); - DEFINE_SNMP_STAT(struct icmpmsg_mib, icmpmsg_statistics); + DEFINE_SNMP_STAT_ATOMIC(struct icmpmsg_mib, icmpmsg_statistics); -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct proc_dir_entry *proc_net_devsnmp6; DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6); DEFINE_SNMP_STAT(struct udp_mib, udplite_stats_in6); DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics); DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics); - DEFINE_SNMP_STAT(struct icmpv6msg_mib, icmpv6msg_statistics); + DEFINE_SNMP_STAT_ATOMIC(struct icmpv6msg_mib, icmpv6msg_statistics); #endif #ifdef CONFIG_XFRM_STATISTICS DEFINE_SNMP_STAT(struct linux_xfrm_mib, xfrm_statistics); diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 748f91f87cd5..5299e69a32af 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -56,7 +56,7 @@ struct netns_xfrm { #endif struct dst_ops xfrm4_dst_ops; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct dst_ops xfrm6_dst_ops; #endif }; diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h new file mode 100644 index 000000000000..e503b87c4c1b --- /dev/null +++ b/include/net/netprio_cgroup.h @@ -0,0 +1,57 @@ +/* + * netprio_cgroup.h Control Group Priority set + * + * + * Authors: Neil Horman <nhorman@tuxdriver.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#ifndef _NETPRIO_CGROUP_H +#define _NETPRIO_CGROUP_H +#include <linux/module.h> +#include <linux/cgroup.h> +#include <linux/hardirq.h> +#include <linux/rcupdate.h> + + +struct netprio_map { + struct rcu_head rcu; + u32 priomap_len; + u32 priomap[]; +}; + +#ifdef CONFIG_CGROUPS + +struct cgroup_netprio_state { + struct cgroup_subsys_state css; + u32 prioidx; +}; + +#ifndef CONFIG_NETPRIO_CGROUP +extern int net_prio_subsys_id; +#endif + +extern void sock_update_netprioidx(struct sock *sk); + +static inline struct cgroup_netprio_state + *task_netprio_state(struct task_struct *p) +{ +#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) + return container_of(task_subsys_state(p, net_prio_subsys_id), + struct cgroup_netprio_state, css); +#else + return NULL; +#endif +} + +#else + +#define sock_update_netprioidx(sk) +#endif + +#endif /* _NET_CLS_CGROUP_H */ diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index b61eb6c9df14..2be95e2626c0 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -54,11 +54,10 @@ #define NCI_STATUS_RF_PROTOCOL_ERROR 0xb1 #define NCI_STATUS_RF_TIMEOUT_ERROR 0xb2 /* NFCEE Interface Specific Status Codes */ -#define NCI_STATUS_MAX_ACTIVE_NFCEE_INTERFACES_REACHED 0xc0 -#define NCI_STATUS_NFCEE_INTERFACE_ACTIVATION_FAILED 0xc1 -#define NCI_STATUS_NFCEE_TRANSMISSION_ERROR 0xc2 -#define NCI_STATUS_NFCEE_PROTOCOL_ERROR 0xc3 -#define NCI_STATUS_NFCEE_TIMEOUT_ERROR 0xc4 +#define NCI_STATUS_NFCEE_INTERFACE_ACTIVATION_FAILED 0xc0 +#define NCI_STATUS_NFCEE_TRANSMISSION_ERROR 0xc1 +#define NCI_STATUS_NFCEE_PROTOCOL_ERROR 0xc2 +#define NCI_STATUS_NFCEE_TIMEOUT_ERROR 0xc3 /* NCI RF Technology and Mode */ #define NCI_NFC_A_PASSIVE_POLL_MODE 0x00 @@ -66,11 +65,13 @@ #define NCI_NFC_F_PASSIVE_POLL_MODE 0x02 #define NCI_NFC_A_ACTIVE_POLL_MODE 0x03 #define NCI_NFC_F_ACTIVE_POLL_MODE 0x05 +#define NCI_NFC_15693_PASSIVE_POLL_MODE 0x06 #define NCI_NFC_A_PASSIVE_LISTEN_MODE 0x80 #define NCI_NFC_B_PASSIVE_LISTEN_MODE 0x81 #define NCI_NFC_F_PASSIVE_LISTEN_MODE 0x82 #define NCI_NFC_A_ACTIVE_LISTEN_MODE 0x83 #define NCI_NFC_F_ACTIVE_LISTEN_MODE 0x85 +#define NCI_NFC_15693_PASSIVE_LISTEN_MODE 0x86 /* NCI RF Technologies */ #define NCI_NFC_RF_TECHNOLOGY_A 0x00 @@ -83,9 +84,9 @@ #define NCI_NFC_BIT_RATE_212 0x01 #define NCI_NFC_BIT_RATE_424 0x02 #define NCI_NFC_BIT_RATE_848 0x03 -#define NCI_NFC_BIT_RATE_1696 0x04 -#define NCI_NFC_BIT_RATE_3392 0x05 -#define NCI_NFC_BIT_RATE_6784 0x06 +#define NCI_NFC_BIT_RATE_1695 0x04 +#define NCI_NFC_BIT_RATE_3390 0x05 +#define NCI_NFC_BIT_RATE_6780 0x06 /* NCI RF Protocols */ #define NCI_RF_PROTOCOL_UNKNOWN 0x00 @@ -114,20 +115,6 @@ /* NCI RF_DISCOVER_MAP_CMD modes */ #define NCI_DISC_MAP_MODE_POLL 0x01 #define NCI_DISC_MAP_MODE_LISTEN 0x02 -#define NCI_DISC_MAP_MODE_BOTH 0x03 - -/* NCI Discovery Types */ -#define NCI_DISCOVERY_TYPE_POLL_A_PASSIVE 0x00 -#define NCI_DISCOVERY_TYPE_POLL_B_PASSIVE 0x01 -#define NCI_DISCOVERY_TYPE_POLL_F_PASSIVE 0x02 -#define NCI_DISCOVERY_TYPE_POLL_A_ACTIVE 0x03 -#define NCI_DISCOVERY_TYPE_POLL_F_ACTIVE 0x05 -#define NCI_DISCOVERY_TYPE_WAKEUP_A_ACTIVE 0x09 -#define NCI_DISCOVERY_TYPE_LISTEN_A_PASSIVE 0x80 -#define NCI_DISCOVERY_TYPE_LISTEN_B_PASSIVE 0x81 -#define NCI_DISCOVERY_TYPE_LISTEN_F_PASSIVE 0x82 -#define NCI_DISCOVERY_TYPE_LISTEN_A_ACTIVE 0x83 -#define NCI_DISCOVERY_TYPE_LISTEN_F_ACTIVE 0x85 /* NCI Deactivation Type */ #define NCI_DEACTIVATE_TYPE_IDLE_MODE 0x00 @@ -200,7 +187,7 @@ struct nci_core_reset_cmd { struct disc_map_config { __u8 rf_protocol; __u8 mode; - __u8 rf_interface_type; + __u8 rf_interface; } __packed; struct nci_rf_disc_map_cmd { @@ -211,7 +198,7 @@ struct nci_rf_disc_map_cmd { #define NCI_OP_RF_DISCOVER_CMD nci_opcode_pack(NCI_GID_RF_MGMT, 0x03) struct disc_config { - __u8 type; + __u8 rf_tech_and_mode; __u8 frequency; } __packed; @@ -249,8 +236,6 @@ struct nci_core_init_rsp_2 { __le16 max_routing_table_size; __u8 max_ctrl_pkt_payload_len; __le16 max_size_for_large_params; - __u8 max_data_pkt_payload_size; - __u8 initial_num_credits; __u8 manufact_id; __le32 manufact_specific_info; } __packed; @@ -264,7 +249,7 @@ struct nci_core_init_rsp_2 { /* --------------------------- */ /* ---- NCI Notifications ---- */ /* --------------------------- */ -#define NCI_OP_CORE_CONN_CREDITS_NTF nci_opcode_pack(NCI_GID_CORE, 0x07) +#define NCI_OP_CORE_CONN_CREDITS_NTF nci_opcode_pack(NCI_GID_CORE, 0x06) struct conn_credit_entry { __u8 conn_id; __u8 credits; @@ -275,6 +260,12 @@ struct nci_core_conn_credit_ntf { struct conn_credit_entry conn_entries[NCI_MAX_NUM_CONN]; } __packed; +#define NCI_OP_CORE_INTF_ERROR_NTF nci_opcode_pack(NCI_GID_CORE, 0x08) +struct nci_core_intf_error_ntf { + __u8 status; + __u8 conn_id; +} __packed; + #define NCI_OP_RF_INTF_ACTIVATED_NTF nci_opcode_pack(NCI_GID_RF_MGMT, 0x05) struct rf_tech_specific_params_nfca_poll { __u16 sens_res; @@ -291,9 +282,11 @@ struct activation_params_nfca_poll_iso_dep { struct nci_rf_intf_activated_ntf { __u8 rf_discovery_id; - __u8 rf_interface_type; + __u8 rf_interface; __u8 rf_protocol; __u8 activation_rf_tech_and_mode; + __u8 max_data_pkt_payload_size; + __u8 initial_num_credits; __u8 rf_tech_specific_params_len; union { diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index c92b69d7e0c2..bccd89e9d4c2 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -111,11 +111,13 @@ struct nci_dev { __u16 max_routing_table_size; __u8 max_ctrl_pkt_payload_len; __u16 max_size_for_large_params; - __u8 max_data_pkt_payload_size; - __u8 initial_num_credits; __u8 manufact_id; __u32 manufact_specific_info; + /* received during NCI_OP_RF_INTF_ACTIVATED_NTF */ + __u8 max_data_pkt_payload_size; + __u8 initial_num_credits; + /* stored during nci_data_exchange */ data_exchange_cb_t data_exchange_cb; void *data_exchange_cb_context; diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index ccfe757a94ec..8696b773a695 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -65,12 +65,15 @@ struct nfc_ops { #define NFC_TARGET_IDX_ANY -1 #define NFC_MAX_GT_LEN 48 +#define NFC_MAX_NFCID1_LEN 10 struct nfc_target { u32 idx; u32 supported_protocols; u16 sens_res; u8 sel_res; + u8 nfcid1_len; + u8 nfcid1[NFC_MAX_NFCID1_LEN]; }; struct nfc_genl_data { diff --git a/include/net/protocol.h b/include/net/protocol.h index 6f7eb800974a..875f4895b033 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -25,7 +25,7 @@ #define _PROTOCOL_H #include <linux/in6.h> -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) #include <linux/ipv6.h> #endif @@ -38,7 +38,7 @@ struct net_protocol { void (*err_handler)(struct sk_buff *skb, u32 info); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - u32 features); + netdev_features_t features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); @@ -46,7 +46,7 @@ struct net_protocol { netns_ok:1; }; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct inet6_protocol { int (*handler)(struct sk_buff *skb); @@ -57,7 +57,7 @@ struct inet6_protocol { int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - u32 features); + netdev_features_t features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); @@ -91,7 +91,7 @@ struct inet_protosw { extern const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS]; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS]; #endif @@ -100,7 +100,7 @@ extern int inet_del_protocol(const struct net_protocol *prot, unsigned char num) extern void inet_register_protosw(struct inet_protosw *p); extern void inet_unregister_protosw(struct inet_protosw *p); -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) extern int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num); extern int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num); extern int inet6_register_protosw(struct inet_protosw *p); diff --git a/include/net/red.h b/include/net/red.h index 3319f16b3beb..baab385a4736 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -5,6 +5,7 @@ #include <net/pkt_sched.h> #include <net/inet_ecn.h> #include <net/dsfield.h> +#include <linux/reciprocal_div.h> /* Random Early Detection (RED) algorithm. ======================================= @@ -87,6 +88,29 @@ etc. */ +/* + * Adaptative RED : An Algorithm for Increasing the Robustness of RED's AQM + * (Sally FLoyd, Ramakrishna Gummadi, and Scott Shenker) August 2001 + * + * Every 500 ms: + * if (avg > target and max_p <= 0.5) + * increase max_p : max_p += alpha; + * else if (avg < target and max_p >= 0.01) + * decrease max_p : max_p *= beta; + * + * target :[qth_min + 0.4*(qth_min - qth_max), + * qth_min + 0.6*(qth_min - qth_max)]. + * alpha : min(0.01, max_p / 4) + * beta : 0.9 + * max_P is a Q0.32 fixed point number (with 32 bits mantissa) + * max_P between 0.01 and 0.5 (1% - 50%) [ Its no longer a negative power of two ] + */ +#define RED_ONE_PERCENT ((u32)DIV_ROUND_CLOSEST(1ULL<<32, 100)) + +#define MAX_P_MIN (1 * RED_ONE_PERCENT) +#define MAX_P_MAX (50 * RED_ONE_PERCENT) +#define MAX_P_ALPHA(val) min(MAX_P_MIN, val / 4) + #define RED_STAB_SIZE 256 #define RED_STAB_MASK (RED_STAB_SIZE - 1) @@ -101,82 +125,112 @@ struct red_stats { struct red_parms { /* Parameters */ - u32 qth_min; /* Min avg length threshold: A scaled */ - u32 qth_max; /* Max avg length threshold: A scaled */ + u32 qth_min; /* Min avg length threshold: Wlog scaled */ + u32 qth_max; /* Max avg length threshold: Wlog scaled */ u32 Scell_max; - u32 Rmask; /* Cached random mask, see red_rmask */ + u32 max_P; /* probability, [0 .. 1.0] 32 scaled */ + u32 max_P_reciprocal; /* reciprocal_value(max_P / qth_delta) */ + u32 qth_delta; /* max_th - min_th */ + u32 target_min; /* min_th + 0.4*(max_th - min_th) */ + u32 target_max; /* min_th + 0.6*(max_th - min_th) */ u8 Scell_log; u8 Wlog; /* log(W) */ u8 Plog; /* random number bits */ u8 Stab[RED_STAB_SIZE]; +}; +struct red_vars { /* Variables */ int qcount; /* Number of packets since last random number generation */ u32 qR; /* Cached random number */ - unsigned long qavg; /* Average queue length: A scaled */ - psched_time_t qidlestart; /* Start of current idle period */ + unsigned long qavg; /* Average queue length: Wlog scaled */ + ktime_t qidlestart; /* Start of current idle period */ }; -static inline u32 red_rmask(u8 Plog) +static inline u32 red_maxp(u8 Plog) { - return Plog < 32 ? ((1 << Plog) - 1) : ~0UL; + return Plog < 32 ? (~0U >> Plog) : ~0U; } -static inline void red_set_parms(struct red_parms *p, - u32 qth_min, u32 qth_max, u8 Wlog, u8 Plog, - u8 Scell_log, u8 *stab) +static inline void red_set_vars(struct red_vars *v) { /* Reset average queue length, the value is strictly bound * to the parameters below, reseting hurts a bit but leaving * it might result in an unreasonable qavg for a while. --TGR */ - p->qavg = 0; + v->qavg = 0; + + v->qcount = -1; +} + +static inline void red_set_parms(struct red_parms *p, + u32 qth_min, u32 qth_max, u8 Wlog, u8 Plog, + u8 Scell_log, u8 *stab, u32 max_P) +{ + int delta = qth_max - qth_min; + u32 max_p_delta; - p->qcount = -1; p->qth_min = qth_min << Wlog; p->qth_max = qth_max << Wlog; p->Wlog = Wlog; p->Plog = Plog; - p->Rmask = red_rmask(Plog); + if (delta < 0) + delta = 1; + p->qth_delta = delta; + if (!max_P) { + max_P = red_maxp(Plog); + max_P *= delta; /* max_P = (qth_max - qth_min)/2^Plog */ + } + p->max_P = max_P; + max_p_delta = max_P / delta; + max_p_delta = max(max_p_delta, 1U); + p->max_P_reciprocal = reciprocal_value(max_p_delta); + + /* RED Adaptative target : + * [min_th + 0.4*(min_th - max_th), + * min_th + 0.6*(min_th - max_th)]. + */ + delta /= 5; + p->target_min = qth_min + 2*delta; + p->target_max = qth_min + 3*delta; + p->Scell_log = Scell_log; p->Scell_max = (255 << Scell_log); memcpy(p->Stab, stab, sizeof(p->Stab)); } -static inline int red_is_idling(struct red_parms *p) +static inline int red_is_idling(const struct red_vars *v) { - return p->qidlestart != PSCHED_PASTPERFECT; + return v->qidlestart.tv64 != 0; } -static inline void red_start_of_idle_period(struct red_parms *p) +static inline void red_start_of_idle_period(struct red_vars *v) { - p->qidlestart = psched_get_time(); + v->qidlestart = ktime_get(); } -static inline void red_end_of_idle_period(struct red_parms *p) +static inline void red_end_of_idle_period(struct red_vars *v) { - p->qidlestart = PSCHED_PASTPERFECT; + v->qidlestart.tv64 = 0; } -static inline void red_restart(struct red_parms *p) +static inline void red_restart(struct red_vars *v) { - red_end_of_idle_period(p); - p->qavg = 0; - p->qcount = -1; + red_end_of_idle_period(v); + v->qavg = 0; + v->qcount = -1; } -static inline unsigned long red_calc_qavg_from_idle_time(struct red_parms *p) +static inline unsigned long red_calc_qavg_from_idle_time(const struct red_parms *p, + const struct red_vars *v) { - psched_time_t now; - long us_idle; + s64 delta = ktime_us_delta(ktime_get(), v->qidlestart); + long us_idle = min_t(s64, delta, p->Scell_max); int shift; - now = psched_get_time(); - us_idle = psched_tdiff_bounded(now, p->qidlestart, p->Scell_max); - /* * The problem: ideally, average length queue recalcultion should * be done over constant clock intervals. This is too expensive, so @@ -200,7 +254,7 @@ static inline unsigned long red_calc_qavg_from_idle_time(struct red_parms *p) shift = p->Stab[(us_idle >> p->Scell_log) & RED_STAB_MASK]; if (shift) - return p->qavg >> shift; + return v->qavg >> shift; else { /* Approximate initial part of exponent with linear function: * @@ -209,16 +263,17 @@ static inline unsigned long red_calc_qavg_from_idle_time(struct red_parms *p) * Seems, it is the best solution to * problem of too coarse exponent tabulation. */ - us_idle = (p->qavg * (u64)us_idle) >> p->Scell_log; + us_idle = (v->qavg * (u64)us_idle) >> p->Scell_log; - if (us_idle < (p->qavg >> 1)) - return p->qavg - us_idle; + if (us_idle < (v->qavg >> 1)) + return v->qavg - us_idle; else - return p->qavg >> 1; + return v->qavg >> 1; } } -static inline unsigned long red_calc_qavg_no_idle_time(struct red_parms *p, +static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p, + const struct red_vars *v, unsigned int backlog) { /* @@ -230,42 +285,46 @@ static inline unsigned long red_calc_qavg_no_idle_time(struct red_parms *p, * * --ANK (980924) */ - return p->qavg + (backlog - (p->qavg >> p->Wlog)); + return v->qavg + (backlog - (v->qavg >> p->Wlog)); } -static inline unsigned long red_calc_qavg(struct red_parms *p, +static inline unsigned long red_calc_qavg(const struct red_parms *p, + const struct red_vars *v, unsigned int backlog) { - if (!red_is_idling(p)) - return red_calc_qavg_no_idle_time(p, backlog); + if (!red_is_idling(v)) + return red_calc_qavg_no_idle_time(p, v, backlog); else - return red_calc_qavg_from_idle_time(p); + return red_calc_qavg_from_idle_time(p, v); } -static inline u32 red_random(struct red_parms *p) + +static inline u32 red_random(const struct red_parms *p) { - return net_random() & p->Rmask; + return reciprocal_divide(net_random(), p->max_P_reciprocal); } -static inline int red_mark_probability(struct red_parms *p, unsigned long qavg) +static inline int red_mark_probability(const struct red_parms *p, + const struct red_vars *v, + unsigned long qavg) { /* The formula used below causes questions. - OK. qR is random number in the interval 0..Rmask + OK. qR is random number in the interval + (0..1/max_P)*(qth_max-qth_min) i.e. 0..(2^Plog). If we used floating point arithmetics, it would be: (2^Plog)*rnd_num, where rnd_num is less 1. Taking into account, that qavg have fixed - point at Wlog, and Plog is related to max_P by - max_P = (qth_max-qth_min)/2^Plog; two lines + point at Wlog, two lines below have the following floating point equivalent: max_P*(qavg - qth_min)/(qth_max-qth_min) < rnd/qcount Any questions? --ANK (980924) */ - return !(((qavg - p->qth_min) >> p->Wlog) * p->qcount < p->qR); + return !(((qavg - p->qth_min) >> p->Wlog) * v->qcount < v->qR); } enum { @@ -274,7 +333,7 @@ enum { RED_ABOVE_MAX_TRESH, }; -static inline int red_cmp_thresh(struct red_parms *p, unsigned long qavg) +static inline int red_cmp_thresh(const struct red_parms *p, unsigned long qavg) { if (qavg < p->qth_min) return RED_BELOW_MIN_THRESH; @@ -290,27 +349,29 @@ enum { RED_HARD_MARK, }; -static inline int red_action(struct red_parms *p, unsigned long qavg) +static inline int red_action(const struct red_parms *p, + struct red_vars *v, + unsigned long qavg) { switch (red_cmp_thresh(p, qavg)) { case RED_BELOW_MIN_THRESH: - p->qcount = -1; + v->qcount = -1; return RED_DONT_MARK; case RED_BETWEEN_TRESH: - if (++p->qcount) { - if (red_mark_probability(p, qavg)) { - p->qcount = 0; - p->qR = red_random(p); + if (++v->qcount) { + if (red_mark_probability(p, v, qavg)) { + v->qcount = 0; + v->qR = red_random(p); return RED_PROB_MARK; } } else - p->qR = red_random(p); + v->qR = red_random(p); return RED_DONT_MARK; case RED_ABOVE_MAX_TRESH: - p->qcount = -1; + v->qcount = -1; return RED_HARD_MARK; } @@ -318,4 +379,25 @@ static inline int red_action(struct red_parms *p, unsigned long qavg) return RED_DONT_MARK; } +static inline void red_adaptative_algo(struct red_parms *p, struct red_vars *v) +{ + unsigned long qavg; + u32 max_p_delta; + + qavg = v->qavg; + if (red_is_idling(v)) + qavg = red_calc_qavg_from_idle_time(p, v); + + /* p->qavg is fixed point number with point at Wlog */ + qavg >>= p->Wlog; + + if (qavg > p->target_max && p->max_P <= MAX_P_MAX) + p->max_P += MAX_P_ALPHA(p->max_P); /* maxp = maxp + alpha */ + else if (qavg < p->target_min && p->max_P >= MAX_P_MIN) + p->max_P = (p->max_P/10)*9; /* maxp = maxp * Beta */ + + max_p_delta = DIV_ROUND_CLOSEST(p->max_P, p->qth_delta); + max_p_delta = max(max_p_delta, 1U); + p->max_P_reciprocal = reciprocal_value(max_p_delta); +} #endif diff --git a/include/net/route.h b/include/net/route.h index db7b3432f07c..91855d185b53 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -71,12 +71,12 @@ struct rtable { struct fib_info *fi; /* for client ref to shared metrics */ }; -static inline bool rt_is_input_route(struct rtable *rt) +static inline bool rt_is_input_route(const struct rtable *rt) { return rt->rt_route_iif != 0; } -static inline bool rt_is_output_route(struct rtable *rt) +static inline bool rt_is_output_route(const struct rtable *rt) { return rt->rt_route_iif == 0; } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 6a72a58cde59..d3685615a8b0 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -71,7 +71,7 @@ #include <linux/jiffies.h> #include <linux/idr.h> -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ip6_route.h> #endif @@ -383,7 +383,7 @@ static inline void sctp_sysctl_unregister(void) { return; } /* Size of Supported Address Parameter for 'x' address types. */ #define SCTP_SAT_LEN(x) (sizeof(struct sctp_paramhdr) + (x) * sizeof(__u16)) -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) void sctp_v6_pf_init(void); void sctp_v6_pf_exit(void); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index e90e7a9935dd..88949a994538 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -235,12 +235,15 @@ extern struct sctp_globals { /* Flag to indicate whether computing and verifying checksum * is disabled. */ - int checksum_disable; + bool checksum_disable; /* Threshold for rwnd update SACKS. Receive buffer shifted this many * bits is an indicator of when to send and window update SACK. */ int rwnd_update_shift; + + /* Threshold for autoclose timeout, in seconds. */ + unsigned long max_autoclose; } sctp_globals; #define sctp_rto_initial (sctp_globals.rto_initial) @@ -281,6 +284,7 @@ extern struct sctp_globals { #define sctp_auth_enable (sctp_globals.auth_enable) #define sctp_checksum_disable (sctp_globals.checksum_disable) #define sctp_rwnd_upd_shift (sctp_globals.rwnd_update_shift) +#define sctp_max_autoclose (sctp_globals.max_autoclose) /* SCTP Socket type: UDP or TCP style. */ typedef enum { @@ -365,7 +369,7 @@ static inline struct sock *sctp_opt2sk(const struct sctp_sock *sp) return (struct sock *)sp; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct sctp6_sock { struct sctp_sock sctp; struct ipv6_pinfo inet6; @@ -1085,6 +1089,7 @@ void sctp_transport_burst_reset(struct sctp_transport *); unsigned long sctp_transport_timeout(struct sctp_transport *); void sctp_transport_reset(struct sctp_transport *); void sctp_transport_update_pmtu(struct sctp_transport *, u32); +void sctp_transport_immediate_rtx(struct sctp_transport *); /* This is the structure we use to queue packets as they come into diff --git a/include/net/snmp.h b/include/net/snmp.h index 8f0f9ac0307f..2f65e1686fc8 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -67,7 +67,7 @@ struct icmp_mib { #define ICMPMSG_MIB_MAX __ICMPMSG_MIB_MAX struct icmpmsg_mib { - unsigned long mibs[ICMPMSG_MIB_MAX]; + atomic_long_t mibs[ICMPMSG_MIB_MAX]; }; /* ICMP6 (IPv6-ICMP) */ @@ -84,7 +84,7 @@ struct icmpv6_mib_device { #define ICMP6MSG_MIB_MAX __ICMP6MSG_MIB_MAX /* per network ns counters */ struct icmpv6msg_mib { - unsigned long mibs[ICMP6MSG_MIB_MAX]; + atomic_long_t mibs[ICMP6MSG_MIB_MAX]; }; /* per device counters, (shared on all cpus) */ struct icmpv6msg_mib_device { diff --git a/include/net/sock.h b/include/net/sock.h index c0c32a4cdd07..bb972d254dff 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -53,6 +53,8 @@ #include <linux/security.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/memcontrol.h> +#include <linux/res_counter.h> #include <linux/filter.h> #include <linux/rculist_nulls.h> @@ -62,6 +64,22 @@ #include <net/dst.h> #include <net/checksum.h> +struct cgroup; +struct cgroup_subsys; +#ifdef CONFIG_NET +int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss); +void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss); +#else +static inline +int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + return 0; +} +static inline +void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ +} +#endif /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of @@ -167,6 +185,7 @@ struct sock_common { /* public: */ }; +struct cg_proto; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock @@ -227,6 +246,7 @@ struct sock_common { * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_classid: this socket's cgroup classid + * @sk_cgrp: this socket's cgroup-specific proto data * @sk_write_pending: a write to stream socket waits to start * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed @@ -306,8 +326,8 @@ struct sock { kmemcheck_bitfield_end(flags); int sk_wmem_queued; gfp_t sk_allocation; - int sk_route_caps; - int sk_route_nocaps; + netdev_features_t sk_route_caps; + netdev_features_t sk_route_nocaps; int sk_gso_type; unsigned int sk_gso_max_size; int sk_rcvlowat; @@ -320,6 +340,9 @@ struct sock { unsigned short sk_ack_backlog; unsigned short sk_max_ack_backlog; __u32 sk_priority; +#ifdef CONFIG_CGROUPS + __u32 sk_cgrp_prioidx; +#endif struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; @@ -338,6 +361,7 @@ struct sock { #endif __u32 sk_mark; u32 sk_classid; + struct cg_proto *sk_cgrp; void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk, int bytes); void (*sk_write_space)(struct sock *sk); @@ -638,12 +662,14 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) /* * Take into account size of receive queue and backlog queue + * Do not take into account this skb truesize, + * to allow even a single big packet to come. */ static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb) { unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); - return qsize + skb->truesize > sk->sk_rcvbuf; + return qsize > sk->sk_rcvbuf; } /* The per-socket spinlock must be held here. */ @@ -834,6 +860,37 @@ struct proto { #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM + /* + * cgroup specific init/deinit functions. Called once for all + * protocols that implement it, from cgroups populate function. + * This function has to setup any files the protocol want to + * appear in the kmem cgroup filesystem. + */ + int (*init_cgroup)(struct cgroup *cgrp, + struct cgroup_subsys *ss); + void (*destroy_cgroup)(struct cgroup *cgrp, + struct cgroup_subsys *ss); + struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg); +#endif +}; + +struct cg_proto { + void (*enter_memory_pressure)(struct sock *sk); + struct res_counter *memory_allocated; /* Current allocated memory. */ + struct percpu_counter *sockets_allocated; /* Current number of sockets. */ + int *memory_pressure; + long *sysctl_mem; + /* + * memcg field is used to find which memcg we belong directly + * Each memcg struct can hold more than one cg_proto, so container_of + * won't really cut. + * + * The elegant solution would be having an inverse function to + * proto_cgroup in struct proto, but that means polluting the structure + * for everybody, instead of just for memcg users. + */ + struct mem_cgroup *memcg; }; extern int proto_register(struct proto *prot, int alloc_slab); @@ -852,7 +909,7 @@ static inline void sk_refcnt_debug_dec(struct sock *sk) sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks)); } -static inline void sk_refcnt_debug_release(const struct sock *sk) +inline void sk_refcnt_debug_release(const struct sock *sk) { if (atomic_read(&sk->sk_refcnt) != 1) printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n", @@ -864,6 +921,208 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +extern struct jump_label_key memcg_socket_limit_enabled; +static inline struct cg_proto *parent_cg_proto(struct proto *proto, + struct cg_proto *cg_proto) +{ + return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg)); +} +#define mem_cgroup_sockets_enabled static_branch(&memcg_socket_limit_enabled) +#else +#define mem_cgroup_sockets_enabled 0 +static inline struct cg_proto *parent_cg_proto(struct proto *proto, + struct cg_proto *cg_proto) +{ + return NULL; +} +#endif + + +static inline bool sk_has_memory_pressure(const struct sock *sk) +{ + return sk->sk_prot->memory_pressure != NULL; +} + +static inline bool sk_under_memory_pressure(const struct sock *sk) +{ + if (!sk->sk_prot->memory_pressure) + return false; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + return !!*sk->sk_cgrp->memory_pressure; + + return !!*sk->sk_prot->memory_pressure; +} + +static inline void sk_leave_memory_pressure(struct sock *sk) +{ + int *memory_pressure = sk->sk_prot->memory_pressure; + + if (!memory_pressure) + return; + + if (*memory_pressure) + *memory_pressure = 0; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + struct proto *prot = sk->sk_prot; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + if (*cg_proto->memory_pressure) + *cg_proto->memory_pressure = 0; + } + +} + +static inline void sk_enter_memory_pressure(struct sock *sk) +{ + if (!sk->sk_prot->enter_memory_pressure) + return; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + struct proto *prot = sk->sk_prot; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + cg_proto->enter_memory_pressure(sk); + } + + sk->sk_prot->enter_memory_pressure(sk); +} + +static inline long sk_prot_mem_limits(const struct sock *sk, int index) +{ + long *prot = sk->sk_prot->sysctl_mem; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + prot = sk->sk_cgrp->sysctl_mem; + return prot[index]; +} + +static inline void memcg_memory_allocated_add(struct cg_proto *prot, + unsigned long amt, + int *parent_status) +{ + struct res_counter *fail; + int ret; + + ret = res_counter_charge(prot->memory_allocated, + amt << PAGE_SHIFT, &fail); + + if (ret < 0) + *parent_status = OVER_LIMIT; +} + +static inline void memcg_memory_allocated_sub(struct cg_proto *prot, + unsigned long amt) +{ + res_counter_uncharge(prot->memory_allocated, amt << PAGE_SHIFT); +} + +static inline u64 memcg_memory_allocated_read(struct cg_proto *prot) +{ + u64 ret; + ret = res_counter_read_u64(prot->memory_allocated, RES_USAGE); + return ret >> PAGE_SHIFT; +} + +static inline long +sk_memory_allocated(const struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + return memcg_memory_allocated_read(sk->sk_cgrp); + + return atomic_long_read(prot->memory_allocated); +} + +static inline long +sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status) +{ + struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status); + /* update the root cgroup regardless */ + atomic_long_add_return(amt, prot->memory_allocated); + return memcg_memory_allocated_read(sk->sk_cgrp); + } + + return atomic_long_add_return(amt, prot->memory_allocated); +} + +static inline void +sk_memory_allocated_sub(struct sock *sk, int amt, int parent_status) +{ + struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp && + parent_status != OVER_LIMIT) /* Otherwise was uncharged already */ + memcg_memory_allocated_sub(sk->sk_cgrp, amt); + + atomic_long_sub(amt, prot->memory_allocated); +} + +static inline void sk_sockets_allocated_dec(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + percpu_counter_dec(cg_proto->sockets_allocated); + } + + percpu_counter_dec(prot->sockets_allocated); +} + +static inline void sk_sockets_allocated_inc(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { + struct cg_proto *cg_proto = sk->sk_cgrp; + + for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) + percpu_counter_inc(cg_proto->sockets_allocated); + } + + percpu_counter_inc(prot->sockets_allocated); +} + +static inline int +sk_sockets_allocated_read_positive(struct sock *sk) +{ + struct proto *prot = sk->sk_prot; + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + return percpu_counter_sum_positive(sk->sk_cgrp->sockets_allocated); + + return percpu_counter_sum_positive(prot->sockets_allocated); +} + +static inline int +proto_sockets_allocated_sum_positive(struct proto *prot) +{ + return percpu_counter_sum_positive(prot->sockets_allocated); +} + +static inline long +proto_memory_allocated(struct proto *prot) +{ + return atomic_long_read(prot->memory_allocated); +} + +static inline bool +proto_memory_pressure(struct proto *prot) +{ + if (!prot->memory_pressure) + return false; + return !!*prot->memory_pressure; +} + #ifdef CONFIG_PROC_FS /* Called with local bh disabled */ @@ -1090,8 +1349,8 @@ extern struct sock *sk_alloc(struct net *net, int family, struct proto *prot); extern void sk_free(struct sock *sk); extern void sk_release_kernel(struct sock *sk); -extern struct sock *sk_clone(const struct sock *sk, - const gfp_t priority); +extern struct sock *sk_clone_lock(const struct sock *sk, + const gfp_t priority); extern struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, @@ -1394,7 +1653,7 @@ static inline int sk_can_gso(const struct sock *sk) extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst); -static inline void sk_nocaps_add(struct sock *sk, int flags) +static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) { sk->sk_route_nocaps |= flags; sk->sk_route_caps &= ~flags; @@ -1671,7 +1930,7 @@ static inline struct page *sk_stream_alloc_page(struct sock *sk) page = alloc_pages(sk->sk_allocation, 0); if (!page) { - sk->sk_prot->enter_memory_pressure(sk); + sk_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return page; diff --git a/include/net/tcp.h b/include/net/tcp.h index bb18c4d69aba..0118ea999f67 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -44,6 +44,7 @@ #include <net/dst.h> #include <linux/seq_file.h> +#include <linux/memcontrol.h> extern struct inet_hashinfo tcp_hashinfo; @@ -229,7 +230,6 @@ extern int sysctl_tcp_fack; extern int sysctl_tcp_reordering; extern int sysctl_tcp_ecn; extern int sysctl_tcp_dsack; -extern long sysctl_tcp_mem[3]; extern int sysctl_tcp_wmem[3]; extern int sysctl_tcp_rmem[3]; extern int sysctl_tcp_app_win; @@ -285,7 +285,7 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift) } if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && - atomic_long_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]) + sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) return true; return false; } @@ -628,7 +628,7 @@ extern u32 __tcp_select_window(struct sock *sk); struct tcp_skb_cb { union { struct inet_skb_parm h4; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; /* For incoming frames */ @@ -773,12 +773,12 @@ static inline int tcp_is_reno(const struct tcp_sock *tp) static inline int tcp_is_fack(const struct tcp_sock *tp) { - return tp->rx_opt.sack_ok & 2; + return tp->rx_opt.sack_ok & TCP_FACK_ENABLED; } static inline void tcp_enable_fack(struct tcp_sock *tp) { - tp->rx_opt.sack_ok |= 2; + tp->rx_opt.sack_ok |= TCP_FACK_ENABLED; } static inline unsigned int tcp_left_out(const struct tcp_sock *tp) @@ -834,6 +834,14 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh); extern __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst); +/* The maximum number of MSS of available cwnd for which TSO defers + * sending if not using sysctl_tcp_tso_win_divisor. + */ +static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp) +{ + return 3; +} + /* Slow start with delack produces 3 packets of burst, so that * it is safe "de facto". This will be the default - same as * the default reordering threshold - but if reordering increases, @@ -1144,7 +1152,7 @@ struct tcp6_md5sig_key { /* - sock block */ struct tcp_md5sig_info { struct tcp4_md5sig_key *keys4; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct tcp6_md5sig_key *keys6; u32 entries6; u32 alloced6; @@ -1171,7 +1179,7 @@ struct tcp6_pseudohdr { union tcp_md5sum_block { struct tcp4_pseudohdr ip4; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct tcp6_pseudohdr ip6; #endif }; @@ -1430,7 +1438,8 @@ extern struct request_sock_ops tcp6_request_sock_ops; extern void tcp_v4_destroy_sock(struct sock *sk); extern int tcp_v4_gso_send_check(struct sk_buff *skb); -extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features); +extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, + netdev_features_t features); extern struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb); extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head, diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h new file mode 100644 index 000000000000..3512082fa909 --- /dev/null +++ b/include/net/tcp_memcontrol.h @@ -0,0 +1,19 @@ +#ifndef _TCP_MEMCG_H +#define _TCP_MEMCG_H + +struct tcp_memcontrol { + struct cg_proto cg_proto; + /* per-cgroup tcp memory pressure knobs */ + struct res_counter tcp_memory_allocated; + struct percpu_counter tcp_sockets_allocated; + /* those two are read-mostly, leave them at the end */ + long tcp_prot_mem[3]; + int tcp_memory_pressure; +}; + +struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg); +int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss); +void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss); +unsigned long long tcp_max_memory(const struct mem_cgroup *memcg); +void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx); +#endif /* _TCP_MEMCG_H */ diff --git a/include/net/udp.h b/include/net/udp.h index 3b285f402f48..e39592f682c3 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -41,7 +41,7 @@ struct udp_skb_cb { union { struct inet_skb_parm h4; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; @@ -194,9 +194,15 @@ extern int udp_lib_setsockopt(struct sock *sk, int level, int optname, extern struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); +extern struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, + __be32 daddr, __be16 dport, + int dif, struct udp_table *tbl); extern struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif); +extern struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, + int dif, struct udp_table *tbl); /* * SNMP statistics for UDP and UDP-Lite @@ -217,7 +223,7 @@ extern struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *sadd else SNMP_INC_STATS_USER((net)->mib.udp_stats_in6, field); \ } while(0) -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) #define UDPX_INC_STATS_BH(sk, field) \ do { \ if ((sk)->sk_family == AF_INET) \ @@ -258,5 +264,6 @@ extern void udp4_proc_exit(void); extern void udp_init(void); extern int udp4_ufo_send_check(struct sk_buff *skb); -extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features); +extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, + netdev_features_t features); #endif /* _UDP_H */ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b203e14d26b7..89174e29dca9 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -827,6 +827,14 @@ static inline bool addr_match(const void *token1, const void *token2, return true; } +static inline bool addr4_match(__be32 a1, __be32 a2, u8 prefixlen) +{ + /* C99 6.5.7 (3): u32 << 32 is undefined behaviour */ + if (prefixlen == 0) + return true; + return !((a1 ^ a2) & htonl(0xFFFFFFFFu << (32 - prefixlen))); +} + static __inline__ __be16 xfrm_flowi_sport(const struct flowi *fl, const union flowi_uli *uli) { @@ -1209,8 +1217,8 @@ void xfrm_flowi_addr_get(const struct flowi *fl, memcpy(&daddr->a4, &fl->u.ip4.daddr, sizeof(daddr->a4)); break; case AF_INET6: - ipv6_addr_copy((struct in6_addr *)&saddr->a6, &fl->u.ip6.saddr); - ipv6_addr_copy((struct in6_addr *)&daddr->a6, &fl->u.ip6.daddr); + *(struct in6_addr *)saddr->a6 = fl->u.ip6.saddr; + *(struct in6_addr *)daddr->a6 = fl->u.ip6.daddr; break; } } |