12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192 |
- /* Copyright (c) 2015 Samsung Electronics Co., Ltd. */
- /*
- * INET An implementation of the TCP/IP protocol suite for the LINUX
- * operating system. INET is implemented using the BSD Socket
- * interface as the means of communication with the user level.
- *
- * Definitions for the AF_INET socket handler.
- *
- * Version: @(#)sock.h 1.0.4 05/13/93
- *
- * Authors: Ross Biro
- * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
- * Corey Minyard <wf-rch!minyard@relay.EU.net>
- * Florian La Roche <flla@stud.uni-sb.de>
- *
- * Fixes:
- * Alan Cox : Volatiles in skbuff pointers. See
- * skbuff comments. May be overdone,
- * better to prove they can be removed
- * than the reverse.
- * Alan Cox : Added a zapped field for tcp to note
- * a socket is reset and must stay shut up
- * Alan Cox : New fields for options
- * Pauline Middelink : identd support
- * Alan Cox : Eliminate low level recv/recvfrom
- * David S. Miller : New socket lookup architecture.
- * Steve Whitehouse: Default routines for sock_ops
- * Arnaldo C. Melo : removed net_pinfo, tp_pinfo and made
- * protinfo be just a void pointer, as the
- * protocol specific parts were moved to
- * respective headers and ipv4/v6, etc now
- * use private slabcaches for its socks
- * Pedro Hortas : New flags field for socket options
- *
- *
- * 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.
- */
- /*
- * Changes:
- * KwnagHyun Kim <kh0304.kim@samsung.com> 2015/07/08
- * Baesung Park <baesung.park@samsung.com> 2015/07/08
- * Vignesh Saravanaperumal <vignesh1.s@samsung.com> 2015/07/08
- * Add codes to share UID/PID information
- *
- */
-
- #ifndef _SOCK_H
- #define _SOCK_H
- #include <linux/hardirq.h>
- #include <linux/kernel.h>
- #include <linux/list.h>
- #include <linux/list_nulls.h>
- #include <linux/timer.h>
- #include <linux/cache.h>
- #include <linux/lockdep.h>
- #include <linux/netdevice.h>
- #include <linux/skbuff.h> /* struct sk_buff */
- #include <linux/mm.h>
- #include <linux/security.h>
- #include <linux/slab.h>
- #include <linux/uaccess.h>
- #include <linux/memcontrol.h>
- #include <linux/res_counter.h>
- #include <linux/static_key.h>
- #include <linux/aio.h>
- #include <linux/sched.h>
- #include <linux/filter.h>
- #include <linux/rculist_nulls.h>
- #include <linux/poll.h>
- #include <linux/atomic.h>
- #include <net/dst.h>
- #include <net/checksum.h>
- #include <net/tcp_states.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);
- #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)
- {
- }
- #endif
- /*
- * This structure really needs to be cleaned up.
- * Most of it is for TCP, and not used by any of
- * the other protocols.
- */
- /* Define this to get the SOCK_DBG debugging facility. */
- #define SOCK_DEBUGGING
- #ifdef SOCK_DEBUGGING
- #define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \
- printk(KERN_DEBUG msg); } while (0)
- #else
- /* Validate arguments and do nothing */
- static inline __printf(2, 3)
- void SOCK_DEBUG(const struct sock *sk, const char *msg, ...)
- {
- }
- #endif
- /* This is the per-socket lock. The spinlock provides a synchronization
- * between user contexts and software interrupt processing, whereas the
- * mini-semaphore synchronizes multiple users amongst themselves.
- */
- typedef struct {
- spinlock_t slock;
- int owned;
- wait_queue_head_t wq;
- /*
- * We express the mutex-alike socket_lock semantics
- * to the lock validator by explicitly managing
- * the slock as a lock variant (in addition to
- * the slock itself):
- */
- #ifdef CONFIG_DEBUG_LOCK_ALLOC
- struct lockdep_map dep_map;
- #endif
- } socket_lock_t;
- struct sock;
- struct proto;
- struct net;
- /**
- * struct sock_common - minimal network layer representation of sockets
- * @skc_daddr: Foreign IPv4 addr
- * @skc_rcv_saddr: Bound local IPv4 addr
- * @skc_hash: hash value used with various protocol lookup tables
- * @skc_u16hashes: two u16 hash values used by UDP lookup tables
- * @skc_family: network address family
- * @skc_state: Connection state
- * @skc_reuse: %SO_REUSEADDR setting
- * @skc_bound_dev_if: bound device index if != 0
- * @skc_bind_node: bind hash linkage for various protocol lookup tables
- * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
- * @skc_prot: protocol handlers inside a network family
- * @skc_net: reference to the network namespace of this socket
- * @skc_node: main hash linkage for various protocol lookup tables
- * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
- * @skc_tx_queue_mapping: tx queue number for this connection
- * @skc_refcnt: reference count
- *
- * This is the minimal network layer representation of sockets, the header
- * for struct sock and struct inet_timewait_sock.
- */
- struct sock_common {
- /* skc_daddr and skc_rcv_saddr must be grouped :
- * cf INET_MATCH() and INET_TW_MATCH()
- */
- __be32 skc_daddr;
- __be32 skc_rcv_saddr;
- union {
- unsigned int skc_hash;
- __u16 skc_u16hashes[2];
- };
- unsigned short skc_family;
- volatile unsigned char skc_state;
- unsigned char skc_reuse;
- int skc_bound_dev_if;
- int padding[2];
- union {
- struct hlist_node skc_bind_node;
- struct hlist_nulls_node skc_portaddr_node;
- };
- struct proto *skc_prot;
- #ifdef CONFIG_NET_NS
- struct net *skc_net;
- #endif
- /*
- * fields between dontcopy_begin/dontcopy_end
- * are not copied in sock_copy()
- */
- /* private: */
- int skc_dontcopy_begin[0];
- /* public: */
- union {
- struct hlist_node skc_node;
- struct hlist_nulls_node skc_nulls_node;
- };
- int skc_tx_queue_mapping;
- atomic_t skc_refcnt;
- /* private: */
- int skc_dontcopy_end[0];
- /* public: */
- };
- struct cg_proto;
- /**
- * struct sock - network layer representation of sockets
- * @__sk_common: shared layout with inet_timewait_sock
- * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
- * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
- * @sk_lock: synchronizer
- * @sk_rcvbuf: size of receive buffer in bytes
- * @sk_wq: sock wait queue and async head
- * @sk_dst_cache: destination cache
- * @sk_dst_lock: destination cache lock
- * @sk_policy: flow policy
- * @sk_receive_queue: incoming packets
- * @sk_wmem_alloc: transmit queue bytes committed
- * @sk_write_queue: Packet sending queue
- * @sk_async_wait_queue: DMA copied packets
- * @sk_omem_alloc: "o" is "option" or "other"
- * @sk_wmem_queued: persistent queue size
- * @sk_forward_alloc: space allocated forward
- * @sk_allocation: allocation mode
- * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
- * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
- * @sk_sndbuf: size of send buffer in bytes
- * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
- * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
- * @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
- * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
- * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
- * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
- * @sk_gso_max_size: Maximum GSO segment size to build
- * @sk_gso_max_segs: Maximum number of GSO segments
- * @sk_lingertime: %SO_LINGER l_linger setting
- * @sk_backlog: always used with the per-socket spinlock held
- * @sk_callback_lock: used with the callbacks in the end of this struct
- * @sk_error_queue: rarely used
- * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
- * IPV6_ADDRFORM for instance)
- * @sk_err: last error
- * @sk_err_soft: errors that don't cause failure but are the cause of a
- * persistent failure not just 'timed out'
- * @sk_drops: raw/udp drops counter
- * @sk_ack_backlog: current listen backlog
- * @sk_max_ack_backlog: listen backlog set in listen()
- * @sk_priority: %SO_PRIORITY setting
- * @sk_cgrp_prioidx: socket group's priority map index
- * @sk_type: socket type (%SOCK_STREAM, etc)
- * @sk_protocol: which protocol this socket belongs in this network family
- * @sk_peer_pid: &struct pid for this socket's peer
- * @sk_peer_cred: %SO_PEERCRED setting
- * @sk_rcvlowat: %SO_RCVLOWAT setting
- * @sk_rcvtimeo: %SO_RCVTIMEO setting
- * @sk_sndtimeo: %SO_SNDTIMEO setting
- * @sk_rxhash: flow hash received from netif layer
- * @sk_filter: socket filtering instructions
- * @sk_protinfo: private area, net family specific, when not using slab
- * @sk_timer: sock cleanup timer
- * @sk_stamp: time stamp of last packet received
- * @sk_socket: Identd and reporting IO signals
- * @sk_user_data: RPC layer private data
- * @sk_sndmsg_page: cached page for sendmsg
- * @sk_sndmsg_off: cached offset for sendmsg
- * @sk_peek_off: current peek_offset value
- * @sk_send_head: front of stuff to transmit
- * @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
- * @sk_write_space: callback to indicate there is bf sending space available
- * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
- * @sk_backlog_rcv: callback to process the backlog
- * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
- */
- struct sock {
- /*
- * Now struct inet_timewait_sock also uses sock_common, so please just
- * don't add nothing before this first member (__sk_common) --acme
- */
- struct sock_common __sk_common;
- #define sk_node __sk_common.skc_node
- #define sk_nulls_node __sk_common.skc_nulls_node
- #define sk_refcnt __sk_common.skc_refcnt
- #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping
- #define sk_dontcopy_begin __sk_common.skc_dontcopy_begin
- #define sk_dontcopy_end __sk_common.skc_dontcopy_end
- #define sk_hash __sk_common.skc_hash
- #define sk_family __sk_common.skc_family
- #define sk_state __sk_common.skc_state
- #define sk_reuse __sk_common.skc_reuse
- #define sk_bound_dev_if __sk_common.skc_bound_dev_if
- #define sk_bind_node __sk_common.skc_bind_node
- #define sk_prot __sk_common.skc_prot
- #define sk_net __sk_common.skc_net
- socket_lock_t sk_lock;
- struct sk_buff_head sk_receive_queue;
- /*
- * The backlog queue is special, it is always used with
- * the per-socket spinlock held and requires low latency
- * access. Therefore we special case it's implementation.
- * Note : rmem_alloc is in this structure to fill a hole
- * on 64bit arches, not because its logically part of
- * backlog.
- */
- struct {
- atomic_t rmem_alloc;
- int len;
- struct sk_buff *head;
- struct sk_buff *tail;
- } sk_backlog;
- #define sk_rmem_alloc sk_backlog.rmem_alloc
- int sk_forward_alloc;
- #ifdef CONFIG_RPS
- __u32 sk_rxhash;
- #endif
- atomic_t sk_drops;
- int sk_rcvbuf;
- struct sk_filter __rcu *sk_filter;
- struct socket_wq __rcu *sk_wq;
- #ifdef CONFIG_NET_DMA
- struct sk_buff_head sk_async_wait_queue;
- #endif
- #ifdef CONFIG_XFRM
- struct xfrm_policy *sk_policy[2];
- #endif
- unsigned long sk_flags;
- struct dst_entry *sk_dst_cache;
- spinlock_t sk_dst_lock;
- atomic_t sk_wmem_alloc;
- atomic_t sk_omem_alloc;
- int sk_sndbuf;
- struct sk_buff_head sk_write_queue;
- kmemcheck_bitfield_begin(flags);
- unsigned int sk_shutdown : 2,
- sk_no_check : 2,
- sk_userlocks : 4,
- sk_protocol : 8,
- sk_type : 16;
- #define SK_PROTOCOL_MAX ((u8)~0U)
- kmemcheck_bitfield_end(flags);
- int sk_wmem_queued;
- gfp_t sk_allocation;
- u32 sk_pacing_rate; /* bytes per second */
- u32 sk_max_pacing_rate;
- netdev_features_t sk_route_caps;
- netdev_features_t sk_route_nocaps;
- int sk_gso_type;
- unsigned int sk_gso_max_size;
- u16 sk_gso_max_segs;
- int sk_rcvlowat;
- unsigned long sk_lingertime;
- struct sk_buff_head sk_error_queue;
- struct proto *sk_prot_creator;
- rwlock_t sk_callback_lock;
- int sk_err,
- sk_err_soft;
- 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;
- long sk_sndtimeo;
- void *sk_protinfo;
- struct timer_list sk_timer;
- ktime_t sk_stamp;
- struct socket *sk_socket;
- void *sk_user_data;
- struct page *sk_sndmsg_page;
- struct sk_buff *sk_send_head;
- __u32 sk_sndmsg_off;
- __s32 sk_peek_off;
- int sk_write_pending;
- #ifdef CONFIG_SECURITY
- void *sk_security;
- #endif
- __u32 sk_mark;
- kuid_t sk_uid;
- 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);
- void (*sk_error_report)(struct sock *sk);
- int (*sk_backlog_rcv)(struct sock *sk,
- struct sk_buff *skb);
- void (*sk_destruct)(struct sock *sk);
- };
- static inline int sk_peek_offset(struct sock *sk, int flags)
- {
- if ((flags & MSG_PEEK) && (sk->sk_peek_off >= 0))
- return sk->sk_peek_off;
- else
- return 0;
- }
- static inline void sk_peek_offset_bwd(struct sock *sk, int val)
- {
- if (sk->sk_peek_off >= 0) {
- if (sk->sk_peek_off >= val)
- sk->sk_peek_off -= val;
- else
- sk->sk_peek_off = 0;
- }
- }
- static inline void sk_peek_offset_fwd(struct sock *sk, int val)
- {
- if (sk->sk_peek_off >= 0)
- sk->sk_peek_off += val;
- }
- /*
- * Hashed lists helper routines
- */
- static inline struct sock *sk_entry(const struct hlist_node *node)
- {
- return hlist_entry(node, struct sock, sk_node);
- }
- static inline struct sock *__sk_head(const struct hlist_head *head)
- {
- return hlist_entry(head->first, struct sock, sk_node);
- }
- static inline struct sock *sk_head(const struct hlist_head *head)
- {
- return hlist_empty(head) ? NULL : __sk_head(head);
- }
- static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head)
- {
- return hlist_nulls_entry(head->first, struct sock, sk_nulls_node);
- }
- static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head)
- {
- return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head);
- }
- static inline struct sock *sk_next(const struct sock *sk)
- {
- return sk->sk_node.next ?
- hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
- }
- static inline struct sock *sk_nulls_next(const struct sock *sk)
- {
- return (!is_a_nulls(sk->sk_nulls_node.next)) ?
- hlist_nulls_entry(sk->sk_nulls_node.next,
- struct sock, sk_nulls_node) :
- NULL;
- }
- static inline bool sk_unhashed(const struct sock *sk)
- {
- return hlist_unhashed(&sk->sk_node);
- }
- static inline bool sk_hashed(const struct sock *sk)
- {
- return !sk_unhashed(sk);
- }
- static inline void sk_node_init(struct hlist_node *node)
- {
- node->pprev = NULL;
- }
- static inline void sk_nulls_node_init(struct hlist_nulls_node *node)
- {
- node->pprev = NULL;
- }
- static inline void __sk_del_node(struct sock *sk)
- {
- __hlist_del(&sk->sk_node);
- }
- /* NB: equivalent to hlist_del_init_rcu */
- static inline bool __sk_del_node_init(struct sock *sk)
- {
- if (sk_hashed(sk)) {
- __sk_del_node(sk);
- sk_node_init(&sk->sk_node);
- return true;
- }
- return false;
- }
- /* Grab socket reference count. This operation is valid only
- when sk is ALREADY grabbed f.e. it is found in hash table
- or a list and the lookup is made under lock preventing hash table
- modifications.
- */
- static inline void sock_hold(struct sock *sk)
- {
- atomic_inc(&sk->sk_refcnt);
- }
- /* Ungrab socket in the context, which assumes that socket refcnt
- cannot hit zero, f.e. it is true in context of any socketcall.
- */
- static inline void __sock_put(struct sock *sk)
- {
- atomic_dec(&sk->sk_refcnt);
- }
- static inline bool sk_del_node_init(struct sock *sk)
- {
- bool rc = __sk_del_node_init(sk);
- if (rc) {
- /* paranoid for a while -acme */
- WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
- __sock_put(sk);
- }
- return rc;
- }
- #define sk_del_node_init_rcu(sk) sk_del_node_init(sk)
- static inline bool __sk_nulls_del_node_init_rcu(struct sock *sk)
- {
- if (sk_hashed(sk)) {
- hlist_nulls_del_init_rcu(&sk->sk_nulls_node);
- return true;
- }
- return false;
- }
- static inline bool sk_nulls_del_node_init_rcu(struct sock *sk)
- {
- bool rc = __sk_nulls_del_node_init_rcu(sk);
- if (rc) {
- /* paranoid for a while -acme */
- WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
- __sock_put(sk);
- }
- return rc;
- }
- static inline void __sk_add_node(struct sock *sk, struct hlist_head *list)
- {
- hlist_add_head(&sk->sk_node, list);
- }
- static inline void sk_add_node(struct sock *sk, struct hlist_head *list)
- {
- sock_hold(sk);
- __sk_add_node(sk, list);
- }
- static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
- {
- sock_hold(sk);
- hlist_add_head_rcu(&sk->sk_node, list);
- }
- static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
- {
- hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
- }
- static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
- {
- sock_hold(sk);
- __sk_nulls_add_node_rcu(sk, list);
- }
- static inline void __sk_del_bind_node(struct sock *sk)
- {
- __hlist_del(&sk->sk_bind_node);
- }
- static inline void sk_add_bind_node(struct sock *sk,
- struct hlist_head *list)
- {
- hlist_add_head(&sk->sk_bind_node, list);
- }
- #define sk_for_each(__sk, node, list) \
- hlist_for_each_entry(__sk, node, list, sk_node)
- #define sk_for_each_rcu(__sk, node, list) \
- hlist_for_each_entry_rcu(__sk, node, list, sk_node)
- #define sk_nulls_for_each(__sk, node, list) \
- hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
- #define sk_nulls_for_each_rcu(__sk, node, list) \
- hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
- #define sk_for_each_from(__sk, node) \
- if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
- hlist_for_each_entry_from(__sk, node, sk_node)
- #define sk_nulls_for_each_from(__sk, node) \
- if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \
- hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node)
- #define sk_for_each_safe(__sk, node, tmp, list) \
- hlist_for_each_entry_safe(__sk, node, tmp, list, sk_node)
- #define sk_for_each_bound(__sk, node, list) \
- hlist_for_each_entry(__sk, node, list, sk_bind_node)
- /* Sock flags */
- enum sock_flags {
- SOCK_DEAD,
- SOCK_DONE,
- SOCK_URGINLINE,
- SOCK_KEEPOPEN,
- SOCK_LINGER,
- SOCK_DESTROY,
- SOCK_BROADCAST,
- SOCK_TIMESTAMP,
- SOCK_ZAPPED,
- SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */
- SOCK_DBG, /* %SO_DEBUG setting */
- SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
- SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
- SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
- SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
- SOCK_TIMESTAMPING_TX_HARDWARE, /* %SOF_TIMESTAMPING_TX_HARDWARE */
- SOCK_TIMESTAMPING_TX_SOFTWARE, /* %SOF_TIMESTAMPING_TX_SOFTWARE */
- SOCK_TIMESTAMPING_RX_HARDWARE, /* %SOF_TIMESTAMPING_RX_HARDWARE */
- SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */
- SOCK_TIMESTAMPING_SOFTWARE, /* %SOF_TIMESTAMPING_SOFTWARE */
- SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SOF_TIMESTAMPING_RAW_HARDWARE */
- SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */
- SOCK_FASYNC, /* fasync() active */
- SOCK_RXQ_OVFL,
- SOCK_ZEROCOPY, /* buffers from userspace */
- SOCK_WIFI_STATUS, /* push wifi status to userspace */
- SOCK_NOFCS, /* Tell NIC not to do the Ethernet FCS.
- * Will use last 4 bytes of packet sent from
- * user-space instead.
- */
- };
- static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
- {
- nsk->sk_flags = osk->sk_flags;
- }
- static inline void sock_set_flag(struct sock *sk, enum sock_flags flag)
- {
- __set_bit(flag, &sk->sk_flags);
- }
- static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag)
- {
- __clear_bit(flag, &sk->sk_flags);
- }
- static inline int sock_flag(struct sock *sk, enum sock_flags flag)
- {
- return test_bit(flag, &sk->sk_flags);
- }
- static inline void sk_acceptq_removed(struct sock *sk)
- {
- sk->sk_ack_backlog--;
- }
- static inline void sk_acceptq_added(struct sock *sk)
- {
- sk->sk_ack_backlog++;
- }
- static inline bool sk_acceptq_is_full(const struct sock *sk)
- {
- return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
- }
- /*
- * Compute minimal free write space needed to queue new packets.
- */
- static inline int sk_stream_min_wspace(const struct sock *sk)
- {
- return sk->sk_wmem_queued >> 1;
- }
- static inline int sk_stream_wspace(const struct sock *sk)
- {
- return sk->sk_sndbuf - sk->sk_wmem_queued;
- }
- void sk_stream_write_space(struct sock *sk);
- static inline bool sk_stream_memory_free(const struct sock *sk)
- {
- return sk->sk_wmem_queued < sk->sk_sndbuf;
- }
- /* OOB backlog add */
- static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
- {
- /* dont let skb dst not refcounted, we are going to leave rcu lock */
- skb_dst_force(skb);
- if (!sk->sk_backlog.tail)
- sk->sk_backlog.head = skb;
- else
- sk->sk_backlog.tail->next = skb;
- sk->sk_backlog.tail = skb;
- skb->next = NULL;
- }
- /*
- * 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 > sk->sk_rcvbuf;
- }
- /* The per-socket spinlock must be held here. */
- static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb)
- {
- if (sk_rcvqueues_full(sk, skb))
- return -ENOBUFS;
- __sk_add_backlog(sk, skb);
- sk->sk_backlog.len += skb->truesize;
- return 0;
- }
- static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
- {
- return sk->sk_backlog_rcv(sk, skb);
- }
- static inline void sock_rps_record_flow(const struct sock *sk)
- {
- #ifdef CONFIG_RPS
- struct rps_sock_flow_table *sock_flow_table;
- rcu_read_lock();
- sock_flow_table = rcu_dereference(rps_sock_flow_table);
- rps_record_sock_flow(sock_flow_table, sk->sk_rxhash);
- rcu_read_unlock();
- #endif
- }
- static inline void sock_rps_reset_flow(const struct sock *sk)
- {
- #ifdef CONFIG_RPS
- struct rps_sock_flow_table *sock_flow_table;
- rcu_read_lock();
- sock_flow_table = rcu_dereference(rps_sock_flow_table);
- rps_reset_sock_flow(sock_flow_table, sk->sk_rxhash);
- rcu_read_unlock();
- #endif
- }
- static inline void sock_rps_save_rxhash(struct sock *sk,
- const struct sk_buff *skb)
- {
- #ifdef CONFIG_RPS
- if (unlikely(sk->sk_rxhash != skb->rxhash)) {
- sock_rps_reset_flow(sk);
- sk->sk_rxhash = skb->rxhash;
- }
- #endif
- }
- static inline void sock_rps_reset_rxhash(struct sock *sk)
- {
- #ifdef CONFIG_RPS
- sock_rps_reset_flow(sk);
- sk->sk_rxhash = 0;
- #endif
- }
- #define sk_wait_event(__sk, __timeo, __condition) \
- ({ int __rc; \
- release_sock(__sk); \
- __rc = __condition; \
- if (!__rc) { \
- *(__timeo) = schedule_timeout(*(__timeo)); \
- } \
- lock_sock(__sk); \
- __rc = __condition; \
- __rc; \
- })
- int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
- int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
- void sk_stream_wait_close(struct sock *sk, long timeo_p);
- int sk_stream_error(struct sock *sk, int flags, int err);
- void sk_stream_kill_queues(struct sock *sk);
- int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb);
- struct request_sock_ops;
- struct timewait_sock_ops;
- struct inet_hashinfo;
- struct raw_hashinfo;
- struct module;
- /*
- * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes
- * un-modified. Special care is taken when initializing object to zero.
- */
- static inline void sk_prot_clear_nulls(struct sock *sk, int size)
- {
- if (offsetof(struct sock, sk_node.next) != 0)
- memset(sk, 0, offsetof(struct sock, sk_node.next));
- memset(&sk->sk_node.pprev, 0,
- size - offsetof(struct sock, sk_node.pprev));
- }
- /* Networking protocol blocks we attach to sockets.
- * socket layer -> transport layer interface
- * transport -> network interface is defined by struct inet_proto
- */
- struct proto {
- void (*close)(struct sock *sk,
- long timeout);
- int (*connect)(struct sock *sk,
- struct sockaddr *uaddr,
- int addr_len);
- int (*disconnect)(struct sock *sk, int flags);
- struct sock * (*accept)(struct sock *sk, int flags, int *err);
- int (*ioctl)(struct sock *sk, int cmd,
- unsigned long arg);
- int (*init)(struct sock *sk);
- void (*destroy)(struct sock *sk);
- void (*shutdown)(struct sock *sk, int how);
- int (*setsockopt)(struct sock *sk, int level,
- int optname, char __user *optval,
- unsigned int optlen);
- int (*getsockopt)(struct sock *sk, int level,
- int optname, char __user *optval,
- int __user *option);
- #ifdef CONFIG_COMPAT
- int (*compat_setsockopt)(struct sock *sk,
- int level,
- int optname, char __user *optval,
- unsigned int optlen);
- int (*compat_getsockopt)(struct sock *sk,
- int level,
- int optname, char __user *optval,
- int __user *option);
- int (*compat_ioctl)(struct sock *sk,
- unsigned int cmd, unsigned long arg);
- #endif
- int (*sendmsg)(struct kiocb *iocb, struct sock *sk,
- struct msghdr *msg, size_t len);
- int (*recvmsg)(struct kiocb *iocb, struct sock *sk,
- struct msghdr *msg,
- size_t len, int noblock, int flags,
- int *addr_len);
- int (*sendpage)(struct sock *sk, struct page *page,
- int offset, size_t size, int flags);
- int (*bind)(struct sock *sk,
- struct sockaddr *uaddr, int addr_len);
- int (*backlog_rcv) (struct sock *sk,
- struct sk_buff *skb);
- void (*release_cb)(struct sock *sk);
- /* Keeping track of sk's, looking them up, and port selection methods. */
- void (*hash)(struct sock *sk);
- void (*unhash)(struct sock *sk);
- void (*rehash)(struct sock *sk);
- int (*get_port)(struct sock *sk, unsigned short snum);
- void (*clear_sk)(struct sock *sk, int size);
- /* Keeping track of sockets in use */
- #ifdef CONFIG_PROC_FS
- unsigned int inuse_idx;
- #endif
- /* Memory pressure */
- void (*enter_memory_pressure)(struct sock *sk);
- atomic_long_t *memory_allocated; /* Current allocated memory. */
- struct percpu_counter *sockets_allocated; /* Current number of sockets. */
- /*
- * Pressure flag: try to collapse.
- * Technical note: it is used by multiple contexts non atomically.
- * All the __sk_mem_schedule() is of this nature: accounting
- * is strict, actions are advisory and have some latency.
- */
- int *memory_pressure;
- long *sysctl_mem;
- int *sysctl_wmem;
- int *sysctl_rmem;
- int max_header;
- bool no_autobind;
- struct kmem_cache *slab;
- unsigned int obj_size;
- int slab_flags;
- struct percpu_counter *orphan_count;
- struct request_sock_ops *rsk_prot;
- struct timewait_sock_ops *twsk_prot;
- union {
- struct inet_hashinfo *hashinfo;
- struct udp_table *udp_table;
- struct raw_hashinfo *raw_hash;
- } h;
- struct module *owner;
- char name[32];
- struct list_head node;
- #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 cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg);
- #endif
- int (*diag_destroy)(struct sock *sk, int err);
- };
- 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;
- };
- int proto_register(struct proto *prot, int alloc_slab);
- void proto_unregister(struct proto *prot);
- #ifdef SOCK_REFCNT_DEBUG
- static inline void sk_refcnt_debug_inc(struct sock *sk)
- {
- atomic_inc(&sk->sk_prot->socks);
- }
- static inline void sk_refcnt_debug_dec(struct sock *sk)
- {
- atomic_dec(&sk->sk_prot->socks);
- printk(KERN_DEBUG "%s socket %p released, %d are still alive\n",
- sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
- }
- static 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",
- sk->sk_prot->name, sk, atomic_read(&sk->sk_refcnt));
- }
- #else /* SOCK_REFCNT_DEBUG */
- #define sk_refcnt_debug_inc(sk) do { } while (0)
- #define sk_refcnt_debug_dec(sk) do { } while (0)
- #define sk_refcnt_debug_release(sk) do { } while (0)
- #endif /* SOCK_REFCNT_DEBUG */
- #if defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) && defined(CONFIG_NET)
- extern struct static_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_key_false(&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_nofail(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)
- {
- struct proto *prot = sk->sk_prot;
- if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
- 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_read_positive(sk->sk_cgrp->sockets_allocated);
- return percpu_counter_read_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 */
- void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
- int sock_prot_inuse_get(struct net *net, struct proto *proto);
- #else
- static inline void sock_prot_inuse_add(struct net *net, struct proto *prot,
- int inc)
- {
- }
- #endif
- /* With per-bucket locks this operation is not-atomic, so that
- * this version is not worse.
- */
- static inline void __sk_prot_rehash(struct sock *sk)
- {
- sk->sk_prot->unhash(sk);
- sk->sk_prot->hash(sk);
- }
- void sk_prot_clear_portaddr_nulls(struct sock *sk, int size);
- /* About 10 seconds */
- #define SOCK_DESTROY_TIME (10*HZ)
- /* Sockets 0-1023 can't be bound to unless you are superuser */
- #define PROT_SOCK 1024
- #define SHUTDOWN_MASK 3
- #define RCV_SHUTDOWN 1
- #define SEND_SHUTDOWN 2
- #define SOCK_SNDBUF_LOCK 1
- #define SOCK_RCVBUF_LOCK 2
- #define SOCK_BINDADDR_LOCK 4
- #define SOCK_BINDPORT_LOCK 8
- /* sock_iocb: used to kick off async processing of socket ios */
- struct sock_iocb {
- struct list_head list;
- int flags;
- int size;
- struct socket *sock;
- struct sock *sk;
- struct scm_cookie *scm;
- struct msghdr *msg, async_msg;
- struct kiocb *kiocb;
- };
- static inline struct sock_iocb *kiocb_to_siocb(struct kiocb *iocb)
- {
- return (struct sock_iocb *)iocb->private;
- }
- static inline struct kiocb *siocb_to_kiocb(struct sock_iocb *si)
- {
- return si->kiocb;
- }
- struct socket_alloc {
- struct socket socket;
- struct inode vfs_inode;
- };
- static inline struct socket *SOCKET_I(struct inode *inode)
- {
- return &container_of(inode, struct socket_alloc, vfs_inode)->socket;
- }
- static inline struct inode *SOCK_INODE(struct socket *socket)
- {
- return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
- }
- /*
- * Functions for memory accounting
- */
- int __sk_mem_schedule(struct sock *sk, int size, int kind);
- void __sk_mem_reclaim(struct sock *sk);
- #define SK_MEM_QUANTUM ((int)PAGE_SIZE)
- #define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
- #define SK_MEM_SEND 0
- #define SK_MEM_RECV 1
- static inline int sk_mem_pages(int amt)
- {
- return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT;
- }
- static inline bool sk_has_account(struct sock *sk)
- {
- /* return true if protocol supports memory accounting */
- return !!sk->sk_prot->memory_allocated;
- }
- static inline bool sk_wmem_schedule(struct sock *sk, int size)
- {
- if (!sk_has_account(sk))
- return true;
- return size <= sk->sk_forward_alloc ||
- __sk_mem_schedule(sk, size, SK_MEM_SEND);
- }
- static inline bool sk_rmem_schedule(struct sock *sk, int size)
- {
- if (!sk_has_account(sk))
- return true;
- return size <= sk->sk_forward_alloc ||
- __sk_mem_schedule(sk, size, SK_MEM_RECV);
- }
- static inline void sk_mem_reclaim(struct sock *sk)
- {
- if (!sk_has_account(sk))
- return;
- if (sk->sk_forward_alloc >= SK_MEM_QUANTUM)
- __sk_mem_reclaim(sk);
- }
- static inline void sk_mem_reclaim_partial(struct sock *sk)
- {
- if (!sk_has_account(sk))
- return;
- if (sk->sk_forward_alloc > SK_MEM_QUANTUM)
- __sk_mem_reclaim(sk);
- }
- static inline void sk_mem_charge(struct sock *sk, int size)
- {
- if (!sk_has_account(sk))
- return;
- sk->sk_forward_alloc -= size;
- }
- static inline void sk_mem_uncharge(struct sock *sk, int size)
- {
- if (!sk_has_account(sk))
- return;
- sk->sk_forward_alloc += size;
- }
- static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
- {
- sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
- sk->sk_wmem_queued -= skb->truesize;
- sk_mem_uncharge(sk, skb->truesize);
- __kfree_skb(skb);
- }
- /* Used by processes to "lock" a socket state, so that
- * interrupts and bottom half handlers won't change it
- * from under us. It essentially blocks any incoming
- * packets, so that we won't get any new data or any
- * packets that change the state of the socket.
- *
- * While locked, BH processing will add new packets to
- * the backlog queue. This queue is processed by the
- * owner of the socket lock right before it is released.
- *
- * Since ~2.3.5 it is also exclusive sleep lock serializing
- * accesses from user process context.
- */
- #define sock_owned_by_user(sk) ((sk)->sk_lock.owned)
- /*
- * Macro so as to not evaluate some arguments when
- * lockdep is not enabled.
- *
- * Mark both the sk_lock and the sk_lock.slock as a
- * per-address-family lock class.
- */
- #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \
- do { \
- sk->sk_lock.owned = 0; \
- init_waitqueue_head(&sk->sk_lock.wq); \
- spin_lock_init(&(sk)->sk_lock.slock); \
- debug_check_no_locks_freed((void *)&(sk)->sk_lock, \
- sizeof((sk)->sk_lock)); \
- lockdep_set_class_and_name(&(sk)->sk_lock.slock, \
- (skey), (sname)); \
- lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \
- } while (0)
- void lock_sock_nested(struct sock *sk, int subclass);
- static inline void lock_sock(struct sock *sk)
- {
- lock_sock_nested(sk, 0);
- }
- void release_sock(struct sock *sk);
- /* BH context may only use the following locking interface. */
- #define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock))
- #define bh_lock_sock_nested(__sk) \
- spin_lock_nested(&((__sk)->sk_lock.slock), \
- SINGLE_DEPTH_NESTING)
- #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock))
- bool lock_sock_fast(struct sock *sk);
- /**
- * unlock_sock_fast - complement of lock_sock_fast
- * @sk: socket
- * @slow: slow mode
- *
- * fast unlock socket for user context.
- * If slow mode is on, we call regular release_sock()
- */
- static inline void unlock_sock_fast(struct sock *sk, bool slow)
- {
- if (slow)
- release_sock(sk);
- else
- spin_unlock_bh(&sk->sk_lock.slock);
- }
- struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
- struct proto *prot);
- void sk_free(struct sock *sk);
- void sk_release_kernel(struct sock *sk);
- struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
- struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
- gfp_t priority);
- struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
- gfp_t priority);
- void sock_wfree(struct sk_buff *skb);
- void sock_rfree(struct sk_buff *skb);
- int sock_setsockopt(struct socket *sock, int level, int op,
- char __user *optval, unsigned int optlen);
- int sock_getsockopt(struct socket *sock, int level, int op,
- char __user *optval, int __user *optlen);
- struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
- int noblock, int *errcode);
- struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
- unsigned long data_len, int noblock,
- int *errcode);
- void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
- void sock_kfree_s(struct sock *sk, void *mem, int size);
- void sk_send_sigurg(struct sock *sk);
- #ifdef CONFIG_CGROUPS
- void sock_update_classid(struct sock *sk);
- #else
- static inline void sock_update_classid(struct sock *sk)
- {
- }
- #endif
- /*
- * Functions to fill in entries in struct proto_ops when a protocol
- * does not implement a particular function.
- */
- int sock_no_bind(struct socket *, struct sockaddr *, int);
- int sock_no_connect(struct socket *, struct sockaddr *, int, int);
- int sock_no_socketpair(struct socket *, struct socket *);
- int sock_no_accept(struct socket *, struct socket *, int);
- int sock_no_getname(struct socket *, struct sockaddr *, int *, int);
- unsigned int sock_no_poll(struct file *, struct socket *,
- struct poll_table_struct *);
- int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
- int sock_no_listen(struct socket *, int);
- int sock_no_shutdown(struct socket *, int);
- int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *);
- int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int);
- int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t);
- int sock_no_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t,
- int);
- int sock_no_mmap(struct file *file, struct socket *sock,
- struct vm_area_struct *vma);
- ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset,
- size_t size, int flags);
- /*
- * Functions to fill in entries in struct proto_ops when a protocol
- * uses the inet style.
- */
- int sock_common_getsockopt(struct socket *sock, int level, int optname,
- char __user *optval, int __user *optlen);
- int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
- struct msghdr *msg, size_t size, int flags);
- int sock_common_setsockopt(struct socket *sock, int level, int optname,
- char __user *optval, unsigned int optlen);
- int compat_sock_common_getsockopt(struct socket *sock, int level,
- int optname, char __user *optval, int __user *optlen);
- int compat_sock_common_setsockopt(struct socket *sock, int level,
- int optname, char __user *optval, unsigned int optlen);
- void sk_common_release(struct sock *sk);
- /*
- * Default socket callbacks and setup code
- */
- /* Initialise core socket variables */
- void sock_init_data(struct socket *sock, struct sock *sk);
- void sk_filter_release_rcu(struct rcu_head *rcu);
- /**
- * sk_filter_release - release a socket filter
- * @fp: filter to remove
- *
- * Remove a filter from a socket and release its resources.
- */
- static inline void sk_filter_release(struct sk_filter *fp)
- {
- if (atomic_dec_and_test(&fp->refcnt))
- call_rcu(&fp->rcu, sk_filter_release_rcu);
- }
- static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
- {
- unsigned int size = sk_filter_len(fp);
- atomic_sub(size, &sk->sk_omem_alloc);
- sk_filter_release(fp);
- }
- static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
- {
- atomic_inc(&fp->refcnt);
- atomic_add(sk_filter_len(fp), &sk->sk_omem_alloc);
- }
- /*
- * Socket reference counting postulates.
- *
- * * Each user of socket SHOULD hold a reference count.
- * * Each access point to socket (an hash table bucket, reference from a list,
- * running timer, skb in flight MUST hold a reference count.
- * * When reference count hits 0, it means it will never increase back.
- * * When reference count hits 0, it means that no references from
- * outside exist to this socket and current process on current CPU
- * is last user and may/should destroy this socket.
- * * sk_free is called from any context: process, BH, IRQ. When
- * it is called, socket has no references from outside -> sk_free
- * may release descendant resources allocated by the socket, but
- * to the time when it is called, socket is NOT referenced by any
- * hash tables, lists etc.
- * * Packets, delivered from outside (from network or from another process)
- * and enqueued on receive/error queues SHOULD NOT grab reference count,
- * when they sit in queue. Otherwise, packets will leak to hole, when
- * socket is looked up by one cpu and unhasing is made by another CPU.
- * It is true for udp/raw, netlink (leak to receive and error queues), tcp
- * (leak to backlog). Packet socket does all the processing inside
- * BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets
- * use separate SMP lock, so that they are prone too.
- */
- /* Ungrab socket and destroy it, if it was the last reference. */
- static inline void sock_put(struct sock *sk)
- {
- if (atomic_dec_and_test(&sk->sk_refcnt))
- sk_free(sk);
- }
- int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested);
- static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
- {
- sk->sk_tx_queue_mapping = tx_queue;
- }
- static inline void sk_tx_queue_clear(struct sock *sk)
- {
- sk->sk_tx_queue_mapping = -1;
- }
- static inline int sk_tx_queue_get(const struct sock *sk)
- {
- return sk ? sk->sk_tx_queue_mapping : -1;
- }
- static inline void sk_set_socket(struct sock *sk, struct socket *sock)
- {
- sk_tx_queue_clear(sk);
- sk->sk_socket = sock;
- }
- static inline wait_queue_head_t *sk_sleep(struct sock *sk)
- {
- BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0);
- return &rcu_dereference_raw(sk->sk_wq)->wait;
- }
- /* Detach socket from process context.
- * Announce socket dead, detach it from wait queue and inode.
- * Note that parent inode held reference count on this struct sock,
- * we do not release it in this function, because protocol
- * probably wants some additional cleanups or even continuing
- * to work with this socket (TCP).
- */
- static inline void sock_orphan(struct sock *sk)
- {
- write_lock_bh(&sk->sk_callback_lock);
- sock_set_flag(sk, SOCK_DEAD);
- sk_set_socket(sk, NULL);
- sk->sk_wq = NULL;
- write_unlock_bh(&sk->sk_callback_lock);
- }
- static inline void sock_graft(struct sock *sk, struct socket *parent)
- {
- write_lock_bh(&sk->sk_callback_lock);
- sk->sk_wq = parent->wq;
- parent->sk = sk;
- sk_set_socket(sk, parent);
- sk->sk_uid = SOCK_INODE(parent)->i_uid;
- security_sock_graft(sk, parent);
- write_unlock_bh(&sk->sk_callback_lock);
- }
- int sock_i_uid(struct sock *sk);
- unsigned long sock_i_ino(struct sock *sk);
- static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
- {
- return sk ? sk->sk_uid : make_kuid(net->user_ns, 0);
- }
- static inline struct dst_entry *
- __sk_dst_get(struct sock *sk)
- {
- return rcu_dereference_check(sk->sk_dst_cache, sock_owned_by_user(sk) ||
- lockdep_is_held(&sk->sk_lock.slock));
- }
- static inline struct dst_entry *
- sk_dst_get(struct sock *sk)
- {
- struct dst_entry *dst;
- rcu_read_lock();
- dst = rcu_dereference(sk->sk_dst_cache);
- if (dst)
- dst_hold(dst);
- rcu_read_unlock();
- return dst;
- }
- void sk_reset_txq(struct sock *sk);
- static inline void dst_negative_advice(struct sock *sk)
- {
- struct dst_entry *ndst, *dst = __sk_dst_get(sk);
- if (dst && dst->ops->negative_advice) {
- ndst = dst->ops->negative_advice(dst);
- if (ndst != dst) {
- rcu_assign_pointer(sk->sk_dst_cache, ndst);
- sk_reset_txq(sk);
- }
- }
- }
- static inline void
- __sk_dst_set(struct sock *sk, struct dst_entry *dst)
- {
- struct dst_entry *old_dst;
- sk_tx_queue_clear(sk);
- /*
- * This can be called while sk is owned by the caller only,
- * with no state that can be checked in a rcu_dereference_check() cond
- */
- old_dst = rcu_dereference_raw(sk->sk_dst_cache);
- rcu_assign_pointer(sk->sk_dst_cache, dst);
- dst_release(old_dst);
- }
- static inline void
- sk_dst_set(struct sock *sk, struct dst_entry *dst)
- {
- spin_lock(&sk->sk_dst_lock);
- __sk_dst_set(sk, dst);
- spin_unlock(&sk->sk_dst_lock);
- }
- static inline void
- __sk_dst_reset(struct sock *sk)
- {
- __sk_dst_set(sk, NULL);
- }
- static inline void
- sk_dst_reset(struct sock *sk)
- {
- spin_lock(&sk->sk_dst_lock);
- __sk_dst_reset(sk);
- spin_unlock(&sk->sk_dst_lock);
- }
- struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
- struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
- static inline bool sk_can_gso(const struct sock *sk)
- {
- return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
- }
- void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
- static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
- {
- sk->sk_route_nocaps |= flags;
- sk->sk_route_caps &= ~flags;
- }
- static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
- char __user *from, char *to,
- int copy, int offset)
- {
- if (skb->ip_summed == CHECKSUM_NONE) {
- int err = 0;
- __wsum csum = csum_and_copy_from_user(from, to, copy, 0, &err);
- if (err)
- return err;
- skb->csum = csum_block_add(skb->csum, csum, offset);
- } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
- if (!access_ok(VERIFY_READ, from, copy) ||
- __copy_from_user_nocache(to, from, copy))
- return -EFAULT;
- } else if (copy_from_user(to, from, copy))
- return -EFAULT;
- return 0;
- }
- static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
- char __user *from, int copy)
- {
- int err, offset = skb->len;
- err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy),
- copy, offset);
- if (err)
- __skb_trim(skb, offset);
- return err;
- }
- static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from,
- struct sk_buff *skb,
- struct page *page,
- int off, int copy)
- {
- int err;
- err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off,
- copy, skb->len);
- if (err)
- return err;
- skb->len += copy;
- skb->data_len += copy;
- skb->truesize += copy;
- sk->sk_wmem_queued += copy;
- sk_mem_charge(sk, copy);
- return 0;
- }
- static inline int skb_copy_to_page(struct sock *sk, char __user *from,
- struct sk_buff *skb, struct page *page,
- int off, int copy)
- {
- if (skb->ip_summed == CHECKSUM_NONE) {
- int err = 0;
- __wsum csum = csum_and_copy_from_user(from,
- page_address(page) + off,
- copy, 0, &err);
- if (err)
- return err;
- skb->csum = csum_block_add(skb->csum, csum, skb->len);
- } else if (copy_from_user(page_address(page) + off, from, copy))
- return -EFAULT;
- skb->len += copy;
- skb->data_len += copy;
- skb->truesize += copy;
- sk->sk_wmem_queued += copy;
- sk_mem_charge(sk, copy);
- return 0;
- }
- /**
- * sk_wmem_alloc_get - returns write allocations
- * @sk: socket
- *
- * Returns sk_wmem_alloc minus initial offset of one
- */
- static inline int sk_wmem_alloc_get(const struct sock *sk)
- {
- return atomic_read(&sk->sk_wmem_alloc) - 1;
- }
- /**
- * sk_rmem_alloc_get - returns read allocations
- * @sk: socket
- *
- * Returns sk_rmem_alloc
- */
- static inline int sk_rmem_alloc_get(const struct sock *sk)
- {
- return atomic_read(&sk->sk_rmem_alloc);
- }
- /**
- * sk_has_allocations - check if allocations are outstanding
- * @sk: socket
- *
- * Returns true if socket has write or read allocations
- */
- static inline bool sk_has_allocations(const struct sock *sk)
- {
- return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
- }
- /**
- * wq_has_sleeper - check if there are any waiting processes
- * @wq: struct socket_wq
- *
- * Returns true if socket_wq has waiting processes
- *
- * The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory
- * barrier call. They were added due to the race found within the tcp code.
- *
- * Consider following tcp code paths:
- *
- * CPU1 CPU2
- *
- * sys_select receive packet
- * ... ...
- * __add_wait_queue update tp->rcv_nxt
- * ... ...
- * tp->rcv_nxt check sock_def_readable
- * ... {
- * schedule rcu_read_lock();
- * wq = rcu_dereference(sk->sk_wq);
- * if (wq && waitqueue_active(&wq->wait))
- * wake_up_interruptible(&wq->wait)
- * ...
- * }
- *
- * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
- * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1
- * could then endup calling schedule and sleep forever if there are no more
- * data on the socket.
- *
- */
- static inline bool wq_has_sleeper(struct socket_wq *wq)
- {
- /* We need to be sure we are in sync with the
- * add_wait_queue modifications to the wait queue.
- *
- * This memory barrier is paired in the sock_poll_wait.
- */
- smp_mb();
- return wq && waitqueue_active(&wq->wait);
- }
- /**
- * sock_poll_wait - place memory barrier behind the poll_wait call.
- * @filp: file
- * @wait_address: socket wait queue
- * @p: poll_table
- *
- * See the comments in the wq_has_sleeper function.
- */
- static inline void sock_poll_wait(struct file *filp,
- wait_queue_head_t *wait_address, poll_table *p)
- {
- if (!poll_does_not_wait(p) && wait_address) {
- poll_wait(filp, wait_address, p);
- /* We need to be sure we are in sync with the
- * socket flags modification.
- *
- * This memory barrier is paired in the wq_has_sleeper.
- */
- smp_mb();
- }
- }
- /*
- * Queue a received datagram if it will fit. Stream and sequenced
- * protocols can't normally use this as they need to fit buffers in
- * and play with them.
- *
- * Inlined as it's very short and called for pretty much every
- * packet ever received.
- */
- static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
- {
- skb_orphan(skb);
- skb->sk = sk;
- skb->destructor = sock_wfree;
- /*
- * We used to take a refcount on sk, but following operation
- * is enough to guarantee sk_free() wont free this sock until
- * all in-flight packets are completed
- */
- atomic_add(skb->truesize, &sk->sk_wmem_alloc);
- }
- static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
- {
- skb_orphan(skb);
- skb->sk = sk;
- skb->destructor = sock_rfree;
- atomic_add(skb->truesize, &sk->sk_rmem_alloc);
- sk_mem_charge(sk, skb->truesize);
- }
- void sk_reset_timer(struct sock *sk, struct timer_list *timer,
- unsigned long expires);
- void sk_stop_timer(struct sock *sk, struct timer_list *timer);
- int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
- int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
- /*
- * Recover an error report and clear atomically
- */
- static inline int sock_error(struct sock *sk)
- {
- int err;
- if (likely(!sk->sk_err))
- return 0;
- err = xchg(&sk->sk_err, 0);
- return -err;
- }
- static inline unsigned long sock_wspace(struct sock *sk)
- {
- int amt = 0;
- if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
- amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc);
- if (amt < 0)
- amt = 0;
- }
- return amt;
- }
- static inline void sk_wake_async(struct sock *sk, int how, int band)
- {
- if (sock_flag(sk, SOCK_FASYNC))
- sock_wake_async(sk->sk_socket, how, band);
- }
- #define SOCK_MIN_SNDBUF 2048
- /*
- * Since sk_rmem_alloc sums skb->truesize, even a small frame might need
- * sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak
- */
- #define SOCK_MIN_RCVBUF (2048 + sizeof(struct sk_buff))
- static inline void sk_stream_moderate_sndbuf(struct sock *sk)
- {
- if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
- sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
- sk->sk_sndbuf = max(sk->sk_sndbuf, SOCK_MIN_SNDBUF);
- }
- }
- struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp);
- static inline struct page *sk_stream_alloc_page(struct sock *sk)
- {
- struct page *page = NULL;
- page = alloc_pages(sk->sk_allocation, 0);
- if (!page) {
- sk_enter_memory_pressure(sk);
- sk_stream_moderate_sndbuf(sk);
- }
- return page;
- }
- /*
- * Default write policy as shown to user space via poll/select/SIGIO
- */
- static inline bool sock_writeable(const struct sock *sk)
- {
- return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1);
- }
- static inline gfp_t gfp_any(void)
- {
- return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
- }
- static inline long sock_rcvtimeo(const struct sock *sk, bool noblock)
- {
- return noblock ? 0 : sk->sk_rcvtimeo;
- }
- static inline long sock_sndtimeo(const struct sock *sk, bool noblock)
- {
- return noblock ? 0 : sk->sk_sndtimeo;
- }
- static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
- {
- return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1;
- }
- /* Alas, with timeout socket operations are not restartable.
- * Compare this to poll().
- */
- static inline int sock_intr_errno(long timeo)
- {
- return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
- }
- void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
- struct sk_buff *skb);
- void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
- struct sk_buff *skb);
- static inline void
- sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
- {
- ktime_t kt = skb->tstamp;
- struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
- /*
- * generate control messages if
- * - receive time stamping in software requested (SOCK_RCVTSTAMP
- * or SOCK_TIMESTAMPING_RX_SOFTWARE)
- * - software time stamp available and wanted
- * (SOCK_TIMESTAMPING_SOFTWARE)
- * - hardware time stamps available and wanted
- * (SOCK_TIMESTAMPING_SYS_HARDWARE or
- * SOCK_TIMESTAMPING_RAW_HARDWARE)
- */
- if (sock_flag(sk, SOCK_RCVTSTAMP) ||
- sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE) ||
- (kt.tv64 && sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) ||
- (hwtstamps->hwtstamp.tv64 &&
- sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) ||
- (hwtstamps->syststamp.tv64 &&
- sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE)))
- __sock_recv_timestamp(msg, sk, skb);
- else
- sk->sk_stamp = kt;
- if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
- __sock_recv_wifi_status(msg, sk, skb);
- }
- void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
- struct sk_buff *skb);
- static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
- struct sk_buff *skb)
- {
- #define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \
- (1UL << SOCK_RCVTSTAMP) | \
- (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \
- (1UL << SOCK_TIMESTAMPING_SOFTWARE) | \
- (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE) | \
- (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE))
- if (sk->sk_flags & FLAGS_TS_OR_DROPS)
- __sock_recv_ts_and_drops(msg, sk, skb);
- else
- sk->sk_stamp = skb->tstamp;
- }
- /**
- * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
- * @sk: socket sending this packet
- * @tx_flags: filled with instructions for time stamping
- *
- * Currently only depends on SOCK_TIMESTAMPING* flags.
- */
- void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags);
- /**
- * sk_eat_skb - Release a skb if it is no longer needed
- * @sk: socket to eat this skb from
- * @skb: socket buffer to eat
- * @copied_early: flag indicating whether DMA operations copied this data early
- *
- * This routine must be called with interrupts disabled or with the socket
- * locked so that the sk_buff queue operation is ok.
- */
- #ifdef CONFIG_NET_DMA
- static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, bool copied_early)
- {
- __skb_unlink(skb, &sk->sk_receive_queue);
- if (!copied_early)
- __kfree_skb(skb);
- else
- __skb_queue_tail(&sk->sk_async_wait_queue, skb);
- }
- #else
- static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, bool copied_early)
- {
- __skb_unlink(skb, &sk->sk_receive_queue);
- __kfree_skb(skb);
- }
- #endif
- static inline
- struct net *sock_net(const struct sock *sk)
- {
- return read_pnet(&sk->sk_net);
- }
- static inline
- void sock_net_set(struct sock *sk, struct net *net)
- {
- write_pnet(&sk->sk_net, net);
- }
- /*
- * Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace.
- * They should not hold a reference to a namespace in order to allow
- * to stop it.
- * Sockets after sk_change_net should be released using sk_release_kernel
- */
- static inline void sk_change_net(struct sock *sk, struct net *net)
- {
- put_net(sock_net(sk));
- sock_net_set(sk, hold_net(net));
- }
- static inline struct sock *skb_steal_sock(struct sk_buff *skb)
- {
- if (unlikely(skb->sk)) {
- struct sock *sk = skb->sk;
- skb->destructor = NULL;
- skb->sk = NULL;
- return sk;
- }
- return NULL;
- }
- /* This helper checks if a socket is a full socket,
- * ie _not_ a timewait or request socket.
- * TODO: Check for TCPF_NEW_SYN_RECV when that starts to exist.
- */
- static inline bool sk_fullsock(const struct sock *sk)
- {
- return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT);
- }
- void sock_enable_timestamp(struct sock *sk, int flag);
- int sock_get_timestamp(struct sock *, struct timeval __user *);
- int sock_get_timestampns(struct sock *, struct timespec __user *);
- /*
- * Enable debug/info messages
- */
- extern int net_msg_warn;
- #define NETDEBUG(fmt, args...) \
- do { if (net_msg_warn) printk(fmt,##args); } while (0)
- #define LIMIT_NETDEBUG(fmt, args...) \
- do { if (net_msg_warn && net_ratelimit()) printk(fmt,##args); } while(0)
- extern __u32 sysctl_wmem_max;
- extern __u32 sysctl_rmem_max;
- void sk_init(void);
- extern int sysctl_optmem_max;
- extern __u32 sysctl_wmem_default;
- extern __u32 sysctl_rmem_default;
- /* SOCKEV Notifier Events */
- #define SOCKEV_SOCKET 0x00
- #define SOCKEV_BIND 0x01
- #define SOCKEV_LISTEN 0x02
- #define SOCKEV_ACCEPT 0x03
- #define SOCKEV_CONNECT 0x04
- #define SOCKEV_SHUTDOWN 0x05
- int sockev_register_notify(struct notifier_block *nb);
- int sockev_unregister_notify(struct notifier_block *nb);
- #endif /* _SOCK_H */
|