12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290329132923293329432953296329732983299330033013302330333043305330633073308330933103311331233133314331533163317331833193320332133223323332433253326332733283329333033313332333333343335333633373338333933403341334233433344334533463347334833493350335133523353335433553356335733583359336033613362336333643365336633673368336933703371337233733374337533763377337833793380338133823383338433853386338733883389339033913392339333943395339633973398339934003401340234033404340534063407340834093410341134123413341434153416341734183419342034213422342334243425342634273428342934303431343234333434343534363437343834393440344134423443344434453446344734483449345034513452345334543455345634573458345934603461346234633464346534663467346834693470347134723473347434753476347734783479348034813482348334843485348634873488348934903491349234933494349534963497349834993500350135023503350435053506350735083509351035113512351335143515351635173518351935203521352235233524352535263527352835293530353135323533353435353536353735383539354035413542354335443545354635473548354935503551355235533554355535563557355835593560356135623563356435653566356735683569357035713572357335743575357635773578357935803581358235833584358535863587358835893590359135923593359435953596359735983599360036013602360336043605360636073608360936103611361236133614361536163617361836193620362136223623362436253626362736283629363036313632363336343635363636373638363936403641364236433644364536463647364836493650365136523653365436553656365736583659366036613662366336643665366636673668366936703671367236733674367536763677367836793680368136823683368436853686368736883689369036913692369336943695369636973698369937003701370237033704370537063707370837093710371137123713371437153716371737183719372037213722372337243725372637273728372937303731373237333734373537363737373837393740374137423743374437453746374737483749375037513752375337543755375637573758375937603761376237633764376537663767376837693770377137723773377437753776377737783779378037813782378337843785378637873788378937903791379237933794379537963797379837993800380138023803380438053806380738083809381038113812381338143815381638173818381938203821382238233824382538263827382838293830383138323833383438353836383738383839384038413842384338443845384638473848384938503851385238533854385538563857385838593860386138623863386438653866386738683869387038713872387338743875387638773878387938803881388238833884388538863887388838893890389138923893389438953896389738983899390039013902390339043905390639073908390939103911391239133914391539163917391839193920392139223923392439253926392739283929393039313932393339343935393639373938393939403941394239433944394539463947394839493950395139523953395439553956395739583959396039613962396339643965396639673968396939703971397239733974397539763977397839793980398139823983398439853986398739883989399039913992399339943995399639973998399940004001400240034004400540064007400840094010401140124013401440154016401740184019402040214022402340244025402640274028402940304031403240334034403540364037403840394040404140424043404440454046404740484049405040514052405340544055405640574058405940604061406240634064406540664067406840694070407140724073407440754076 |
- /*
- * IPVS An implementation of the IP virtual server support for the
- * LINUX operating system. IPVS is now implemented as a module
- * over the NetFilter framework. IPVS can be used to build a
- * high-performance and highly available server based on a
- * cluster of servers.
- *
- * Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
- * Peter Kese <peter.kese@ijs.si>
- * Julian Anastasov <ja@ssi.bg>
- *
- * 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:
- *
- */
- #define KMSG_COMPONENT "IPVS"
- #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
- #include <linux/module.h>
- #include <linux/init.h>
- #include <linux/types.h>
- #include <linux/capability.h>
- #include <linux/fs.h>
- #include <linux/sysctl.h>
- #include <linux/proc_fs.h>
- #include <linux/workqueue.h>
- #include <linux/swap.h>
- #include <linux/seq_file.h>
- #include <linux/slab.h>
- #include <linux/netfilter.h>
- #include <linux/netfilter_ipv4.h>
- #include <linux/mutex.h>
- #include <net/net_namespace.h>
- #include <linux/nsproxy.h>
- #include <net/ip.h>
- #ifdef CONFIG_IP_VS_IPV6
- #include <net/ipv6.h>
- #include <net/ip6_route.h>
- #endif
- #include <net/route.h>
- #include <net/sock.h>
- #include <net/genetlink.h>
- #include <asm/uaccess.h>
- #include <net/ip_vs.h>
- /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
- static DEFINE_MUTEX(__ip_vs_mutex);
- /* sysctl variables */
- #ifdef CONFIG_IP_VS_DEBUG
- static int sysctl_ip_vs_debug_level = 0;
- int ip_vs_get_debug_level(void)
- {
- return sysctl_ip_vs_debug_level;
- }
- #endif
- /* Protos */
- static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup);
- #ifdef CONFIG_IP_VS_IPV6
- /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */
- static bool __ip_vs_addr_is_local_v6(struct net *net,
- const struct in6_addr *addr)
- {
- struct flowi6 fl6 = {
- .daddr = *addr,
- };
- struct dst_entry *dst = ip6_route_output(net, NULL, &fl6);
- bool is_local;
- is_local = !dst->error && dst->dev && (dst->dev->flags & IFF_LOOPBACK);
- dst_release(dst);
- return is_local;
- }
- #endif
- #ifdef CONFIG_SYSCTL
- /*
- * update_defense_level is called from keventd and from sysctl,
- * so it needs to protect itself from softirqs
- */
- static void update_defense_level(struct netns_ipvs *ipvs)
- {
- struct sysinfo i;
- static int old_secure_tcp = 0;
- int availmem;
- int nomem;
- int to_change = -1;
- /* we only count free and buffered memory (in pages) */
- si_meminfo(&i);
- availmem = i.freeram + i.bufferram;
- /* however in linux 2.5 the i.bufferram is total page cache size,
- we need adjust it */
- /* si_swapinfo(&i); */
- /* availmem = availmem - (i.totalswap - i.freeswap); */
- nomem = (availmem < ipvs->sysctl_amemthresh);
- local_bh_disable();
- /* drop_entry */
- spin_lock(&ipvs->dropentry_lock);
- switch (ipvs->sysctl_drop_entry) {
- case 0:
- atomic_set(&ipvs->dropentry, 0);
- break;
- case 1:
- if (nomem) {
- atomic_set(&ipvs->dropentry, 1);
- ipvs->sysctl_drop_entry = 2;
- } else {
- atomic_set(&ipvs->dropentry, 0);
- }
- break;
- case 2:
- if (nomem) {
- atomic_set(&ipvs->dropentry, 1);
- } else {
- atomic_set(&ipvs->dropentry, 0);
- ipvs->sysctl_drop_entry = 1;
- };
- break;
- case 3:
- atomic_set(&ipvs->dropentry, 1);
- break;
- }
- spin_unlock(&ipvs->dropentry_lock);
- /* drop_packet */
- spin_lock(&ipvs->droppacket_lock);
- switch (ipvs->sysctl_drop_packet) {
- case 0:
- ipvs->drop_rate = 0;
- break;
- case 1:
- if (nomem) {
- ipvs->drop_rate = ipvs->drop_counter
- = ipvs->sysctl_amemthresh /
- (ipvs->sysctl_amemthresh-availmem);
- ipvs->sysctl_drop_packet = 2;
- } else {
- ipvs->drop_rate = 0;
- }
- break;
- case 2:
- if (nomem) {
- ipvs->drop_rate = ipvs->drop_counter
- = ipvs->sysctl_amemthresh /
- (ipvs->sysctl_amemthresh-availmem);
- } else {
- ipvs->drop_rate = 0;
- ipvs->sysctl_drop_packet = 1;
- }
- break;
- case 3:
- ipvs->drop_rate = ipvs->sysctl_am_droprate;
- break;
- }
- spin_unlock(&ipvs->droppacket_lock);
- /* secure_tcp */
- spin_lock(&ipvs->securetcp_lock);
- switch (ipvs->sysctl_secure_tcp) {
- case 0:
- if (old_secure_tcp >= 2)
- to_change = 0;
- break;
- case 1:
- if (nomem) {
- if (old_secure_tcp < 2)
- to_change = 1;
- ipvs->sysctl_secure_tcp = 2;
- } else {
- if (old_secure_tcp >= 2)
- to_change = 0;
- }
- break;
- case 2:
- if (nomem) {
- if (old_secure_tcp < 2)
- to_change = 1;
- } else {
- if (old_secure_tcp >= 2)
- to_change = 0;
- ipvs->sysctl_secure_tcp = 1;
- }
- break;
- case 3:
- if (old_secure_tcp < 2)
- to_change = 1;
- break;
- }
- old_secure_tcp = ipvs->sysctl_secure_tcp;
- if (to_change >= 0)
- ip_vs_protocol_timeout_change(ipvs,
- ipvs->sysctl_secure_tcp > 1);
- spin_unlock(&ipvs->securetcp_lock);
- local_bh_enable();
- }
- /*
- * Timer for checking the defense
- */
- #define DEFENSE_TIMER_PERIOD 1*HZ
- static void defense_work_handler(struct work_struct *work)
- {
- struct netns_ipvs *ipvs =
- container_of(work, struct netns_ipvs, defense_work.work);
- update_defense_level(ipvs);
- if (atomic_read(&ipvs->dropentry))
- ip_vs_random_dropentry(ipvs);
- schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
- }
- #endif
- int
- ip_vs_use_count_inc(void)
- {
- return try_module_get(THIS_MODULE);
- }
- void
- ip_vs_use_count_dec(void)
- {
- module_put(THIS_MODULE);
- }
- /*
- * Hash table: for virtual service lookups
- */
- #define IP_VS_SVC_TAB_BITS 8
- #define IP_VS_SVC_TAB_SIZE (1 << IP_VS_SVC_TAB_BITS)
- #define IP_VS_SVC_TAB_MASK (IP_VS_SVC_TAB_SIZE - 1)
- /* the service table hashed by <protocol, addr, port> */
- static struct hlist_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
- /* the service table hashed by fwmark */
- static struct hlist_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];
- /*
- * Returns hash value for virtual service
- */
- static inline unsigned int
- ip_vs_svc_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto,
- const union nf_inet_addr *addr, __be16 port)
- {
- register unsigned int porth = ntohs(port);
- __be32 addr_fold = addr->ip;
- __u32 ahash;
- #ifdef CONFIG_IP_VS_IPV6
- if (af == AF_INET6)
- addr_fold = addr->ip6[0]^addr->ip6[1]^
- addr->ip6[2]^addr->ip6[3];
- #endif
- ahash = ntohl(addr_fold);
- ahash ^= ((size_t) ipvs >> 8);
- return (proto ^ ahash ^ (porth >> IP_VS_SVC_TAB_BITS) ^ porth) &
- IP_VS_SVC_TAB_MASK;
- }
- /*
- * Returns hash value of fwmark for virtual service lookup
- */
- static inline unsigned int ip_vs_svc_fwm_hashkey(struct netns_ipvs *ipvs, __u32 fwmark)
- {
- return (((size_t)ipvs>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK;
- }
- /*
- * Hashes a service in the ip_vs_svc_table by <netns,proto,addr,port>
- * or in the ip_vs_svc_fwm_table by fwmark.
- * Should be called with locked tables.
- */
- static int ip_vs_svc_hash(struct ip_vs_service *svc)
- {
- unsigned int hash;
- if (svc->flags & IP_VS_SVC_F_HASHED) {
- pr_err("%s(): request for already hashed, called from %pF\n",
- __func__, __builtin_return_address(0));
- return 0;
- }
- if (svc->fwmark == 0) {
- /*
- * Hash it by <netns,protocol,addr,port> in ip_vs_svc_table
- */
- hash = ip_vs_svc_hashkey(svc->ipvs, svc->af, svc->protocol,
- &svc->addr, svc->port);
- hlist_add_head_rcu(&svc->s_list, &ip_vs_svc_table[hash]);
- } else {
- /*
- * Hash it by fwmark in svc_fwm_table
- */
- hash = ip_vs_svc_fwm_hashkey(svc->ipvs, svc->fwmark);
- hlist_add_head_rcu(&svc->f_list, &ip_vs_svc_fwm_table[hash]);
- }
- svc->flags |= IP_VS_SVC_F_HASHED;
- /* increase its refcnt because it is referenced by the svc table */
- atomic_inc(&svc->refcnt);
- return 1;
- }
- /*
- * Unhashes a service from svc_table / svc_fwm_table.
- * Should be called with locked tables.
- */
- static int ip_vs_svc_unhash(struct ip_vs_service *svc)
- {
- if (!(svc->flags & IP_VS_SVC_F_HASHED)) {
- pr_err("%s(): request for unhash flagged, called from %pF\n",
- __func__, __builtin_return_address(0));
- return 0;
- }
- if (svc->fwmark == 0) {
- /* Remove it from the svc_table table */
- hlist_del_rcu(&svc->s_list);
- } else {
- /* Remove it from the svc_fwm_table table */
- hlist_del_rcu(&svc->f_list);
- }
- svc->flags &= ~IP_VS_SVC_F_HASHED;
- atomic_dec(&svc->refcnt);
- return 1;
- }
- /*
- * Get service by {netns, proto,addr,port} in the service table.
- */
- static inline struct ip_vs_service *
- __ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u16 protocol,
- const union nf_inet_addr *vaddr, __be16 vport)
- {
- unsigned int hash;
- struct ip_vs_service *svc;
- /* Check for "full" addressed entries */
- hash = ip_vs_svc_hashkey(ipvs, af, protocol, vaddr, vport);
- hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[hash], s_list) {
- if ((svc->af == af)
- && ip_vs_addr_equal(af, &svc->addr, vaddr)
- && (svc->port == vport)
- && (svc->protocol == protocol)
- && (svc->ipvs == ipvs)) {
- /* HIT */
- return svc;
- }
- }
- return NULL;
- }
- /*
- * Get service by {fwmark} in the service table.
- */
- static inline struct ip_vs_service *
- __ip_vs_svc_fwm_find(struct netns_ipvs *ipvs, int af, __u32 fwmark)
- {
- unsigned int hash;
- struct ip_vs_service *svc;
- /* Check for fwmark addressed entries */
- hash = ip_vs_svc_fwm_hashkey(ipvs, fwmark);
- hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[hash], f_list) {
- if (svc->fwmark == fwmark && svc->af == af
- && (svc->ipvs == ipvs)) {
- /* HIT */
- return svc;
- }
- }
- return NULL;
- }
- /* Find service, called under RCU lock */
- struct ip_vs_service *
- ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol,
- const union nf_inet_addr *vaddr, __be16 vport)
- {
- struct ip_vs_service *svc;
- /*
- * Check the table hashed by fwmark first
- */
- if (fwmark) {
- svc = __ip_vs_svc_fwm_find(ipvs, af, fwmark);
- if (svc)
- goto out;
- }
- /*
- * Check the table hashed by <protocol,addr,port>
- * for "full" addressed entries
- */
- svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, vport);
- if (svc == NULL
- && protocol == IPPROTO_TCP
- && atomic_read(&ipvs->ftpsvc_counter)
- && (vport == FTPDATA || ntohs(vport) >= PROT_SOCK)) {
- /*
- * Check if ftp service entry exists, the packet
- * might belong to FTP data connections.
- */
- svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, FTPPORT);
- }
- if (svc == NULL
- && atomic_read(&ipvs->nullsvc_counter)) {
- /*
- * Check if the catch-all port (port zero) exists
- */
- svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, 0);
- }
- out:
- IP_VS_DBG_BUF(9, "lookup service: fwm %u %s %s:%u %s\n",
- fwmark, ip_vs_proto_name(protocol),
- IP_VS_DBG_ADDR(af, vaddr), ntohs(vport),
- svc ? "hit" : "not hit");
- return svc;
- }
- static inline void
- __ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc)
- {
- atomic_inc(&svc->refcnt);
- rcu_assign_pointer(dest->svc, svc);
- }
- static void ip_vs_service_free(struct ip_vs_service *svc)
- {
- free_percpu(svc->stats.cpustats);
- kfree(svc);
- }
- static void ip_vs_service_rcu_free(struct rcu_head *head)
- {
- struct ip_vs_service *svc;
- svc = container_of(head, struct ip_vs_service, rcu_head);
- ip_vs_service_free(svc);
- }
- static void __ip_vs_svc_put(struct ip_vs_service *svc, bool do_delay)
- {
- if (atomic_dec_and_test(&svc->refcnt)) {
- IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n",
- svc->fwmark,
- IP_VS_DBG_ADDR(svc->af, &svc->addr),
- ntohs(svc->port));
- if (do_delay)
- call_rcu(&svc->rcu_head, ip_vs_service_rcu_free);
- else
- ip_vs_service_free(svc);
- }
- }
- /*
- * Returns hash value for real service
- */
- static inline unsigned int ip_vs_rs_hashkey(int af,
- const union nf_inet_addr *addr,
- __be16 port)
- {
- register unsigned int porth = ntohs(port);
- __be32 addr_fold = addr->ip;
- #ifdef CONFIG_IP_VS_IPV6
- if (af == AF_INET6)
- addr_fold = addr->ip6[0]^addr->ip6[1]^
- addr->ip6[2]^addr->ip6[3];
- #endif
- return (ntohl(addr_fold)^(porth>>IP_VS_RTAB_BITS)^porth)
- & IP_VS_RTAB_MASK;
- }
- /* Hash ip_vs_dest in rs_table by <proto,addr,port>. */
- static void ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest)
- {
- unsigned int hash;
- if (dest->in_rs_table)
- return;
- /*
- * Hash by proto,addr,port,
- * which are the parameters of the real service.
- */
- hash = ip_vs_rs_hashkey(dest->af, &dest->addr, dest->port);
- hlist_add_head_rcu(&dest->d_list, &ipvs->rs_table[hash]);
- dest->in_rs_table = 1;
- }
- /* Unhash ip_vs_dest from rs_table. */
- static void ip_vs_rs_unhash(struct ip_vs_dest *dest)
- {
- /*
- * Remove it from the rs_table table.
- */
- if (dest->in_rs_table) {
- hlist_del_rcu(&dest->d_list);
- dest->in_rs_table = 0;
- }
- }
- /* Check if real service by <proto,addr,port> is present */
- bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
- const union nf_inet_addr *daddr, __be16 dport)
- {
- unsigned int hash;
- struct ip_vs_dest *dest;
- /* Check for "full" addressed entries */
- hash = ip_vs_rs_hashkey(af, daddr, dport);
- rcu_read_lock();
- hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) {
- if (dest->port == dport &&
- dest->af == af &&
- ip_vs_addr_equal(af, &dest->addr, daddr) &&
- (dest->protocol == protocol || dest->vfwmark)) {
- /* HIT */
- rcu_read_unlock();
- return true;
- }
- }
- rcu_read_unlock();
- return false;
- }
- /* Lookup destination by {addr,port} in the given service
- * Called under RCU lock.
- */
- static struct ip_vs_dest *
- ip_vs_lookup_dest(struct ip_vs_service *svc, int dest_af,
- const union nf_inet_addr *daddr, __be16 dport)
- {
- struct ip_vs_dest *dest;
- /*
- * Find the destination for the given service
- */
- list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- if ((dest->af == dest_af) &&
- ip_vs_addr_equal(dest_af, &dest->addr, daddr) &&
- (dest->port == dport)) {
- /* HIT */
- return dest;
- }
- }
- return NULL;
- }
- /*
- * Find destination by {daddr,dport,vaddr,protocol}
- * Created to be used in ip_vs_process_message() in
- * the backup synchronization daemon. It finds the
- * destination to be bound to the received connection
- * on the backup.
- * Called under RCU lock, no refcnt is returned.
- */
- struct ip_vs_dest *ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af,
- const union nf_inet_addr *daddr,
- __be16 dport,
- const union nf_inet_addr *vaddr,
- __be16 vport, __u16 protocol, __u32 fwmark,
- __u32 flags)
- {
- struct ip_vs_dest *dest;
- struct ip_vs_service *svc;
- __be16 port = dport;
- svc = ip_vs_service_find(ipvs, svc_af, fwmark, protocol, vaddr, vport);
- if (!svc)
- return NULL;
- if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ)
- port = 0;
- dest = ip_vs_lookup_dest(svc, dest_af, daddr, port);
- if (!dest)
- dest = ip_vs_lookup_dest(svc, dest_af, daddr, port ^ dport);
- return dest;
- }
- void ip_vs_dest_dst_rcu_free(struct rcu_head *head)
- {
- struct ip_vs_dest_dst *dest_dst = container_of(head,
- struct ip_vs_dest_dst,
- rcu_head);
- dst_release(dest_dst->dst_cache);
- kfree(dest_dst);
- }
- /* Release dest_dst and dst_cache for dest in user context */
- static void __ip_vs_dst_cache_reset(struct ip_vs_dest *dest)
- {
- struct ip_vs_dest_dst *old;
- old = rcu_dereference_protected(dest->dest_dst, 1);
- if (old) {
- RCU_INIT_POINTER(dest->dest_dst, NULL);
- call_rcu(&old->rcu_head, ip_vs_dest_dst_rcu_free);
- }
- }
- /*
- * Lookup dest by {svc,addr,port} in the destination trash.
- * The destination trash is used to hold the destinations that are removed
- * from the service table but are still referenced by some conn entries.
- * The reason to add the destination trash is when the dest is temporary
- * down (either by administrator or by monitor program), the dest can be
- * picked back from the trash, the remaining connections to the dest can
- * continue, and the counting information of the dest is also useful for
- * scheduling.
- */
- static struct ip_vs_dest *
- ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af,
- const union nf_inet_addr *daddr, __be16 dport)
- {
- struct ip_vs_dest *dest;
- struct netns_ipvs *ipvs = svc->ipvs;
- /*
- * Find the destination in trash
- */
- spin_lock_bh(&ipvs->dest_trash_lock);
- list_for_each_entry(dest, &ipvs->dest_trash, t_list) {
- IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, "
- "dest->refcnt=%d\n",
- dest->vfwmark,
- IP_VS_DBG_ADDR(dest->af, &dest->addr),
- ntohs(dest->port),
- atomic_read(&dest->refcnt));
- if (dest->af == dest_af &&
- ip_vs_addr_equal(dest_af, &dest->addr, daddr) &&
- dest->port == dport &&
- dest->vfwmark == svc->fwmark &&
- dest->protocol == svc->protocol &&
- (svc->fwmark ||
- (ip_vs_addr_equal(svc->af, &dest->vaddr, &svc->addr) &&
- dest->vport == svc->port))) {
- /* HIT */
- list_del(&dest->t_list);
- ip_vs_dest_hold(dest);
- goto out;
- }
- }
- dest = NULL;
- out:
- spin_unlock_bh(&ipvs->dest_trash_lock);
- return dest;
- }
- static void ip_vs_dest_free(struct ip_vs_dest *dest)
- {
- struct ip_vs_service *svc = rcu_dereference_protected(dest->svc, 1);
- __ip_vs_dst_cache_reset(dest);
- __ip_vs_svc_put(svc, false);
- free_percpu(dest->stats.cpustats);
- ip_vs_dest_put_and_free(dest);
- }
- /*
- * Clean up all the destinations in the trash
- * Called by the ip_vs_control_cleanup()
- *
- * When the ip_vs_control_clearup is activated by ipvs module exit,
- * the service tables must have been flushed and all the connections
- * are expired, and the refcnt of each destination in the trash must
- * be 0, so we simply release them here.
- */
- static void ip_vs_trash_cleanup(struct netns_ipvs *ipvs)
- {
- struct ip_vs_dest *dest, *nxt;
- del_timer_sync(&ipvs->dest_trash_timer);
- /* No need to use dest_trash_lock */
- list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, t_list) {
- list_del(&dest->t_list);
- ip_vs_dest_free(dest);
- }
- }
- static void
- ip_vs_copy_stats(struct ip_vs_kstats *dst, struct ip_vs_stats *src)
- {
- #define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->kstats.c - src->kstats0.c
- spin_lock_bh(&src->lock);
- IP_VS_SHOW_STATS_COUNTER(conns);
- IP_VS_SHOW_STATS_COUNTER(inpkts);
- IP_VS_SHOW_STATS_COUNTER(outpkts);
- IP_VS_SHOW_STATS_COUNTER(inbytes);
- IP_VS_SHOW_STATS_COUNTER(outbytes);
- ip_vs_read_estimator(dst, src);
- spin_unlock_bh(&src->lock);
- }
- static void
- ip_vs_export_stats_user(struct ip_vs_stats_user *dst, struct ip_vs_kstats *src)
- {
- dst->conns = (u32)src->conns;
- dst->inpkts = (u32)src->inpkts;
- dst->outpkts = (u32)src->outpkts;
- dst->inbytes = src->inbytes;
- dst->outbytes = src->outbytes;
- dst->cps = (u32)src->cps;
- dst->inpps = (u32)src->inpps;
- dst->outpps = (u32)src->outpps;
- dst->inbps = (u32)src->inbps;
- dst->outbps = (u32)src->outbps;
- }
- static void
- ip_vs_zero_stats(struct ip_vs_stats *stats)
- {
- spin_lock_bh(&stats->lock);
- /* get current counters as zero point, rates are zeroed */
- #define IP_VS_ZERO_STATS_COUNTER(c) stats->kstats0.c = stats->kstats.c
- IP_VS_ZERO_STATS_COUNTER(conns);
- IP_VS_ZERO_STATS_COUNTER(inpkts);
- IP_VS_ZERO_STATS_COUNTER(outpkts);
- IP_VS_ZERO_STATS_COUNTER(inbytes);
- IP_VS_ZERO_STATS_COUNTER(outbytes);
- ip_vs_zero_estimator(stats);
- spin_unlock_bh(&stats->lock);
- }
- /*
- * Update a destination in the given service
- */
- static void
- __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
- struct ip_vs_dest_user_kern *udest, int add)
- {
- struct netns_ipvs *ipvs = svc->ipvs;
- struct ip_vs_service *old_svc;
- struct ip_vs_scheduler *sched;
- int conn_flags;
- /* We cannot modify an address and change the address family */
- BUG_ON(!add && udest->af != dest->af);
- if (add && udest->af != svc->af)
- ipvs->mixed_address_family_dests++;
- /* set the weight and the flags */
- atomic_set(&dest->weight, udest->weight);
- conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
- conn_flags |= IP_VS_CONN_F_INACTIVE;
- /* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */
- if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) {
- conn_flags |= IP_VS_CONN_F_NOOUTPUT;
- } else {
- /*
- * Put the real service in rs_table if not present.
- * For now only for NAT!
- */
- ip_vs_rs_hash(ipvs, dest);
- }
- atomic_set(&dest->conn_flags, conn_flags);
- /* bind the service */
- old_svc = rcu_dereference_protected(dest->svc, 1);
- if (!old_svc) {
- __ip_vs_bind_svc(dest, svc);
- } else {
- if (old_svc != svc) {
- ip_vs_zero_stats(&dest->stats);
- __ip_vs_bind_svc(dest, svc);
- __ip_vs_svc_put(old_svc, true);
- }
- }
- /* set the dest status flags */
- dest->flags |= IP_VS_DEST_F_AVAILABLE;
- if (udest->u_threshold == 0 || udest->u_threshold > dest->u_threshold)
- dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
- dest->u_threshold = udest->u_threshold;
- dest->l_threshold = udest->l_threshold;
- dest->af = udest->af;
- spin_lock_bh(&dest->dst_lock);
- __ip_vs_dst_cache_reset(dest);
- spin_unlock_bh(&dest->dst_lock);
- if (add) {
- ip_vs_start_estimator(svc->ipvs, &dest->stats);
- list_add_rcu(&dest->n_list, &svc->destinations);
- svc->num_dests++;
- sched = rcu_dereference_protected(svc->scheduler, 1);
- if (sched && sched->add_dest)
- sched->add_dest(svc, dest);
- } else {
- sched = rcu_dereference_protected(svc->scheduler, 1);
- if (sched && sched->upd_dest)
- sched->upd_dest(svc, dest);
- }
- }
- /*
- * Create a destination for the given service
- */
- static int
- ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
- struct ip_vs_dest **dest_p)
- {
- struct ip_vs_dest *dest;
- unsigned int atype, i;
- EnterFunction(2);
- #ifdef CONFIG_IP_VS_IPV6
- if (udest->af == AF_INET6) {
- atype = ipv6_addr_type(&udest->addr.in6);
- if ((!(atype & IPV6_ADDR_UNICAST) ||
- atype & IPV6_ADDR_LINKLOCAL) &&
- !__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6))
- return -EINVAL;
- } else
- #endif
- {
- atype = inet_addr_type(svc->ipvs->net, udest->addr.ip);
- if (atype != RTN_LOCAL && atype != RTN_UNICAST)
- return -EINVAL;
- }
- dest = kzalloc(sizeof(struct ip_vs_dest), GFP_KERNEL);
- if (dest == NULL)
- return -ENOMEM;
- dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
- if (!dest->stats.cpustats)
- goto err_alloc;
- for_each_possible_cpu(i) {
- struct ip_vs_cpu_stats *ip_vs_dest_stats;
- ip_vs_dest_stats = per_cpu_ptr(dest->stats.cpustats, i);
- u64_stats_init(&ip_vs_dest_stats->syncp);
- }
- dest->af = udest->af;
- dest->protocol = svc->protocol;
- dest->vaddr = svc->addr;
- dest->vport = svc->port;
- dest->vfwmark = svc->fwmark;
- ip_vs_addr_copy(udest->af, &dest->addr, &udest->addr);
- dest->port = udest->port;
- atomic_set(&dest->activeconns, 0);
- atomic_set(&dest->inactconns, 0);
- atomic_set(&dest->persistconns, 0);
- atomic_set(&dest->refcnt, 1);
- INIT_HLIST_NODE(&dest->d_list);
- spin_lock_init(&dest->dst_lock);
- spin_lock_init(&dest->stats.lock);
- __ip_vs_update_dest(svc, dest, udest, 1);
- *dest_p = dest;
- LeaveFunction(2);
- return 0;
- err_alloc:
- kfree(dest);
- return -ENOMEM;
- }
- /*
- * Add a destination into an existing service
- */
- static int
- ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
- {
- struct ip_vs_dest *dest;
- union nf_inet_addr daddr;
- __be16 dport = udest->port;
- int ret;
- EnterFunction(2);
- if (udest->weight < 0) {
- pr_err("%s(): server weight less than zero\n", __func__);
- return -ERANGE;
- }
- if (udest->l_threshold > udest->u_threshold) {
- pr_err("%s(): lower threshold is higher than upper threshold\n",
- __func__);
- return -ERANGE;
- }
- ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
- /* We use function that requires RCU lock */
- rcu_read_lock();
- dest = ip_vs_lookup_dest(svc, udest->af, &daddr, dport);
- rcu_read_unlock();
- if (dest != NULL) {
- IP_VS_DBG(1, "%s(): dest already exists\n", __func__);
- return -EEXIST;
- }
- /*
- * Check if the dest already exists in the trash and
- * is from the same service
- */
- dest = ip_vs_trash_get_dest(svc, udest->af, &daddr, dport);
- if (dest != NULL) {
- IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, "
- "dest->refcnt=%d, service %u/%s:%u\n",
- IP_VS_DBG_ADDR(udest->af, &daddr), ntohs(dport),
- atomic_read(&dest->refcnt),
- dest->vfwmark,
- IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
- ntohs(dest->vport));
- __ip_vs_update_dest(svc, dest, udest, 1);
- ret = 0;
- } else {
- /*
- * Allocate and initialize the dest structure
- */
- ret = ip_vs_new_dest(svc, udest, &dest);
- }
- LeaveFunction(2);
- return ret;
- }
- /*
- * Edit a destination in the given service
- */
- static int
- ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
- {
- struct ip_vs_dest *dest;
- union nf_inet_addr daddr;
- __be16 dport = udest->port;
- EnterFunction(2);
- if (udest->weight < 0) {
- pr_err("%s(): server weight less than zero\n", __func__);
- return -ERANGE;
- }
- if (udest->l_threshold > udest->u_threshold) {
- pr_err("%s(): lower threshold is higher than upper threshold\n",
- __func__);
- return -ERANGE;
- }
- ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
- /* We use function that requires RCU lock */
- rcu_read_lock();
- dest = ip_vs_lookup_dest(svc, udest->af, &daddr, dport);
- rcu_read_unlock();
- if (dest == NULL) {
- IP_VS_DBG(1, "%s(): dest doesn't exist\n", __func__);
- return -ENOENT;
- }
- __ip_vs_update_dest(svc, dest, udest, 0);
- LeaveFunction(2);
- return 0;
- }
- /*
- * Delete a destination (must be already unlinked from the service)
- */
- static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest,
- bool cleanup)
- {
- ip_vs_stop_estimator(ipvs, &dest->stats);
- /*
- * Remove it from the d-linked list with the real services.
- */
- ip_vs_rs_unhash(dest);
- spin_lock_bh(&ipvs->dest_trash_lock);
- IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n",
- IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
- atomic_read(&dest->refcnt));
- if (list_empty(&ipvs->dest_trash) && !cleanup)
- mod_timer(&ipvs->dest_trash_timer,
- jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1));
- /* dest lives in trash without reference */
- list_add(&dest->t_list, &ipvs->dest_trash);
- dest->idle_start = 0;
- spin_unlock_bh(&ipvs->dest_trash_lock);
- ip_vs_dest_put(dest);
- }
- /*
- * Unlink a destination from the given service
- */
- static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
- struct ip_vs_dest *dest,
- int svcupd)
- {
- dest->flags &= ~IP_VS_DEST_F_AVAILABLE;
- /*
- * Remove it from the d-linked destination list.
- */
- list_del_rcu(&dest->n_list);
- svc->num_dests--;
- if (dest->af != svc->af)
- svc->ipvs->mixed_address_family_dests--;
- if (svcupd) {
- struct ip_vs_scheduler *sched;
- sched = rcu_dereference_protected(svc->scheduler, 1);
- if (sched && sched->del_dest)
- sched->del_dest(svc, dest);
- }
- }
- /*
- * Delete a destination server in the given service
- */
- static int
- ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
- {
- struct ip_vs_dest *dest;
- __be16 dport = udest->port;
- EnterFunction(2);
- /* We use function that requires RCU lock */
- rcu_read_lock();
- dest = ip_vs_lookup_dest(svc, udest->af, &udest->addr, dport);
- rcu_read_unlock();
- if (dest == NULL) {
- IP_VS_DBG(1, "%s(): destination not found!\n", __func__);
- return -ENOENT;
- }
- /*
- * Unlink dest from the service
- */
- __ip_vs_unlink_dest(svc, dest, 1);
- /*
- * Delete the destination
- */
- __ip_vs_del_dest(svc->ipvs, dest, false);
- LeaveFunction(2);
- return 0;
- }
- static void ip_vs_dest_trash_expire(unsigned long data)
- {
- struct netns_ipvs *ipvs = (struct netns_ipvs *)data;
- struct ip_vs_dest *dest, *next;
- unsigned long now = jiffies;
- spin_lock(&ipvs->dest_trash_lock);
- list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) {
- if (atomic_read(&dest->refcnt) > 0)
- continue;
- if (dest->idle_start) {
- if (time_before(now, dest->idle_start +
- IP_VS_DEST_TRASH_PERIOD))
- continue;
- } else {
- dest->idle_start = max(1UL, now);
- continue;
- }
- IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u from trash\n",
- dest->vfwmark,
- IP_VS_DBG_ADDR(dest->af, &dest->addr),
- ntohs(dest->port));
- list_del(&dest->t_list);
- ip_vs_dest_free(dest);
- }
- if (!list_empty(&ipvs->dest_trash))
- mod_timer(&ipvs->dest_trash_timer,
- jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1));
- spin_unlock(&ipvs->dest_trash_lock);
- }
- /*
- * Add a service into the service hash table
- */
- static int
- ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
- struct ip_vs_service **svc_p)
- {
- int ret = 0, i;
- struct ip_vs_scheduler *sched = NULL;
- struct ip_vs_pe *pe = NULL;
- struct ip_vs_service *svc = NULL;
- /* increase the module use count */
- ip_vs_use_count_inc();
- /* Lookup the scheduler by 'u->sched_name' */
- if (strcmp(u->sched_name, "none")) {
- sched = ip_vs_scheduler_get(u->sched_name);
- if (!sched) {
- pr_info("Scheduler module ip_vs_%s not found\n",
- u->sched_name);
- ret = -ENOENT;
- goto out_err;
- }
- }
- if (u->pe_name && *u->pe_name) {
- pe = ip_vs_pe_getbyname(u->pe_name);
- if (pe == NULL) {
- pr_info("persistence engine module ip_vs_pe_%s "
- "not found\n", u->pe_name);
- ret = -ENOENT;
- goto out_err;
- }
- }
- #ifdef CONFIG_IP_VS_IPV6
- if (u->af == AF_INET6) {
- __u32 plen = (__force __u32) u->netmask;
- if (plen < 1 || plen > 128) {
- ret = -EINVAL;
- goto out_err;
- }
- }
- #endif
- svc = kzalloc(sizeof(struct ip_vs_service), GFP_KERNEL);
- if (svc == NULL) {
- IP_VS_DBG(1, "%s(): no memory\n", __func__);
- ret = -ENOMEM;
- goto out_err;
- }
- svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
- if (!svc->stats.cpustats) {
- ret = -ENOMEM;
- goto out_err;
- }
- for_each_possible_cpu(i) {
- struct ip_vs_cpu_stats *ip_vs_stats;
- ip_vs_stats = per_cpu_ptr(svc->stats.cpustats, i);
- u64_stats_init(&ip_vs_stats->syncp);
- }
- /* I'm the first user of the service */
- atomic_set(&svc->refcnt, 0);
- svc->af = u->af;
- svc->protocol = u->protocol;
- ip_vs_addr_copy(svc->af, &svc->addr, &u->addr);
- svc->port = u->port;
- svc->fwmark = u->fwmark;
- svc->flags = u->flags;
- svc->timeout = u->timeout * HZ;
- svc->netmask = u->netmask;
- svc->ipvs = ipvs;
- INIT_LIST_HEAD(&svc->destinations);
- spin_lock_init(&svc->sched_lock);
- spin_lock_init(&svc->stats.lock);
- /* Bind the scheduler */
- if (sched) {
- ret = ip_vs_bind_scheduler(svc, sched);
- if (ret)
- goto out_err;
- sched = NULL;
- }
- /* Bind the ct retriever */
- RCU_INIT_POINTER(svc->pe, pe);
- pe = NULL;
- /* Update the virtual service counters */
- if (svc->port == FTPPORT)
- atomic_inc(&ipvs->ftpsvc_counter);
- else if (svc->port == 0)
- atomic_inc(&ipvs->nullsvc_counter);
- ip_vs_start_estimator(ipvs, &svc->stats);
- /* Count only IPv4 services for old get/setsockopt interface */
- if (svc->af == AF_INET)
- ipvs->num_services++;
- /* Hash the service into the service table */
- ip_vs_svc_hash(svc);
- *svc_p = svc;
- /* Now there is a service - full throttle */
- ipvs->enable = 1;
- return 0;
- out_err:
- if (svc != NULL) {
- ip_vs_unbind_scheduler(svc, sched);
- ip_vs_service_free(svc);
- }
- ip_vs_scheduler_put(sched);
- ip_vs_pe_put(pe);
- /* decrease the module use count */
- ip_vs_use_count_dec();
- return ret;
- }
- /*
- * Edit a service and bind it with a new scheduler
- */
- static int
- ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
- {
- struct ip_vs_scheduler *sched = NULL, *old_sched;
- struct ip_vs_pe *pe = NULL, *old_pe = NULL;
- int ret = 0;
- /*
- * Lookup the scheduler, by 'u->sched_name'
- */
- if (strcmp(u->sched_name, "none")) {
- sched = ip_vs_scheduler_get(u->sched_name);
- if (!sched) {
- pr_info("Scheduler module ip_vs_%s not found\n",
- u->sched_name);
- return -ENOENT;
- }
- }
- old_sched = sched;
- if (u->pe_name && *u->pe_name) {
- pe = ip_vs_pe_getbyname(u->pe_name);
- if (pe == NULL) {
- pr_info("persistence engine module ip_vs_pe_%s "
- "not found\n", u->pe_name);
- ret = -ENOENT;
- goto out;
- }
- old_pe = pe;
- }
- #ifdef CONFIG_IP_VS_IPV6
- if (u->af == AF_INET6) {
- __u32 plen = (__force __u32) u->netmask;
- if (plen < 1 || plen > 128) {
- ret = -EINVAL;
- goto out;
- }
- }
- #endif
- old_sched = rcu_dereference_protected(svc->scheduler, 1);
- if (sched != old_sched) {
- if (old_sched) {
- ip_vs_unbind_scheduler(svc, old_sched);
- RCU_INIT_POINTER(svc->scheduler, NULL);
- /* Wait all svc->sched_data users */
- synchronize_rcu();
- }
- /* Bind the new scheduler */
- if (sched) {
- ret = ip_vs_bind_scheduler(svc, sched);
- if (ret) {
- ip_vs_scheduler_put(sched);
- goto out;
- }
- }
- }
- /*
- * Set the flags and timeout value
- */
- svc->flags = u->flags | IP_VS_SVC_F_HASHED;
- svc->timeout = u->timeout * HZ;
- svc->netmask = u->netmask;
- old_pe = rcu_dereference_protected(svc->pe, 1);
- if (pe != old_pe)
- rcu_assign_pointer(svc->pe, pe);
- out:
- ip_vs_scheduler_put(old_sched);
- ip_vs_pe_put(old_pe);
- return ret;
- }
- /*
- * Delete a service from the service list
- * - The service must be unlinked, unlocked and not referenced!
- * - We are called under _bh lock
- */
- static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
- {
- struct ip_vs_dest *dest, *nxt;
- struct ip_vs_scheduler *old_sched;
- struct ip_vs_pe *old_pe;
- struct netns_ipvs *ipvs = svc->ipvs;
- pr_info("%s: enter\n", __func__);
- /* Count only IPv4 services for old get/setsockopt interface */
- if (svc->af == AF_INET)
- ipvs->num_services--;
- ip_vs_stop_estimator(svc->ipvs, &svc->stats);
- /* Unbind scheduler */
- old_sched = rcu_dereference_protected(svc->scheduler, 1);
- ip_vs_unbind_scheduler(svc, old_sched);
- ip_vs_scheduler_put(old_sched);
- /* Unbind persistence engine, keep svc->pe */
- old_pe = rcu_dereference_protected(svc->pe, 1);
- ip_vs_pe_put(old_pe);
- /*
- * Unlink the whole destination list
- */
- list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) {
- __ip_vs_unlink_dest(svc, dest, 0);
- __ip_vs_del_dest(svc->ipvs, dest, cleanup);
- }
- /*
- * Update the virtual service counters
- */
- if (svc->port == FTPPORT)
- atomic_dec(&ipvs->ftpsvc_counter);
- else if (svc->port == 0)
- atomic_dec(&ipvs->nullsvc_counter);
- /*
- * Free the service if nobody refers to it
- */
- __ip_vs_svc_put(svc, true);
- /* decrease the module use count */
- ip_vs_use_count_dec();
- }
- /*
- * Unlink a service from list and try to delete it if its refcnt reached 0
- */
- static void ip_vs_unlink_service(struct ip_vs_service *svc, bool cleanup)
- {
- /* Hold svc to avoid double release from dest_trash */
- atomic_inc(&svc->refcnt);
- /*
- * Unhash it from the service table
- */
- ip_vs_svc_unhash(svc);
- __ip_vs_del_service(svc, cleanup);
- }
- /*
- * Delete a service from the service list
- */
- static int ip_vs_del_service(struct ip_vs_service *svc)
- {
- if (svc == NULL)
- return -EEXIST;
- ip_vs_unlink_service(svc, false);
- return 0;
- }
- /*
- * Flush all the virtual services
- */
- static int ip_vs_flush(struct netns_ipvs *ipvs, bool cleanup)
- {
- int idx;
- struct ip_vs_service *svc;
- struct hlist_node *n;
- /*
- * Flush the service table hashed by <netns,protocol,addr,port>
- */
- for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- hlist_for_each_entry_safe(svc, n, &ip_vs_svc_table[idx],
- s_list) {
- if (svc->ipvs == ipvs)
- ip_vs_unlink_service(svc, cleanup);
- }
- }
- /*
- * Flush the service table hashed by fwmark
- */
- for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- hlist_for_each_entry_safe(svc, n, &ip_vs_svc_fwm_table[idx],
- f_list) {
- if (svc->ipvs == ipvs)
- ip_vs_unlink_service(svc, cleanup);
- }
- }
- return 0;
- }
- /*
- * Delete service by {netns} in the service table.
- * Called by __ip_vs_cleanup()
- */
- void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs)
- {
- EnterFunction(2);
- /* Check for "full" addressed entries */
- mutex_lock(&__ip_vs_mutex);
- ip_vs_flush(ipvs, true);
- mutex_unlock(&__ip_vs_mutex);
- LeaveFunction(2);
- }
- /* Put all references for device (dst_cache) */
- static inline void
- ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev)
- {
- struct ip_vs_dest_dst *dest_dst;
- spin_lock_bh(&dest->dst_lock);
- dest_dst = rcu_dereference_protected(dest->dest_dst, 1);
- if (dest_dst && dest_dst->dst_cache->dev == dev) {
- IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n",
- dev->name,
- IP_VS_DBG_ADDR(dest->af, &dest->addr),
- ntohs(dest->port),
- atomic_read(&dest->refcnt));
- __ip_vs_dst_cache_reset(dest);
- }
- spin_unlock_bh(&dest->dst_lock);
- }
- /* Netdev event receiver
- * Currently only NETDEV_DOWN is handled to release refs to cached dsts
- */
- static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
- void *ptr)
- {
- struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- struct net *net = dev_net(dev);
- struct netns_ipvs *ipvs = net_ipvs(net);
- struct ip_vs_service *svc;
- struct ip_vs_dest *dest;
- unsigned int idx;
- if (event != NETDEV_DOWN || !ipvs)
- return NOTIFY_DONE;
- IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name);
- EnterFunction(2);
- mutex_lock(&__ip_vs_mutex);
- for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
- if (svc->ipvs == ipvs) {
- list_for_each_entry(dest, &svc->destinations,
- n_list) {
- ip_vs_forget_dev(dest, dev);
- }
- }
- }
- hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
- if (svc->ipvs == ipvs) {
- list_for_each_entry(dest, &svc->destinations,
- n_list) {
- ip_vs_forget_dev(dest, dev);
- }
- }
- }
- }
- spin_lock_bh(&ipvs->dest_trash_lock);
- list_for_each_entry(dest, &ipvs->dest_trash, t_list) {
- ip_vs_forget_dev(dest, dev);
- }
- spin_unlock_bh(&ipvs->dest_trash_lock);
- mutex_unlock(&__ip_vs_mutex);
- LeaveFunction(2);
- return NOTIFY_DONE;
- }
- /*
- * Zero counters in a service or all services
- */
- static int ip_vs_zero_service(struct ip_vs_service *svc)
- {
- struct ip_vs_dest *dest;
- list_for_each_entry(dest, &svc->destinations, n_list) {
- ip_vs_zero_stats(&dest->stats);
- }
- ip_vs_zero_stats(&svc->stats);
- return 0;
- }
- static int ip_vs_zero_all(struct netns_ipvs *ipvs)
- {
- int idx;
- struct ip_vs_service *svc;
- for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
- if (svc->ipvs == ipvs)
- ip_vs_zero_service(svc);
- }
- }
- for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
- if (svc->ipvs == ipvs)
- ip_vs_zero_service(svc);
- }
- }
- ip_vs_zero_stats(&ipvs->tot_stats);
- return 0;
- }
- #ifdef CONFIG_SYSCTL
- static int zero;
- static int three = 3;
- static int
- proc_do_defense_mode(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
- {
- struct netns_ipvs *ipvs = table->extra2;
- int *valp = table->data;
- int val = *valp;
- int rc;
- rc = proc_dointvec(table, write, buffer, lenp, ppos);
- if (write && (*valp != val)) {
- if ((*valp < 0) || (*valp > 3)) {
- /* Restore the correct value */
- *valp = val;
- } else {
- update_defense_level(ipvs);
- }
- }
- return rc;
- }
- static int
- proc_do_sync_threshold(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
- {
- int *valp = table->data;
- int val[2];
- int rc;
- /* backup the value first */
- memcpy(val, valp, sizeof(val));
- rc = proc_dointvec(table, write, buffer, lenp, ppos);
- if (write && (valp[0] < 0 || valp[1] < 0 ||
- (valp[0] >= valp[1] && valp[1]))) {
- /* Restore the correct value */
- memcpy(valp, val, sizeof(val));
- }
- return rc;
- }
- static int
- proc_do_sync_mode(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
- {
- int *valp = table->data;
- int val = *valp;
- int rc;
- rc = proc_dointvec(table, write, buffer, lenp, ppos);
- if (write && (*valp != val)) {
- if ((*valp < 0) || (*valp > 1)) {
- /* Restore the correct value */
- *valp = val;
- }
- }
- return rc;
- }
- static int
- proc_do_sync_ports(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
- {
- int *valp = table->data;
- int val = *valp;
- int rc;
- rc = proc_dointvec(table, write, buffer, lenp, ppos);
- if (write && (*valp != val)) {
- if (*valp < 1 || !is_power_of_2(*valp)) {
- /* Restore the correct value */
- *valp = val;
- }
- }
- return rc;
- }
- /*
- * IPVS sysctl table (under the /proc/sys/net/ipv4/vs/)
- * Do not change order or insert new entries without
- * align with netns init in ip_vs_control_net_init()
- */
- static struct ctl_table vs_vars[] = {
- {
- .procname = "amemthresh",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "am_droprate",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "drop_entry",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_do_defense_mode,
- },
- {
- .procname = "drop_packet",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_do_defense_mode,
- },
- #ifdef CONFIG_IP_VS_NFCT
- {
- .procname = "conntrack",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- #endif
- {
- .procname = "secure_tcp",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_do_defense_mode,
- },
- {
- .procname = "snat_reroute",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec,
- },
- {
- .procname = "sync_version",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_do_sync_mode,
- },
- {
- .procname = "sync_ports",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_do_sync_ports,
- },
- {
- .procname = "sync_persist_mode",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "sync_qlen_max",
- .maxlen = sizeof(unsigned long),
- .mode = 0644,
- .proc_handler = proc_doulongvec_minmax,
- },
- {
- .procname = "sync_sock_size",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "cache_bypass",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "expire_nodest_conn",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "sloppy_tcp",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "sloppy_sctp",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "expire_quiescent_template",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "sync_threshold",
- .maxlen =
- sizeof(((struct netns_ipvs *)0)->sysctl_sync_threshold),
- .mode = 0644,
- .proc_handler = proc_do_sync_threshold,
- },
- {
- .procname = "sync_refresh_period",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
- {
- .procname = "sync_retries",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &three,
- },
- {
- .procname = "nat_icmp_send",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "pmtu_disc",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "backup_only",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "conn_reuse_mode",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "schedule_icmp",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "ignore_tunneled",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- #ifdef CONFIG_IP_VS_DEBUG
- {
- .procname = "debug_level",
- .data = &sysctl_ip_vs_debug_level,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- #endif
- { }
- };
- #endif
- #ifdef CONFIG_PROC_FS
- struct ip_vs_iter {
- struct seq_net_private p; /* Do not move this, netns depends upon it*/
- struct hlist_head *table;
- int bucket;
- };
- /*
- * Write the contents of the VS rule table to a PROCfs file.
- * (It is kept just for backward compatibility)
- */
- static inline const char *ip_vs_fwd_name(unsigned int flags)
- {
- switch (flags & IP_VS_CONN_F_FWD_MASK) {
- case IP_VS_CONN_F_LOCALNODE:
- return "Local";
- case IP_VS_CONN_F_TUNNEL:
- return "Tunnel";
- case IP_VS_CONN_F_DROUTE:
- return "Route";
- default:
- return "Masq";
- }
- }
- /* Get the Nth entry in the two lists */
- static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
- {
- struct net *net = seq_file_net(seq);
- struct netns_ipvs *ipvs = net_ipvs(net);
- struct ip_vs_iter *iter = seq->private;
- int idx;
- struct ip_vs_service *svc;
- /* look in hash by protocol */
- for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[idx], s_list) {
- if ((svc->ipvs == ipvs) && pos-- == 0) {
- iter->table = ip_vs_svc_table;
- iter->bucket = idx;
- return svc;
- }
- }
- }
- /* keep looking in fwmark */
- for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[idx],
- f_list) {
- if ((svc->ipvs == ipvs) && pos-- == 0) {
- iter->table = ip_vs_svc_fwm_table;
- iter->bucket = idx;
- return svc;
- }
- }
- }
- return NULL;
- }
- static void *ip_vs_info_seq_start(struct seq_file *seq, loff_t *pos)
- __acquires(RCU)
- {
- rcu_read_lock();
- return *pos ? ip_vs_info_array(seq, *pos - 1) : SEQ_START_TOKEN;
- }
- static void *ip_vs_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
- {
- struct hlist_node *e;
- struct ip_vs_iter *iter;
- struct ip_vs_service *svc;
- ++*pos;
- if (v == SEQ_START_TOKEN)
- return ip_vs_info_array(seq,0);
- svc = v;
- iter = seq->private;
- if (iter->table == ip_vs_svc_table) {
- /* next service in table hashed by protocol */
- e = rcu_dereference(hlist_next_rcu(&svc->s_list));
- if (e)
- return hlist_entry(e, struct ip_vs_service, s_list);
- while (++iter->bucket < IP_VS_SVC_TAB_SIZE) {
- hlist_for_each_entry_rcu(svc,
- &ip_vs_svc_table[iter->bucket],
- s_list) {
- return svc;
- }
- }
- iter->table = ip_vs_svc_fwm_table;
- iter->bucket = -1;
- goto scan_fwmark;
- }
- /* next service in hashed by fwmark */
- e = rcu_dereference(hlist_next_rcu(&svc->f_list));
- if (e)
- return hlist_entry(e, struct ip_vs_service, f_list);
- scan_fwmark:
- while (++iter->bucket < IP_VS_SVC_TAB_SIZE) {
- hlist_for_each_entry_rcu(svc,
- &ip_vs_svc_fwm_table[iter->bucket],
- f_list)
- return svc;
- }
- return NULL;
- }
- static void ip_vs_info_seq_stop(struct seq_file *seq, void *v)
- __releases(RCU)
- {
- rcu_read_unlock();
- }
- static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
- {
- if (v == SEQ_START_TOKEN) {
- seq_printf(seq,
- "IP Virtual Server version %d.%d.%d (size=%d)\n",
- NVERSION(IP_VS_VERSION_CODE), ip_vs_conn_tab_size);
- seq_puts(seq,
- "Prot LocalAddress:Port Scheduler Flags\n");
- seq_puts(seq,
- " -> RemoteAddress:Port Forward Weight ActiveConn InActConn\n");
- } else {
- struct net *net = seq_file_net(seq);
- struct netns_ipvs *ipvs = net_ipvs(net);
- const struct ip_vs_service *svc = v;
- const struct ip_vs_iter *iter = seq->private;
- const struct ip_vs_dest *dest;
- struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
- char *sched_name = sched ? sched->name : "none";
- if (svc->ipvs != ipvs)
- return 0;
- if (iter->table == ip_vs_svc_table) {
- #ifdef CONFIG_IP_VS_IPV6
- if (svc->af == AF_INET6)
- seq_printf(seq, "%s [%pI6]:%04X %s ",
- ip_vs_proto_name(svc->protocol),
- &svc->addr.in6,
- ntohs(svc->port),
- sched_name);
- else
- #endif
- seq_printf(seq, "%s %08X:%04X %s %s ",
- ip_vs_proto_name(svc->protocol),
- ntohl(svc->addr.ip),
- ntohs(svc->port),
- sched_name,
- (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
- } else {
- seq_printf(seq, "FWM %08X %s %s",
- svc->fwmark, sched_name,
- (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
- }
- if (svc->flags & IP_VS_SVC_F_PERSISTENT)
- seq_printf(seq, "persistent %d %08X\n",
- svc->timeout,
- ntohl(svc->netmask));
- else
- seq_putc(seq, '\n');
- list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
- #ifdef CONFIG_IP_VS_IPV6
- if (dest->af == AF_INET6)
- seq_printf(seq,
- " -> [%pI6]:%04X"
- " %-7s %-6d %-10d %-10d\n",
- &dest->addr.in6,
- ntohs(dest->port),
- ip_vs_fwd_name(atomic_read(&dest->conn_flags)),
- atomic_read(&dest->weight),
- atomic_read(&dest->activeconns),
- atomic_read(&dest->inactconns));
- else
- #endif
- seq_printf(seq,
- " -> %08X:%04X "
- "%-7s %-6d %-10d %-10d\n",
- ntohl(dest->addr.ip),
- ntohs(dest->port),
- ip_vs_fwd_name(atomic_read(&dest->conn_flags)),
- atomic_read(&dest->weight),
- atomic_read(&dest->activeconns),
- atomic_read(&dest->inactconns));
- }
- }
- return 0;
- }
- static const struct seq_operations ip_vs_info_seq_ops = {
- .start = ip_vs_info_seq_start,
- .next = ip_vs_info_seq_next,
- .stop = ip_vs_info_seq_stop,
- .show = ip_vs_info_seq_show,
- };
- static int ip_vs_info_open(struct inode *inode, struct file *file)
- {
- return seq_open_net(inode, file, &ip_vs_info_seq_ops,
- sizeof(struct ip_vs_iter));
- }
- static const struct file_operations ip_vs_info_fops = {
- .owner = THIS_MODULE,
- .open = ip_vs_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
- };
- static int ip_vs_stats_show(struct seq_file *seq, void *v)
- {
- struct net *net = seq_file_single_net(seq);
- struct ip_vs_kstats show;
- /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */
- seq_puts(seq,
- " Total Incoming Outgoing Incoming Outgoing\n");
- seq_printf(seq,
- " Conns Packets Packets Bytes Bytes\n");
- ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats);
- seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n\n",
- (unsigned long long)show.conns,
- (unsigned long long)show.inpkts,
- (unsigned long long)show.outpkts,
- (unsigned long long)show.inbytes,
- (unsigned long long)show.outbytes);
- /* 01234567 01234567 01234567 0123456701234567 0123456701234567*/
- seq_puts(seq,
- " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n");
- seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n",
- (unsigned long long)show.cps,
- (unsigned long long)show.inpps,
- (unsigned long long)show.outpps,
- (unsigned long long)show.inbps,
- (unsigned long long)show.outbps);
- return 0;
- }
- static int ip_vs_stats_seq_open(struct inode *inode, struct file *file)
- {
- return single_open_net(inode, file, ip_vs_stats_show);
- }
- static const struct file_operations ip_vs_stats_fops = {
- .owner = THIS_MODULE,
- .open = ip_vs_stats_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
- };
- static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
- {
- struct net *net = seq_file_single_net(seq);
- struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
- struct ip_vs_cpu_stats __percpu *cpustats = tot_stats->cpustats;
- struct ip_vs_kstats kstats;
- int i;
- /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */
- seq_puts(seq,
- " Total Incoming Outgoing Incoming Outgoing\n");
- seq_printf(seq,
- "CPU Conns Packets Packets Bytes Bytes\n");
- for_each_possible_cpu(i) {
- struct ip_vs_cpu_stats *u = per_cpu_ptr(cpustats, i);
- unsigned int start;
- u64 conns, inpkts, outpkts, inbytes, outbytes;
- do {
- start = u64_stats_fetch_begin_irq(&u->syncp);
- conns = u->cnt.conns;
- inpkts = u->cnt.inpkts;
- outpkts = u->cnt.outpkts;
- inbytes = u->cnt.inbytes;
- outbytes = u->cnt.outbytes;
- } while (u64_stats_fetch_retry_irq(&u->syncp, start));
- seq_printf(seq, "%3X %8LX %8LX %8LX %16LX %16LX\n",
- i, (u64)conns, (u64)inpkts,
- (u64)outpkts, (u64)inbytes,
- (u64)outbytes);
- }
- ip_vs_copy_stats(&kstats, tot_stats);
- seq_printf(seq, " ~ %8LX %8LX %8LX %16LX %16LX\n\n",
- (unsigned long long)kstats.conns,
- (unsigned long long)kstats.inpkts,
- (unsigned long long)kstats.outpkts,
- (unsigned long long)kstats.inbytes,
- (unsigned long long)kstats.outbytes);
- /* ... 01234567 01234567 01234567 0123456701234567 0123456701234567 */
- seq_puts(seq,
- " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n");
- seq_printf(seq, " %8LX %8LX %8LX %16LX %16LX\n",
- kstats.cps,
- kstats.inpps,
- kstats.outpps,
- kstats.inbps,
- kstats.outbps);
- return 0;
- }
- static int ip_vs_stats_percpu_seq_open(struct inode *inode, struct file *file)
- {
- return single_open_net(inode, file, ip_vs_stats_percpu_show);
- }
- static const struct file_operations ip_vs_stats_percpu_fops = {
- .owner = THIS_MODULE,
- .open = ip_vs_stats_percpu_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
- };
- #endif
- /*
- * Set timeout values for tcp tcpfin udp in the timeout_table.
- */
- static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user *u)
- {
- #if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP)
- struct ip_vs_proto_data *pd;
- #endif
- IP_VS_DBG(2, "Setting timeout tcp:%d tcpfin:%d udp:%d\n",
- u->tcp_timeout,
- u->tcp_fin_timeout,
- u->udp_timeout);
- #ifdef CONFIG_IP_VS_PROTO_TCP
- if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) ||
- u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) {
- return -EINVAL;
- }
- #endif
- #ifdef CONFIG_IP_VS_PROTO_UDP
- if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ))
- return -EINVAL;
- #endif
- #ifdef CONFIG_IP_VS_PROTO_TCP
- if (u->tcp_timeout) {
- pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
- pd->timeout_table[IP_VS_TCP_S_ESTABLISHED]
- = u->tcp_timeout * HZ;
- }
- if (u->tcp_fin_timeout) {
- pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
- pd->timeout_table[IP_VS_TCP_S_FIN_WAIT]
- = u->tcp_fin_timeout * HZ;
- }
- #endif
- #ifdef CONFIG_IP_VS_PROTO_UDP
- if (u->udp_timeout) {
- pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP);
- pd->timeout_table[IP_VS_UDP_S_NORMAL]
- = u->udp_timeout * HZ;
- }
- #endif
- return 0;
- }
- #define CMDID(cmd) (cmd - IP_VS_BASE_CTL)
- struct ip_vs_svcdest_user {
- struct ip_vs_service_user s;
- struct ip_vs_dest_user d;
- };
- static const unsigned char set_arglen[CMDID(IP_VS_SO_SET_MAX) + 1] = {
- [CMDID(IP_VS_SO_SET_ADD)] = sizeof(struct ip_vs_service_user),
- [CMDID(IP_VS_SO_SET_EDIT)] = sizeof(struct ip_vs_service_user),
- [CMDID(IP_VS_SO_SET_DEL)] = sizeof(struct ip_vs_service_user),
- [CMDID(IP_VS_SO_SET_ADDDEST)] = sizeof(struct ip_vs_svcdest_user),
- [CMDID(IP_VS_SO_SET_DELDEST)] = sizeof(struct ip_vs_svcdest_user),
- [CMDID(IP_VS_SO_SET_EDITDEST)] = sizeof(struct ip_vs_svcdest_user),
- [CMDID(IP_VS_SO_SET_TIMEOUT)] = sizeof(struct ip_vs_timeout_user),
- [CMDID(IP_VS_SO_SET_STARTDAEMON)] = sizeof(struct ip_vs_daemon_user),
- [CMDID(IP_VS_SO_SET_STOPDAEMON)] = sizeof(struct ip_vs_daemon_user),
- [CMDID(IP_VS_SO_SET_ZERO)] = sizeof(struct ip_vs_service_user),
- };
- union ip_vs_set_arglen {
- struct ip_vs_service_user field_IP_VS_SO_SET_ADD;
- struct ip_vs_service_user field_IP_VS_SO_SET_EDIT;
- struct ip_vs_service_user field_IP_VS_SO_SET_DEL;
- struct ip_vs_svcdest_user field_IP_VS_SO_SET_ADDDEST;
- struct ip_vs_svcdest_user field_IP_VS_SO_SET_DELDEST;
- struct ip_vs_svcdest_user field_IP_VS_SO_SET_EDITDEST;
- struct ip_vs_timeout_user field_IP_VS_SO_SET_TIMEOUT;
- struct ip_vs_daemon_user field_IP_VS_SO_SET_STARTDAEMON;
- struct ip_vs_daemon_user field_IP_VS_SO_SET_STOPDAEMON;
- struct ip_vs_service_user field_IP_VS_SO_SET_ZERO;
- };
- #define MAX_SET_ARGLEN sizeof(union ip_vs_set_arglen)
- static void ip_vs_copy_usvc_compat(struct ip_vs_service_user_kern *usvc,
- struct ip_vs_service_user *usvc_compat)
- {
- memset(usvc, 0, sizeof(*usvc));
- usvc->af = AF_INET;
- usvc->protocol = usvc_compat->protocol;
- usvc->addr.ip = usvc_compat->addr;
- usvc->port = usvc_compat->port;
- usvc->fwmark = usvc_compat->fwmark;
- /* Deep copy of sched_name is not needed here */
- usvc->sched_name = usvc_compat->sched_name;
- usvc->flags = usvc_compat->flags;
- usvc->timeout = usvc_compat->timeout;
- usvc->netmask = usvc_compat->netmask;
- }
- static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest,
- struct ip_vs_dest_user *udest_compat)
- {
- memset(udest, 0, sizeof(*udest));
- udest->addr.ip = udest_compat->addr;
- udest->port = udest_compat->port;
- udest->conn_flags = udest_compat->conn_flags;
- udest->weight = udest_compat->weight;
- udest->u_threshold = udest_compat->u_threshold;
- udest->l_threshold = udest_compat->l_threshold;
- udest->af = AF_INET;
- }
- static int
- do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
- {
- struct net *net = sock_net(sk);
- int ret;
- unsigned char arg[MAX_SET_ARGLEN];
- struct ip_vs_service_user *usvc_compat;
- struct ip_vs_service_user_kern usvc;
- struct ip_vs_service *svc;
- struct ip_vs_dest_user *udest_compat;
- struct ip_vs_dest_user_kern udest;
- struct netns_ipvs *ipvs = net_ipvs(net);
- BUILD_BUG_ON(sizeof(arg) > 255);
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
- return -EPERM;
- if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_SET_MAX)
- return -EINVAL;
- if (len != set_arglen[CMDID(cmd)]) {
- IP_VS_DBG(1, "set_ctl: len %u != %u\n",
- len, set_arglen[CMDID(cmd)]);
- return -EINVAL;
- }
- if (copy_from_user(arg, user, len) != 0)
- return -EFAULT;
- /* increase the module use count */
- ip_vs_use_count_inc();
- /* Handle daemons since they have another lock */
- if (cmd == IP_VS_SO_SET_STARTDAEMON ||
- cmd == IP_VS_SO_SET_STOPDAEMON) {
- struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
- if (cmd == IP_VS_SO_SET_STARTDAEMON) {
- struct ipvs_sync_daemon_cfg cfg;
- memset(&cfg, 0, sizeof(cfg));
- ret = -EINVAL;
- if (strscpy(cfg.mcast_ifn, dm->mcast_ifn,
- sizeof(cfg.mcast_ifn)) <= 0)
- goto out_dec;
- cfg.syncid = dm->syncid;
- ret = start_sync_thread(ipvs, &cfg, dm->state);
- } else {
- mutex_lock(&ipvs->sync_mutex);
- ret = stop_sync_thread(ipvs, dm->state);
- mutex_unlock(&ipvs->sync_mutex);
- }
- goto out_dec;
- }
- mutex_lock(&__ip_vs_mutex);
- if (cmd == IP_VS_SO_SET_FLUSH) {
- /* Flush the virtual service */
- ret = ip_vs_flush(ipvs, false);
- goto out_unlock;
- } else if (cmd == IP_VS_SO_SET_TIMEOUT) {
- /* Set timeout values for (tcp tcpfin udp) */
- ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg);
- goto out_unlock;
- }
- usvc_compat = (struct ip_vs_service_user *)arg;
- udest_compat = (struct ip_vs_dest_user *)(usvc_compat + 1);
- /* We only use the new structs internally, so copy userspace compat
- * structs to extended internal versions */
- ip_vs_copy_usvc_compat(&usvc, usvc_compat);
- ip_vs_copy_udest_compat(&udest, udest_compat);
- if (cmd == IP_VS_SO_SET_ZERO) {
- /* if no service address is set, zero counters in all */
- if (!usvc.fwmark && !usvc.addr.ip && !usvc.port) {
- ret = ip_vs_zero_all(ipvs);
- goto out_unlock;
- }
- }
- if ((cmd == IP_VS_SO_SET_ADD || cmd == IP_VS_SO_SET_EDIT) &&
- strnlen(usvc.sched_name, IP_VS_SCHEDNAME_MAXLEN) ==
- IP_VS_SCHEDNAME_MAXLEN) {
- ret = -EINVAL;
- goto out_unlock;
- }
- /* Check for valid protocol: TCP or UDP or SCTP, even for fwmark!=0 */
- if (usvc.protocol != IPPROTO_TCP && usvc.protocol != IPPROTO_UDP &&
- usvc.protocol != IPPROTO_SCTP) {
- pr_err("set_ctl: invalid protocol: %d %pI4:%d\n",
- usvc.protocol, &usvc.addr.ip,
- ntohs(usvc.port));
- ret = -EFAULT;
- goto out_unlock;
- }
- /* Lookup the exact service by <protocol, addr, port> or fwmark */
- rcu_read_lock();
- if (usvc.fwmark == 0)
- svc = __ip_vs_service_find(ipvs, usvc.af, usvc.protocol,
- &usvc.addr, usvc.port);
- else
- svc = __ip_vs_svc_fwm_find(ipvs, usvc.af, usvc.fwmark);
- rcu_read_unlock();
- if (cmd != IP_VS_SO_SET_ADD
- && (svc == NULL || svc->protocol != usvc.protocol)) {
- ret = -ESRCH;
- goto out_unlock;
- }
- switch (cmd) {
- case IP_VS_SO_SET_ADD:
- if (svc != NULL)
- ret = -EEXIST;
- else
- ret = ip_vs_add_service(ipvs, &usvc, &svc);
- break;
- case IP_VS_SO_SET_EDIT:
- ret = ip_vs_edit_service(svc, &usvc);
- break;
- case IP_VS_SO_SET_DEL:
- ret = ip_vs_del_service(svc);
- if (!ret)
- goto out_unlock;
- break;
- case IP_VS_SO_SET_ZERO:
- ret = ip_vs_zero_service(svc);
- break;
- case IP_VS_SO_SET_ADDDEST:
- ret = ip_vs_add_dest(svc, &udest);
- break;
- case IP_VS_SO_SET_EDITDEST:
- ret = ip_vs_edit_dest(svc, &udest);
- break;
- case IP_VS_SO_SET_DELDEST:
- ret = ip_vs_del_dest(svc, &udest);
- break;
- default:
- ret = -EINVAL;
- }
- out_unlock:
- mutex_unlock(&__ip_vs_mutex);
- out_dec:
- /* decrease the module use count */
- ip_vs_use_count_dec();
- return ret;
- }
- static void
- ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
- {
- struct ip_vs_scheduler *sched;
- struct ip_vs_kstats kstats;
- char *sched_name;
- sched = rcu_dereference_protected(src->scheduler, 1);
- sched_name = sched ? sched->name : "none";
- dst->protocol = src->protocol;
- dst->addr = src->addr.ip;
- dst->port = src->port;
- dst->fwmark = src->fwmark;
- strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name));
- dst->flags = src->flags;
- dst->timeout = src->timeout / HZ;
- dst->netmask = src->netmask;
- dst->num_dests = src->num_dests;
- ip_vs_copy_stats(&kstats, &src->stats);
- ip_vs_export_stats_user(&dst->stats, &kstats);
- }
- static inline int
- __ip_vs_get_service_entries(struct netns_ipvs *ipvs,
- const struct ip_vs_get_services *get,
- struct ip_vs_get_services __user *uptr)
- {
- int idx, count=0;
- struct ip_vs_service *svc;
- struct ip_vs_service_entry entry;
- int ret = 0;
- for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
- /* Only expose IPv4 entries to old interface */
- if (svc->af != AF_INET || (svc->ipvs != ipvs))
- continue;
- if (count >= get->num_services)
- goto out;
- memset(&entry, 0, sizeof(entry));
- ip_vs_copy_service(&entry, svc);
- if (copy_to_user(&uptr->entrytable[count],
- &entry, sizeof(entry))) {
- ret = -EFAULT;
- goto out;
- }
- count++;
- }
- }
- for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
- /* Only expose IPv4 entries to old interface */
- if (svc->af != AF_INET || (svc->ipvs != ipvs))
- continue;
- if (count >= get->num_services)
- goto out;
- memset(&entry, 0, sizeof(entry));
- ip_vs_copy_service(&entry, svc);
- if (copy_to_user(&uptr->entrytable[count],
- &entry, sizeof(entry))) {
- ret = -EFAULT;
- goto out;
- }
- count++;
- }
- }
- out:
- return ret;
- }
- static inline int
- __ip_vs_get_dest_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_dests *get,
- struct ip_vs_get_dests __user *uptr)
- {
- struct ip_vs_service *svc;
- union nf_inet_addr addr = { .ip = get->addr };
- int ret = 0;
- rcu_read_lock();
- if (get->fwmark)
- svc = __ip_vs_svc_fwm_find(ipvs, AF_INET, get->fwmark);
- else
- svc = __ip_vs_service_find(ipvs, AF_INET, get->protocol, &addr,
- get->port);
- rcu_read_unlock();
- if (svc) {
- int count = 0;
- struct ip_vs_dest *dest;
- struct ip_vs_dest_entry entry;
- struct ip_vs_kstats kstats;
- memset(&entry, 0, sizeof(entry));
- list_for_each_entry(dest, &svc->destinations, n_list) {
- if (count >= get->num_dests)
- break;
- /* Cannot expose heterogeneous members via sockopt
- * interface
- */
- if (dest->af != svc->af)
- continue;
- entry.addr = dest->addr.ip;
- entry.port = dest->port;
- entry.conn_flags = atomic_read(&dest->conn_flags);
- entry.weight = atomic_read(&dest->weight);
- entry.u_threshold = dest->u_threshold;
- entry.l_threshold = dest->l_threshold;
- entry.activeconns = atomic_read(&dest->activeconns);
- entry.inactconns = atomic_read(&dest->inactconns);
- entry.persistconns = atomic_read(&dest->persistconns);
- ip_vs_copy_stats(&kstats, &dest->stats);
- ip_vs_export_stats_user(&entry.stats, &kstats);
- if (copy_to_user(&uptr->entrytable[count],
- &entry, sizeof(entry))) {
- ret = -EFAULT;
- break;
- }
- count++;
- }
- } else
- ret = -ESRCH;
- return ret;
- }
- static inline void
- __ip_vs_get_timeouts(struct netns_ipvs *ipvs, struct ip_vs_timeout_user *u)
- {
- #if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP)
- struct ip_vs_proto_data *pd;
- #endif
- memset(u, 0, sizeof (*u));
- #ifdef CONFIG_IP_VS_PROTO_TCP
- pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
- u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ;
- u->tcp_fin_timeout = pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ;
- #endif
- #ifdef CONFIG_IP_VS_PROTO_UDP
- pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP);
- u->udp_timeout =
- pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ;
- #endif
- }
- static const unsigned char get_arglen[CMDID(IP_VS_SO_GET_MAX) + 1] = {
- [CMDID(IP_VS_SO_GET_VERSION)] = 64,
- [CMDID(IP_VS_SO_GET_INFO)] = sizeof(struct ip_vs_getinfo),
- [CMDID(IP_VS_SO_GET_SERVICES)] = sizeof(struct ip_vs_get_services),
- [CMDID(IP_VS_SO_GET_SERVICE)] = sizeof(struct ip_vs_service_entry),
- [CMDID(IP_VS_SO_GET_DESTS)] = sizeof(struct ip_vs_get_dests),
- [CMDID(IP_VS_SO_GET_TIMEOUT)] = sizeof(struct ip_vs_timeout_user),
- [CMDID(IP_VS_SO_GET_DAEMON)] = 2 * sizeof(struct ip_vs_daemon_user),
- };
- union ip_vs_get_arglen {
- char field_IP_VS_SO_GET_VERSION[64];
- struct ip_vs_getinfo field_IP_VS_SO_GET_INFO;
- struct ip_vs_get_services field_IP_VS_SO_GET_SERVICES;
- struct ip_vs_service_entry field_IP_VS_SO_GET_SERVICE;
- struct ip_vs_get_dests field_IP_VS_SO_GET_DESTS;
- struct ip_vs_timeout_user field_IP_VS_SO_GET_TIMEOUT;
- struct ip_vs_daemon_user field_IP_VS_SO_GET_DAEMON[2];
- };
- #define MAX_GET_ARGLEN sizeof(union ip_vs_get_arglen)
- static int
- do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
- {
- unsigned char arg[MAX_GET_ARGLEN];
- int ret = 0;
- unsigned int copylen;
- struct net *net = sock_net(sk);
- struct netns_ipvs *ipvs = net_ipvs(net);
- BUG_ON(!net);
- BUILD_BUG_ON(sizeof(arg) > 255);
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
- return -EPERM;
- if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_GET_MAX)
- return -EINVAL;
- copylen = get_arglen[CMDID(cmd)];
- if (*len < (int) copylen) {
- IP_VS_DBG(1, "get_ctl: len %d < %u\n", *len, copylen);
- return -EINVAL;
- }
- if (copy_from_user(arg, user, copylen) != 0)
- return -EFAULT;
- /*
- * Handle daemons first since it has its own locking
- */
- if (cmd == IP_VS_SO_GET_DAEMON) {
- struct ip_vs_daemon_user d[2];
- memset(&d, 0, sizeof(d));
- mutex_lock(&ipvs->sync_mutex);
- if (ipvs->sync_state & IP_VS_STATE_MASTER) {
- d[0].state = IP_VS_STATE_MASTER;
- strlcpy(d[0].mcast_ifn, ipvs->mcfg.mcast_ifn,
- sizeof(d[0].mcast_ifn));
- d[0].syncid = ipvs->mcfg.syncid;
- }
- if (ipvs->sync_state & IP_VS_STATE_BACKUP) {
- d[1].state = IP_VS_STATE_BACKUP;
- strlcpy(d[1].mcast_ifn, ipvs->bcfg.mcast_ifn,
- sizeof(d[1].mcast_ifn));
- d[1].syncid = ipvs->bcfg.syncid;
- }
- if (copy_to_user(user, &d, sizeof(d)) != 0)
- ret = -EFAULT;
- mutex_unlock(&ipvs->sync_mutex);
- return ret;
- }
- mutex_lock(&__ip_vs_mutex);
- switch (cmd) {
- case IP_VS_SO_GET_VERSION:
- {
- char buf[64];
- sprintf(buf, "IP Virtual Server version %d.%d.%d (size=%d)",
- NVERSION(IP_VS_VERSION_CODE), ip_vs_conn_tab_size);
- if (copy_to_user(user, buf, strlen(buf)+1) != 0) {
- ret = -EFAULT;
- goto out;
- }
- *len = strlen(buf)+1;
- }
- break;
- case IP_VS_SO_GET_INFO:
- {
- struct ip_vs_getinfo info;
- info.version = IP_VS_VERSION_CODE;
- info.size = ip_vs_conn_tab_size;
- info.num_services = ipvs->num_services;
- if (copy_to_user(user, &info, sizeof(info)) != 0)
- ret = -EFAULT;
- }
- break;
- case IP_VS_SO_GET_SERVICES:
- {
- struct ip_vs_get_services *get;
- int size;
- get = (struct ip_vs_get_services *)arg;
- size = sizeof(*get) +
- sizeof(struct ip_vs_service_entry) * get->num_services;
- if (*len != size) {
- pr_err("length: %u != %u\n", *len, size);
- ret = -EINVAL;
- goto out;
- }
- ret = __ip_vs_get_service_entries(ipvs, get, user);
- }
- break;
- case IP_VS_SO_GET_SERVICE:
- {
- struct ip_vs_service_entry *entry;
- struct ip_vs_service *svc;
- union nf_inet_addr addr;
- entry = (struct ip_vs_service_entry *)arg;
- addr.ip = entry->addr;
- rcu_read_lock();
- if (entry->fwmark)
- svc = __ip_vs_svc_fwm_find(ipvs, AF_INET, entry->fwmark);
- else
- svc = __ip_vs_service_find(ipvs, AF_INET,
- entry->protocol, &addr,
- entry->port);
- rcu_read_unlock();
- if (svc) {
- ip_vs_copy_service(entry, svc);
- if (copy_to_user(user, entry, sizeof(*entry)) != 0)
- ret = -EFAULT;
- } else
- ret = -ESRCH;
- }
- break;
- case IP_VS_SO_GET_DESTS:
- {
- struct ip_vs_get_dests *get;
- int size;
- get = (struct ip_vs_get_dests *)arg;
- size = sizeof(*get) +
- sizeof(struct ip_vs_dest_entry) * get->num_dests;
- if (*len != size) {
- pr_err("length: %u != %u\n", *len, size);
- ret = -EINVAL;
- goto out;
- }
- ret = __ip_vs_get_dest_entries(ipvs, get, user);
- }
- break;
- case IP_VS_SO_GET_TIMEOUT:
- {
- struct ip_vs_timeout_user t;
- __ip_vs_get_timeouts(ipvs, &t);
- if (copy_to_user(user, &t, sizeof(t)) != 0)
- ret = -EFAULT;
- }
- break;
- default:
- ret = -EINVAL;
- }
- out:
- mutex_unlock(&__ip_vs_mutex);
- return ret;
- }
- static struct nf_sockopt_ops ip_vs_sockopts = {
- .pf = PF_INET,
- .set_optmin = IP_VS_BASE_CTL,
- .set_optmax = IP_VS_SO_SET_MAX+1,
- .set = do_ip_vs_set_ctl,
- .get_optmin = IP_VS_BASE_CTL,
- .get_optmax = IP_VS_SO_GET_MAX+1,
- .get = do_ip_vs_get_ctl,
- .owner = THIS_MODULE,
- };
- /*
- * Generic Netlink interface
- */
- /* IPVS genetlink family */
- static struct genl_family ip_vs_genl_family = {
- .id = GENL_ID_GENERATE,
- .hdrsize = 0,
- .name = IPVS_GENL_NAME,
- .version = IPVS_GENL_VERSION,
- .maxattr = IPVS_CMD_MAX,
- .netnsok = true, /* Make ipvsadm to work on netns */
- };
- /* Policy used for first-level command attributes */
- static const struct nla_policy ip_vs_cmd_policy[IPVS_CMD_ATTR_MAX + 1] = {
- [IPVS_CMD_ATTR_SERVICE] = { .type = NLA_NESTED },
- [IPVS_CMD_ATTR_DEST] = { .type = NLA_NESTED },
- [IPVS_CMD_ATTR_DAEMON] = { .type = NLA_NESTED },
- [IPVS_CMD_ATTR_TIMEOUT_TCP] = { .type = NLA_U32 },
- [IPVS_CMD_ATTR_TIMEOUT_TCP_FIN] = { .type = NLA_U32 },
- [IPVS_CMD_ATTR_TIMEOUT_UDP] = { .type = NLA_U32 },
- };
- /* Policy used for attributes in nested attribute IPVS_CMD_ATTR_DAEMON */
- static const struct nla_policy ip_vs_daemon_policy[IPVS_DAEMON_ATTR_MAX + 1] = {
- [IPVS_DAEMON_ATTR_STATE] = { .type = NLA_U32 },
- [IPVS_DAEMON_ATTR_MCAST_IFN] = { .type = NLA_NUL_STRING,
- .len = IP_VS_IFNAME_MAXLEN - 1 },
- [IPVS_DAEMON_ATTR_SYNC_ID] = { .type = NLA_U32 },
- [IPVS_DAEMON_ATTR_SYNC_MAXLEN] = { .type = NLA_U16 },
- [IPVS_DAEMON_ATTR_MCAST_GROUP] = { .type = NLA_U32 },
- [IPVS_DAEMON_ATTR_MCAST_GROUP6] = { .len = sizeof(struct in6_addr) },
- [IPVS_DAEMON_ATTR_MCAST_PORT] = { .type = NLA_U16 },
- [IPVS_DAEMON_ATTR_MCAST_TTL] = { .type = NLA_U8 },
- };
- /* Policy used for attributes in nested attribute IPVS_CMD_ATTR_SERVICE */
- static const struct nla_policy ip_vs_svc_policy[IPVS_SVC_ATTR_MAX + 1] = {
- [IPVS_SVC_ATTR_AF] = { .type = NLA_U16 },
- [IPVS_SVC_ATTR_PROTOCOL] = { .type = NLA_U16 },
- [IPVS_SVC_ATTR_ADDR] = { .type = NLA_BINARY,
- .len = sizeof(union nf_inet_addr) },
- [IPVS_SVC_ATTR_PORT] = { .type = NLA_U16 },
- [IPVS_SVC_ATTR_FWMARK] = { .type = NLA_U32 },
- [IPVS_SVC_ATTR_SCHED_NAME] = { .type = NLA_NUL_STRING,
- .len = IP_VS_SCHEDNAME_MAXLEN - 1 },
- [IPVS_SVC_ATTR_PE_NAME] = { .type = NLA_NUL_STRING,
- .len = IP_VS_PENAME_MAXLEN },
- [IPVS_SVC_ATTR_FLAGS] = { .type = NLA_BINARY,
- .len = sizeof(struct ip_vs_flags) },
- [IPVS_SVC_ATTR_TIMEOUT] = { .type = NLA_U32 },
- [IPVS_SVC_ATTR_NETMASK] = { .type = NLA_U32 },
- [IPVS_SVC_ATTR_STATS] = { .type = NLA_NESTED },
- };
- /* Policy used for attributes in nested attribute IPVS_CMD_ATTR_DEST */
- static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = {
- [IPVS_DEST_ATTR_ADDR] = { .type = NLA_BINARY,
- .len = sizeof(union nf_inet_addr) },
- [IPVS_DEST_ATTR_PORT] = { .type = NLA_U16 },
- [IPVS_DEST_ATTR_FWD_METHOD] = { .type = NLA_U32 },
- [IPVS_DEST_ATTR_WEIGHT] = { .type = NLA_U32 },
- [IPVS_DEST_ATTR_U_THRESH] = { .type = NLA_U32 },
- [IPVS_DEST_ATTR_L_THRESH] = { .type = NLA_U32 },
- [IPVS_DEST_ATTR_ACTIVE_CONNS] = { .type = NLA_U32 },
- [IPVS_DEST_ATTR_INACT_CONNS] = { .type = NLA_U32 },
- [IPVS_DEST_ATTR_PERSIST_CONNS] = { .type = NLA_U32 },
- [IPVS_DEST_ATTR_STATS] = { .type = NLA_NESTED },
- [IPVS_DEST_ATTR_ADDR_FAMILY] = { .type = NLA_U16 },
- };
- static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
- struct ip_vs_kstats *kstats)
- {
- struct nlattr *nl_stats = nla_nest_start(skb, container_type);
- if (!nl_stats)
- return -EMSGSIZE;
- if (nla_put_u32(skb, IPVS_STATS_ATTR_CONNS, (u32)kstats->conns) ||
- nla_put_u32(skb, IPVS_STATS_ATTR_INPKTS, (u32)kstats->inpkts) ||
- nla_put_u32(skb, IPVS_STATS_ATTR_OUTPKTS, (u32)kstats->outpkts) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_INBYTES, kstats->inbytes) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_OUTBYTES, kstats->outbytes) ||
- nla_put_u32(skb, IPVS_STATS_ATTR_CPS, (u32)kstats->cps) ||
- nla_put_u32(skb, IPVS_STATS_ATTR_INPPS, (u32)kstats->inpps) ||
- nla_put_u32(skb, IPVS_STATS_ATTR_OUTPPS, (u32)kstats->outpps) ||
- nla_put_u32(skb, IPVS_STATS_ATTR_INBPS, (u32)kstats->inbps) ||
- nla_put_u32(skb, IPVS_STATS_ATTR_OUTBPS, (u32)kstats->outbps))
- goto nla_put_failure;
- nla_nest_end(skb, nl_stats);
- return 0;
- nla_put_failure:
- nla_nest_cancel(skb, nl_stats);
- return -EMSGSIZE;
- }
- static int ip_vs_genl_fill_stats64(struct sk_buff *skb, int container_type,
- struct ip_vs_kstats *kstats)
- {
- struct nlattr *nl_stats = nla_nest_start(skb, container_type);
- if (!nl_stats)
- return -EMSGSIZE;
- if (nla_put_u64(skb, IPVS_STATS_ATTR_CONNS, kstats->conns) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_INPKTS, kstats->inpkts) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_OUTPKTS, kstats->outpkts) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_INBYTES, kstats->inbytes) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_OUTBYTES, kstats->outbytes) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_CPS, kstats->cps) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_INPPS, kstats->inpps) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_OUTPPS, kstats->outpps) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_INBPS, kstats->inbps) ||
- nla_put_u64(skb, IPVS_STATS_ATTR_OUTBPS, kstats->outbps))
- goto nla_put_failure;
- nla_nest_end(skb, nl_stats);
- return 0;
- nla_put_failure:
- nla_nest_cancel(skb, nl_stats);
- return -EMSGSIZE;
- }
- static int ip_vs_genl_fill_service(struct sk_buff *skb,
- struct ip_vs_service *svc)
- {
- struct ip_vs_scheduler *sched;
- struct ip_vs_pe *pe;
- struct nlattr *nl_service;
- struct ip_vs_flags flags = { .flags = svc->flags,
- .mask = ~0 };
- struct ip_vs_kstats kstats;
- char *sched_name;
- nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE);
- if (!nl_service)
- return -EMSGSIZE;
- if (nla_put_u16(skb, IPVS_SVC_ATTR_AF, svc->af))
- goto nla_put_failure;
- if (svc->fwmark) {
- if (nla_put_u32(skb, IPVS_SVC_ATTR_FWMARK, svc->fwmark))
- goto nla_put_failure;
- } else {
- if (nla_put_u16(skb, IPVS_SVC_ATTR_PROTOCOL, svc->protocol) ||
- nla_put(skb, IPVS_SVC_ATTR_ADDR, sizeof(svc->addr), &svc->addr) ||
- nla_put_be16(skb, IPVS_SVC_ATTR_PORT, svc->port))
- goto nla_put_failure;
- }
- sched = rcu_dereference_protected(svc->scheduler, 1);
- sched_name = sched ? sched->name : "none";
- pe = rcu_dereference_protected(svc->pe, 1);
- if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) ||
- (pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) ||
- nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) ||
- nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) ||
- nla_put_be32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask))
- goto nla_put_failure;
- ip_vs_copy_stats(&kstats, &svc->stats);
- if (ip_vs_genl_fill_stats(skb, IPVS_SVC_ATTR_STATS, &kstats))
- goto nla_put_failure;
- if (ip_vs_genl_fill_stats64(skb, IPVS_SVC_ATTR_STATS64, &kstats))
- goto nla_put_failure;
- nla_nest_end(skb, nl_service);
- return 0;
- nla_put_failure:
- nla_nest_cancel(skb, nl_service);
- return -EMSGSIZE;
- }
- static int ip_vs_genl_dump_service(struct sk_buff *skb,
- struct ip_vs_service *svc,
- struct netlink_callback *cb)
- {
- void *hdr;
- hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
- &ip_vs_genl_family, NLM_F_MULTI,
- IPVS_CMD_NEW_SERVICE);
- if (!hdr)
- return -EMSGSIZE;
- if (ip_vs_genl_fill_service(skb, svc) < 0)
- goto nla_put_failure;
- genlmsg_end(skb, hdr);
- return 0;
- nla_put_failure:
- genlmsg_cancel(skb, hdr);
- return -EMSGSIZE;
- }
- static int ip_vs_genl_dump_services(struct sk_buff *skb,
- struct netlink_callback *cb)
- {
- int idx = 0, i;
- int start = cb->args[0];
- struct ip_vs_service *svc;
- struct net *net = sock_net(skb->sk);
- struct netns_ipvs *ipvs = net_ipvs(net);
- mutex_lock(&__ip_vs_mutex);
- for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
- hlist_for_each_entry(svc, &ip_vs_svc_table[i], s_list) {
- if (++idx <= start || (svc->ipvs != ipvs))
- continue;
- if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
- idx--;
- goto nla_put_failure;
- }
- }
- }
- for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
- hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) {
- if (++idx <= start || (svc->ipvs != ipvs))
- continue;
- if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
- idx--;
- goto nla_put_failure;
- }
- }
- }
- nla_put_failure:
- mutex_unlock(&__ip_vs_mutex);
- cb->args[0] = idx;
- return skb->len;
- }
- static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs,
- struct ip_vs_service_user_kern *usvc,
- struct nlattr *nla, int full_entry,
- struct ip_vs_service **ret_svc)
- {
- struct nlattr *attrs[IPVS_SVC_ATTR_MAX + 1];
- struct nlattr *nla_af, *nla_port, *nla_fwmark, *nla_protocol, *nla_addr;
- struct ip_vs_service *svc;
- /* Parse mandatory identifying service fields first */
- if (nla == NULL ||
- nla_parse_nested(attrs, IPVS_SVC_ATTR_MAX, nla, ip_vs_svc_policy))
- return -EINVAL;
- nla_af = attrs[IPVS_SVC_ATTR_AF];
- nla_protocol = attrs[IPVS_SVC_ATTR_PROTOCOL];
- nla_addr = attrs[IPVS_SVC_ATTR_ADDR];
- nla_port = attrs[IPVS_SVC_ATTR_PORT];
- nla_fwmark = attrs[IPVS_SVC_ATTR_FWMARK];
- if (!(nla_af && (nla_fwmark || (nla_port && nla_protocol && nla_addr))))
- return -EINVAL;
- memset(usvc, 0, sizeof(*usvc));
- usvc->af = nla_get_u16(nla_af);
- #ifdef CONFIG_IP_VS_IPV6
- if (usvc->af != AF_INET && usvc->af != AF_INET6)
- #else
- if (usvc->af != AF_INET)
- #endif
- return -EAFNOSUPPORT;
- if (nla_fwmark) {
- usvc->protocol = IPPROTO_TCP;
- usvc->fwmark = nla_get_u32(nla_fwmark);
- } else {
- usvc->protocol = nla_get_u16(nla_protocol);
- nla_memcpy(&usvc->addr, nla_addr, sizeof(usvc->addr));
- usvc->port = nla_get_be16(nla_port);
- usvc->fwmark = 0;
- }
- rcu_read_lock();
- if (usvc->fwmark)
- svc = __ip_vs_svc_fwm_find(ipvs, usvc->af, usvc->fwmark);
- else
- svc = __ip_vs_service_find(ipvs, usvc->af, usvc->protocol,
- &usvc->addr, usvc->port);
- rcu_read_unlock();
- *ret_svc = svc;
- /* If a full entry was requested, check for the additional fields */
- if (full_entry) {
- struct nlattr *nla_sched, *nla_flags, *nla_pe, *nla_timeout,
- *nla_netmask;
- struct ip_vs_flags flags;
- nla_sched = attrs[IPVS_SVC_ATTR_SCHED_NAME];
- nla_pe = attrs[IPVS_SVC_ATTR_PE_NAME];
- nla_flags = attrs[IPVS_SVC_ATTR_FLAGS];
- nla_timeout = attrs[IPVS_SVC_ATTR_TIMEOUT];
- nla_netmask = attrs[IPVS_SVC_ATTR_NETMASK];
- if (!(nla_sched && nla_flags && nla_timeout && nla_netmask))
- return -EINVAL;
- nla_memcpy(&flags, nla_flags, sizeof(flags));
- /* prefill flags from service if it already exists */
- if (svc)
- usvc->flags = svc->flags;
- /* set new flags from userland */
- usvc->flags = (usvc->flags & ~flags.mask) |
- (flags.flags & flags.mask);
- usvc->sched_name = nla_data(nla_sched);
- usvc->pe_name = nla_pe ? nla_data(nla_pe) : NULL;
- usvc->timeout = nla_get_u32(nla_timeout);
- usvc->netmask = nla_get_be32(nla_netmask);
- }
- return 0;
- }
- static struct ip_vs_service *ip_vs_genl_find_service(struct netns_ipvs *ipvs,
- struct nlattr *nla)
- {
- struct ip_vs_service_user_kern usvc;
- struct ip_vs_service *svc;
- int ret;
- ret = ip_vs_genl_parse_service(ipvs, &usvc, nla, 0, &svc);
- return ret ? ERR_PTR(ret) : svc;
- }
- static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
- {
- struct nlattr *nl_dest;
- struct ip_vs_kstats kstats;
- nl_dest = nla_nest_start(skb, IPVS_CMD_ATTR_DEST);
- if (!nl_dest)
- return -EMSGSIZE;
- if (nla_put(skb, IPVS_DEST_ATTR_ADDR, sizeof(dest->addr), &dest->addr) ||
- nla_put_be16(skb, IPVS_DEST_ATTR_PORT, dest->port) ||
- nla_put_u32(skb, IPVS_DEST_ATTR_FWD_METHOD,
- (atomic_read(&dest->conn_flags) &
- IP_VS_CONN_F_FWD_MASK)) ||
- nla_put_u32(skb, IPVS_DEST_ATTR_WEIGHT,
- atomic_read(&dest->weight)) ||
- nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) ||
- nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) ||
- nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS,
- atomic_read(&dest->activeconns)) ||
- nla_put_u32(skb, IPVS_DEST_ATTR_INACT_CONNS,
- atomic_read(&dest->inactconns)) ||
- nla_put_u32(skb, IPVS_DEST_ATTR_PERSIST_CONNS,
- atomic_read(&dest->persistconns)) ||
- nla_put_u16(skb, IPVS_DEST_ATTR_ADDR_FAMILY, dest->af))
- goto nla_put_failure;
- ip_vs_copy_stats(&kstats, &dest->stats);
- if (ip_vs_genl_fill_stats(skb, IPVS_DEST_ATTR_STATS, &kstats))
- goto nla_put_failure;
- if (ip_vs_genl_fill_stats64(skb, IPVS_DEST_ATTR_STATS64, &kstats))
- goto nla_put_failure;
- nla_nest_end(skb, nl_dest);
- return 0;
- nla_put_failure:
- nla_nest_cancel(skb, nl_dest);
- return -EMSGSIZE;
- }
- static int ip_vs_genl_dump_dest(struct sk_buff *skb, struct ip_vs_dest *dest,
- struct netlink_callback *cb)
- {
- void *hdr;
- hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
- &ip_vs_genl_family, NLM_F_MULTI,
- IPVS_CMD_NEW_DEST);
- if (!hdr)
- return -EMSGSIZE;
- if (ip_vs_genl_fill_dest(skb, dest) < 0)
- goto nla_put_failure;
- genlmsg_end(skb, hdr);
- return 0;
- nla_put_failure:
- genlmsg_cancel(skb, hdr);
- return -EMSGSIZE;
- }
- static int ip_vs_genl_dump_dests(struct sk_buff *skb,
- struct netlink_callback *cb)
- {
- int idx = 0;
- int start = cb->args[0];
- struct ip_vs_service *svc;
- struct ip_vs_dest *dest;
- struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1];
- struct net *net = sock_net(skb->sk);
- struct netns_ipvs *ipvs = net_ipvs(net);
- mutex_lock(&__ip_vs_mutex);
- /* Try to find the service for which to dump destinations */
- if (nlmsg_parse(cb->nlh, GENL_HDRLEN, attrs,
- IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy))
- goto out_err;
- svc = ip_vs_genl_find_service(ipvs, attrs[IPVS_CMD_ATTR_SERVICE]);
- if (IS_ERR(svc) || svc == NULL)
- goto out_err;
- /* Dump the destinations */
- list_for_each_entry(dest, &svc->destinations, n_list) {
- if (++idx <= start)
- continue;
- if (ip_vs_genl_dump_dest(skb, dest, cb) < 0) {
- idx--;
- goto nla_put_failure;
- }
- }
- nla_put_failure:
- cb->args[0] = idx;
- out_err:
- mutex_unlock(&__ip_vs_mutex);
- return skb->len;
- }
- static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
- struct nlattr *nla, int full_entry)
- {
- struct nlattr *attrs[IPVS_DEST_ATTR_MAX + 1];
- struct nlattr *nla_addr, *nla_port;
- struct nlattr *nla_addr_family;
- /* Parse mandatory identifying destination fields first */
- if (nla == NULL ||
- nla_parse_nested(attrs, IPVS_DEST_ATTR_MAX, nla, ip_vs_dest_policy))
- return -EINVAL;
- nla_addr = attrs[IPVS_DEST_ATTR_ADDR];
- nla_port = attrs[IPVS_DEST_ATTR_PORT];
- nla_addr_family = attrs[IPVS_DEST_ATTR_ADDR_FAMILY];
- if (!(nla_addr && nla_port))
- return -EINVAL;
- memset(udest, 0, sizeof(*udest));
- nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr));
- udest->port = nla_get_be16(nla_port);
- if (nla_addr_family)
- udest->af = nla_get_u16(nla_addr_family);
- else
- udest->af = 0;
- /* If a full entry was requested, check for the additional fields */
- if (full_entry) {
- struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh,
- *nla_l_thresh;
- nla_fwd = attrs[IPVS_DEST_ATTR_FWD_METHOD];
- nla_weight = attrs[IPVS_DEST_ATTR_WEIGHT];
- nla_u_thresh = attrs[IPVS_DEST_ATTR_U_THRESH];
- nla_l_thresh = attrs[IPVS_DEST_ATTR_L_THRESH];
- if (!(nla_fwd && nla_weight && nla_u_thresh && nla_l_thresh))
- return -EINVAL;
- udest->conn_flags = nla_get_u32(nla_fwd)
- & IP_VS_CONN_F_FWD_MASK;
- udest->weight = nla_get_u32(nla_weight);
- udest->u_threshold = nla_get_u32(nla_u_thresh);
- udest->l_threshold = nla_get_u32(nla_l_thresh);
- }
- return 0;
- }
- static int ip_vs_genl_fill_daemon(struct sk_buff *skb, __u32 state,
- struct ipvs_sync_daemon_cfg *c)
- {
- struct nlattr *nl_daemon;
- nl_daemon = nla_nest_start(skb, IPVS_CMD_ATTR_DAEMON);
- if (!nl_daemon)
- return -EMSGSIZE;
- if (nla_put_u32(skb, IPVS_DAEMON_ATTR_STATE, state) ||
- nla_put_string(skb, IPVS_DAEMON_ATTR_MCAST_IFN, c->mcast_ifn) ||
- nla_put_u32(skb, IPVS_DAEMON_ATTR_SYNC_ID, c->syncid) ||
- nla_put_u16(skb, IPVS_DAEMON_ATTR_SYNC_MAXLEN, c->sync_maxlen) ||
- nla_put_u16(skb, IPVS_DAEMON_ATTR_MCAST_PORT, c->mcast_port) ||
- nla_put_u8(skb, IPVS_DAEMON_ATTR_MCAST_TTL, c->mcast_ttl))
- goto nla_put_failure;
- #ifdef CONFIG_IP_VS_IPV6
- if (c->mcast_af == AF_INET6) {
- if (nla_put_in6_addr(skb, IPVS_DAEMON_ATTR_MCAST_GROUP6,
- &c->mcast_group.in6))
- goto nla_put_failure;
- } else
- #endif
- if (c->mcast_af == AF_INET &&
- nla_put_in_addr(skb, IPVS_DAEMON_ATTR_MCAST_GROUP,
- c->mcast_group.ip))
- goto nla_put_failure;
- nla_nest_end(skb, nl_daemon);
- return 0;
- nla_put_failure:
- nla_nest_cancel(skb, nl_daemon);
- return -EMSGSIZE;
- }
- static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __u32 state,
- struct ipvs_sync_daemon_cfg *c,
- struct netlink_callback *cb)
- {
- void *hdr;
- hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
- &ip_vs_genl_family, NLM_F_MULTI,
- IPVS_CMD_NEW_DAEMON);
- if (!hdr)
- return -EMSGSIZE;
- if (ip_vs_genl_fill_daemon(skb, state, c))
- goto nla_put_failure;
- genlmsg_end(skb, hdr);
- return 0;
- nla_put_failure:
- genlmsg_cancel(skb, hdr);
- return -EMSGSIZE;
- }
- static int ip_vs_genl_dump_daemons(struct sk_buff *skb,
- struct netlink_callback *cb)
- {
- struct net *net = sock_net(skb->sk);
- struct netns_ipvs *ipvs = net_ipvs(net);
- mutex_lock(&ipvs->sync_mutex);
- if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) {
- if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER,
- &ipvs->mcfg, cb) < 0)
- goto nla_put_failure;
- cb->args[0] = 1;
- }
- if ((ipvs->sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) {
- if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_BACKUP,
- &ipvs->bcfg, cb) < 0)
- goto nla_put_failure;
- cb->args[1] = 1;
- }
- nla_put_failure:
- mutex_unlock(&ipvs->sync_mutex);
- return skb->len;
- }
- static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
- {
- struct ipvs_sync_daemon_cfg c;
- struct nlattr *a;
- int ret;
- memset(&c, 0, sizeof(c));
- if (!(attrs[IPVS_DAEMON_ATTR_STATE] &&
- attrs[IPVS_DAEMON_ATTR_MCAST_IFN] &&
- attrs[IPVS_DAEMON_ATTR_SYNC_ID]))
- return -EINVAL;
- strlcpy(c.mcast_ifn, nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]),
- sizeof(c.mcast_ifn));
- c.syncid = nla_get_u32(attrs[IPVS_DAEMON_ATTR_SYNC_ID]);
- a = attrs[IPVS_DAEMON_ATTR_SYNC_MAXLEN];
- if (a)
- c.sync_maxlen = nla_get_u16(a);
- a = attrs[IPVS_DAEMON_ATTR_MCAST_GROUP];
- if (a) {
- c.mcast_af = AF_INET;
- c.mcast_group.ip = nla_get_in_addr(a);
- if (!ipv4_is_multicast(c.mcast_group.ip))
- return -EINVAL;
- } else {
- a = attrs[IPVS_DAEMON_ATTR_MCAST_GROUP6];
- if (a) {
- #ifdef CONFIG_IP_VS_IPV6
- int addr_type;
- c.mcast_af = AF_INET6;
- c.mcast_group.in6 = nla_get_in6_addr(a);
- addr_type = ipv6_addr_type(&c.mcast_group.in6);
- if (!(addr_type & IPV6_ADDR_MULTICAST))
- return -EINVAL;
- #else
- return -EAFNOSUPPORT;
- #endif
- }
- }
- a = attrs[IPVS_DAEMON_ATTR_MCAST_PORT];
- if (a)
- c.mcast_port = nla_get_u16(a);
- a = attrs[IPVS_DAEMON_ATTR_MCAST_TTL];
- if (a)
- c.mcast_ttl = nla_get_u8(a);
- /* The synchronization protocol is incompatible with mixed family
- * services
- */
- if (ipvs->mixed_address_family_dests > 0)
- return -EINVAL;
- ret = start_sync_thread(ipvs, &c,
- nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
- return ret;
- }
- static int ip_vs_genl_del_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
- {
- int ret;
- if (!attrs[IPVS_DAEMON_ATTR_STATE])
- return -EINVAL;
- mutex_lock(&ipvs->sync_mutex);
- ret = stop_sync_thread(ipvs,
- nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
- mutex_unlock(&ipvs->sync_mutex);
- return ret;
- }
- static int ip_vs_genl_set_config(struct netns_ipvs *ipvs, struct nlattr **attrs)
- {
- struct ip_vs_timeout_user t;
- __ip_vs_get_timeouts(ipvs, &t);
- if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP])
- t.tcp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]);
- if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP_FIN])
- t.tcp_fin_timeout =
- nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP_FIN]);
- if (attrs[IPVS_CMD_ATTR_TIMEOUT_UDP])
- t.udp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]);
- return ip_vs_set_timeout(ipvs, &t);
- }
- static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info)
- {
- int ret = -EINVAL, cmd;
- struct net *net = sock_net(skb->sk);
- struct netns_ipvs *ipvs = net_ipvs(net);
- cmd = info->genlhdr->cmd;
- if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) {
- struct nlattr *daemon_attrs[IPVS_DAEMON_ATTR_MAX + 1];
- if (!info->attrs[IPVS_CMD_ATTR_DAEMON] ||
- nla_parse_nested(daemon_attrs, IPVS_DAEMON_ATTR_MAX,
- info->attrs[IPVS_CMD_ATTR_DAEMON],
- ip_vs_daemon_policy))
- goto out;
- if (cmd == IPVS_CMD_NEW_DAEMON)
- ret = ip_vs_genl_new_daemon(ipvs, daemon_attrs);
- else
- ret = ip_vs_genl_del_daemon(ipvs, daemon_attrs);
- }
- out:
- return ret;
- }
- static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
- {
- struct ip_vs_service *svc = NULL;
- struct ip_vs_service_user_kern usvc;
- struct ip_vs_dest_user_kern udest;
- int ret = 0, cmd;
- int need_full_svc = 0, need_full_dest = 0;
- struct net *net = sock_net(skb->sk);
- struct netns_ipvs *ipvs = net_ipvs(net);
- cmd = info->genlhdr->cmd;
- mutex_lock(&__ip_vs_mutex);
- if (cmd == IPVS_CMD_FLUSH) {
- ret = ip_vs_flush(ipvs, false);
- goto out;
- } else if (cmd == IPVS_CMD_SET_CONFIG) {
- ret = ip_vs_genl_set_config(ipvs, info->attrs);
- goto out;
- } else if (cmd == IPVS_CMD_ZERO &&
- !info->attrs[IPVS_CMD_ATTR_SERVICE]) {
- ret = ip_vs_zero_all(ipvs);
- goto out;
- }
- /* All following commands require a service argument, so check if we
- * received a valid one. We need a full service specification when
- * adding / editing a service. Only identifying members otherwise. */
- if (cmd == IPVS_CMD_NEW_SERVICE || cmd == IPVS_CMD_SET_SERVICE)
- need_full_svc = 1;
- ret = ip_vs_genl_parse_service(ipvs, &usvc,
- info->attrs[IPVS_CMD_ATTR_SERVICE],
- need_full_svc, &svc);
- if (ret)
- goto out;
- /* Unless we're adding a new service, the service must already exist */
- if ((cmd != IPVS_CMD_NEW_SERVICE) && (svc == NULL)) {
- ret = -ESRCH;
- goto out;
- }
- /* Destination commands require a valid destination argument. For
- * adding / editing a destination, we need a full destination
- * specification. */
- if (cmd == IPVS_CMD_NEW_DEST || cmd == IPVS_CMD_SET_DEST ||
- cmd == IPVS_CMD_DEL_DEST) {
- if (cmd != IPVS_CMD_DEL_DEST)
- need_full_dest = 1;
- ret = ip_vs_genl_parse_dest(&udest,
- info->attrs[IPVS_CMD_ATTR_DEST],
- need_full_dest);
- if (ret)
- goto out;
- /* Old protocols did not allow the user to specify address
- * family, so we set it to zero instead. We also didn't
- * allow heterogeneous pools in the old code, so it's safe
- * to assume that this will have the same address family as
- * the service.
- */
- if (udest.af == 0)
- udest.af = svc->af;
- if (udest.af != svc->af && cmd != IPVS_CMD_DEL_DEST) {
- /* The synchronization protocol is incompatible
- * with mixed family services
- */
- if (ipvs->sync_state) {
- ret = -EINVAL;
- goto out;
- }
- /* Which connection types do we support? */
- switch (udest.conn_flags) {
- case IP_VS_CONN_F_TUNNEL:
- /* We are able to forward this */
- break;
- default:
- ret = -EINVAL;
- goto out;
- }
- }
- }
- switch (cmd) {
- case IPVS_CMD_NEW_SERVICE:
- if (svc == NULL)
- ret = ip_vs_add_service(ipvs, &usvc, &svc);
- else
- ret = -EEXIST;
- break;
- case IPVS_CMD_SET_SERVICE:
- ret = ip_vs_edit_service(svc, &usvc);
- break;
- case IPVS_CMD_DEL_SERVICE:
- ret = ip_vs_del_service(svc);
- /* do not use svc, it can be freed */
- break;
- case IPVS_CMD_NEW_DEST:
- ret = ip_vs_add_dest(svc, &udest);
- break;
- case IPVS_CMD_SET_DEST:
- ret = ip_vs_edit_dest(svc, &udest);
- break;
- case IPVS_CMD_DEL_DEST:
- ret = ip_vs_del_dest(svc, &udest);
- break;
- case IPVS_CMD_ZERO:
- ret = ip_vs_zero_service(svc);
- break;
- default:
- ret = -EINVAL;
- }
- out:
- mutex_unlock(&__ip_vs_mutex);
- return ret;
- }
- static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
- {
- struct sk_buff *msg;
- void *reply;
- int ret, cmd, reply_cmd;
- struct net *net = sock_net(skb->sk);
- struct netns_ipvs *ipvs = net_ipvs(net);
- cmd = info->genlhdr->cmd;
- if (cmd == IPVS_CMD_GET_SERVICE)
- reply_cmd = IPVS_CMD_NEW_SERVICE;
- else if (cmd == IPVS_CMD_GET_INFO)
- reply_cmd = IPVS_CMD_SET_INFO;
- else if (cmd == IPVS_CMD_GET_CONFIG)
- reply_cmd = IPVS_CMD_SET_CONFIG;
- else {
- pr_err("unknown Generic Netlink command\n");
- return -EINVAL;
- }
- msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!msg)
- return -ENOMEM;
- mutex_lock(&__ip_vs_mutex);
- reply = genlmsg_put_reply(msg, info, &ip_vs_genl_family, 0, reply_cmd);
- if (reply == NULL)
- goto nla_put_failure;
- switch (cmd) {
- case IPVS_CMD_GET_SERVICE:
- {
- struct ip_vs_service *svc;
- svc = ip_vs_genl_find_service(ipvs,
- info->attrs[IPVS_CMD_ATTR_SERVICE]);
- if (IS_ERR(svc)) {
- ret = PTR_ERR(svc);
- goto out_err;
- } else if (svc) {
- ret = ip_vs_genl_fill_service(msg, svc);
- if (ret)
- goto nla_put_failure;
- } else {
- ret = -ESRCH;
- goto out_err;
- }
- break;
- }
- case IPVS_CMD_GET_CONFIG:
- {
- struct ip_vs_timeout_user t;
- __ip_vs_get_timeouts(ipvs, &t);
- #ifdef CONFIG_IP_VS_PROTO_TCP
- if (nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP,
- t.tcp_timeout) ||
- nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP_FIN,
- t.tcp_fin_timeout))
- goto nla_put_failure;
- #endif
- #ifdef CONFIG_IP_VS_PROTO_UDP
- if (nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_UDP, t.udp_timeout))
- goto nla_put_failure;
- #endif
- break;
- }
- case IPVS_CMD_GET_INFO:
- if (nla_put_u32(msg, IPVS_INFO_ATTR_VERSION,
- IP_VS_VERSION_CODE) ||
- nla_put_u32(msg, IPVS_INFO_ATTR_CONN_TAB_SIZE,
- ip_vs_conn_tab_size))
- goto nla_put_failure;
- break;
- }
- genlmsg_end(msg, reply);
- ret = genlmsg_reply(msg, info);
- goto out;
- nla_put_failure:
- pr_err("not enough space in Netlink message\n");
- ret = -EMSGSIZE;
- out_err:
- nlmsg_free(msg);
- out:
- mutex_unlock(&__ip_vs_mutex);
- return ret;
- }
- static const struct genl_ops ip_vs_genl_ops[] = {
- {
- .cmd = IPVS_CMD_NEW_SERVICE,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .doit = ip_vs_genl_set_cmd,
- },
- {
- .cmd = IPVS_CMD_SET_SERVICE,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .doit = ip_vs_genl_set_cmd,
- },
- {
- .cmd = IPVS_CMD_DEL_SERVICE,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .doit = ip_vs_genl_set_cmd,
- },
- {
- .cmd = IPVS_CMD_GET_SERVICE,
- .flags = GENL_ADMIN_PERM,
- .doit = ip_vs_genl_get_cmd,
- .dumpit = ip_vs_genl_dump_services,
- .policy = ip_vs_cmd_policy,
- },
- {
- .cmd = IPVS_CMD_NEW_DEST,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .doit = ip_vs_genl_set_cmd,
- },
- {
- .cmd = IPVS_CMD_SET_DEST,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .doit = ip_vs_genl_set_cmd,
- },
- {
- .cmd = IPVS_CMD_DEL_DEST,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .doit = ip_vs_genl_set_cmd,
- },
- {
- .cmd = IPVS_CMD_GET_DEST,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .dumpit = ip_vs_genl_dump_dests,
- },
- {
- .cmd = IPVS_CMD_NEW_DAEMON,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .doit = ip_vs_genl_set_daemon,
- },
- {
- .cmd = IPVS_CMD_DEL_DAEMON,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .doit = ip_vs_genl_set_daemon,
- },
- {
- .cmd = IPVS_CMD_GET_DAEMON,
- .flags = GENL_ADMIN_PERM,
- .dumpit = ip_vs_genl_dump_daemons,
- },
- {
- .cmd = IPVS_CMD_SET_CONFIG,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .doit = ip_vs_genl_set_cmd,
- },
- {
- .cmd = IPVS_CMD_GET_CONFIG,
- .flags = GENL_ADMIN_PERM,
- .doit = ip_vs_genl_get_cmd,
- },
- {
- .cmd = IPVS_CMD_GET_INFO,
- .flags = GENL_ADMIN_PERM,
- .doit = ip_vs_genl_get_cmd,
- },
- {
- .cmd = IPVS_CMD_ZERO,
- .flags = GENL_ADMIN_PERM,
- .policy = ip_vs_cmd_policy,
- .doit = ip_vs_genl_set_cmd,
- },
- {
- .cmd = IPVS_CMD_FLUSH,
- .flags = GENL_ADMIN_PERM,
- .doit = ip_vs_genl_set_cmd,
- },
- };
- static int __init ip_vs_genl_register(void)
- {
- return genl_register_family_with_ops(&ip_vs_genl_family,
- ip_vs_genl_ops);
- }
- static void ip_vs_genl_unregister(void)
- {
- genl_unregister_family(&ip_vs_genl_family);
- }
- /* End of Generic Netlink interface definitions */
- /*
- * per netns intit/exit func.
- */
- #ifdef CONFIG_SYSCTL
- static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
- {
- struct net *net = ipvs->net;
- int idx;
- struct ctl_table *tbl;
- atomic_set(&ipvs->dropentry, 0);
- spin_lock_init(&ipvs->dropentry_lock);
- spin_lock_init(&ipvs->droppacket_lock);
- spin_lock_init(&ipvs->securetcp_lock);
- if (!net_eq(net, &init_net)) {
- tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL);
- if (tbl == NULL)
- return -ENOMEM;
- /* Don't export sysctls to unprivileged users */
- if (net->user_ns != &init_user_ns)
- tbl[0].procname = NULL;
- } else
- tbl = vs_vars;
- /* Initialize sysctl defaults */
- for (idx = 0; idx < ARRAY_SIZE(vs_vars); idx++) {
- if (tbl[idx].proc_handler == proc_do_defense_mode)
- tbl[idx].extra2 = ipvs;
- }
- idx = 0;
- ipvs->sysctl_amemthresh = 1024;
- tbl[idx++].data = &ipvs->sysctl_amemthresh;
- ipvs->sysctl_am_droprate = 10;
- tbl[idx++].data = &ipvs->sysctl_am_droprate;
- tbl[idx++].data = &ipvs->sysctl_drop_entry;
- tbl[idx++].data = &ipvs->sysctl_drop_packet;
- #ifdef CONFIG_IP_VS_NFCT
- tbl[idx++].data = &ipvs->sysctl_conntrack;
- #endif
- tbl[idx++].data = &ipvs->sysctl_secure_tcp;
- ipvs->sysctl_snat_reroute = 1;
- tbl[idx++].data = &ipvs->sysctl_snat_reroute;
- ipvs->sysctl_sync_ver = 1;
- tbl[idx++].data = &ipvs->sysctl_sync_ver;
- ipvs->sysctl_sync_ports = 1;
- tbl[idx++].data = &ipvs->sysctl_sync_ports;
- tbl[idx++].data = &ipvs->sysctl_sync_persist_mode;
- ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32;
- tbl[idx++].data = &ipvs->sysctl_sync_qlen_max;
- ipvs->sysctl_sync_sock_size = 0;
- tbl[idx++].data = &ipvs->sysctl_sync_sock_size;
- tbl[idx++].data = &ipvs->sysctl_cache_bypass;
- tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn;
- tbl[idx++].data = &ipvs->sysctl_sloppy_tcp;
- tbl[idx++].data = &ipvs->sysctl_sloppy_sctp;
- tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template;
- ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD;
- ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;
- tbl[idx].data = &ipvs->sysctl_sync_threshold;
- tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
- ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD;
- tbl[idx++].data = &ipvs->sysctl_sync_refresh_period;
- ipvs->sysctl_sync_retries = clamp_t(int, DEFAULT_SYNC_RETRIES, 0, 3);
- tbl[idx++].data = &ipvs->sysctl_sync_retries;
- tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
- ipvs->sysctl_pmtu_disc = 1;
- tbl[idx++].data = &ipvs->sysctl_pmtu_disc;
- tbl[idx++].data = &ipvs->sysctl_backup_only;
- ipvs->sysctl_conn_reuse_mode = 1;
- tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode;
- tbl[idx++].data = &ipvs->sysctl_schedule_icmp;
- tbl[idx++].data = &ipvs->sysctl_ignore_tunneled;
- ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
- if (ipvs->sysctl_hdr == NULL) {
- if (!net_eq(net, &init_net))
- kfree(tbl);
- return -ENOMEM;
- }
- ip_vs_start_estimator(ipvs, &ipvs->tot_stats);
- ipvs->sysctl_tbl = tbl;
- /* Schedule defense work */
- INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
- schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
- return 0;
- }
- static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs)
- {
- struct net *net = ipvs->net;
- cancel_delayed_work_sync(&ipvs->defense_work);
- cancel_work_sync(&ipvs->defense_work.work);
- unregister_net_sysctl_table(ipvs->sysctl_hdr);
- ip_vs_stop_estimator(ipvs, &ipvs->tot_stats);
- if (!net_eq(net, &init_net))
- kfree(ipvs->sysctl_tbl);
- }
- #else
- static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) { return 0; }
- static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) { }
- #endif
- static struct notifier_block ip_vs_dst_notifier = {
- .notifier_call = ip_vs_dst_event,
- };
- int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
- {
- int i, idx;
- /* Initialize rs_table */
- for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
- INIT_HLIST_HEAD(&ipvs->rs_table[idx]);
- INIT_LIST_HEAD(&ipvs->dest_trash);
- spin_lock_init(&ipvs->dest_trash_lock);
- setup_timer(&ipvs->dest_trash_timer, ip_vs_dest_trash_expire,
- (unsigned long) ipvs);
- atomic_set(&ipvs->ftpsvc_counter, 0);
- atomic_set(&ipvs->nullsvc_counter, 0);
- /* procfs stats */
- ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
- if (!ipvs->tot_stats.cpustats)
- return -ENOMEM;
- for_each_possible_cpu(i) {
- struct ip_vs_cpu_stats *ipvs_tot_stats;
- ipvs_tot_stats = per_cpu_ptr(ipvs->tot_stats.cpustats, i);
- u64_stats_init(&ipvs_tot_stats->syncp);
- }
- spin_lock_init(&ipvs->tot_stats.lock);
- proc_create("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_fops);
- proc_create("ip_vs_stats", 0, ipvs->net->proc_net, &ip_vs_stats_fops);
- proc_create("ip_vs_stats_percpu", 0, ipvs->net->proc_net,
- &ip_vs_stats_percpu_fops);
- if (ip_vs_control_net_init_sysctl(ipvs))
- goto err;
- return 0;
- err:
- free_percpu(ipvs->tot_stats.cpustats);
- return -ENOMEM;
- }
- void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs)
- {
- ip_vs_trash_cleanup(ipvs);
- ip_vs_control_net_cleanup_sysctl(ipvs);
- remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net);
- remove_proc_entry("ip_vs_stats", ipvs->net->proc_net);
- remove_proc_entry("ip_vs", ipvs->net->proc_net);
- free_percpu(ipvs->tot_stats.cpustats);
- }
- int __init ip_vs_register_nl_ioctl(void)
- {
- int ret;
- ret = nf_register_sockopt(&ip_vs_sockopts);
- if (ret) {
- pr_err("cannot register sockopt.\n");
- goto err_sock;
- }
- ret = ip_vs_genl_register();
- if (ret) {
- pr_err("cannot register Generic Netlink interface.\n");
- goto err_genl;
- }
- return 0;
- err_genl:
- nf_unregister_sockopt(&ip_vs_sockopts);
- err_sock:
- return ret;
- }
- void ip_vs_unregister_nl_ioctl(void)
- {
- ip_vs_genl_unregister();
- nf_unregister_sockopt(&ip_vs_sockopts);
- }
- int __init ip_vs_control_init(void)
- {
- int idx;
- int ret;
- EnterFunction(2);
- /* Initialize svc_table, ip_vs_svc_fwm_table */
- for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- INIT_HLIST_HEAD(&ip_vs_svc_table[idx]);
- INIT_HLIST_HEAD(&ip_vs_svc_fwm_table[idx]);
- }
- smp_wmb(); /* Do we really need it now ? */
- ret = register_netdevice_notifier(&ip_vs_dst_notifier);
- if (ret < 0)
- return ret;
- LeaveFunction(2);
- return 0;
- }
- void ip_vs_control_cleanup(void)
- {
- EnterFunction(2);
- unregister_netdevice_notifier(&ip_vs_dst_notifier);
- LeaveFunction(2);
- }
|