1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740 |
- // SPDX-License-Identifier: GPL-2.0-only
- /* Connection state tracking for netfilter. This is separated from,
- but required by, the NAT layer; it can also be used by an iptables
- extension. */
- /* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
- * (C) 2005-2012 Patrick McHardy <kaber@trash.net>
- */
- #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
- #include <linux/types.h>
- #include <linux/netfilter.h>
- #include <linux/module.h>
- #include <linux/sched.h>
- #include <linux/skbuff.h>
- #include <linux/proc_fs.h>
- #include <linux/vmalloc.h>
- #include <linux/stddef.h>
- #include <linux/slab.h>
- #include <linux/random.h>
- #include <linux/jhash.h>
- #include <linux/siphash.h>
- #include <linux/err.h>
- #include <linux/percpu.h>
- #include <linux/moduleparam.h>
- #include <linux/notifier.h>
- #include <linux/kernel.h>
- #include <linux/netdevice.h>
- #include <linux/socket.h>
- #include <linux/mm.h>
- #include <linux/nsproxy.h>
- #include <linux/rculist_nulls.h>
- #include <trace/hooks/net.h>
- #include <net/netfilter/nf_conntrack.h>
- #include <net/netfilter/nf_conntrack_l4proto.h>
- #include <net/netfilter/nf_conntrack_expect.h>
- #include <net/netfilter/nf_conntrack_helper.h>
- #include <net/netfilter/nf_conntrack_seqadj.h>
- #include <net/netfilter/nf_conntrack_core.h>
- #include <net/netfilter/nf_conntrack_extend.h>
- #include <net/netfilter/nf_conntrack_acct.h>
- #include <net/netfilter/nf_conntrack_ecache.h>
- #include <net/netfilter/nf_conntrack_zones.h>
- #include <net/netfilter/nf_conntrack_timestamp.h>
- #include <net/netfilter/nf_conntrack_timeout.h>
- #include <net/netfilter/nf_conntrack_labels.h>
- #include <net/netfilter/nf_conntrack_synproxy.h>
- #include <net/netfilter/nf_nat.h>
- #include <net/netfilter/nf_nat_helper.h>
- #include <net/netns/hash.h>
- #include <net/ip.h>
- #include "nf_internals.h"
- __cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
- EXPORT_SYMBOL_GPL(nf_conntrack_locks);
- __cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock);
- EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);
- struct hlist_nulls_head *nf_conntrack_hash __read_mostly;
- EXPORT_SYMBOL_GPL(nf_conntrack_hash);
- struct conntrack_gc_work {
- struct delayed_work dwork;
- u32 next_bucket;
- bool exiting;
- bool early_drop;
- };
- static __read_mostly struct kmem_cache *nf_conntrack_cachep;
- static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
- static __read_mostly bool nf_conntrack_locks_all;
- /* serialize hash resizes and nf_ct_iterate_cleanup */
- static DEFINE_MUTEX(nf_conntrack_mutex);
- #define GC_SCAN_INTERVAL (120u * HZ)
- #define GC_SCAN_MAX_DURATION msecs_to_jiffies(10)
- static struct conntrack_gc_work conntrack_gc_work;
- void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
- {
- /* 1) Acquire the lock */
- spin_lock(lock);
- /* 2) read nf_conntrack_locks_all, with ACQUIRE semantics
- * It pairs with the smp_store_release() in nf_conntrack_all_unlock()
- */
- if (likely(smp_load_acquire(&nf_conntrack_locks_all) == false))
- return;
- /* fast path failed, unlock */
- spin_unlock(lock);
- /* Slow path 1) get global lock */
- spin_lock(&nf_conntrack_locks_all_lock);
- /* Slow path 2) get the lock we want */
- spin_lock(lock);
- /* Slow path 3) release the global lock */
- spin_unlock(&nf_conntrack_locks_all_lock);
- }
- EXPORT_SYMBOL_GPL(nf_conntrack_lock);
- static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2)
- {
- h1 %= CONNTRACK_LOCKS;
- h2 %= CONNTRACK_LOCKS;
- spin_unlock(&nf_conntrack_locks[h1]);
- if (h1 != h2)
- spin_unlock(&nf_conntrack_locks[h2]);
- }
- /* return true if we need to recompute hashes (in case hash table was resized) */
- static bool nf_conntrack_double_lock(struct net *net, unsigned int h1,
- unsigned int h2, unsigned int sequence)
- {
- h1 %= CONNTRACK_LOCKS;
- h2 %= CONNTRACK_LOCKS;
- if (h1 <= h2) {
- nf_conntrack_lock(&nf_conntrack_locks[h1]);
- if (h1 != h2)
- spin_lock_nested(&nf_conntrack_locks[h2],
- SINGLE_DEPTH_NESTING);
- } else {
- nf_conntrack_lock(&nf_conntrack_locks[h2]);
- spin_lock_nested(&nf_conntrack_locks[h1],
- SINGLE_DEPTH_NESTING);
- }
- if (read_seqcount_retry(&nf_conntrack_generation, sequence)) {
- nf_conntrack_double_unlock(h1, h2);
- return true;
- }
- return false;
- }
- static void nf_conntrack_all_lock(void)
- __acquires(&nf_conntrack_locks_all_lock)
- {
- int i;
- spin_lock(&nf_conntrack_locks_all_lock);
- nf_conntrack_locks_all = true;
- for (i = 0; i < CONNTRACK_LOCKS; i++) {
- spin_lock(&nf_conntrack_locks[i]);
- /* This spin_unlock provides the "release" to ensure that
- * nf_conntrack_locks_all==true is visible to everyone that
- * acquired spin_lock(&nf_conntrack_locks[]).
- */
- spin_unlock(&nf_conntrack_locks[i]);
- }
- }
- static void nf_conntrack_all_unlock(void)
- __releases(&nf_conntrack_locks_all_lock)
- {
- /* All prior stores must be complete before we clear
- * 'nf_conntrack_locks_all'. Otherwise nf_conntrack_lock()
- * might observe the false value but not the entire
- * critical section.
- * It pairs with the smp_load_acquire() in nf_conntrack_lock()
- */
- smp_store_release(&nf_conntrack_locks_all, false);
- spin_unlock(&nf_conntrack_locks_all_lock);
- }
- unsigned int nf_conntrack_htable_size __read_mostly;
- EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
- unsigned int nf_conntrack_max __read_mostly;
- EXPORT_SYMBOL_GPL(nf_conntrack_max);
- seqcount_spinlock_t nf_conntrack_generation __read_mostly;
- static unsigned int nf_conntrack_hash_rnd __read_mostly;
- static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
- const struct net *net)
- {
- unsigned int n;
- u32 seed;
- get_random_once(&nf_conntrack_hash_rnd, sizeof(nf_conntrack_hash_rnd));
- /* The direction must be ignored, so we hash everything up to the
- * destination ports (which is a multiple of 4) and treat the last
- * three bytes manually.
- */
- seed = nf_conntrack_hash_rnd ^ net_hash_mix(net);
- n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32);
- return jhash2((u32 *)tuple, n, seed ^
- (((__force __u16)tuple->dst.u.all << 16) |
- tuple->dst.protonum));
- }
- static u32 scale_hash(u32 hash)
- {
- return reciprocal_scale(hash, nf_conntrack_htable_size);
- }
- static u32 __hash_conntrack(const struct net *net,
- const struct nf_conntrack_tuple *tuple,
- unsigned int size)
- {
- return reciprocal_scale(hash_conntrack_raw(tuple, net), size);
- }
- static u32 hash_conntrack(const struct net *net,
- const struct nf_conntrack_tuple *tuple)
- {
- return scale_hash(hash_conntrack_raw(tuple, net));
- }
- static bool nf_ct_get_tuple_ports(const struct sk_buff *skb,
- unsigned int dataoff,
- struct nf_conntrack_tuple *tuple)
- { struct {
- __be16 sport;
- __be16 dport;
- } _inet_hdr, *inet_hdr;
- /* Actually only need first 4 bytes to get ports. */
- inet_hdr = skb_header_pointer(skb, dataoff, sizeof(_inet_hdr), &_inet_hdr);
- if (!inet_hdr)
- return false;
- tuple->src.u.udp.port = inet_hdr->sport;
- tuple->dst.u.udp.port = inet_hdr->dport;
- return true;
- }
- static bool
- nf_ct_get_tuple(const struct sk_buff *skb,
- unsigned int nhoff,
- unsigned int dataoff,
- u_int16_t l3num,
- u_int8_t protonum,
- struct net *net,
- struct nf_conntrack_tuple *tuple)
- {
- unsigned int size;
- const __be32 *ap;
- __be32 _addrs[8];
- memset(tuple, 0, sizeof(*tuple));
- tuple->src.l3num = l3num;
- switch (l3num) {
- case NFPROTO_IPV4:
- nhoff += offsetof(struct iphdr, saddr);
- size = 2 * sizeof(__be32);
- break;
- case NFPROTO_IPV6:
- nhoff += offsetof(struct ipv6hdr, saddr);
- size = sizeof(_addrs);
- break;
- default:
- return true;
- }
- ap = skb_header_pointer(skb, nhoff, size, _addrs);
- if (!ap)
- return false;
- switch (l3num) {
- case NFPROTO_IPV4:
- tuple->src.u3.ip = ap[0];
- tuple->dst.u3.ip = ap[1];
- break;
- case NFPROTO_IPV6:
- memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6));
- memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6));
- break;
- }
- tuple->dst.protonum = protonum;
- tuple->dst.dir = IP_CT_DIR_ORIGINAL;
- switch (protonum) {
- #if IS_ENABLED(CONFIG_IPV6)
- case IPPROTO_ICMPV6:
- return icmpv6_pkt_to_tuple(skb, dataoff, net, tuple);
- #endif
- case IPPROTO_ICMP:
- return icmp_pkt_to_tuple(skb, dataoff, net, tuple);
- #ifdef CONFIG_NF_CT_PROTO_GRE
- case IPPROTO_GRE:
- return gre_pkt_to_tuple(skb, dataoff, net, tuple);
- #endif
- case IPPROTO_TCP:
- case IPPROTO_UDP: /* fallthrough */
- return nf_ct_get_tuple_ports(skb, dataoff, tuple);
- #ifdef CONFIG_NF_CT_PROTO_UDPLITE
- case IPPROTO_UDPLITE:
- return nf_ct_get_tuple_ports(skb, dataoff, tuple);
- #endif
- #ifdef CONFIG_NF_CT_PROTO_SCTP
- case IPPROTO_SCTP:
- return nf_ct_get_tuple_ports(skb, dataoff, tuple);
- #endif
- #ifdef CONFIG_NF_CT_PROTO_DCCP
- case IPPROTO_DCCP:
- return nf_ct_get_tuple_ports(skb, dataoff, tuple);
- #endif
- default:
- break;
- }
- return true;
- }
- static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
- u_int8_t *protonum)
- {
- int dataoff = -1;
- const struct iphdr *iph;
- struct iphdr _iph;
- iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
- if (!iph)
- return -1;
- /* Conntrack defragments packets, we might still see fragments
- * inside ICMP packets though.
- */
- if (iph->frag_off & htons(IP_OFFSET))
- return -1;
- dataoff = nhoff + (iph->ihl << 2);
- *protonum = iph->protocol;
- /* Check bogus IP headers */
- if (dataoff > skb->len) {
- pr_debug("bogus IPv4 packet: nhoff %u, ihl %u, skblen %u\n",
- nhoff, iph->ihl << 2, skb->len);
- return -1;
- }
- return dataoff;
- }
- #if IS_ENABLED(CONFIG_IPV6)
- static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
- u8 *protonum)
- {
- int protoff = -1;
- unsigned int extoff = nhoff + sizeof(struct ipv6hdr);
- __be16 frag_off;
- u8 nexthdr;
- if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr),
- &nexthdr, sizeof(nexthdr)) != 0) {
- pr_debug("can't get nexthdr\n");
- return -1;
- }
- protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off);
- /*
- * (protoff == skb->len) means the packet has not data, just
- * IPv6 and possibly extensions headers, but it is tracked anyway
- */
- if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
- pr_debug("can't find proto in pkt\n");
- return -1;
- }
- *protonum = nexthdr;
- return protoff;
- }
- #endif
- static int get_l4proto(const struct sk_buff *skb,
- unsigned int nhoff, u8 pf, u8 *l4num)
- {
- switch (pf) {
- case NFPROTO_IPV4:
- return ipv4_get_l4proto(skb, nhoff, l4num);
- #if IS_ENABLED(CONFIG_IPV6)
- case NFPROTO_IPV6:
- return ipv6_get_l4proto(skb, nhoff, l4num);
- #endif
- default:
- *l4num = 0;
- break;
- }
- return -1;
- }
- bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
- u_int16_t l3num,
- struct net *net, struct nf_conntrack_tuple *tuple)
- {
- u8 protonum;
- int protoff;
- protoff = get_l4proto(skb, nhoff, l3num, &protonum);
- if (protoff <= 0)
- return false;
- return nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple);
- }
- EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr);
- bool
- nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
- const struct nf_conntrack_tuple *orig)
- {
- memset(inverse, 0, sizeof(*inverse));
- inverse->src.l3num = orig->src.l3num;
- switch (orig->src.l3num) {
- case NFPROTO_IPV4:
- inverse->src.u3.ip = orig->dst.u3.ip;
- inverse->dst.u3.ip = orig->src.u3.ip;
- break;
- case NFPROTO_IPV6:
- inverse->src.u3.in6 = orig->dst.u3.in6;
- inverse->dst.u3.in6 = orig->src.u3.in6;
- break;
- default:
- break;
- }
- inverse->dst.dir = !orig->dst.dir;
- inverse->dst.protonum = orig->dst.protonum;
- switch (orig->dst.protonum) {
- case IPPROTO_ICMP:
- return nf_conntrack_invert_icmp_tuple(inverse, orig);
- #if IS_ENABLED(CONFIG_IPV6)
- case IPPROTO_ICMPV6:
- return nf_conntrack_invert_icmpv6_tuple(inverse, orig);
- #endif
- }
- inverse->src.u.all = orig->dst.u.all;
- inverse->dst.u.all = orig->src.u.all;
- return true;
- }
- EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
- /* Generate a almost-unique pseudo-id for a given conntrack.
- *
- * intentionally doesn't re-use any of the seeds used for hash
- * table location, we assume id gets exposed to userspace.
- *
- * Following nf_conn items do not change throughout lifetime
- * of the nf_conn:
- *
- * 1. nf_conn address
- * 2. nf_conn->master address (normally NULL)
- * 3. the associated net namespace
- * 4. the original direction tuple
- */
- u32 nf_ct_get_id(const struct nf_conn *ct)
- {
- static __read_mostly siphash_key_t ct_id_seed;
- unsigned long a, b, c, d;
- net_get_random_once(&ct_id_seed, sizeof(ct_id_seed));
- a = (unsigned long)ct;
- b = (unsigned long)ct->master;
- c = (unsigned long)nf_ct_net(ct);
- d = (unsigned long)siphash(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- sizeof(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple),
- &ct_id_seed);
- #ifdef CONFIG_64BIT
- return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed);
- #else
- return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed);
- #endif
- }
- EXPORT_SYMBOL_GPL(nf_ct_get_id);
- static void
- clean_from_lists(struct nf_conn *ct)
- {
- pr_debug("clean_from_lists(%p)\n", ct);
- hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
- hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode);
- /* Destroy all pending expectations */
- nf_ct_remove_expectations(ct);
- }
- /* must be called with local_bh_disable */
- static void nf_ct_add_to_dying_list(struct nf_conn *ct)
- {
- struct ct_pcpu *pcpu;
- /* add this conntrack to the (per cpu) dying list */
- ct->cpu = smp_processor_id();
- pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
- spin_lock(&pcpu->lock);
- hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &pcpu->dying);
- spin_unlock(&pcpu->lock);
- }
- /* must be called with local_bh_disable */
- static void nf_ct_add_to_unconfirmed_list(struct nf_conn *ct)
- {
- struct ct_pcpu *pcpu;
- /* add this conntrack to the (per cpu) unconfirmed list */
- ct->cpu = smp_processor_id();
- pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
- spin_lock(&pcpu->lock);
- hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &pcpu->unconfirmed);
- spin_unlock(&pcpu->lock);
- }
- /* must be called with local_bh_disable */
- static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
- {
- struct ct_pcpu *pcpu;
- /* We overload first tuple to link into unconfirmed or dying list.*/
- pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
- spin_lock(&pcpu->lock);
- BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
- hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
- spin_unlock(&pcpu->lock);
- }
- #define NFCT_ALIGN(len) (((len) + NFCT_INFOMASK) & ~NFCT_INFOMASK)
- /* Released via destroy_conntrack() */
- struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
- const struct nf_conntrack_zone *zone,
- gfp_t flags)
- {
- struct nf_conn *tmpl, *p;
- if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK) {
- tmpl = kzalloc(sizeof(*tmpl) + NFCT_INFOMASK, flags);
- if (!tmpl)
- return NULL;
- p = tmpl;
- tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p);
- if (tmpl != p) {
- tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p);
- tmpl->proto.tmpl_padto = (char *)tmpl - (char *)p;
- }
- } else {
- tmpl = kzalloc(sizeof(*tmpl), flags);
- if (!tmpl)
- return NULL;
- }
- tmpl->status = IPS_TEMPLATE;
- write_pnet(&tmpl->ct_net, net);
- nf_ct_zone_add(tmpl, zone);
- atomic_set(&tmpl->ct_general.use, 0);
- return tmpl;
- }
- EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);
- void nf_ct_tmpl_free(struct nf_conn *tmpl)
- {
- nf_ct_ext_destroy(tmpl);
- if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK)
- kfree((char *)tmpl - tmpl->proto.tmpl_padto);
- else
- kfree(tmpl);
- }
- EXPORT_SYMBOL_GPL(nf_ct_tmpl_free);
- static void destroy_gre_conntrack(struct nf_conn *ct)
- {
- #ifdef CONFIG_NF_CT_PROTO_GRE
- struct nf_conn *master = ct->master;
- if (master)
- nf_ct_gre_keymap_destroy(master);
- #endif
- }
- static void
- destroy_conntrack(struct nf_conntrack *nfct)
- {
- struct nf_conn *ct = (struct nf_conn *)nfct;
- pr_debug("destroy_conntrack(%p)\n", ct);
- WARN_ON(atomic_read(&nfct->use) != 0);
- if (unlikely(nf_ct_is_template(ct))) {
- nf_ct_tmpl_free(ct);
- return;
- }
- if (unlikely(nf_ct_protonum(ct) == IPPROTO_GRE))
- destroy_gre_conntrack(ct);
- local_bh_disable();
- /* Expectations will have been removed in clean_from_lists,
- * except TFTP can create an expectation on the first packet,
- * before connection is in the list, so we need to clean here,
- * too.
- */
- nf_ct_remove_expectations(ct);
- nf_ct_del_from_dying_or_unconfirmed_list(ct);
- local_bh_enable();
- if (ct->master)
- nf_ct_put(ct->master);
- pr_debug("destroy_conntrack: returning ct=%p to slab\n", ct);
- nf_conntrack_free(ct);
- }
- static void nf_ct_delete_from_lists(struct nf_conn *ct)
- {
- struct net *net = nf_ct_net(ct);
- unsigned int hash, reply_hash;
- unsigned int sequence;
- nf_ct_helper_destroy(ct);
- local_bh_disable();
- do {
- sequence = read_seqcount_begin(&nf_conntrack_generation);
- hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- reply_hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
- } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
- clean_from_lists(ct);
- nf_conntrack_double_unlock(hash, reply_hash);
- nf_ct_add_to_dying_list(ct);
- local_bh_enable();
- }
- bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
- {
- struct nf_conn_tstamp *tstamp;
- if (test_and_set_bit(IPS_DYING_BIT, &ct->status))
- return false;
- tstamp = nf_conn_tstamp_find(ct);
- if (tstamp) {
- s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp;
- tstamp->stop = ktime_get_real_ns();
- if (timeout < 0)
- tstamp->stop -= jiffies_to_nsecs(-timeout);
- }
- if (nf_conntrack_event_report(IPCT_DESTROY, ct,
- portid, report) < 0) {
- /* destroy event was not delivered. nf_ct_put will
- * be done by event cache worker on redelivery.
- */
- nf_ct_delete_from_lists(ct);
- nf_conntrack_ecache_delayed_work(nf_ct_net(ct));
- return false;
- }
- nf_conntrack_ecache_work(nf_ct_net(ct));
- nf_ct_delete_from_lists(ct);
- nf_ct_put(ct);
- return true;
- }
- EXPORT_SYMBOL_GPL(nf_ct_delete);
- static inline bool
- nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
- const struct nf_conntrack_tuple *tuple,
- const struct nf_conntrack_zone *zone,
- const struct net *net)
- {
- struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
- /* A conntrack can be recreated with the equal tuple,
- * so we need to check that the conntrack is confirmed
- */
- return nf_ct_tuple_equal(tuple, &h->tuple) &&
- nf_ct_zone_equal(ct, zone, NF_CT_DIRECTION(h)) &&
- nf_ct_is_confirmed(ct) &&
- net_eq(net, nf_ct_net(ct));
- }
- static inline bool
- nf_ct_match(const struct nf_conn *ct1, const struct nf_conn *ct2)
- {
- return nf_ct_tuple_equal(&ct1->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- &ct2->tuplehash[IP_CT_DIR_ORIGINAL].tuple) &&
- nf_ct_tuple_equal(&ct1->tuplehash[IP_CT_DIR_REPLY].tuple,
- &ct2->tuplehash[IP_CT_DIR_REPLY].tuple) &&
- nf_ct_zone_equal(ct1, nf_ct_zone(ct2), IP_CT_DIR_ORIGINAL) &&
- nf_ct_zone_equal(ct1, nf_ct_zone(ct2), IP_CT_DIR_REPLY) &&
- net_eq(nf_ct_net(ct1), nf_ct_net(ct2));
- }
- /* caller must hold rcu readlock and none of the nf_conntrack_locks */
- static void nf_ct_gc_expired(struct nf_conn *ct)
- {
- if (!atomic_inc_not_zero(&ct->ct_general.use))
- return;
- if (nf_ct_should_gc(ct))
- nf_ct_kill(ct);
- nf_ct_put(ct);
- }
- /*
- * Warning :
- * - Caller must take a reference on returned object
- * and recheck nf_ct_tuple_equal(tuple, &h->tuple)
- */
- static struct nf_conntrack_tuple_hash *
- ____nf_conntrack_find(struct net *net, const struct nf_conntrack_zone *zone,
- const struct nf_conntrack_tuple *tuple, u32 hash)
- {
- struct nf_conntrack_tuple_hash *h;
- struct hlist_nulls_head *ct_hash;
- struct hlist_nulls_node *n;
- unsigned int bucket, hsize;
- begin:
- nf_conntrack_get_ht(&ct_hash, &hsize);
- bucket = reciprocal_scale(hash, hsize);
- hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[bucket], hnnode) {
- struct nf_conn *ct;
- ct = nf_ct_tuplehash_to_ctrack(h);
- if (nf_ct_is_expired(ct)) {
- nf_ct_gc_expired(ct);
- continue;
- }
- if (nf_ct_key_equal(h, tuple, zone, net))
- return h;
- }
- /*
- * if the nulls value we got at the end of this lookup is
- * not the expected one, we must restart lookup.
- * We probably met an item that was moved to another chain.
- */
- if (get_nulls_value(n) != bucket) {
- NF_CT_STAT_INC_ATOMIC(net, search_restart);
- goto begin;
- }
- return NULL;
- }
- /* Find a connection corresponding to a tuple. */
- static struct nf_conntrack_tuple_hash *
- __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
- const struct nf_conntrack_tuple *tuple, u32 hash)
- {
- struct nf_conntrack_tuple_hash *h;
- struct nf_conn *ct;
- rcu_read_lock();
- h = ____nf_conntrack_find(net, zone, tuple, hash);
- if (h) {
- /* We have a candidate that matches the tuple we're interested
- * in, try to obtain a reference and re-check tuple
- */
- ct = nf_ct_tuplehash_to_ctrack(h);
- if (likely(atomic_inc_not_zero(&ct->ct_general.use))) {
- if (likely(nf_ct_key_equal(h, tuple, zone, net)))
- goto found;
- /* TYPESAFE_BY_RCU recycled the candidate */
- nf_ct_put(ct);
- }
- h = NULL;
- }
- found:
- rcu_read_unlock();
- return h;
- }
- struct nf_conntrack_tuple_hash *
- nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
- const struct nf_conntrack_tuple *tuple)
- {
- return __nf_conntrack_find_get(net, zone, tuple,
- hash_conntrack_raw(tuple, net));
- }
- EXPORT_SYMBOL_GPL(nf_conntrack_find_get);
- static void __nf_conntrack_hash_insert(struct nf_conn *ct,
- unsigned int hash,
- unsigned int reply_hash)
- {
- hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &nf_conntrack_hash[hash]);
- hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
- &nf_conntrack_hash[reply_hash]);
- }
- int
- nf_conntrack_hash_check_insert(struct nf_conn *ct)
- {
- const struct nf_conntrack_zone *zone;
- struct net *net = nf_ct_net(ct);
- unsigned int hash, reply_hash;
- struct nf_conntrack_tuple_hash *h;
- struct hlist_nulls_node *n;
- unsigned int sequence;
- zone = nf_ct_zone(ct);
- local_bh_disable();
- do {
- sequence = read_seqcount_begin(&nf_conntrack_generation);
- hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- reply_hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
- } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
- /* See if there's one in the list already, including reverse */
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
- if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- zone, net))
- goto out;
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
- if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
- zone, net))
- goto out;
- smp_wmb();
- /* The caller holds a reference to this object */
- atomic_set(&ct->ct_general.use, 2);
- __nf_conntrack_hash_insert(ct, hash, reply_hash);
- nf_conntrack_double_unlock(hash, reply_hash);
- NF_CT_STAT_INC(net, insert);
- local_bh_enable();
- return 0;
- out:
- nf_conntrack_double_unlock(hash, reply_hash);
- local_bh_enable();
- return -EEXIST;
- }
- EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
- void nf_ct_acct_add(struct nf_conn *ct, u32 dir, unsigned int packets,
- unsigned int bytes)
- {
- struct nf_conn_acct *acct;
- acct = nf_conn_acct_find(ct);
- if (acct) {
- struct nf_conn_counter *counter = acct->counter;
- atomic64_add(packets, &counter[dir].packets);
- atomic64_add(bytes, &counter[dir].bytes);
- }
- }
- EXPORT_SYMBOL_GPL(nf_ct_acct_add);
- static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
- const struct nf_conn *loser_ct)
- {
- struct nf_conn_acct *acct;
- acct = nf_conn_acct_find(loser_ct);
- if (acct) {
- struct nf_conn_counter *counter = acct->counter;
- unsigned int bytes;
- /* u32 should be fine since we must have seen one packet. */
- bytes = atomic64_read(&counter[CTINFO2DIR(ctinfo)].bytes);
- nf_ct_acct_update(ct, CTINFO2DIR(ctinfo), bytes);
- }
- }
- static void __nf_conntrack_insert_prepare(struct nf_conn *ct)
- {
- struct nf_conn_tstamp *tstamp;
- atomic_inc(&ct->ct_general.use);
- ct->status |= IPS_CONFIRMED;
- /* set conntrack timestamp, if enabled. */
- tstamp = nf_conn_tstamp_find(ct);
- if (tstamp)
- tstamp->start = ktime_get_real_ns();
- }
- /* caller must hold locks to prevent concurrent changes */
- static int __nf_ct_resolve_clash(struct sk_buff *skb,
- struct nf_conntrack_tuple_hash *h)
- {
- /* This is the conntrack entry already in hashes that won race. */
- struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
- enum ip_conntrack_info ctinfo;
- struct nf_conn *loser_ct;
- loser_ct = nf_ct_get(skb, &ctinfo);
- if (nf_ct_is_dying(ct))
- return NF_DROP;
- if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
- nf_ct_match(ct, loser_ct)) {
- struct net *net = nf_ct_net(ct);
- nf_conntrack_get(&ct->ct_general);
- nf_ct_acct_merge(ct, ctinfo, loser_ct);
- nf_ct_add_to_dying_list(loser_ct);
- nf_conntrack_put(&loser_ct->ct_general);
- nf_ct_set(skb, ct, ctinfo);
- NF_CT_STAT_INC(net, clash_resolve);
- return NF_ACCEPT;
- }
- return NF_DROP;
- }
- /**
- * nf_ct_resolve_clash_harder - attempt to insert clashing conntrack entry
- *
- * @skb: skb that causes the collision
- * @repl_idx: hash slot for reply direction
- *
- * Called when origin or reply direction had a clash.
- * The skb can be handled without packet drop provided the reply direction
- * is unique or there the existing entry has the identical tuple in both
- * directions.
- *
- * Caller must hold conntrack table locks to prevent concurrent updates.
- *
- * Returns NF_DROP if the clash could not be handled.
- */
- static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
- {
- struct nf_conn *loser_ct = (struct nf_conn *)skb_nfct(skb);
- const struct nf_conntrack_zone *zone;
- struct nf_conntrack_tuple_hash *h;
- struct hlist_nulls_node *n;
- struct net *net;
- zone = nf_ct_zone(loser_ct);
- net = nf_ct_net(loser_ct);
- /* Reply direction must never result in a clash, unless both origin
- * and reply tuples are identical.
- */
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[repl_idx], hnnode) {
- if (nf_ct_key_equal(h,
- &loser_ct->tuplehash[IP_CT_DIR_REPLY].tuple,
- zone, net))
- return __nf_ct_resolve_clash(skb, h);
- }
- /* We want the clashing entry to go away real soon: 1 second timeout. */
- WRITE_ONCE(loser_ct->timeout, nfct_time_stamp + HZ);
- /* IPS_NAT_CLASH removes the entry automatically on the first
- * reply. Also prevents UDP tracker from moving the entry to
- * ASSURED state, i.e. the entry can always be evicted under
- * pressure.
- */
- loser_ct->status |= IPS_FIXED_TIMEOUT | IPS_NAT_CLASH;
- __nf_conntrack_insert_prepare(loser_ct);
- /* fake add for ORIGINAL dir: we want lookups to only find the entry
- * already in the table. This also hides the clashing entry from
- * ctnetlink iteration, i.e. conntrack -L won't show them.
- */
- hlist_nulls_add_fake(&loser_ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
- hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
- &nf_conntrack_hash[repl_idx]);
- NF_CT_STAT_INC(net, clash_resolve);
- return NF_ACCEPT;
- }
- /**
- * nf_ct_resolve_clash - attempt to handle clash without packet drop
- *
- * @skb: skb that causes the clash
- * @h: tuplehash of the clashing entry already in table
- * @reply_hash: hash slot for reply direction
- *
- * A conntrack entry can be inserted to the connection tracking table
- * if there is no existing entry with an identical tuple.
- *
- * If there is one, @skb (and the assocated, unconfirmed conntrack) has
- * to be dropped. In case @skb is retransmitted, next conntrack lookup
- * will find the already-existing entry.
- *
- * The major problem with such packet drop is the extra delay added by
- * the packet loss -- it will take some time for a retransmit to occur
- * (or the sender to time out when waiting for a reply).
- *
- * This function attempts to handle the situation without packet drop.
- *
- * If @skb has no NAT transformation or if the colliding entries are
- * exactly the same, only the to-be-confirmed conntrack entry is discarded
- * and @skb is associated with the conntrack entry already in the table.
- *
- * Failing that, the new, unconfirmed conntrack is still added to the table
- * provided that the collision only occurs in the ORIGINAL direction.
- * The new entry will be added only in the non-clashing REPLY direction,
- * so packets in the ORIGINAL direction will continue to match the existing
- * entry. The new entry will also have a fixed timeout so it expires --
- * due to the collision, it will only see reply traffic.
- *
- * Returns NF_DROP if the clash could not be resolved.
- */
- static __cold noinline int
- nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h,
- u32 reply_hash)
- {
- /* This is the conntrack entry already in hashes that won race. */
- struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
- const struct nf_conntrack_l4proto *l4proto;
- enum ip_conntrack_info ctinfo;
- struct nf_conn *loser_ct;
- struct net *net;
- int ret;
- loser_ct = nf_ct_get(skb, &ctinfo);
- net = nf_ct_net(loser_ct);
- l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct));
- if (!l4proto->allow_clash)
- goto drop;
- ret = __nf_ct_resolve_clash(skb, h);
- if (ret == NF_ACCEPT)
- return ret;
- ret = nf_ct_resolve_clash_harder(skb, reply_hash);
- if (ret == NF_ACCEPT)
- return ret;
- drop:
- nf_ct_add_to_dying_list(loser_ct);
- NF_CT_STAT_INC(net, drop);
- NF_CT_STAT_INC(net, insert_failed);
- return NF_DROP;
- }
- /* Confirm a connection given skb; places it in hash table */
- int
- __nf_conntrack_confirm(struct sk_buff *skb)
- {
- const struct nf_conntrack_zone *zone;
- unsigned int hash, reply_hash;
- struct nf_conntrack_tuple_hash *h;
- struct nf_conn *ct;
- struct nf_conn_help *help;
- struct hlist_nulls_node *n;
- enum ip_conntrack_info ctinfo;
- struct net *net;
- unsigned int sequence;
- int ret = NF_DROP;
- ct = nf_ct_get(skb, &ctinfo);
- net = nf_ct_net(ct);
- /* ipt_REJECT uses nf_conntrack_attach to attach related
- ICMP/TCP RST packets in other direction. Actual packet
- which created connection will be IP_CT_NEW or for an
- expected connection, IP_CT_RELATED. */
- if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
- return NF_ACCEPT;
- zone = nf_ct_zone(ct);
- local_bh_disable();
- do {
- sequence = read_seqcount_begin(&nf_conntrack_generation);
- /* reuse the hash saved before */
- hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
- hash = scale_hash(hash);
- reply_hash = hash_conntrack(net,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
- } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
- /* We're not in hash table, and we refuse to set up related
- * connections for unconfirmed conns. But packet copies and
- * REJECT will give spurious warnings here.
- */
- /* Another skb with the same unconfirmed conntrack may
- * win the race. This may happen for bridge(br_flood)
- * or broadcast/multicast packets do skb_clone with
- * unconfirmed conntrack.
- */
- if (unlikely(nf_ct_is_confirmed(ct))) {
- WARN_ON_ONCE(1);
- nf_conntrack_double_unlock(hash, reply_hash);
- local_bh_enable();
- return NF_DROP;
- }
- pr_debug("Confirming conntrack %p\n", ct);
- /* We have to check the DYING flag after unlink to prevent
- * a race against nf_ct_get_next_corpse() possibly called from
- * user context, else we insert an already 'dead' hash, blocking
- * further use of that particular connection -JM.
- */
- nf_ct_del_from_dying_or_unconfirmed_list(ct);
- if (unlikely(nf_ct_is_dying(ct))) {
- nf_ct_add_to_dying_list(ct);
- NF_CT_STAT_INC(net, insert_failed);
- goto dying;
- }
- /* See if there's one in the list already, including reverse:
- NAT could have grabbed it without realizing, since we're
- not in the hash. If there is, we lost race. */
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
- if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- zone, net))
- goto out;
- hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
- if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
- zone, net))
- goto out;
- /* Timer relative to confirmation time, not original
- setting time, otherwise we'd get timer wrap in
- weird delay cases. */
- ct->timeout += nfct_time_stamp;
- __nf_conntrack_insert_prepare(ct);
- /* Since the lookup is lockless, hash insertion must be done after
- * starting the timer and setting the CONFIRMED bit. The RCU barriers
- * guarantee that no other CPU can find the conntrack before the above
- * stores are visible.
- */
- __nf_conntrack_hash_insert(ct, hash, reply_hash);
- nf_conntrack_double_unlock(hash, reply_hash);
- local_bh_enable();
- help = nfct_help(ct);
- if (help && help->helper)
- nf_conntrack_event_cache(IPCT_HELPER, ct);
- nf_conntrack_event_cache(master_ct(ct) ?
- IPCT_RELATED : IPCT_NEW, ct);
- return NF_ACCEPT;
- out:
- ret = nf_ct_resolve_clash(skb, h, reply_hash);
- dying:
- nf_conntrack_double_unlock(hash, reply_hash);
- local_bh_enable();
- return ret;
- }
- EXPORT_SYMBOL_GPL(__nf_conntrack_confirm);
- /* Returns true if a connection correspondings to the tuple (required
- for NAT). */
- int
- nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
- const struct nf_conn *ignored_conntrack)
- {
- struct net *net = nf_ct_net(ignored_conntrack);
- const struct nf_conntrack_zone *zone;
- struct nf_conntrack_tuple_hash *h;
- struct hlist_nulls_head *ct_hash;
- unsigned int hash, hsize;
- struct hlist_nulls_node *n;
- struct nf_conn *ct;
- zone = nf_ct_zone(ignored_conntrack);
- rcu_read_lock();
- begin:
- nf_conntrack_get_ht(&ct_hash, &hsize);
- hash = __hash_conntrack(net, tuple, hsize);
- hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {
- ct = nf_ct_tuplehash_to_ctrack(h);
- if (ct == ignored_conntrack)
- continue;
- if (nf_ct_is_expired(ct)) {
- nf_ct_gc_expired(ct);
- continue;
- }
- if (nf_ct_key_equal(h, tuple, zone, net)) {
- /* Tuple is taken already, so caller will need to find
- * a new source port to use.
- *
- * Only exception:
- * If the *original tuples* are identical, then both
- * conntracks refer to the same flow.
- * This is a rare situation, it can occur e.g. when
- * more than one UDP packet is sent from same socket
- * in different threads.
- *
- * Let nf_ct_resolve_clash() deal with this later.
- */
- if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple) &&
- nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL))
- continue;
- NF_CT_STAT_INC_ATOMIC(net, found);
- rcu_read_unlock();
- return 1;
- }
- }
- if (get_nulls_value(n) != hash) {
- NF_CT_STAT_INC_ATOMIC(net, search_restart);
- goto begin;
- }
- rcu_read_unlock();
- return 0;
- }
- EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken);
- #define NF_CT_EVICTION_RANGE 8
- /* There's a small race here where we may free a just-assured
- connection. Too bad: we're in trouble anyway. */
- static unsigned int early_drop_list(struct net *net,
- struct hlist_nulls_head *head)
- {
- struct nf_conntrack_tuple_hash *h;
- struct hlist_nulls_node *n;
- unsigned int drops = 0;
- struct nf_conn *tmp;
- hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) {
- tmp = nf_ct_tuplehash_to_ctrack(h);
- if (test_bit(IPS_OFFLOAD_BIT, &tmp->status))
- continue;
- if (nf_ct_is_expired(tmp)) {
- nf_ct_gc_expired(tmp);
- continue;
- }
- if (test_bit(IPS_ASSURED_BIT, &tmp->status) ||
- !net_eq(nf_ct_net(tmp), net) ||
- nf_ct_is_dying(tmp))
- continue;
- if (!atomic_inc_not_zero(&tmp->ct_general.use))
- continue;
- /* kill only if still in same netns -- might have moved due to
- * SLAB_TYPESAFE_BY_RCU rules.
- *
- * We steal the timer reference. If that fails timer has
- * already fired or someone else deleted it. Just drop ref
- * and move to next entry.
- */
- if (net_eq(nf_ct_net(tmp), net) &&
- nf_ct_is_confirmed(tmp) &&
- nf_ct_delete(tmp, 0, 0))
- drops++;
- nf_ct_put(tmp);
- }
- return drops;
- }
- static noinline int early_drop(struct net *net, unsigned int hash)
- {
- unsigned int i, bucket;
- for (i = 0; i < NF_CT_EVICTION_RANGE; i++) {
- struct hlist_nulls_head *ct_hash;
- unsigned int hsize, drops;
- rcu_read_lock();
- nf_conntrack_get_ht(&ct_hash, &hsize);
- if (!i)
- bucket = reciprocal_scale(hash, hsize);
- else
- bucket = (bucket + 1) % hsize;
- drops = early_drop_list(net, &ct_hash[bucket]);
- rcu_read_unlock();
- if (drops) {
- NF_CT_STAT_ADD_ATOMIC(net, early_drop, drops);
- return true;
- }
- }
- return false;
- }
- static bool gc_worker_skip_ct(const struct nf_conn *ct)
- {
- return !nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct);
- }
- static bool gc_worker_can_early_drop(const struct nf_conn *ct)
- {
- const struct nf_conntrack_l4proto *l4proto;
- if (!test_bit(IPS_ASSURED_BIT, &ct->status))
- return true;
- l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct));
- if (l4proto->can_early_drop && l4proto->can_early_drop(ct))
- return true;
- return false;
- }
- static void gc_worker(struct work_struct *work)
- {
- unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION;
- unsigned int i, hashsz, nf_conntrack_max95 = 0;
- unsigned long next_run = GC_SCAN_INTERVAL;
- struct conntrack_gc_work *gc_work;
- gc_work = container_of(work, struct conntrack_gc_work, dwork.work);
- i = gc_work->next_bucket;
- if (gc_work->early_drop)
- nf_conntrack_max95 = nf_conntrack_max / 100u * 95u;
- do {
- struct nf_conntrack_tuple_hash *h;
- struct hlist_nulls_head *ct_hash;
- struct hlist_nulls_node *n;
- struct nf_conn *tmp;
- rcu_read_lock();
- nf_conntrack_get_ht(&ct_hash, &hashsz);
- if (i >= hashsz) {
- rcu_read_unlock();
- break;
- }
- hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) {
- struct net *net;
- tmp = nf_ct_tuplehash_to_ctrack(h);
- if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) {
- nf_ct_offload_timeout(tmp);
- continue;
- }
- if (nf_ct_is_expired(tmp)) {
- nf_ct_gc_expired(tmp);
- continue;
- }
- if (nf_conntrack_max95 == 0 || gc_worker_skip_ct(tmp))
- continue;
- net = nf_ct_net(tmp);
- if (atomic_read(&net->ct.count) < nf_conntrack_max95)
- continue;
- /* need to take reference to avoid possible races */
- if (!atomic_inc_not_zero(&tmp->ct_general.use))
- continue;
- if (gc_worker_skip_ct(tmp)) {
- nf_ct_put(tmp);
- continue;
- }
- if (gc_worker_can_early_drop(tmp))
- nf_ct_kill(tmp);
- nf_ct_put(tmp);
- }
- /* could check get_nulls_value() here and restart if ct
- * was moved to another chain. But given gc is best-effort
- * we will just continue with next hash slot.
- */
- rcu_read_unlock();
- cond_resched();
- i++;
- if (time_after(jiffies, end_time) && i < hashsz) {
- gc_work->next_bucket = i;
- next_run = 0;
- break;
- }
- } while (i < hashsz);
- if (gc_work->exiting)
- return;
- /*
- * Eviction will normally happen from the packet path, and not
- * from this gc worker.
- *
- * This worker is only here to reap expired entries when system went
- * idle after a busy period.
- */
- if (next_run) {
- gc_work->early_drop = false;
- gc_work->next_bucket = 0;
- }
- queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run);
- }
- static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
- {
- INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker);
- gc_work->exiting = false;
- }
- static struct nf_conn *
- __nf_conntrack_alloc(struct net *net,
- const struct nf_conntrack_zone *zone,
- const struct nf_conntrack_tuple *orig,
- const struct nf_conntrack_tuple *repl,
- gfp_t gfp, u32 hash)
- {
- struct nf_conn *ct;
- /* We don't want any race condition at early drop stage */
- atomic_inc(&net->ct.count);
- if (nf_conntrack_max &&
- unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {
- if (!early_drop(net, hash)) {
- if (!conntrack_gc_work.early_drop)
- conntrack_gc_work.early_drop = true;
- atomic_dec(&net->ct.count);
- net_warn_ratelimited("nf_conntrack: table full, dropping packet\n");
- return ERR_PTR(-ENOMEM);
- }
- }
- /*
- * Do not use kmem_cache_zalloc(), as this cache uses
- * SLAB_TYPESAFE_BY_RCU.
- */
- ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
- if (ct == NULL)
- goto out;
- spin_lock_init(&ct->lock);
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
- ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
- ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
- /* save hash for reusing when confirming */
- *(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
- ct->status = 0;
- WRITE_ONCE(ct->timeout, 0);
- write_pnet(&ct->ct_net, net);
- memset(&ct->__nfct_init_offset, 0,
- offsetof(struct nf_conn, proto) -
- offsetof(struct nf_conn, __nfct_init_offset));
- nf_ct_zone_add(ct, zone);
- /* Because we use RCU lookups, we set ct_general.use to zero before
- * this is inserted in any list.
- */
- atomic_set(&ct->ct_general.use, 0);
- return ct;
- out:
- atomic_dec(&net->ct.count);
- return ERR_PTR(-ENOMEM);
- }
- struct nf_conn *nf_conntrack_alloc(struct net *net,
- const struct nf_conntrack_zone *zone,
- const struct nf_conntrack_tuple *orig,
- const struct nf_conntrack_tuple *repl,
- gfp_t gfp)
- {
- return __nf_conntrack_alloc(net, zone, orig, repl, gfp, 0);
- }
- EXPORT_SYMBOL_GPL(nf_conntrack_alloc);
- void nf_conntrack_free(struct nf_conn *ct)
- {
- struct net *net = nf_ct_net(ct);
- /* A freed object has refcnt == 0, that's
- * the golden rule for SLAB_TYPESAFE_BY_RCU
- */
- WARN_ON(atomic_read(&ct->ct_general.use) != 0);
- nf_ct_ext_destroy(ct);
- kmem_cache_free(nf_conntrack_cachep, ct);
- smp_mb__before_atomic();
- atomic_dec(&net->ct.count);
- }
- EXPORT_SYMBOL_GPL(nf_conntrack_free);
- /* Allocate a new conntrack: we return -ENOMEM if classification
- failed due to stress. Otherwise it really is unclassifiable. */
- static noinline struct nf_conntrack_tuple_hash *
- init_conntrack(struct net *net, struct nf_conn *tmpl,
- const struct nf_conntrack_tuple *tuple,
- struct sk_buff *skb,
- unsigned int dataoff, u32 hash)
- {
- struct nf_conn *ct;
- struct nf_conn_help *help;
- struct nf_conntrack_tuple repl_tuple;
- struct nf_conntrack_ecache *ecache;
- struct nf_conntrack_expect *exp = NULL;
- const struct nf_conntrack_zone *zone;
- struct nf_conn_timeout *timeout_ext;
- struct nf_conntrack_zone tmp;
- if (!nf_ct_invert_tuple(&repl_tuple, tuple)) {
- pr_debug("Can't invert tuple.\n");
- return NULL;
- }
- zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
- ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC,
- hash);
- if (IS_ERR(ct))
- return (struct nf_conntrack_tuple_hash *)ct;
- if (!nf_ct_add_synproxy(ct, tmpl)) {
- nf_conntrack_free(ct);
- return ERR_PTR(-ENOMEM);
- }
- timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL;
- if (timeout_ext)
- nf_ct_timeout_ext_add(ct, rcu_dereference(timeout_ext->timeout),
- GFP_ATOMIC);
- nf_ct_acct_ext_add(ct, GFP_ATOMIC);
- nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
- nf_ct_labels_ext_add(ct);
- ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL;
- nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0,
- ecache ? ecache->expmask : 0,
- GFP_ATOMIC);
- local_bh_disable();
- if (net->ct.expect_count) {
- spin_lock(&nf_conntrack_expect_lock);
- exp = nf_ct_find_expectation(net, zone, tuple);
- if (exp) {
- pr_debug("expectation arrives ct=%p exp=%p\n",
- ct, exp);
- /* Welcome, Mr. Bond. We've been expecting you... */
- __set_bit(IPS_EXPECTED_BIT, &ct->status);
- /* exp->master safe, refcnt bumped in nf_ct_find_expectation */
- ct->master = exp->master;
- if (exp->helper) {
- help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
- if (help)
- rcu_assign_pointer(help->helper, exp->helper);
- }
- #ifdef CONFIG_NF_CONNTRACK_MARK
- ct->mark = exp->master->mark;
- #endif
- #ifdef CONFIG_NF_CONNTRACK_SECMARK
- ct->secmark = exp->master->secmark;
- #endif
- NF_CT_STAT_INC(net, expect_new);
- }
- spin_unlock(&nf_conntrack_expect_lock);
- }
- if (!exp)
- __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
- /* Now it is inserted into the unconfirmed list, bump refcount */
- nf_conntrack_get(&ct->ct_general);
- nf_ct_add_to_unconfirmed_list(ct);
- local_bh_enable();
- if (exp) {
- if (exp->expectfn)
- exp->expectfn(ct, exp);
- nf_ct_expect_put(exp);
- }
- return &ct->tuplehash[IP_CT_DIR_ORIGINAL];
- }
- /* On success, returns 0, sets skb->_nfct | ctinfo */
- static int
- resolve_normal_ct(struct nf_conn *tmpl,
- struct sk_buff *skb,
- unsigned int dataoff,
- u_int8_t protonum,
- const struct nf_hook_state *state)
- {
- const struct nf_conntrack_zone *zone;
- struct nf_conntrack_tuple tuple;
- struct nf_conntrack_tuple_hash *h;
- enum ip_conntrack_info ctinfo;
- struct nf_conntrack_zone tmp;
- struct nf_conn *ct;
- u32 hash;
- if (!nf_ct_get_tuple(skb, skb_network_offset(skb),
- dataoff, state->pf, protonum, state->net,
- &tuple)) {
- pr_debug("Can't get tuple\n");
- return 0;
- }
- /* look for tuple match */
- zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
- hash = hash_conntrack_raw(&tuple, state->net);
- h = __nf_conntrack_find_get(state->net, zone, &tuple, hash);
- if (!h) {
- h = init_conntrack(state->net, tmpl, &tuple,
- skb, dataoff, hash);
- if (!h)
- return 0;
- if (IS_ERR(h))
- return PTR_ERR(h);
- }
- ct = nf_ct_tuplehash_to_ctrack(h);
- /* It exists; we have (non-exclusive) reference. */
- if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) {
- ctinfo = IP_CT_ESTABLISHED_REPLY;
- } else {
- /* Once we've had two way comms, always ESTABLISHED. */
- if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
- pr_debug("normal packet for %p\n", ct);
- ctinfo = IP_CT_ESTABLISHED;
- } else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) {
- pr_debug("related packet for %p\n", ct);
- ctinfo = IP_CT_RELATED;
- } else {
- pr_debug("new packet for %p\n", ct);
- ctinfo = IP_CT_NEW;
- }
- }
- nf_ct_set(skb, ct, ctinfo);
- return 0;
- }
- /*
- * icmp packets need special treatment to handle error messages that are
- * related to a connection.
- *
- * Callers need to check if skb has a conntrack assigned when this
- * helper returns; in such case skb belongs to an already known connection.
- */
- static unsigned int __cold
- nf_conntrack_handle_icmp(struct nf_conn *tmpl,
- struct sk_buff *skb,
- unsigned int dataoff,
- u8 protonum,
- const struct nf_hook_state *state)
- {
- int ret;
- if (state->pf == NFPROTO_IPV4 && protonum == IPPROTO_ICMP)
- ret = nf_conntrack_icmpv4_error(tmpl, skb, dataoff, state);
- #if IS_ENABLED(CONFIG_IPV6)
- else if (state->pf == NFPROTO_IPV6 && protonum == IPPROTO_ICMPV6)
- ret = nf_conntrack_icmpv6_error(tmpl, skb, dataoff, state);
- #endif
- else
- return NF_ACCEPT;
- if (ret <= 0)
- NF_CT_STAT_INC_ATOMIC(state->net, error);
- return ret;
- }
- static int generic_packet(struct nf_conn *ct, struct sk_buff *skb,
- enum ip_conntrack_info ctinfo)
- {
- const unsigned int *timeout = nf_ct_timeout_lookup(ct);
- if (!timeout)
- timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout;
- nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
- return NF_ACCEPT;
- }
- /* Returns verdict for packet, or -1 for invalid. */
- static int nf_conntrack_handle_packet(struct nf_conn *ct,
- struct sk_buff *skb,
- unsigned int dataoff,
- enum ip_conntrack_info ctinfo,
- const struct nf_hook_state *state)
- {
- switch (nf_ct_protonum(ct)) {
- case IPPROTO_TCP:
- return nf_conntrack_tcp_packet(ct, skb, dataoff,
- ctinfo, state);
- case IPPROTO_UDP:
- return nf_conntrack_udp_packet(ct, skb, dataoff,
- ctinfo, state);
- case IPPROTO_ICMP:
- return nf_conntrack_icmp_packet(ct, skb, ctinfo, state);
- #if IS_ENABLED(CONFIG_IPV6)
- case IPPROTO_ICMPV6:
- return nf_conntrack_icmpv6_packet(ct, skb, ctinfo, state);
- #endif
- #ifdef CONFIG_NF_CT_PROTO_UDPLITE
- case IPPROTO_UDPLITE:
- return nf_conntrack_udplite_packet(ct, skb, dataoff,
- ctinfo, state);
- #endif
- #ifdef CONFIG_NF_CT_PROTO_SCTP
- case IPPROTO_SCTP:
- return nf_conntrack_sctp_packet(ct, skb, dataoff,
- ctinfo, state);
- #endif
- #ifdef CONFIG_NF_CT_PROTO_DCCP
- case IPPROTO_DCCP:
- return nf_conntrack_dccp_packet(ct, skb, dataoff,
- ctinfo, state);
- #endif
- #ifdef CONFIG_NF_CT_PROTO_GRE
- case IPPROTO_GRE:
- return nf_conntrack_gre_packet(ct, skb, dataoff,
- ctinfo, state);
- #endif
- }
- return generic_packet(ct, skb, ctinfo);
- }
- unsigned int
- nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state)
- {
- enum ip_conntrack_info ctinfo;
- struct nf_conn *ct, *tmpl;
- u_int8_t protonum;
- int dataoff, ret;
- tmpl = nf_ct_get(skb, &ctinfo);
- if (tmpl || ctinfo == IP_CT_UNTRACKED) {
- /* Previously seen (loopback or untracked)? Ignore. */
- if ((tmpl && !nf_ct_is_template(tmpl)) ||
- ctinfo == IP_CT_UNTRACKED)
- return NF_ACCEPT;
- skb->_nfct = 0;
- }
- /* rcu_read_lock()ed by nf_hook_thresh */
- dataoff = get_l4proto(skb, skb_network_offset(skb), state->pf, &protonum);
- if (dataoff <= 0) {
- pr_debug("not prepared to track yet or error occurred\n");
- NF_CT_STAT_INC_ATOMIC(state->net, invalid);
- ret = NF_ACCEPT;
- goto out;
- }
- if (protonum == IPPROTO_ICMP || protonum == IPPROTO_ICMPV6) {
- ret = nf_conntrack_handle_icmp(tmpl, skb, dataoff,
- protonum, state);
- if (ret <= 0) {
- ret = -ret;
- goto out;
- }
- /* ICMP[v6] protocol trackers may assign one conntrack. */
- if (skb->_nfct)
- goto out;
- }
- repeat:
- ret = resolve_normal_ct(tmpl, skb, dataoff,
- protonum, state);
- if (ret < 0) {
- /* Too stressed to deal. */
- NF_CT_STAT_INC_ATOMIC(state->net, drop);
- ret = NF_DROP;
- goto out;
- }
- ct = nf_ct_get(skb, &ctinfo);
- if (!ct) {
- /* Not valid part of a connection */
- NF_CT_STAT_INC_ATOMIC(state->net, invalid);
- ret = NF_ACCEPT;
- goto out;
- }
- ret = nf_conntrack_handle_packet(ct, skb, dataoff, ctinfo, state);
- if (ret <= 0) {
- /* Invalid: inverse of the return code tells
- * the netfilter core what to do */
- pr_debug("nf_conntrack_in: Can't track with proto module\n");
- nf_conntrack_put(&ct->ct_general);
- skb->_nfct = 0;
- /* Special case: TCP tracker reports an attempt to reopen a
- * closed/aborted connection. We have to go back and create a
- * fresh conntrack.
- */
- if (ret == -NF_REPEAT)
- goto repeat;
- NF_CT_STAT_INC_ATOMIC(state->net, invalid);
- if (ret == -NF_DROP)
- NF_CT_STAT_INC_ATOMIC(state->net, drop);
- ret = -ret;
- goto out;
- }
- if (ctinfo == IP_CT_ESTABLISHED_REPLY &&
- !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
- nf_conntrack_event_cache(IPCT_REPLY, ct);
- out:
- if (tmpl)
- nf_ct_put(tmpl);
- return ret;
- }
- EXPORT_SYMBOL_GPL(nf_conntrack_in);
- /* Alter reply tuple (maybe alter helper). This is for NAT, and is
- implicitly racy: see __nf_conntrack_confirm */
- void nf_conntrack_alter_reply(struct nf_conn *ct,
- const struct nf_conntrack_tuple *newreply)
- {
- struct nf_conn_help *help = nfct_help(ct);
- /* Should be unconfirmed, so not in hash table yet */
- WARN_ON(nf_ct_is_confirmed(ct));
- pr_debug("Altering reply tuple of %p to ", ct);
- nf_ct_dump_tuple(newreply);
- ct->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply;
- if (ct->master || (help && !hlist_empty(&help->expectations)))
- return;
- rcu_read_lock();
- __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC);
- rcu_read_unlock();
- }
- EXPORT_SYMBOL_GPL(nf_conntrack_alter_reply);
- /* Refresh conntrack for this many jiffies and do accounting if do_acct is 1 */
- void __nf_ct_refresh_acct(struct nf_conn *ct,
- enum ip_conntrack_info ctinfo,
- const struct sk_buff *skb,
- u32 extra_jiffies,
- bool do_acct)
- {
- /* Only update if this is not a fixed timeout */
- if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status))
- goto acct;
- /* If not in hash table, timer will not be active yet */
- if (nf_ct_is_confirmed(ct))
- extra_jiffies += nfct_time_stamp;
- if (READ_ONCE(ct->timeout) != extra_jiffies)
- WRITE_ONCE(ct->timeout, extra_jiffies);
- acct:
- if (do_acct)
- nf_ct_acct_update(ct, CTINFO2DIR(ctinfo), skb->len);
- }
- EXPORT_SYMBOL_GPL(__nf_ct_refresh_acct);
- bool nf_ct_kill_acct(struct nf_conn *ct,
- enum ip_conntrack_info ctinfo,
- const struct sk_buff *skb)
- {
- nf_ct_acct_update(ct, CTINFO2DIR(ctinfo), skb->len);
- return nf_ct_delete(ct, 0, 0);
- }
- EXPORT_SYMBOL_GPL(nf_ct_kill_acct);
- #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
- #include <linux/netfilter/nfnetlink.h>
- #include <linux/netfilter/nfnetlink_conntrack.h>
- #include <linux/mutex.h>
- /* Generic function for tcp/udp/sctp/dccp and alike. */
- int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
- const struct nf_conntrack_tuple *tuple)
- {
- if (nla_put_be16(skb, CTA_PROTO_SRC_PORT, tuple->src.u.tcp.port) ||
- nla_put_be16(skb, CTA_PROTO_DST_PORT, tuple->dst.u.tcp.port))
- goto nla_put_failure;
- return 0;
- nla_put_failure:
- return -1;
- }
- EXPORT_SYMBOL_GPL(nf_ct_port_tuple_to_nlattr);
- const struct nla_policy nf_ct_port_nla_policy[CTA_PROTO_MAX+1] = {
- [CTA_PROTO_SRC_PORT] = { .type = NLA_U16 },
- [CTA_PROTO_DST_PORT] = { .type = NLA_U16 },
- };
- EXPORT_SYMBOL_GPL(nf_ct_port_nla_policy);
- int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[],
- struct nf_conntrack_tuple *t,
- u_int32_t flags)
- {
- if (flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) {
- if (!tb[CTA_PROTO_SRC_PORT])
- return -EINVAL;
- t->src.u.tcp.port = nla_get_be16(tb[CTA_PROTO_SRC_PORT]);
- }
- if (flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) {
- if (!tb[CTA_PROTO_DST_PORT])
- return -EINVAL;
- t->dst.u.tcp.port = nla_get_be16(tb[CTA_PROTO_DST_PORT]);
- }
- return 0;
- }
- EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_to_tuple);
- unsigned int nf_ct_port_nlattr_tuple_size(void)
- {
- static unsigned int size __read_mostly;
- if (!size)
- size = nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1);
- return size;
- }
- EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size);
- #endif
- /* Used by ipt_REJECT and ip6t_REJECT. */
- static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb)
- {
- struct nf_conn *ct;
- enum ip_conntrack_info ctinfo;
- /* This ICMP is in reverse direction to the packet which caused it */
- ct = nf_ct_get(skb, &ctinfo);
- if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL)
- ctinfo = IP_CT_RELATED_REPLY;
- else
- ctinfo = IP_CT_RELATED;
- /* Attach to new skbuff, and increment count */
- nf_ct_set(nskb, ct, ctinfo);
- nf_conntrack_get(skb_nfct(nskb));
- }
- static int __nf_conntrack_update(struct net *net, struct sk_buff *skb,
- struct nf_conn *ct,
- enum ip_conntrack_info ctinfo)
- {
- struct nf_conntrack_tuple_hash *h;
- struct nf_conntrack_tuple tuple;
- struct nf_nat_hook *nat_hook;
- unsigned int status;
- int dataoff;
- u16 l3num;
- u8 l4num;
- l3num = nf_ct_l3num(ct);
- dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num);
- if (dataoff <= 0)
- return -1;
- if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num,
- l4num, net, &tuple))
- return -1;
- if (ct->status & IPS_SRC_NAT) {
- memcpy(tuple.src.u3.all,
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.all,
- sizeof(tuple.src.u3.all));
- tuple.src.u.all =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.all;
- }
- if (ct->status & IPS_DST_NAT) {
- memcpy(tuple.dst.u3.all,
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.all,
- sizeof(tuple.dst.u3.all));
- tuple.dst.u.all =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.all;
- }
- h = nf_conntrack_find_get(net, nf_ct_zone(ct), &tuple);
- if (!h)
- return 0;
- /* Store status bits of the conntrack that is clashing to re-do NAT
- * mangling according to what it has been done already to this packet.
- */
- status = ct->status;
- nf_ct_put(ct);
- ct = nf_ct_tuplehash_to_ctrack(h);
- nf_ct_set(skb, ct, ctinfo);
- nat_hook = rcu_dereference(nf_nat_hook);
- if (!nat_hook)
- return 0;
- if (status & IPS_SRC_NAT &&
- nat_hook->manip_pkt(skb, ct, NF_NAT_MANIP_SRC,
- IP_CT_DIR_ORIGINAL) == NF_DROP)
- return -1;
- if (status & IPS_DST_NAT &&
- nat_hook->manip_pkt(skb, ct, NF_NAT_MANIP_DST,
- IP_CT_DIR_ORIGINAL) == NF_DROP)
- return -1;
- return 0;
- }
- /* This packet is coming from userspace via nf_queue, complete the packet
- * processing after the helper invocation in nf_confirm().
- */
- static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct,
- enum ip_conntrack_info ctinfo)
- {
- const struct nf_conntrack_helper *helper;
- const struct nf_conn_help *help;
- int protoff;
- help = nfct_help(ct);
- if (!help)
- return 0;
- helper = rcu_dereference(help->helper);
- if (!(helper->flags & NF_CT_HELPER_F_USERSPACE))
- return 0;
- switch (nf_ct_l3num(ct)) {
- case NFPROTO_IPV4:
- protoff = skb_network_offset(skb) + ip_hdrlen(skb);
- break;
- #if IS_ENABLED(CONFIG_IPV6)
- case NFPROTO_IPV6: {
- __be16 frag_off;
- u8 pnum;
- pnum = ipv6_hdr(skb)->nexthdr;
- protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
- &frag_off);
- if (protoff < 0 || (frag_off & htons(~0x7)) != 0)
- return 0;
- break;
- }
- #endif
- default:
- return 0;
- }
- if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
- !nf_is_loopback_packet(skb)) {
- if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) {
- NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
- return -1;
- }
- }
- /* We've seen it coming out the other side: confirm it */
- return nf_conntrack_confirm(skb) == NF_DROP ? - 1 : 0;
- }
- static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
- {
- enum ip_conntrack_info ctinfo;
- struct nf_conn *ct;
- int err;
- ct = nf_ct_get(skb, &ctinfo);
- if (!ct)
- return 0;
- if (!nf_ct_is_confirmed(ct)) {
- err = __nf_conntrack_update(net, skb, ct, ctinfo);
- if (err < 0)
- return err;
- ct = nf_ct_get(skb, &ctinfo);
- }
- return nf_confirm_cthelper(skb, ct, ctinfo);
- }
- static bool nf_conntrack_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
- const struct sk_buff *skb)
- {
- const struct nf_conntrack_tuple *src_tuple;
- const struct nf_conntrack_tuple_hash *hash;
- struct nf_conntrack_tuple srctuple;
- enum ip_conntrack_info ctinfo;
- struct nf_conn *ct;
- ct = nf_ct_get(skb, &ctinfo);
- if (ct) {
- src_tuple = nf_ct_tuple(ct, CTINFO2DIR(ctinfo));
- memcpy(dst_tuple, src_tuple, sizeof(*dst_tuple));
- return true;
- }
- if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
- NFPROTO_IPV4, dev_net(skb->dev),
- &srctuple))
- return false;
- hash = nf_conntrack_find_get(dev_net(skb->dev),
- &nf_ct_zone_dflt,
- &srctuple);
- if (!hash)
- return false;
- ct = nf_ct_tuplehash_to_ctrack(hash);
- src_tuple = nf_ct_tuple(ct, !hash->tuple.dst.dir);
- memcpy(dst_tuple, src_tuple, sizeof(*dst_tuple));
- nf_ct_put(ct);
- return true;
- }
- /* Bring out ya dead! */
- static struct nf_conn *
- get_next_corpse(int (*iter)(struct nf_conn *i, void *data),
- void *data, unsigned int *bucket)
- {
- struct nf_conntrack_tuple_hash *h;
- struct nf_conn *ct;
- struct hlist_nulls_node *n;
- spinlock_t *lockp;
- for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
- struct hlist_nulls_head *hslot = &nf_conntrack_hash[*bucket];
- if (hlist_nulls_empty(hslot))
- continue;
- lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
- local_bh_disable();
- nf_conntrack_lock(lockp);
- hlist_nulls_for_each_entry(h, n, hslot, hnnode) {
- if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY)
- continue;
- /* All nf_conn objects are added to hash table twice, one
- * for original direction tuple, once for the reply tuple.
- *
- * Exception: In the IPS_NAT_CLASH case, only the reply
- * tuple is added (the original tuple already existed for
- * a different object).
- *
- * We only need to call the iterator once for each
- * conntrack, so we just use the 'reply' direction
- * tuple while iterating.
- */
- ct = nf_ct_tuplehash_to_ctrack(h);
- if (iter(ct, data))
- goto found;
- }
- spin_unlock(lockp);
- local_bh_enable();
- cond_resched();
- }
- return NULL;
- found:
- atomic_inc(&ct->ct_general.use);
- spin_unlock(lockp);
- local_bh_enable();
- return ct;
- }
- static void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data),
- void *data, u32 portid, int report)
- {
- unsigned int bucket = 0;
- struct nf_conn *ct;
- might_sleep();
- mutex_lock(&nf_conntrack_mutex);
- while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) {
- /* Time to push up daises... */
- nf_ct_delete(ct, portid, report);
- nf_ct_put(ct);
- cond_resched();
- }
- mutex_unlock(&nf_conntrack_mutex);
- }
- struct iter_data {
- int (*iter)(struct nf_conn *i, void *data);
- void *data;
- struct net *net;
- };
- static int iter_net_only(struct nf_conn *i, void *data)
- {
- struct iter_data *d = data;
- if (!net_eq(d->net, nf_ct_net(i)))
- return 0;
- return d->iter(i, d->data);
- }
- static void
- __nf_ct_unconfirmed_destroy(struct net *net)
- {
- int cpu;
- for_each_possible_cpu(cpu) {
- struct nf_conntrack_tuple_hash *h;
- struct hlist_nulls_node *n;
- struct ct_pcpu *pcpu;
- pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
- spin_lock_bh(&pcpu->lock);
- hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) {
- struct nf_conn *ct;
- ct = nf_ct_tuplehash_to_ctrack(h);
- /* we cannot call iter() on unconfirmed list, the
- * owning cpu can reallocate ct->ext at any time.
- */
- set_bit(IPS_DYING_BIT, &ct->status);
- }
- spin_unlock_bh(&pcpu->lock);
- cond_resched();
- }
- }
- void nf_ct_unconfirmed_destroy(struct net *net)
- {
- might_sleep();
- if (atomic_read(&net->ct.count) > 0) {
- __nf_ct_unconfirmed_destroy(net);
- nf_queue_nf_hook_drop(net);
- synchronize_net();
- }
- }
- EXPORT_SYMBOL_GPL(nf_ct_unconfirmed_destroy);
- void nf_ct_iterate_cleanup_net(struct net *net,
- int (*iter)(struct nf_conn *i, void *data),
- void *data, u32 portid, int report)
- {
- struct iter_data d;
- might_sleep();
- if (atomic_read(&net->ct.count) == 0)
- return;
- d.iter = iter;
- d.data = data;
- d.net = net;
- nf_ct_iterate_cleanup(iter_net_only, &d, portid, report);
- }
- EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup_net);
- /**
- * nf_ct_iterate_destroy - destroy unconfirmed conntracks and iterate table
- * @iter: callback to invoke for each conntrack
- * @data: data to pass to @iter
- *
- * Like nf_ct_iterate_cleanup, but first marks conntracks on the
- * unconfirmed list as dying (so they will not be inserted into
- * main table).
- *
- * Can only be called in module exit path.
- */
- void
- nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data)
- {
- struct net *net;
- down_read(&net_rwsem);
- for_each_net(net) {
- if (atomic_read(&net->ct.count) == 0)
- continue;
- __nf_ct_unconfirmed_destroy(net);
- nf_queue_nf_hook_drop(net);
- }
- up_read(&net_rwsem);
- /* Need to wait for netns cleanup worker to finish, if its
- * running -- it might have deleted a net namespace from
- * the global list, so our __nf_ct_unconfirmed_destroy() might
- * not have affected all namespaces.
- */
- net_ns_barrier();
- /* a conntrack could have been unlinked from unconfirmed list
- * before we grabbed pcpu lock in __nf_ct_unconfirmed_destroy().
- * This makes sure its inserted into conntrack table.
- */
- synchronize_net();
- nf_ct_iterate_cleanup(iter, data, 0, 0);
- }
- EXPORT_SYMBOL_GPL(nf_ct_iterate_destroy);
- static int kill_all(struct nf_conn *i, void *data)
- {
- return net_eq(nf_ct_net(i), data);
- }
- void nf_conntrack_cleanup_start(void)
- {
- conntrack_gc_work.exiting = true;
- RCU_INIT_POINTER(ip_ct_attach, NULL);
- }
- void nf_conntrack_cleanup_end(void)
- {
- RCU_INIT_POINTER(nf_ct_hook, NULL);
- cancel_delayed_work_sync(&conntrack_gc_work.dwork);
- kvfree(nf_conntrack_hash);
- nf_conntrack_proto_fini();
- nf_conntrack_seqadj_fini();
- nf_conntrack_labels_fini();
- nf_conntrack_helper_fini();
- nf_conntrack_timeout_fini();
- nf_conntrack_ecache_fini();
- nf_conntrack_tstamp_fini();
- nf_conntrack_acct_fini();
- nf_conntrack_expect_fini();
- kmem_cache_destroy(nf_conntrack_cachep);
- }
- /*
- * Mishearing the voices in his head, our hero wonders how he's
- * supposed to kill the mall.
- */
- void nf_conntrack_cleanup_net(struct net *net)
- {
- LIST_HEAD(single);
- list_add(&net->exit_list, &single);
- nf_conntrack_cleanup_net_list(&single);
- }
- void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
- {
- int busy;
- struct net *net;
- /*
- * This makes sure all current packets have passed through
- * netfilter framework. Roll on, two-stage module
- * delete...
- */
- synchronize_net();
- i_see_dead_people:
- busy = 0;
- list_for_each_entry(net, net_exit_list, exit_list) {
- nf_ct_iterate_cleanup(kill_all, net, 0, 0);
- if (atomic_read(&net->ct.count) != 0)
- busy = 1;
- }
- if (busy) {
- schedule();
- goto i_see_dead_people;
- }
- list_for_each_entry(net, net_exit_list, exit_list) {
- nf_conntrack_proto_pernet_fini(net);
- nf_conntrack_ecache_pernet_fini(net);
- nf_conntrack_expect_pernet_fini(net);
- free_percpu(net->ct.stat);
- free_percpu(net->ct.pcpu_lists);
- }
- }
- void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
- {
- struct hlist_nulls_head *hash;
- unsigned int nr_slots, i;
- if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head)))
- return NULL;
- BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head));
- nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head));
- hash = kvcalloc(nr_slots, sizeof(struct hlist_nulls_head), GFP_KERNEL);
- if (hash && nulls)
- for (i = 0; i < nr_slots; i++)
- INIT_HLIST_NULLS_HEAD(&hash[i], i);
- return hash;
- }
- EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable);
- int nf_conntrack_hash_resize(unsigned int hashsize)
- {
- int i, bucket;
- unsigned int old_size;
- struct hlist_nulls_head *hash, *old_hash;
- struct nf_conntrack_tuple_hash *h;
- struct nf_conn *ct;
- if (!hashsize)
- return -EINVAL;
- hash = nf_ct_alloc_hashtable(&hashsize, 1);
- if (!hash)
- return -ENOMEM;
- mutex_lock(&nf_conntrack_mutex);
- old_size = nf_conntrack_htable_size;
- if (old_size == hashsize) {
- mutex_unlock(&nf_conntrack_mutex);
- kvfree(hash);
- return 0;
- }
- local_bh_disable();
- nf_conntrack_all_lock();
- write_seqcount_begin(&nf_conntrack_generation);
- /* Lookups in the old hash might happen in parallel, which means we
- * might get false negatives during connection lookup. New connections
- * created because of a false negative won't make it into the hash
- * though since that required taking the locks.
- */
- for (i = 0; i < nf_conntrack_htable_size; i++) {
- while (!hlist_nulls_empty(&nf_conntrack_hash[i])) {
- h = hlist_nulls_entry(nf_conntrack_hash[i].first,
- struct nf_conntrack_tuple_hash, hnnode);
- ct = nf_ct_tuplehash_to_ctrack(h);
- hlist_nulls_del_rcu(&h->hnnode);
- bucket = __hash_conntrack(nf_ct_net(ct),
- &h->tuple, hashsize);
- hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
- }
- }
- old_size = nf_conntrack_htable_size;
- old_hash = nf_conntrack_hash;
- nf_conntrack_hash = hash;
- nf_conntrack_htable_size = hashsize;
- write_seqcount_end(&nf_conntrack_generation);
- nf_conntrack_all_unlock();
- local_bh_enable();
- mutex_unlock(&nf_conntrack_mutex);
- synchronize_net();
- kvfree(old_hash);
- return 0;
- }
- int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp)
- {
- unsigned int hashsize;
- int rc;
- if (current->nsproxy->net_ns != &init_net)
- return -EOPNOTSUPP;
- /* On boot, we can set this without any fancy locking. */
- if (!nf_conntrack_hash)
- return param_set_uint(val, kp);
- rc = kstrtouint(val, 0, &hashsize);
- if (rc)
- return rc;
- return nf_conntrack_hash_resize(hashsize);
- }
- static __always_inline unsigned int total_extension_size(void)
- {
- /* remember to add new extensions below */
- BUILD_BUG_ON(NF_CT_EXT_NUM > 9);
- return sizeof(struct nf_ct_ext) +
- sizeof(struct nf_conn_help)
- #if IS_ENABLED(CONFIG_NF_NAT)
- + sizeof(struct nf_conn_nat)
- #endif
- + sizeof(struct nf_conn_seqadj)
- + sizeof(struct nf_conn_acct)
- #ifdef CONFIG_NF_CONNTRACK_EVENTS
- + sizeof(struct nf_conntrack_ecache)
- #endif
- #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
- + sizeof(struct nf_conn_tstamp)
- #endif
- #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
- + sizeof(struct nf_conn_timeout)
- #endif
- #ifdef CONFIG_NF_CONNTRACK_LABELS
- + sizeof(struct nf_conn_labels)
- #endif
- #if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY)
- + sizeof(struct nf_conn_synproxy)
- #endif
- ;
- };
- int nf_conntrack_init_start(void)
- {
- unsigned long nr_pages = totalram_pages();
- int max_factor = 8;
- int ret = -ENOMEM;
- int i;
- /* struct nf_ct_ext uses u8 to store offsets/size */
- BUILD_BUG_ON(total_extension_size() > 255u);
- seqcount_spinlock_init(&nf_conntrack_generation,
- &nf_conntrack_locks_all_lock);
- for (i = 0; i < CONNTRACK_LOCKS; i++)
- spin_lock_init(&nf_conntrack_locks[i]);
- if (!nf_conntrack_htable_size) {
- /* Idea from tcp.c: use 1/16384 of memory.
- * On i386: 32MB machine has 512 buckets.
- * >= 1GB machines have 16384 buckets.
- * >= 4GB machines have 65536 buckets.
- */
- nf_conntrack_htable_size
- = (((nr_pages << PAGE_SHIFT) / 16384)
- / sizeof(struct hlist_head));
- if (nr_pages > (4 * (1024 * 1024 * 1024 / PAGE_SIZE)))
- nf_conntrack_htable_size = 65536;
- else if (nr_pages > (1024 * 1024 * 1024 / PAGE_SIZE))
- nf_conntrack_htable_size = 16384;
- if (nf_conntrack_htable_size < 32)
- nf_conntrack_htable_size = 32;
- /* Use a max. factor of four by default to get the same max as
- * with the old struct list_heads. When a table size is given
- * we use the old value of 8 to avoid reducing the max.
- * entries. */
- max_factor = 4;
- }
- nf_conntrack_hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, 1);
- if (!nf_conntrack_hash)
- return -ENOMEM;
- nf_conntrack_max = max_factor * nf_conntrack_htable_size;
- nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
- sizeof(struct nf_conn),
- NFCT_INFOMASK + 1,
- SLAB_TYPESAFE_BY_RCU | SLAB_HWCACHE_ALIGN, NULL);
- if (!nf_conntrack_cachep)
- goto err_cachep;
- ret = nf_conntrack_expect_init();
- if (ret < 0)
- goto err_expect;
- ret = nf_conntrack_acct_init();
- if (ret < 0)
- goto err_acct;
- ret = nf_conntrack_tstamp_init();
- if (ret < 0)
- goto err_tstamp;
- ret = nf_conntrack_ecache_init();
- if (ret < 0)
- goto err_ecache;
- ret = nf_conntrack_timeout_init();
- if (ret < 0)
- goto err_timeout;
- ret = nf_conntrack_helper_init();
- if (ret < 0)
- goto err_helper;
- ret = nf_conntrack_labels_init();
- if (ret < 0)
- goto err_labels;
- ret = nf_conntrack_seqadj_init();
- if (ret < 0)
- goto err_seqadj;
- ret = nf_conntrack_proto_init();
- if (ret < 0)
- goto err_proto;
- conntrack_gc_work_init(&conntrack_gc_work);
- queue_delayed_work(system_power_efficient_wq, &conntrack_gc_work.dwork, HZ);
- return 0;
- err_proto:
- nf_conntrack_seqadj_fini();
- err_seqadj:
- nf_conntrack_labels_fini();
- err_labels:
- nf_conntrack_helper_fini();
- err_helper:
- nf_conntrack_timeout_fini();
- err_timeout:
- nf_conntrack_ecache_fini();
- err_ecache:
- nf_conntrack_tstamp_fini();
- err_tstamp:
- nf_conntrack_acct_fini();
- err_acct:
- nf_conntrack_expect_fini();
- err_expect:
- kmem_cache_destroy(nf_conntrack_cachep);
- err_cachep:
- kvfree(nf_conntrack_hash);
- return ret;
- }
- static struct nf_ct_hook nf_conntrack_hook = {
- .update = nf_conntrack_update,
- .destroy = destroy_conntrack,
- .get_tuple_skb = nf_conntrack_get_tuple_skb,
- };
- void nf_conntrack_init_end(void)
- {
- /* For use by REJECT target */
- RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach);
- RCU_INIT_POINTER(nf_ct_hook, &nf_conntrack_hook);
- }
- /*
- * We need to use special "null" values, not used in hash table
- */
- #define UNCONFIRMED_NULLS_VAL ((1<<30)+0)
- #define DYING_NULLS_VAL ((1<<30)+1)
- int nf_conntrack_init_net(struct net *net)
- {
- int ret = -ENOMEM;
- int cpu;
- BUILD_BUG_ON(IP_CT_UNTRACKED == IP_CT_NUMBER);
- BUILD_BUG_ON_NOT_POWER_OF_2(CONNTRACK_LOCKS);
- atomic_set(&net->ct.count, 0);
- net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu);
- if (!net->ct.pcpu_lists)
- goto err_stat;
- for_each_possible_cpu(cpu) {
- struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
- spin_lock_init(&pcpu->lock);
- INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL);
- INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL);
- }
- net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
- if (!net->ct.stat)
- goto err_pcpu_lists;
- ret = nf_conntrack_expect_pernet_init(net);
- if (ret < 0)
- goto err_expect;
- nf_conntrack_acct_pernet_init(net);
- nf_conntrack_tstamp_pernet_init(net);
- nf_conntrack_ecache_pernet_init(net);
- nf_conntrack_helper_pernet_init(net);
- nf_conntrack_proto_pernet_init(net);
- return 0;
- err_expect:
- free_percpu(net->ct.stat);
- err_pcpu_lists:
- free_percpu(net->ct.pcpu_lists);
- err_stat:
- return ret;
- }
|