Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
53 kB · 2029 lines
C
at master
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030// SPDX-License-Identifier: GPL-2.0-only/* * Copyright (c) 2015 Nicira, Inc. */
#include <linux/module.h>#include <linux/openvswitch.h>#include <linux/tcp.h>#include <linux/udp.h>#include <linux/sctp.h>#include <linux/static_key.h>#include <linux/string_helpers.h>#include <net/ip.h>#include <net/genetlink.h>#include <net/netfilter/nf_conntrack_core.h>#include <net/netfilter/nf_conntrack_count.h>#include <net/netfilter/nf_conntrack_helper.h>#include <net/netfilter/nf_conntrack_labels.h>#include <net/netfilter/nf_conntrack_seqadj.h>#include <net/netfilter/nf_conntrack_timeout.h>#include <net/netfilter/nf_conntrack_zones.h>#include <net/netfilter/ipv6/nf_defrag_ipv6.h>#include <net/ipv6_frag.h>
#if IS_ENABLED(CONFIG_NF_NAT)#include <net/netfilter/nf_nat.h>#endif
#include <net/netfilter/nf_conntrack_act_ct.h>
#include "datapath.h"#include "drop.h"#include "conntrack.h"#include "flow.h"#include "flow_netlink.h"
struct ovs_ct_len_tbl { int maxlen; int minlen;};
/* Metadata mark for masked write to conntrack mark */struct md_mark { u32 value; u32 mask;};
/* Metadata label for masked write to conntrack label. */struct md_labels { struct ovs_key_ct_labels value; struct ovs_key_ct_labels mask;};
enum ovs_ct_nat { OVS_CT_NAT = 1 << 0, /* NAT for committed connections only. */ OVS_CT_SRC_NAT = 1 << 1, /* Source NAT for NEW connections. */ OVS_CT_DST_NAT = 1 << 2, /* Destination NAT for NEW connections. */};
/* Conntrack action context for execution. */struct ovs_conntrack_info { struct nf_conntrack_helper *helper; struct nf_conntrack_zone zone; struct nf_conn *ct; u8 commit : 1; u8 nat : 3; /* enum ovs_ct_nat */ u8 force : 1; u8 have_eventmask : 1; u16 family; u32 eventmask; /* Mask of 1 << IPCT_*. */ struct md_mark mark; struct md_labels labels; char timeout[CTNL_TIMEOUT_NAME_MAX]; struct nf_ct_timeout *nf_ct_timeout;#if IS_ENABLED(CONFIG_NF_NAT) struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */#endif};
#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)#define OVS_CT_LIMIT_UNLIMITED 0#define OVS_CT_LIMIT_DEFAULT OVS_CT_LIMIT_UNLIMITED#define CT_LIMIT_HASH_BUCKETS 512static DEFINE_STATIC_KEY_FALSE(ovs_ct_limit_enabled);
struct ovs_ct_limit { /* Elements in ovs_ct_limit_info->limits hash table */ struct hlist_node hlist_node; struct rcu_head rcu; u16 zone; u32 limit;};
struct ovs_ct_limit_info { u32 default_limit; struct hlist_head *limits; struct nf_conncount_data *data;};
static const struct nla_policy ct_limit_policy[OVS_CT_LIMIT_ATTR_MAX + 1] = { [OVS_CT_LIMIT_ATTR_ZONE_LIMIT] = { .type = NLA_NESTED, },};#endif
static bool labels_nonzero(const struct ovs_key_ct_labels *labels);
static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info);
static u16 key_to_nfproto(const struct sw_flow_key *key){ switch (ntohs(key->eth.type)) { case ETH_P_IP: return NFPROTO_IPV4; case ETH_P_IPV6: return NFPROTO_IPV6; default: return NFPROTO_UNSPEC; }}
/* Map SKB connection state into the values used by flow definition. */static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo){ u8 ct_state = OVS_CS_F_TRACKED;
switch (ctinfo) { case IP_CT_ESTABLISHED_REPLY: case IP_CT_RELATED_REPLY: ct_state |= OVS_CS_F_REPLY_DIR; break; default: break; }
switch (ctinfo) { case IP_CT_ESTABLISHED: case IP_CT_ESTABLISHED_REPLY: ct_state |= OVS_CS_F_ESTABLISHED; break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: ct_state |= OVS_CS_F_RELATED; break; case IP_CT_NEW: ct_state |= OVS_CS_F_NEW; break; default: break; }
return ct_state;}
static u32 ovs_ct_get_mark(const struct nf_conn *ct){#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) return ct ? READ_ONCE(ct->mark) : 0;#else return 0;#endif}
/* Guard against conntrack labels max size shrinking below 128 bits. */#if NF_CT_LABELS_MAX_SIZE < 16#error NF_CT_LABELS_MAX_SIZE must be at least 16 bytes#endif
static void ovs_ct_get_labels(const struct nf_conn *ct, struct ovs_key_ct_labels *labels){ struct nf_conn_labels *cl = NULL;
if (ct) { if (ct->master && !nf_ct_is_confirmed(ct)) ct = ct->master; cl = nf_ct_labels_find(ct); } if (cl) memcpy(labels, cl->bits, OVS_CT_LABELS_LEN); else memset(labels, 0, OVS_CT_LABELS_LEN);}
static void __ovs_ct_update_key_orig_tp(struct sw_flow_key *key, const struct nf_conntrack_tuple *orig, u8 icmp_proto){ key->ct_orig_proto = orig->dst.protonum; if (orig->dst.protonum == icmp_proto) { key->ct.orig_tp.src = htons(orig->dst.u.icmp.type); key->ct.orig_tp.dst = htons(orig->dst.u.icmp.code); } else { key->ct.orig_tp.src = orig->src.u.all; key->ct.orig_tp.dst = orig->dst.u.all; }}
static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, const struct nf_conntrack_zone *zone, const struct nf_conn *ct){ key->ct_state = state; key->ct_zone = zone->id; key->ct.mark = ovs_ct_get_mark(ct); ovs_ct_get_labels(ct, &key->ct.labels);
if (ct) { const struct nf_conntrack_tuple *orig;
/* Use the master if we have one. */ if (ct->master) ct = ct->master; orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
/* IP version must match with the master connection. */ if (key->eth.type == htons(ETH_P_IP) && nf_ct_l3num(ct) == NFPROTO_IPV4) { key->ipv4.ct_orig.src = orig->src.u3.ip; key->ipv4.ct_orig.dst = orig->dst.u3.ip; __ovs_ct_update_key_orig_tp(key, orig, IPPROTO_ICMP); return; } else if (key->eth.type == htons(ETH_P_IPV6) && !sw_flow_key_is_nd(key) && nf_ct_l3num(ct) == NFPROTO_IPV6) { key->ipv6.ct_orig.src = orig->src.u3.in6; key->ipv6.ct_orig.dst = orig->dst.u3.in6; __ovs_ct_update_key_orig_tp(key, orig, NEXTHDR_ICMP); return; } } /* Clear 'ct_orig_proto' to mark the non-existence of conntrack * original direction key fields. */ key->ct_orig_proto = 0;}
/* Update 'key' based on skb->_nfct. If 'post_ct' is true, then OVS has * previously sent the packet to conntrack via the ct action. If * 'keep_nat_flags' is true, the existing NAT flags retained, else they are * initialized from the connection status. */static void ovs_ct_update_key(const struct sk_buff *skb, const struct ovs_conntrack_info *info, struct sw_flow_key *key, bool post_ct, bool keep_nat_flags){ const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; enum ip_conntrack_info ctinfo; struct nf_conn *ct; u8 state = 0;
ct = nf_ct_get(skb, &ctinfo); if (ct) { state = ovs_ct_get_state(ctinfo); /* All unconfirmed entries are NEW connections. */ if (!nf_ct_is_confirmed(ct)) state |= OVS_CS_F_NEW; /* OVS persists the related flag for the duration of the * connection. */ if (ct->master) state |= OVS_CS_F_RELATED; if (keep_nat_flags) { state |= key->ct_state & OVS_CS_F_NAT_MASK; } else { if (ct->status & IPS_SRC_NAT) state |= OVS_CS_F_SRC_NAT; if (ct->status & IPS_DST_NAT) state |= OVS_CS_F_DST_NAT; } zone = nf_ct_zone(ct); } else if (post_ct) { state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID; if (info) zone = &info->zone; } __ovs_ct_update_key(key, state, zone, ct);}
/* This is called to initialize CT key fields possibly coming in from the local * stack. */void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key, bool post_ct){ ovs_ct_update_key(skb, NULL, key, post_ct, false);}
int ovs_ct_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, struct sk_buff *skb){ if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, output->ct_state)) return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, output->ct_zone)) return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, output->ct.mark)) return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(output->ct.labels), &output->ct.labels)) return -EMSGSIZE;
if (swkey->ct_orig_proto) { if (swkey->eth.type == htons(ETH_P_IP)) { struct ovs_key_ct_tuple_ipv4 orig;
memset(&orig, 0, sizeof(orig)); orig.ipv4_src = output->ipv4.ct_orig.src; orig.ipv4_dst = output->ipv4.ct_orig.dst; orig.src_port = output->ct.orig_tp.src; orig.dst_port = output->ct.orig_tp.dst; orig.ipv4_proto = output->ct_orig_proto;
if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, sizeof(orig), &orig)) return -EMSGSIZE; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { struct ovs_key_ct_tuple_ipv6 orig;
memset(&orig, 0, sizeof(orig)); memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32, sizeof(orig.ipv6_src)); memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32, sizeof(orig.ipv6_dst)); orig.src_port = output->ct.orig_tp.src; orig.dst_port = output->ct.orig_tp.dst; orig.ipv6_proto = output->ct_orig_proto;
if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, sizeof(orig), &orig)) return -EMSGSIZE; } }
return 0;}
static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key, u32 ct_mark, u32 mask){#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark;
new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask)); if (READ_ONCE(ct->mark) != new_mark) { WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); key->ct.mark = new_mark; }
return 0;#else return -ENOTSUPP;#endif}
static struct nf_conn_labels *ovs_ct_get_conn_labels(struct nf_conn *ct){ struct nf_conn_labels *cl;
cl = nf_ct_labels_find(ct); if (!cl) { nf_ct_labels_ext_add(ct); cl = nf_ct_labels_find(ct); }
return cl;}
/* Initialize labels for a new, yet to be committed conntrack entry. Note that * since the new connection is not yet confirmed, and thus no-one else has * access to it's labels, we simply write them over. */static int ovs_ct_init_labels(struct nf_conn *ct, struct sw_flow_key *key, const struct ovs_key_ct_labels *labels, const struct ovs_key_ct_labels *mask){ struct nf_conn_labels *cl, *master_cl; bool have_mask = labels_nonzero(mask);
/* Inherit master's labels to the related connection? */ master_cl = ct->master ? nf_ct_labels_find(ct->master) : NULL;
if (!master_cl && !have_mask) return 0; /* Nothing to do. */
cl = ovs_ct_get_conn_labels(ct); if (!cl) return -ENOSPC;
/* Inherit the master's labels, if any. */ if (master_cl) *cl = *master_cl;
if (have_mask) { u32 *dst = (u32 *)cl->bits; int i;
for (i = 0; i < OVS_CT_LABELS_LEN_32; i++) dst[i] = (dst[i] & ~mask->ct_labels_32[i]) | (labels->ct_labels_32[i] & mask->ct_labels_32[i]); }
/* Labels are included in the IPCTNL_MSG_CT_NEW event only if the * IPCT_LABEL bit is set in the event cache. */ nf_conntrack_event_cache(IPCT_LABEL, ct);
memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN);
return 0;}
static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key, const struct ovs_key_ct_labels *labels, const struct ovs_key_ct_labels *mask){ struct nf_conn_labels *cl; int err;
cl = ovs_ct_get_conn_labels(ct); if (!cl) return -ENOSPC;
err = nf_connlabels_replace(ct, labels->ct_labels_32, mask->ct_labels_32, OVS_CT_LABELS_LEN_32); if (err) return err;
memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN);
return 0;}
static int ovs_ct_handle_fragments(struct net *net, struct sw_flow_key *key, u16 zone, int family, struct sk_buff *skb){ struct ovs_skb_cb ovs_cb = *OVS_CB(skb); int err;
err = nf_ct_handle_fragments(net, skb, zone, family, &key->ip.proto, &ovs_cb.mru); if (err) return err;
/* The key extracted from the fragment that completed this datagram * likely didn't have an L4 header, so regenerate it. */ ovs_flow_key_update_l3l4(skb, key); key->ip.frag = OVS_FRAG_TYPE_NONE; *OVS_CB(skb) = ovs_cb;
return 0;}
/* This replicates logic from nf_conntrack_core.c that is not exported. */static enum ip_conntrack_infoovs_ct_get_info(const struct nf_conntrack_tuple_hash *h){ const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) return IP_CT_ESTABLISHED_REPLY; /* Once we've had two way comms, always ESTABLISHED. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) return IP_CT_ESTABLISHED; if (test_bit(IPS_EXPECTED_BIT, &ct->status)) return IP_CT_RELATED; return IP_CT_NEW;}
/* Find an existing connection which this packet belongs to without * re-attributing statistics or modifying the connection state. This allows an * skb->_nfct lost due to an upcall to be recovered during actions execution. * * Must be called with rcu_read_lock. * * On success, populates skb->_nfct and returns the connection. Returns NULL * if there is no existing entry. */static struct nf_conn *ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, u8 l3num, struct sk_buff *skb, bool natted){ struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct;
if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), l3num, net, &tuple)) { pr_debug("ovs_ct_find_existing: Can't get tuple\n"); return NULL; }
/* Must invert the tuple if skb has been transformed by NAT. */ if (natted) { struct nf_conntrack_tuple inverse;
if (!nf_ct_invert_tuple(&inverse, &tuple)) { pr_debug("ovs_ct_find_existing: Inversion failed!\n"); return NULL; } tuple = inverse; }
/* look for tuple match */ h = nf_conntrack_find_get(net, zone, &tuple); if (!h) return NULL; /* Not found. */
ct = nf_ct_tuplehash_to_ctrack(h);
/* Inverted packet tuple matches the reverse direction conntrack tuple, * select the other tuplehash to get the right 'ctinfo' bits for this * packet. */ if (natted) h = &ct->tuplehash[!h->tuple.dst.dir];
nf_ct_set(skb, ct, ovs_ct_get_info(h)); return ct;}
staticstruct nf_conn *ovs_ct_executed(struct net *net, const struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb, bool *ct_executed){ struct nf_conn *ct = NULL;
/* If no ct, check if we have evidence that an existing conntrack entry * might be found for this skb. This happens when we lose a skb->_nfct * due to an upcall, or if the direction is being forced. If the * connection was not confirmed, it is not cached and needs to be run * through conntrack again. */ *ct_executed = (key->ct_state & OVS_CS_F_TRACKED) && !(key->ct_state & OVS_CS_F_INVALID) && (key->ct_zone == info->zone.id);
if (*ct_executed || (!key->ct_state && info->force)) { ct = ovs_ct_find_existing(net, &info->zone, info->family, skb, !!(key->ct_state & OVS_CS_F_NAT_MASK)); }
return ct;}
/* Determine whether skb->_nfct is equal to the result of conntrack lookup. */static bool skb_nfct_cached(struct net *net, const struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb){ enum ip_conntrack_info ctinfo; struct nf_conn *ct; bool ct_executed = true;
ct = nf_ct_get(skb, &ctinfo); if (!ct) ct = ovs_ct_executed(net, key, info, skb, &ct_executed);
if (ct) nf_ct_get(skb, &ctinfo); else return false;
if (!net_eq(net, read_pnet(&ct->ct_net))) return false; if (!nf_ct_zone_equal_any(info->ct, nf_ct_zone(ct))) return false; if (info->helper) { struct nf_conn_help *help;
help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); if (help && rcu_access_pointer(help->helper) != info->helper) return false; } if (info->nf_ct_timeout) { struct nf_conn_timeout *timeout_ext;
timeout_ext = nf_ct_timeout_find(ct); if (!timeout_ext || info->nf_ct_timeout != rcu_dereference(timeout_ext->timeout)) return false; } /* Force conntrack entry direction to the current packet? */ if (info->force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { /* Delete the conntrack entry if confirmed, else just release * the reference. */ if (nf_ct_is_confirmed(ct)) nf_ct_delete(ct, 0, 0);
nf_ct_put(ct); nf_ct_set(skb, NULL, 0); return false; }
return ct_executed;}
#if IS_ENABLED(CONFIG_NF_NAT)static void ovs_nat_update_key(struct sw_flow_key *key, const struct sk_buff *skb, enum nf_nat_manip_type maniptype){ if (maniptype == NF_NAT_MANIP_SRC) { __be16 src;
key->ct_state |= OVS_CS_F_SRC_NAT; if (key->eth.type == htons(ETH_P_IP)) key->ipv4.addr.src = ip_hdr(skb)->saddr; else if (key->eth.type == htons(ETH_P_IPV6)) memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr, sizeof(key->ipv6.addr.src)); else return;
if (key->ip.proto == IPPROTO_UDP) src = udp_hdr(skb)->source; else if (key->ip.proto == IPPROTO_TCP) src = tcp_hdr(skb)->source; else if (key->ip.proto == IPPROTO_SCTP) src = sctp_hdr(skb)->source; else return;
key->tp.src = src; } else { __be16 dst;
key->ct_state |= OVS_CS_F_DST_NAT; if (key->eth.type == htons(ETH_P_IP)) key->ipv4.addr.dst = ip_hdr(skb)->daddr; else if (key->eth.type == htons(ETH_P_IPV6)) memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr, sizeof(key->ipv6.addr.dst)); else return;
if (key->ip.proto == IPPROTO_UDP) dst = udp_hdr(skb)->dest; else if (key->ip.proto == IPPROTO_TCP) dst = tcp_hdr(skb)->dest; else if (key->ip.proto == IPPROTO_SCTP) dst = sctp_hdr(skb)->dest; else return;
key->tp.dst = dst; }}
/* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo){ int err, action = 0;
if (!(info->nat & OVS_CT_NAT)) return NF_ACCEPT; if (info->nat & OVS_CT_SRC_NAT) action |= BIT(NF_NAT_MANIP_SRC); if (info->nat & OVS_CT_DST_NAT) action |= BIT(NF_NAT_MANIP_DST);
err = nf_ct_nat(skb, ct, ctinfo, &action, &info->range, info->commit); if (err != NF_ACCEPT) return err;
if (action & BIT(NF_NAT_MANIP_SRC)) ovs_nat_update_key(key, skb, NF_NAT_MANIP_SRC); if (action & BIT(NF_NAT_MANIP_DST)) ovs_nat_update_key(key, skb, NF_NAT_MANIP_DST);
return err;}#else /* !CONFIG_NF_NAT */static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo){ return NF_ACCEPT;}#endif
static int verdict_to_errno(unsigned int verdict){ switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: return 0; case NF_DROP: return -EINVAL; case NF_STOLEN: return -EINPROGRESS; default: break; }
return -EINVAL;}
/* Pass 'skb' through conntrack in 'net', using zone configured in 'info', if * not done already. Update key with new CT state after passing the packet * through conntrack. * Note that if the packet is deemed invalid by conntrack, skb->_nfct will be * set to NULL and 0 will be returned. */static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb){ /* If we are recirculating packets to match on conntrack fields and * committing with a separate conntrack action, then we don't need to * actually run the packet through conntrack twice unless it's for a * different zone. */ bool cached = skb_nfct_cached(net, key, info, skb); enum ip_conntrack_info ctinfo; struct nf_conn *ct;
if (!cached) { struct nf_hook_state state = { .hook = NF_INET_PRE_ROUTING, .pf = info->family, .net = net, }; struct nf_conn *tmpl = info->ct; int err;
/* Associate skb with specified zone. */ if (tmpl) { ct = nf_ct_get(skb, &ctinfo); nf_ct_put(ct); nf_conntrack_get(&tmpl->ct_general); nf_ct_set(skb, tmpl, IP_CT_NEW); }
err = nf_conntrack_in(skb, &state); if (err != NF_ACCEPT) return verdict_to_errno(err);
/* Clear CT state NAT flags to mark that we have not yet done * NAT after the nf_conntrack_in() call. We can actually clear * the whole state, as it will be re-initialized below. */ key->ct_state = 0;
/* Update the key, but keep the NAT flags. */ ovs_ct_update_key(skb, info, key, true, true); }
ct = nf_ct_get(skb, &ctinfo); if (ct) { bool add_helper = false;
/* Packets starting a new connection must be NATted before the * helper, so that the helper knows about the NAT. We enforce * this by delaying both NAT and helper calls for unconfirmed * connections until the committing CT action. For later * packets NAT and Helper may be called in either order. * * NAT will be done only if the CT action has NAT, and only * once per packet (per zone), as guarded by the NAT bits in * the key->ct_state. */ if (info->nat && !(key->ct_state & OVS_CS_F_NAT_MASK) && (nf_ct_is_confirmed(ct) || info->commit)) { int err = ovs_ct_nat(net, key, info, skb, ct, ctinfo);
err = verdict_to_errno(err); if (err) return err; }
/* Userspace may decide to perform a ct lookup without a helper * specified followed by a (recirculate and) commit with one, * or attach a helper in a later commit. Therefore, for * connections which we will commit, we may need to attach * the helper here. */ if (!nf_ct_is_confirmed(ct) && info->commit && info->helper && !nfct_help(ct)) { int err = __nf_ct_try_assign_helper(ct, info->ct, GFP_ATOMIC); if (err) return err; add_helper = true;
/* helper installed, add seqadj if NAT is required */ if (info->nat && !nfct_seqadj(ct)) { if (!nfct_seqadj_ext_add(ct)) return -EINVAL; } }
/* Call the helper only if: * - nf_conntrack_in() was executed above ("!cached") or a * helper was just attached ("add_helper") for a confirmed * connection, or * - When committing an unconfirmed connection. */ if ((nf_ct_is_confirmed(ct) ? !cached || add_helper : info->commit)) { int err = nf_ct_helper(skb, ct, ctinfo, info->family);
err = verdict_to_errno(err); if (err) return err; }
if (nf_ct_protonum(ct) == IPPROTO_TCP && nf_ct_is_confirmed(ct) && nf_conntrack_tcp_established(ct)) { /* Be liberal for tcp packets so that out-of-window * packets are not marked invalid. */ nf_ct_set_tcp_be_liberal(ct); }
nf_conn_act_ct_ext_fill(skb, ct, ctinfo); }
return 0;}
/* Lookup connection and read fields into key. */static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb){ struct nf_conn *ct; int err;
err = __ovs_ct_lookup(net, key, info, skb); if (err) return err;
ct = (struct nf_conn *)skb_nfct(skb); if (ct) nf_ct_deliver_cached_events(ct);
return 0;}
static bool labels_nonzero(const struct ovs_key_ct_labels *labels){ size_t i;
for (i = 0; i < OVS_CT_LABELS_LEN_32; i++) if (labels->ct_labels_32[i]) return true;
return false;}
#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)static struct hlist_head *ct_limit_hash_bucket( const struct ovs_ct_limit_info *info, u16 zone){ return &info->limits[zone & (CT_LIMIT_HASH_BUCKETS - 1)];}
/* Call with ovs_mutex */static void ct_limit_set(const struct ovs_ct_limit_info *info, struct ovs_ct_limit *new_ct_limit){ struct ovs_ct_limit *ct_limit; struct hlist_head *head;
head = ct_limit_hash_bucket(info, new_ct_limit->zone); hlist_for_each_entry_rcu(ct_limit, head, hlist_node, lockdep_ovsl_is_held()) { if (ct_limit->zone == new_ct_limit->zone) { hlist_replace_rcu(&ct_limit->hlist_node, &new_ct_limit->hlist_node); kfree_rcu(ct_limit, rcu); return; } }
hlist_add_head_rcu(&new_ct_limit->hlist_node, head);}
/* Call with ovs_mutex */static void ct_limit_del(const struct ovs_ct_limit_info *info, u16 zone){ struct ovs_ct_limit *ct_limit; struct hlist_head *head; struct hlist_node *n;
head = ct_limit_hash_bucket(info, zone); hlist_for_each_entry_safe(ct_limit, n, head, hlist_node) { if (ct_limit->zone == zone) { hlist_del_rcu(&ct_limit->hlist_node); kfree_rcu(ct_limit, rcu); return; } }}
/* Call with RCU read lock */static u32 ct_limit_get(const struct ovs_ct_limit_info *info, u16 zone){ struct ovs_ct_limit *ct_limit; struct hlist_head *head;
head = ct_limit_hash_bucket(info, zone); hlist_for_each_entry_rcu(ct_limit, head, hlist_node) { if (ct_limit->zone == zone) return ct_limit->limit; }
return info->default_limit;}
static int ovs_ct_check_limit(struct net *net, const struct sk_buff *skb, const struct ovs_conntrack_info *info){ struct ovs_net *ovs_net = net_generic(net, ovs_net_id); const struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; u32 per_zone_limit, connections; u32 conncount_key;
conncount_key = info->zone.id;
per_zone_limit = ct_limit_get(ct_limit_info, info->zone.id); if (per_zone_limit == OVS_CT_LIMIT_UNLIMITED) return 0;
connections = nf_conncount_count_skb(net, skb, info->family, ct_limit_info->data, &conncount_key); if (connections > per_zone_limit) return -ENOMEM;
return 0;}#endif
/* Lookup connection and confirm if unconfirmed. */static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb){ enum ip_conntrack_info ctinfo; struct nf_conn *ct; int err;
err = __ovs_ct_lookup(net, key, info, skb); if (err) return err;
/* The connection could be invalid, in which case this is a no-op.*/ ct = nf_ct_get(skb, &ctinfo); if (!ct) return 0;
#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) if (static_branch_unlikely(&ovs_ct_limit_enabled)) { if (!nf_ct_is_confirmed(ct)) { err = ovs_ct_check_limit(net, skb, info); if (err) { net_warn_ratelimited("openvswitch: zone: %u " "exceeds conntrack limit\n", info->zone.id); return err; } } }#endif
/* Set the conntrack event mask if given. NEW and DELETE events have * their own groups, but the NFNLGRP_CONNTRACK_UPDATE group listener * typically would receive many kinds of updates. Setting the event * mask allows those events to be filtered. The set event mask will * remain in effect for the lifetime of the connection unless changed * by a further CT action with both the commit flag and the eventmask * option. */ if (info->have_eventmask) { struct nf_conntrack_ecache *cache = nf_ct_ecache_find(ct);
if (cache) cache->ctmask = info->eventmask; }
/* Apply changes before confirming the connection so that the initial * conntrack NEW netlink event carries the values given in the CT * action. */ if (info->mark.mask) { err = ovs_ct_set_mark(ct, key, info->mark.value, info->mark.mask); if (err) return err; } if (!nf_ct_is_confirmed(ct)) { err = ovs_ct_init_labels(ct, key, &info->labels.value, &info->labels.mask); if (err) return err;
nf_conn_act_ct_ext_add(skb, ct, ctinfo); } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, &info->labels.mask); if (err) return err; } /* This will take care of sending queued events even if the connection * is already confirmed. */ err = nf_conntrack_confirm(skb);
return verdict_to_errno(err);}
/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero * value if 'skb' is freed. */int ovs_ct_execute(struct net *net, struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_conntrack_info *info){ int nh_ofs; int err;
/* The conntrack module expects to be working at L3. */ nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs);
err = nf_ct_skb_network_trim(skb, info->family); if (err) { kfree_skb(skb); return err; }
if (key->ip.frag != OVS_FRAG_TYPE_NONE) { err = ovs_ct_handle_fragments(net, key, info->zone.id, info->family, skb); if (err) return err; }
if (info->commit) err = ovs_ct_commit(net, key, info, skb); else err = ovs_ct_lookup(net, key, info, skb);
/* conntrack core returned NF_STOLEN */ if (err == -EINPROGRESS) return err;
skb_push_rcsum(skb, nh_ofs); if (err) ovs_kfree_skb_reason(skb, OVS_DROP_CONNTRACK); return err;}
int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key){ enum ip_conntrack_info ctinfo; struct nf_conn *ct;
ct = nf_ct_get(skb, &ctinfo);
nf_ct_put(ct); nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
if (key) ovs_ct_fill_key(skb, key, false);
return 0;}
#if IS_ENABLED(CONFIG_NF_NAT)static int parse_nat(const struct nlattr *attr, struct ovs_conntrack_info *info, bool log){ struct nlattr *a; int rem; bool have_ip_max = false; bool have_proto_max = false; bool ip_vers = (info->family == NFPROTO_IPV6);
nla_for_each_nested(a, attr, rem) { static const int ovs_nat_attr_lens[OVS_NAT_ATTR_MAX + 1][2] = { [OVS_NAT_ATTR_SRC] = {0, 0}, [OVS_NAT_ATTR_DST] = {0, 0}, [OVS_NAT_ATTR_IP_MIN] = {sizeof(struct in_addr), sizeof(struct in6_addr)}, [OVS_NAT_ATTR_IP_MAX] = {sizeof(struct in_addr), sizeof(struct in6_addr)}, [OVS_NAT_ATTR_PROTO_MIN] = {sizeof(u16), sizeof(u16)}, [OVS_NAT_ATTR_PROTO_MAX] = {sizeof(u16), sizeof(u16)}, [OVS_NAT_ATTR_PERSISTENT] = {0, 0}, [OVS_NAT_ATTR_PROTO_HASH] = {0, 0}, [OVS_NAT_ATTR_PROTO_RANDOM] = {0, 0}, }; int type = nla_type(a);
if (type > OVS_NAT_ATTR_MAX) { OVS_NLERR(log, "Unknown NAT attribute (type=%d, max=%d)", type, OVS_NAT_ATTR_MAX); return -EINVAL; }
if (nla_len(a) != ovs_nat_attr_lens[type][ip_vers]) { OVS_NLERR(log, "NAT attribute type %d has unexpected length (%d != %d)", type, nla_len(a), ovs_nat_attr_lens[type][ip_vers]); return -EINVAL; }
switch (type) { case OVS_NAT_ATTR_SRC: case OVS_NAT_ATTR_DST: if (info->nat) { OVS_NLERR(log, "Only one type of NAT may be specified"); return -ERANGE; } info->nat |= OVS_CT_NAT; info->nat |= ((type == OVS_NAT_ATTR_SRC) ? OVS_CT_SRC_NAT : OVS_CT_DST_NAT); break;
case OVS_NAT_ATTR_IP_MIN: nla_memcpy(&info->range.min_addr, a, sizeof(info->range.min_addr)); info->range.flags |= NF_NAT_RANGE_MAP_IPS; break;
case OVS_NAT_ATTR_IP_MAX: have_ip_max = true; nla_memcpy(&info->range.max_addr, a, sizeof(info->range.max_addr)); info->range.flags |= NF_NAT_RANGE_MAP_IPS; break;
case OVS_NAT_ATTR_PROTO_MIN: info->range.min_proto.all = htons(nla_get_u16(a)); info->range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; break;
case OVS_NAT_ATTR_PROTO_MAX: have_proto_max = true; info->range.max_proto.all = htons(nla_get_u16(a)); info->range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; break;
case OVS_NAT_ATTR_PERSISTENT: info->range.flags |= NF_NAT_RANGE_PERSISTENT; break;
case OVS_NAT_ATTR_PROTO_HASH: info->range.flags |= NF_NAT_RANGE_PROTO_RANDOM; break;
case OVS_NAT_ATTR_PROTO_RANDOM: info->range.flags |= NF_NAT_RANGE_PROTO_RANDOM_FULLY; break;
default: OVS_NLERR(log, "Unknown nat attribute (%d)", type); return -EINVAL; } }
if (rem > 0) { OVS_NLERR(log, "NAT attribute has %d unknown bytes", rem); return -EINVAL; } if (!info->nat) { /* Do not allow flags if no type is given. */ if (info->range.flags) { OVS_NLERR(log, "NAT flags may be given only when NAT range (SRC or DST) is also specified." ); return -EINVAL; } info->nat = OVS_CT_NAT; /* NAT existing connections. */ } else if (!info->commit) { OVS_NLERR(log, "NAT attributes may be specified only when CT COMMIT flag is also specified." ); return -EINVAL; } /* Allow missing IP_MAX. */ if (info->range.flags & NF_NAT_RANGE_MAP_IPS && !have_ip_max) { memcpy(&info->range.max_addr, &info->range.min_addr, sizeof(info->range.max_addr)); } /* Allow missing PROTO_MAX. */ if (info->range.flags & NF_NAT_RANGE_PROTO_SPECIFIED && !have_proto_max) { info->range.max_proto.all = info->range.min_proto.all; } return 0;}#endif
static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_FORCE_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16), .maxlen = sizeof(u16) }, [OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark), .maxlen = sizeof(struct md_mark) }, [OVS_CT_ATTR_LABELS] = { .minlen = sizeof(struct md_labels), .maxlen = sizeof(struct md_labels) }, [OVS_CT_ATTR_HELPER] = { .minlen = 1, .maxlen = NF_CT_HELPER_NAME_LEN },#if IS_ENABLED(CONFIG_NF_NAT) /* NAT length is checked when parsing the nested attributes. */ [OVS_CT_ATTR_NAT] = { .minlen = 0, .maxlen = INT_MAX },#endif [OVS_CT_ATTR_EVENTMASK] = { .minlen = sizeof(u32), .maxlen = sizeof(u32) }, [OVS_CT_ATTR_TIMEOUT] = { .minlen = 1, .maxlen = CTNL_TIMEOUT_NAME_MAX },};
static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, const char **helper, bool log){ struct nlattr *a; int rem;
nla_for_each_nested(a, attr, rem) { int type = nla_type(a); int maxlen; int minlen;
if (type > OVS_CT_ATTR_MAX) { OVS_NLERR(log, "Unknown conntrack attr (type=%d, max=%d)", type, OVS_CT_ATTR_MAX); return -EINVAL; }
maxlen = ovs_ct_attr_lens[type].maxlen; minlen = ovs_ct_attr_lens[type].minlen; if (nla_len(a) < minlen || nla_len(a) > maxlen) { OVS_NLERR(log, "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)", type, nla_len(a), maxlen); return -EINVAL; }
switch (type) { case OVS_CT_ATTR_FORCE_COMMIT: info->force = true; fallthrough; case OVS_CT_ATTR_COMMIT: info->commit = true; break;#ifdef CONFIG_NF_CONNTRACK_ZONES case OVS_CT_ATTR_ZONE: info->zone.id = nla_get_u16(a); break;#endif#ifdef CONFIG_NF_CONNTRACK_MARK case OVS_CT_ATTR_MARK: { struct md_mark *mark = nla_data(a);
if (!mark->mask) { OVS_NLERR(log, "ct_mark mask cannot be 0"); return -EINVAL; } info->mark = *mark; break; }#endif#ifdef CONFIG_NF_CONNTRACK_LABELS case OVS_CT_ATTR_LABELS: { struct md_labels *labels = nla_data(a);
if (!labels_nonzero(&labels->mask)) { OVS_NLERR(log, "ct_labels mask cannot be 0"); return -EINVAL; } info->labels = *labels; break; }#endif case OVS_CT_ATTR_HELPER: *helper = nla_data(a); if (!string_is_terminated(*helper, nla_len(a))) { OVS_NLERR(log, "Invalid conntrack helper"); return -EINVAL; } break;#if IS_ENABLED(CONFIG_NF_NAT) case OVS_CT_ATTR_NAT: { int err = parse_nat(a, info, log);
if (err) return err; break; }#endif case OVS_CT_ATTR_EVENTMASK: info->have_eventmask = true; info->eventmask = nla_get_u32(a); break;#ifdef CONFIG_NF_CONNTRACK_TIMEOUT case OVS_CT_ATTR_TIMEOUT: memcpy(info->timeout, nla_data(a), nla_len(a)); if (!string_is_terminated(info->timeout, nla_len(a))) { OVS_NLERR(log, "Invalid conntrack timeout"); return -EINVAL; } break;#endif
default: OVS_NLERR(log, "Unknown conntrack attr (%d)", type); return -EINVAL; } }
#ifdef CONFIG_NF_CONNTRACK_MARK if (!info->commit && info->mark.mask) { OVS_NLERR(log, "Setting conntrack mark requires 'commit' flag."); return -EINVAL; }#endif#ifdef CONFIG_NF_CONNTRACK_LABELS if (!info->commit && labels_nonzero(&info->labels.mask)) { OVS_NLERR(log, "Setting conntrack labels requires 'commit' flag."); return -EINVAL; }#endif if (rem > 0) { OVS_NLERR(log, "Conntrack attr has %d unknown bytes", rem); return -EINVAL; }
return 0;}
bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr){ if (attr == OVS_KEY_ATTR_CT_STATE) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && attr == OVS_KEY_ATTR_CT_ZONE) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && attr == OVS_KEY_ATTR_CT_MARK) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && attr == OVS_KEY_ATTR_CT_LABELS) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
return ovs_net->xt_label; }
return false;}
int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, bool log){ struct ovs_conntrack_info ct_info; const char *helper = NULL; u16 family; int err;
family = key_to_nfproto(key); if (family == NFPROTO_UNSPEC) { OVS_NLERR(log, "ct family unspecified"); return -EINVAL; }
memset(&ct_info, 0, sizeof(ct_info)); ct_info.family = family;
nf_ct_zone_init(&ct_info.zone, NF_CT_DEFAULT_ZONE_ID, NF_CT_DEFAULT_ZONE_DIR, 0);
err = parse_ct(attr, &ct_info, &helper, log); if (err) return err;
/* Set up template for tracking connections in specific zones. */ ct_info.ct = nf_ct_tmpl_alloc(net, &ct_info.zone, GFP_KERNEL); if (!ct_info.ct) { OVS_NLERR(log, "Failed to allocate conntrack template"); return -ENOMEM; }
if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) OVS_NLERR(log, "Failed to associated timeout policy '%s'", ct_info.timeout); else ct_info.nf_ct_timeout = rcu_dereference( nf_ct_timeout_find(ct_info.ct)->timeout);
}
if (helper) { err = nf_ct_add_helper(ct_info.ct, helper, ct_info.family, key->ip.proto, ct_info.nat, &ct_info.helper); if (err) { OVS_NLERR(log, "Failed to add %s helper %d", helper, err); goto err_free_ct; } }
err = ovs_nla_add_action(sfa, OVS_ACTION_ATTR_CT, &ct_info, sizeof(ct_info), log); if (err) goto err_free_ct;
if (ct_info.commit) __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); return 0;err_free_ct: __ovs_ct_free_action(&ct_info); return err;}
#if IS_ENABLED(CONFIG_NF_NAT)static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, struct sk_buff *skb){ struct nlattr *start;
start = nla_nest_start_noflag(skb, OVS_CT_ATTR_NAT); if (!start) return false;
if (info->nat & OVS_CT_SRC_NAT) { if (nla_put_flag(skb, OVS_NAT_ATTR_SRC)) return false; } else if (info->nat & OVS_CT_DST_NAT) { if (nla_put_flag(skb, OVS_NAT_ATTR_DST)) return false; } else { goto out; }
if (info->range.flags & NF_NAT_RANGE_MAP_IPS) { if (IS_ENABLED(CONFIG_NF_NAT) && info->family == NFPROTO_IPV4) { if (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MIN, info->range.min_addr.ip) || (info->range.max_addr.ip != info->range.min_addr.ip && (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MAX, info->range.max_addr.ip)))) return false; } else if (IS_ENABLED(CONFIG_IPV6) && info->family == NFPROTO_IPV6) { if (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MIN, &info->range.min_addr.in6) || (memcmp(&info->range.max_addr.in6, &info->range.min_addr.in6, sizeof(info->range.max_addr.in6)) && (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MAX, &info->range.max_addr.in6)))) return false; } else { return false; } } if (info->range.flags & NF_NAT_RANGE_PROTO_SPECIFIED && (nla_put_u16(skb, OVS_NAT_ATTR_PROTO_MIN, ntohs(info->range.min_proto.all)) || (info->range.max_proto.all != info->range.min_proto.all && nla_put_u16(skb, OVS_NAT_ATTR_PROTO_MAX, ntohs(info->range.max_proto.all))))) return false;
if (info->range.flags & NF_NAT_RANGE_PERSISTENT && nla_put_flag(skb, OVS_NAT_ATTR_PERSISTENT)) return false; if (info->range.flags & NF_NAT_RANGE_PROTO_RANDOM && nla_put_flag(skb, OVS_NAT_ATTR_PROTO_HASH)) return false; if (info->range.flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY && nla_put_flag(skb, OVS_NAT_ATTR_PROTO_RANDOM)) return false;out: nla_nest_end(skb, start);
return true;}#endif
int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, struct sk_buff *skb){ struct nlattr *start;
start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CT); if (!start) return -EMSGSIZE;
if (ct_info->commit && nla_put_flag(skb, ct_info->force ? OVS_CT_ATTR_FORCE_COMMIT : OVS_CT_ATTR_COMMIT)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && ct_info->mark.mask && nla_put(skb, OVS_CT_ATTR_MARK, sizeof(ct_info->mark), &ct_info->mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && labels_nonzero(&ct_info->labels.mask) && nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels), &ct_info->labels)) return -EMSGSIZE; if (ct_info->helper) { if (nla_put_string(skb, OVS_CT_ATTR_HELPER, ct_info->helper->name)) return -EMSGSIZE; } if (ct_info->have_eventmask && nla_put_u32(skb, OVS_CT_ATTR_EVENTMASK, ct_info->eventmask)) return -EMSGSIZE; if (ct_info->timeout[0]) { if (nla_put_string(skb, OVS_CT_ATTR_TIMEOUT, ct_info->timeout)) return -EMSGSIZE; }
#if IS_ENABLED(CONFIG_NF_NAT) if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb)) return -EMSGSIZE;#endif nla_nest_end(skb, start);
return 0;}
void ovs_ct_free_action(const struct nlattr *a){ struct ovs_conntrack_info *ct_info = nla_data(a);
__ovs_ct_free_action(ct_info);}
static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info){ if (ct_info->helper) {#if IS_ENABLED(CONFIG_NF_NAT) if (ct_info->nat) nf_nat_helper_put(ct_info->helper);#endif nf_conntrack_helper_put(ct_info->helper); } if (ct_info->ct) { if (ct_info->timeout[0]) nf_ct_destroy_timeout(ct_info->ct); nf_ct_tmpl_free(ct_info->ct); }}
#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)static int ovs_ct_limit_init(struct net *net, struct ovs_net *ovs_net){ int i, err;
ovs_net->ct_limit_info = kmalloc_obj(*ovs_net->ct_limit_info); if (!ovs_net->ct_limit_info) return -ENOMEM;
ovs_net->ct_limit_info->default_limit = OVS_CT_LIMIT_DEFAULT; ovs_net->ct_limit_info->limits = kmalloc_objs(struct hlist_head, CT_LIMIT_HASH_BUCKETS); if (!ovs_net->ct_limit_info->limits) { kfree(ovs_net->ct_limit_info); return -ENOMEM; }
for (i = 0; i < CT_LIMIT_HASH_BUCKETS; i++) INIT_HLIST_HEAD(&ovs_net->ct_limit_info->limits[i]);
ovs_net->ct_limit_info->data = nf_conncount_init(net, sizeof(u32));
if (IS_ERR(ovs_net->ct_limit_info->data)) { err = PTR_ERR(ovs_net->ct_limit_info->data); kfree(ovs_net->ct_limit_info->limits); kfree(ovs_net->ct_limit_info); pr_err("openvswitch: failed to init nf_conncount %d\n", err); return err; } return 0;}
static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net){ const struct ovs_ct_limit_info *info = ovs_net->ct_limit_info; int i;
nf_conncount_destroy(net, info->data); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; struct hlist_node *next;
hlist_for_each_entry_safe(ct_limit, next, head, hlist_node) kfree_rcu(ct_limit, rcu); } kfree(info->limits); kfree(info);}
static struct sk_buff *ovs_ct_limit_cmd_reply_start(struct genl_info *info, u8 cmd, struct ovs_header **ovs_reply_header){ struct ovs_header *ovs_header = genl_info_userhdr(info); struct sk_buff *skb;
skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM);
*ovs_reply_header = genlmsg_put(skb, info->snd_portid, info->snd_seq, &dp_ct_limit_genl_family, 0, cmd);
if (!*ovs_reply_header) { nlmsg_free(skb); return ERR_PTR(-EMSGSIZE); } (*ovs_reply_header)->dp_ifindex = ovs_header->dp_ifindex;
return skb;}
static bool check_zone_id(int zone_id, u16 *pzone){ if (zone_id >= 0 && zone_id <= 65535) { *pzone = (u16)zone_id; return true; } return false;}
static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, struct ovs_ct_limit_info *info){ struct ovs_zone_limit *zone_limit; int rem; u16 zone;
rem = NLA_ALIGN(nla_len(nla_zone_limit)); zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit);
while (rem >= sizeof(*zone_limit)) { if (unlikely(zone_limit->zone_id == OVS_ZONE_LIMIT_DEFAULT_ZONE)) { ovs_lock(); info->default_limit = zone_limit->limit; ovs_unlock(); } else if (unlikely(!check_zone_id( zone_limit->zone_id, &zone))) { OVS_NLERR(true, "zone id is out of range"); } else { struct ovs_ct_limit *ct_limit;
ct_limit = kmalloc_obj(*ct_limit, GFP_KERNEL_ACCOUNT); if (!ct_limit) return -ENOMEM;
ct_limit->zone = zone; ct_limit->limit = zone_limit->limit;
ovs_lock(); ct_limit_set(info, ct_limit); ovs_unlock(); } rem -= NLA_ALIGN(sizeof(*zone_limit)); zone_limit = (struct ovs_zone_limit *)((u8 *)zone_limit + NLA_ALIGN(sizeof(*zone_limit))); }
if (rem) OVS_NLERR(true, "set zone limit has %d unknown bytes", rem);
return 0;}
static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, struct ovs_ct_limit_info *info){ struct ovs_zone_limit *zone_limit; int rem; u16 zone;
rem = NLA_ALIGN(nla_len(nla_zone_limit)); zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit);
while (rem >= sizeof(*zone_limit)) { if (unlikely(zone_limit->zone_id == OVS_ZONE_LIMIT_DEFAULT_ZONE)) { ovs_lock(); info->default_limit = OVS_CT_LIMIT_DEFAULT; ovs_unlock(); } else if (unlikely(!check_zone_id( zone_limit->zone_id, &zone))) { OVS_NLERR(true, "zone id is out of range"); } else { ovs_lock(); ct_limit_del(info, zone); ovs_unlock(); } rem -= NLA_ALIGN(sizeof(*zone_limit)); zone_limit = (struct ovs_zone_limit *)((u8 *)zone_limit + NLA_ALIGN(sizeof(*zone_limit))); }
if (rem) OVS_NLERR(true, "del zone limit has %d unknown bytes", rem);
return 0;}
static int ovs_ct_limit_get_default_limit(struct ovs_ct_limit_info *info, struct sk_buff *reply){ struct ovs_zone_limit zone_limit = { .zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE, .limit = info->default_limit, };
return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit);}
static int __ovs_ct_limit_get_zone_limit(struct net *net, struct nf_conncount_data *data, u16 zone_id, u32 limit, struct sk_buff *reply){ struct nf_conntrack_zone ct_zone; struct ovs_zone_limit zone_limit; u32 conncount_key = zone_id;
zone_limit.zone_id = zone_id; zone_limit.limit = limit; nf_ct_zone_init(&ct_zone, zone_id, NF_CT_DEFAULT_ZONE_DIR, 0);
zone_limit.count = nf_conncount_count_skb(net, NULL, 0, data, &conncount_key); return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit);}
static int ovs_ct_limit_get_zone_limit(struct net *net, struct nlattr *nla_zone_limit, struct ovs_ct_limit_info *info, struct sk_buff *reply){ struct ovs_zone_limit *zone_limit; int rem, err; u32 limit; u16 zone;
rem = NLA_ALIGN(nla_len(nla_zone_limit)); zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit);
while (rem >= sizeof(*zone_limit)) { if (unlikely(zone_limit->zone_id == OVS_ZONE_LIMIT_DEFAULT_ZONE)) { err = ovs_ct_limit_get_default_limit(info, reply); if (err) return err; } else if (unlikely(!check_zone_id(zone_limit->zone_id, &zone))) { OVS_NLERR(true, "zone id is out of range"); } else { rcu_read_lock(); limit = ct_limit_get(info, zone);
err = __ovs_ct_limit_get_zone_limit( net, info->data, zone, limit, reply); rcu_read_unlock(); if (err) return err; } rem -= NLA_ALIGN(sizeof(*zone_limit)); zone_limit = (struct ovs_zone_limit *)((u8 *)zone_limit + NLA_ALIGN(sizeof(*zone_limit))); }
if (rem) OVS_NLERR(true, "get zone limit has %d unknown bytes", rem);
return 0;}
static int ovs_ct_limit_get_all_zone_limit(struct net *net, struct ovs_ct_limit_info *info, struct sk_buff *reply){ struct ovs_ct_limit *ct_limit; struct hlist_head *head; int i, err = 0;
err = ovs_ct_limit_get_default_limit(info, reply); if (err) return err;
rcu_read_lock(); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { head = &info->limits[i]; hlist_for_each_entry_rcu(ct_limit, head, hlist_node) { err = __ovs_ct_limit_get_zone_limit(net, info->data, ct_limit->zone, ct_limit->limit, reply); if (err) goto exit_err; } }
exit_err: rcu_read_unlock(); return err;}
static int ovs_ct_limit_cmd_set(struct sk_buff *skb, struct genl_info *info){ struct nlattr **a = info->attrs; struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; int err;
reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_SET, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply);
if (!a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { err = -EINVAL; goto exit_err; }
err = ovs_ct_limit_set_zone_limit(a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], ct_limit_info); if (err) goto exit_err;
static_branch_enable(&ovs_ct_limit_enabled);
genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info);
exit_err: nlmsg_free(reply); return err;}
static int ovs_ct_limit_cmd_del(struct sk_buff *skb, struct genl_info *info){ struct nlattr **a = info->attrs; struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; int err;
reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_DEL, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply);
if (!a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { err = -EINVAL; goto exit_err; }
err = ovs_ct_limit_del_zone_limit(a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], ct_limit_info); if (err) goto exit_err;
genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info);
exit_err: nlmsg_free(reply); return err;}
static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info){ struct nlattr **a = info->attrs; struct nlattr *nla_reply; struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct net *net = sock_net(skb->sk); struct ovs_net *ovs_net = net_generic(net, ovs_net_id); struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; int err;
reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_GET, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply);
nla_reply = nla_nest_start_noflag(reply, OVS_CT_LIMIT_ATTR_ZONE_LIMIT); if (!nla_reply) { err = -EMSGSIZE; goto exit_err; }
if (a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { err = ovs_ct_limit_get_zone_limit( net, a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], ct_limit_info, reply); if (err) goto exit_err; } else { err = ovs_ct_limit_get_all_zone_limit(net, ct_limit_info, reply); if (err) goto exit_err; }
nla_nest_end(reply, nla_reply); genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info);
exit_err: nlmsg_free(reply); return err;}
static const struct genl_small_ops ct_limit_genl_ops[] = { { .cmd = OVS_CT_LIMIT_CMD_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ .doit = ovs_ct_limit_cmd_set, }, { .cmd = OVS_CT_LIMIT_CMD_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ .doit = ovs_ct_limit_cmd_del, }, { .cmd = OVS_CT_LIMIT_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, /* OK for unprivileged users. */ .doit = ovs_ct_limit_cmd_get, },};
static const struct genl_multicast_group ovs_ct_limit_multicast_group = { .name = OVS_CT_LIMIT_MCGROUP,};
struct genl_family dp_ct_limit_genl_family __ro_after_init = { .hdrsize = sizeof(struct ovs_header), .name = OVS_CT_LIMIT_FAMILY, .version = OVS_CT_LIMIT_VERSION, .maxattr = OVS_CT_LIMIT_ATTR_MAX, .policy = ct_limit_policy, .netnsok = true, .parallel_ops = true, .small_ops = ct_limit_genl_ops, .n_small_ops = ARRAY_SIZE(ct_limit_genl_ops), .resv_start_op = OVS_CT_LIMIT_CMD_GET + 1, .mcgrps = &ovs_ct_limit_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE,};#endif
int ovs_ct_init(struct net *net){ unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
if (nf_connlabels_get(net, n_bits - 1)) { ovs_net->xt_label = false; OVS_NLERR(true, "Failed to set connlabel length"); } else { ovs_net->xt_label = true; }
#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) return ovs_ct_limit_init(net, ovs_net);#else return 0;#endif}
void ovs_ct_exit(struct net *net){ struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) ovs_ct_limit_exit(net, ovs_net);#endif
if (ovs_net->xt_label) nf_connlabels_put(net);}