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.
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483// SPDX-License-Identifier: GPL-2.0-only/* * net/core/fib_rules.c Generic Routing Rules * * Authors: Thomas Graf <tgraf@suug.ch> */
#include <linux/types.h>#include <linux/kernel.h>#include <linux/slab.h>#include <linux/list.h>#include <linux/module.h>#include <net/net_namespace.h>#include <net/inet_dscp.h>#include <net/sock.h>#include <net/fib_rules.h>#include <net/ip_tunnels.h>#include <linux/indirect_call_wrapper.h>
#if defined(CONFIG_IPV6) && defined(CONFIG_IPV6_MULTIPLE_TABLES)#ifdef CONFIG_IP_MULTIPLE_TABLES#define INDIRECT_CALL_MT(f, f2, f1, ...) \ INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__)#else#define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__)#endif#elif defined(CONFIG_IP_MULTIPLE_TABLES)#define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)#else#define INDIRECT_CALL_MT(f, f2, f1, ...) f(__VA_ARGS__)#endif
static const struct fib_kuid_range fib_kuid_range_unset = { KUIDT_INIT(0), KUIDT_INIT(~0),};
bool fib_rule_matchall(const struct fib_rule *rule){ if (READ_ONCE(rule->iifindex) || READ_ONCE(rule->oifindex) || rule->mark || rule->tun_id || rule->flags) return false; if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) return false; if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) || !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end)) return false; if (fib_rule_port_range_set(&rule->sport_range)) return false; if (fib_rule_port_range_set(&rule->dport_range)) return false; return true;}EXPORT_SYMBOL_GPL(fib_rule_matchall);
int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table){ struct fib_rule *r;
r = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (r == NULL) return -ENOMEM;
refcount_set(&r->refcnt, 1); r->action = FR_ACT_TO_TBL; r->pref = pref; r->table = table; r->proto = RTPROT_KERNEL; r->fr_net = ops->fro_net; r->uid_range = fib_kuid_range_unset;
r->suppress_prefixlen = -1; r->suppress_ifgroup = -1;
/* The lock is not required here, the list in unreachable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); return 0;}EXPORT_SYMBOL(fib_default_rule_add);
static u32 fib_default_rule_pref(struct fib_rules_ops *ops){ struct list_head *pos; struct fib_rule *rule;
if (!list_empty(&ops->rules_list)) { pos = ops->rules_list.next; if (pos->next != &ops->rules_list) { rule = list_entry(pos->next, struct fib_rule, list); if (rule->pref) return rule->pref - 1; } }
return 0;}
static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid);
static struct fib_rules_ops *lookup_rules_ops(const struct net *net, int family){ struct fib_rules_ops *ops;
rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (ops->family == family) { if (!try_module_get(ops->owner)) ops = NULL; rcu_read_unlock(); return ops; } } rcu_read_unlock();
return NULL;}
static void rules_ops_put(struct fib_rules_ops *ops){ if (ops) module_put(ops->owner);}
static void flush_route_cache(struct fib_rules_ops *ops){ if (ops->flush_cache) ops->flush_cache(ops);}
static int __fib_rules_register(struct fib_rules_ops *ops){ int err = -EEXIST; struct fib_rules_ops *o; struct net *net;
net = ops->fro_net;
if (ops->rule_size < sizeof(struct fib_rule)) return -EINVAL;
if (ops->match == NULL || ops->configure == NULL || ops->compare == NULL || ops->fill == NULL || ops->action == NULL) return -EINVAL;
spin_lock(&net->rules_mod_lock); list_for_each_entry(o, &net->rules_ops, list) if (ops->family == o->family) goto errout;
list_add_tail_rcu(&ops->list, &net->rules_ops); err = 0;errout: spin_unlock(&net->rules_mod_lock);
return err;}
struct fib_rules_ops *fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net){ struct fib_rules_ops *ops; int err;
ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&ops->rules_list); ops->fro_net = net;
err = __fib_rules_register(ops); if (err) { kfree(ops); ops = ERR_PTR(err); }
return ops;}EXPORT_SYMBOL_GPL(fib_rules_register);
static void fib_rules_cleanup_ops(struct fib_rules_ops *ops){ struct fib_rule *rule, *tmp;
list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) { list_del_rcu(&rule->list); if (ops->delete) ops->delete(rule); fib_rule_put(rule); }}
void fib_rules_unregister(struct fib_rules_ops *ops){ struct net *net = ops->fro_net;
spin_lock(&net->rules_mod_lock); list_del_rcu(&ops->list); spin_unlock(&net->rules_mod_lock);
fib_rules_cleanup_ops(ops); kfree_rcu(ops, rcu);}EXPORT_SYMBOL_GPL(fib_rules_unregister);
static int uid_range_set(struct fib_kuid_range *range){ return uid_valid(range->start) && uid_valid(range->end);}
static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb){ struct fib_rule_uid_range *in; struct fib_kuid_range out;
in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]);
out.start = make_kuid(current_user_ns(), in->start); out.end = make_kuid(current_user_ns(), in->end);
return out;}
static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range){ struct fib_rule_uid_range out = { from_kuid_munged(current_user_ns(), range->start), from_kuid_munged(current_user_ns(), range->end) };
return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out);}
static int nla_get_port_range(struct nlattr *pattr, struct fib_rule_port_range *port_range){ const struct fib_rule_port_range *pr = nla_data(pattr);
if (!fib_rule_port_range_valid(pr)) return -EINVAL;
port_range->start = pr->start; port_range->end = pr->end;
return 0;}
static int nla_put_port_range(struct sk_buff *skb, int attrtype, struct fib_rule_port_range *range){ return nla_put(skb, attrtype, sizeof(*range), range);}
static bool fib_rule_iif_match(const struct fib_rule *rule, int iifindex, const struct flowi *fl){ u8 iif_is_l3_master = READ_ONCE(rule->iif_is_l3_master);
return iif_is_l3_master ? l3mdev_fib_rule_iif_match(fl, iifindex) : fl->flowi_iif == iifindex;}
static bool fib_rule_oif_match(const struct fib_rule *rule, int oifindex, const struct flowi *fl){ u8 oif_is_l3_master = READ_ONCE(rule->oif_is_l3_master);
return oif_is_l3_master ? l3mdev_fib_rule_oif_match(fl, oifindex) : fl->flowi_oif == oifindex;}
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg){ int iifindex, oifindex, ret = 0;
iifindex = READ_ONCE(rule->iifindex); if (iifindex && !fib_rule_iif_match(rule, iifindex, fl)) goto out;
oifindex = READ_ONCE(rule->oifindex); if (oifindex && !fib_rule_oif_match(rule, oifindex, fl)) goto out;
if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) goto out;
if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id)) goto out;
if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg)) goto out;
if (uid_lt(fl->flowi_uid, rule->uid_range.start) || uid_gt(fl->flowi_uid, rule->uid_range.end)) goto out;
ret = INDIRECT_CALL_MT(ops->match, fib6_rule_match, fib4_rule_match, rule, fl, flags);out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;}
int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg){ struct fib_rule *rule; int err;
rcu_read_lock();
list_for_each_entry_rcu(rule, &ops->rules_list, list) {jumped: if (!fib_rule_match(rule, ops, fl, flags, arg)) continue;
if (rule->action == FR_ACT_GOTO) { struct fib_rule *target;
target = rcu_dereference(rule->ctarget); if (target == NULL) { continue; } else { rule = target; goto jumped; } } else if (rule->action == FR_ACT_NOP) continue; else err = INDIRECT_CALL_MT(ops->action, fib6_rule_action, fib4_rule_action, rule, fl, flags, arg);
if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress, fib6_rule_suppress, fib4_rule_suppress, rule, flags, arg)) continue;
if (err != -EAGAIN) { if ((arg->flags & FIB_LOOKUP_NOREF) || likely(fib_rule_get_safe(rule))) { arg->rule = rule; goto out; } break; } }
err = -ESRCH;out: rcu_read_unlock();
return err;}EXPORT_SYMBOL_GPL(fib_rules_lookup);
static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_rule *rule, int family, struct netlink_ext_ack *extack){ struct fib_rule_notifier_info info = { .info.family = family, .info.extack = extack, .rule = rule, };
return call_fib_notifier(nb, event_type, &info.info);}
static int call_fib_rule_notifiers(struct net *net, enum fib_event_type event_type, struct fib_rule *rule, struct fib_rules_ops *ops, struct netlink_ext_ack *extack){ struct fib_rule_notifier_info info = { .info.family = ops->family, .info.extack = extack, .rule = rule, };
ASSERT_RTNL_NET(net);
/* Paired with READ_ONCE() in fib_rules_seq() */ WRITE_ONCE(ops->fib_rules_seq, ops->fib_rules_seq + 1); return call_fib_notifiers(net, event_type, &info.info);}
/* Called with rcu_read_lock() */int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, struct netlink_ext_ack *extack){ struct fib_rules_ops *ops; struct fib_rule *rule; int err = 0;
ops = lookup_rules_ops(net, family); if (!ops) return -EAFNOSUPPORT; list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (!fib_rule_get_safe(rule)) continue;
err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, rule, family, extack); fib_rule_put(rule); if (err) break; } rules_ops_put(ops);
return err;}EXPORT_SYMBOL_GPL(fib_rules_dump);
unsigned int fib_rules_seq_read(const struct net *net, int family){ unsigned int fib_rules_seq; struct fib_rules_ops *ops;
ops = lookup_rules_ops(net, family); if (!ops) return 0; /* Paired with WRITE_ONCE() in call_fib_rule_notifiers() */ fib_rules_seq = READ_ONCE(ops->fib_rules_seq); rules_ops_put(ops);
return fib_rules_seq;}EXPORT_SYMBOL_GPL(fib_rules_seq_read);
static struct fib_rule *rule_find(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule, bool user_priority){ struct fib_rule *r;
list_for_each_entry(r, &ops->rules_list, list) { if (rule->action && r->action != rule->action) continue;
if (rule->table && r->table != rule->table) continue;
if (user_priority && r->pref != rule->pref) continue;
if (rule->iifname[0] && memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue;
if (rule->oifname[0] && memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue;
if (rule->mark && r->mark != rule->mark) continue;
if (rule->suppress_ifgroup != -1 && r->suppress_ifgroup != rule->suppress_ifgroup) continue;
if (rule->suppress_prefixlen != -1 && r->suppress_prefixlen != rule->suppress_prefixlen) continue;
if (rule->mark_mask && r->mark_mask != rule->mark_mask) continue;
if (rule->tun_id && r->tun_id != rule->tun_id) continue;
if (rule->l3mdev && r->l3mdev != rule->l3mdev) continue;
if (uid_range_set(&rule->uid_range) && (!uid_eq(r->uid_range.start, rule->uid_range.start) || !uid_eq(r->uid_range.end, rule->uid_range.end))) continue;
if (rule->ip_proto && r->ip_proto != rule->ip_proto) continue;
if (rule->proto && r->proto != rule->proto) continue;
if (fib_rule_port_range_set(&rule->sport_range) && !fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue;
if (rule->sport_mask && r->sport_mask != rule->sport_mask) continue;
if (fib_rule_port_range_set(&rule->dport_range) && !fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue;
if (rule->dport_mask && r->dport_mask != rule->dport_mask) continue;
if (!ops->compare(r, frh, tb)) continue; return r; }
return NULL;}
#ifdef CONFIG_NET_L3_MASTER_DEVstatic int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, struct netlink_ext_ack *extack){ nlrule->l3mdev = nla_get_u8(nla); if (nlrule->l3mdev != 1) { NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute"); return -1; }
return 0;}#elsestatic int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, struct netlink_ext_ack *extack){ NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel"); return -1;}#endif
static int fib_nl2rule_port_mask(const struct nlattr *mask_attr, const struct fib_rule_port_range *range, u16 *port_mask, struct netlink_ext_ack *extack){ if (!fib_rule_port_range_valid(range)) { NL_SET_ERR_MSG_ATTR(extack, mask_attr, "Cannot specify port mask without port value"); return -EINVAL; }
if (fib_rule_port_is_range(range)) { NL_SET_ERR_MSG_ATTR(extack, mask_attr, "Cannot specify port mask for port range"); return -EINVAL; }
if (range->start & ~nla_get_u16(mask_attr)) { NL_SET_ERR_MSG_ATTR(extack, mask_attr, "Invalid port mask"); return -EINVAL; }
*port_mask = nla_get_u16(mask_attr);
return 0;}
static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, struct fib_rules_ops *ops, struct nlattr *tb[], struct fib_rule **rule, bool *user_priority){ struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rule *nlrule = NULL; int err = -EINVAL;
if (frh->src_len) if (!tb[FRA_SRC] || frh->src_len > (ops->addr_size * 8) || nla_len(tb[FRA_SRC]) != ops->addr_size) { NL_SET_ERR_MSG(extack, "Invalid source address"); goto errout; }
if (frh->dst_len) if (!tb[FRA_DST] || frh->dst_len > (ops->addr_size * 8) || nla_len(tb[FRA_DST]) != ops->addr_size) { NL_SET_ERR_MSG(extack, "Invalid dst address"); goto errout; }
nlrule = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (!nlrule) { err = -ENOMEM; goto errout; } refcount_set(&nlrule->refcnt, 1); nlrule->fr_net = net;
if (tb[FRA_PRIORITY]) { nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]); *user_priority = true; }
nlrule->proto = nla_get_u8_default(tb[FRA_PROTOCOL], RTPROT_UNSPEC);
if (tb[FRA_IIFNAME]) { nlrule->iifindex = -1; nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); }
if (tb[FRA_OIFNAME]) { nlrule->oifindex = -1; nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); }
if (tb[FRA_FWMARK]) { nlrule->mark = nla_get_u32(tb[FRA_FWMARK]); if (nlrule->mark) /* compatibility: if the mark value is non-zero all bits * are compared unless a mask is explicitly specified. */ nlrule->mark_mask = 0xFFFFFFFF; }
if (tb[FRA_FWMASK]) nlrule->mark_mask = nla_get_u32(tb[FRA_FWMASK]);
if (tb[FRA_TUN_ID]) nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
if (tb[FRA_L3MDEV] && fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0) goto errout_free;
nlrule->action = frh->action; nlrule->flags = frh->flags; nlrule->table = frh_get_table(frh, tb); if (tb[FRA_SUPPRESS_PREFIXLEN]) nlrule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); else nlrule->suppress_prefixlen = -1;
if (tb[FRA_SUPPRESS_IFGROUP]) nlrule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); else nlrule->suppress_ifgroup = -1;
if (tb[FRA_GOTO]) { if (nlrule->action != FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Unexpected goto"); goto errout_free; }
nlrule->target = nla_get_u32(tb[FRA_GOTO]); } else if (nlrule->action == FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Missing goto target for action goto"); goto errout_free; }
if (nlrule->l3mdev && nlrule->table) { NL_SET_ERR_MSG(extack, "l3mdev and table are mutually exclusive"); goto errout_free; }
if (tb[FRA_UID_RANGE]) { if (current_user_ns() != net->user_ns) { err = -EPERM; NL_SET_ERR_MSG(extack, "No permission to set uid"); goto errout_free; }
nlrule->uid_range = nla_get_kuid_range(tb);
if (!uid_range_set(&nlrule->uid_range) || !uid_lte(nlrule->uid_range.start, nlrule->uid_range.end)) { NL_SET_ERR_MSG(extack, "Invalid uid range"); goto errout_free; } } else { nlrule->uid_range = fib_kuid_range_unset; }
if (tb[FRA_IP_PROTO]) nlrule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]);
if (tb[FRA_SPORT_RANGE]) { err = nla_get_port_range(tb[FRA_SPORT_RANGE], &nlrule->sport_range); if (err) { NL_SET_ERR_MSG(extack, "Invalid sport range"); goto errout_free; } if (!fib_rule_port_is_range(&nlrule->sport_range)) nlrule->sport_mask = U16_MAX; }
if (tb[FRA_SPORT_MASK]) { err = fib_nl2rule_port_mask(tb[FRA_SPORT_MASK], &nlrule->sport_range, &nlrule->sport_mask, extack); if (err) goto errout_free; }
if (tb[FRA_DPORT_RANGE]) { err = nla_get_port_range(tb[FRA_DPORT_RANGE], &nlrule->dport_range); if (err) { NL_SET_ERR_MSG(extack, "Invalid dport range"); goto errout_free; } if (!fib_rule_port_is_range(&nlrule->dport_range)) nlrule->dport_mask = U16_MAX; }
if (tb[FRA_DPORT_MASK]) { err = fib_nl2rule_port_mask(tb[FRA_DPORT_MASK], &nlrule->dport_range, &nlrule->dport_mask, extack); if (err) goto errout_free; }
*rule = nlrule;
return 0;
errout_free: kfree(nlrule);errout: return err;}
static int fib_nl2rule_rtnl(struct fib_rule *nlrule, struct fib_rules_ops *ops, struct nlattr *tb[], struct netlink_ext_ack *extack){ if (!tb[FRA_PRIORITY]) nlrule->pref = fib_default_rule_pref(ops);
/* Backward jumps are prohibited to avoid endless loops */ if (tb[FRA_GOTO] && nlrule->target <= nlrule->pref) { NL_SET_ERR_MSG(extack, "Backward goto not supported"); return -EINVAL; }
if (tb[FRA_IIFNAME]) { struct net_device *dev;
dev = __dev_get_by_name(nlrule->fr_net, nlrule->iifname); if (dev) { nlrule->iifindex = dev->ifindex; nlrule->iif_is_l3_master = netif_is_l3_master(dev); } }
if (tb[FRA_OIFNAME]) { struct net_device *dev;
dev = __dev_get_by_name(nlrule->fr_net, nlrule->oifname); if (dev) { nlrule->oifindex = dev->ifindex; nlrule->oif_is_l3_master = netif_is_l3_master(dev); } }
return 0;}
static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule){ struct fib_rule *r;
list_for_each_entry(r, &ops->rules_list, list) { if (r->action != rule->action) continue;
if (r->table != rule->table) continue;
if (r->pref != rule->pref) continue;
if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue;
if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue;
if (r->mark != rule->mark) continue;
if (r->suppress_ifgroup != rule->suppress_ifgroup) continue;
if (r->suppress_prefixlen != rule->suppress_prefixlen) continue;
if (r->mark_mask != rule->mark_mask) continue;
if (r->tun_id != rule->tun_id) continue;
if (r->l3mdev != rule->l3mdev) continue;
if (!uid_eq(r->uid_range.start, rule->uid_range.start) || !uid_eq(r->uid_range.end, rule->uid_range.end)) continue;
if (r->ip_proto != rule->ip_proto) continue;
if (r->proto != rule->proto) continue;
if (!fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue;
if (r->sport_mask != rule->sport_mask) continue;
if (!fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue;
if (r->dport_mask != rule->dport_mask) continue;
if (!ops->compare(r, frh, tb)) continue; return 1; } return 0;}
static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = { [FRA_UNSPEC] = { .strict_start_type = FRA_DPORT_RANGE + 1 }, [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_PRIORITY] = { .type = NLA_U32 }, [FRA_FWMARK] = { .type = NLA_U32 }, [FRA_FLOW] = { .type = NLA_U32 }, [FRA_TUN_ID] = { .type = NLA_U64 }, [FRA_FWMASK] = { .type = NLA_U32 }, [FRA_TABLE] = { .type = NLA_U32 }, [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, [FRA_GOTO] = { .type = NLA_U32 }, [FRA_L3MDEV] = { .type = NLA_U8 }, [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }, [FRA_PROTOCOL] = { .type = NLA_U8 }, [FRA_IP_PROTO] = { .type = NLA_U8 }, [FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, [FRA_DSCP] = NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2), [FRA_FLOWLABEL] = { .type = NLA_BE32 }, [FRA_FLOWLABEL_MASK] = { .type = NLA_BE32 }, [FRA_SPORT_MASK] = { .type = NLA_U16 }, [FRA_DPORT_MASK] = { .type = NLA_U16 }, [FRA_DSCP_MASK] = NLA_POLICY_MASK(NLA_U8, INET_DSCP_MASK >> 2),};
int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, bool rtnl_held){ struct fib_rule *rule = NULL, *r, *last = NULL; int err = -EINVAL, unresolved = 0; struct fib_rules_ops *ops = NULL; struct nlattr *tb[FRA_MAX + 1]; bool user_priority = false; struct fib_rule_hdr *frh;
frh = nlmsg_payload(nlh, sizeof(*frh)); if (!frh) { NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; }
ops = lookup_rules_ops(net, frh->family); if (!ops) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; }
err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, fib_rule_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; }
err = fib_nl2rule(net, nlh, extack, ops, tb, &rule, &user_priority); if (err) goto errout;
if (!rtnl_held) rtnl_net_lock(net);
err = fib_nl2rule_rtnl(rule, ops, tb, extack); if (err) goto errout_free;
if ((nlh->nlmsg_flags & NLM_F_EXCL) && rule_exists(ops, frh, tb, rule)) { err = -EEXIST; goto errout_free; }
err = ops->configure(rule, skb, frh, tb, extack); if (err < 0) goto errout_free;
err = call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops, extack); if (err < 0) goto errout_free;
list_for_each_entry(r, &ops->rules_list, list) { if (r->pref == rule->target) { RCU_INIT_POINTER(rule->ctarget, r); break; } }
if (rcu_dereference_protected(rule->ctarget, 1) == NULL) unresolved = 1;
list_for_each_entry(r, &ops->rules_list, list) { if (r->pref > rule->pref) break; last = r; }
if (last) list_add_rcu(&rule->list, &last->list); else list_add_rcu(&rule->list, &ops->rules_list);
if (ops->unresolved_rules) { /* * There are unresolved goto rules in the list, check if * any of them are pointing to this new rule. */ list_for_each_entry(r, &ops->rules_list, list) { if (r->action == FR_ACT_GOTO && r->target == rule->pref && rtnl_dereference(r->ctarget) == NULL) { rcu_assign_pointer(r->ctarget, rule); if (--ops->unresolved_rules == 0) break; } } }
if (rule->action == FR_ACT_GOTO) ops->nr_goto_rules++;
if (unresolved) ops->unresolved_rules++;
if (rule->tun_id) ip_tunnel_need_metadata();
fib_rule_get(rule);
if (!rtnl_held) rtnl_net_unlock(net);
notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); return 0;
errout_free: if (!rtnl_held) rtnl_net_unlock(net); kfree(rule);errout: rules_ops_put(ops); return err;}EXPORT_SYMBOL_GPL(fib_newrule);
static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack){ return fib_newrule(sock_net(skb->sk), skb, nlh, extack, false);}
int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, bool rtnl_held){ struct fib_rule *rule = NULL, *nlrule = NULL; struct fib_rules_ops *ops = NULL; struct nlattr *tb[FRA_MAX+1]; bool user_priority = false; struct fib_rule_hdr *frh; int err = -EINVAL;
frh = nlmsg_payload(nlh, sizeof(*frh)); if (!frh) { NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; }
ops = lookup_rules_ops(net, frh->family); if (ops == NULL) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; }
err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, fib_rule_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; }
err = fib_nl2rule(net, nlh, extack, ops, tb, &nlrule, &user_priority); if (err) goto errout;
if (!rtnl_held) rtnl_net_lock(net);
err = fib_nl2rule_rtnl(nlrule, ops, tb, extack); if (err) goto errout_free;
rule = rule_find(ops, frh, tb, nlrule, user_priority); if (!rule) { err = -ENOENT; goto errout_free; }
if (rule->flags & FIB_RULE_PERMANENT) { err = -EPERM; goto errout_free; }
if (ops->delete) { err = ops->delete(rule); if (err) goto errout_free; }
if (rule->tun_id) ip_tunnel_unneed_metadata();
list_del_rcu(&rule->list);
if (rule->action == FR_ACT_GOTO) { ops->nr_goto_rules--; if (rtnl_dereference(rule->ctarget) == NULL) ops->unresolved_rules--; }
/* * Check if this rule is a target to any of them. If so, * adjust to the next one with the same preference or * disable them. As this operation is eventually very * expensive, it is only performed if goto rules, except * current if it is goto rule, have actually been added. */ if (ops->nr_goto_rules > 0) { struct fib_rule *n, *r;
n = list_next_entry(rule, list); if (&n->list == &ops->rules_list || n->pref != rule->pref) n = NULL; list_for_each_entry(r, &ops->rules_list, list) { if (rtnl_dereference(r->ctarget) != rule) continue; rcu_assign_pointer(r->ctarget, n); if (!n) ops->unresolved_rules++; } }
call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, NULL);
if (!rtnl_held) rtnl_net_unlock(net);
notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); kfree(nlrule); return 0;
errout_free: if (!rtnl_held) rtnl_net_unlock(net); kfree(nlrule);errout: rules_ops_put(ops); return err;}EXPORT_SYMBOL_GPL(fib_delrule);
static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack){ return fib_delrule(sock_net(skb->sk), skb, nlh, extack, false);}
static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule){ size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4) /* FRA_FWMASK */ + nla_total_size_64bit(8) /* FRA_TUN_ID */ + nla_total_size(sizeof(struct fib_kuid_range)) + nla_total_size(1) /* FRA_PROTOCOL */ + nla_total_size(1) /* FRA_IP_PROTO */ + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */ + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_DPORT_RANGE */ + nla_total_size(2) /* FRA_SPORT_MASK */ + nla_total_size(2); /* FRA_DPORT_MASK */
if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule);
return payload;}
static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, u32 pid, u32 seq, int type, int flags, struct fib_rules_ops *ops){ struct nlmsghdr *nlh; struct fib_rule_hdr *frh;
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags); if (nlh == NULL) return -EMSGSIZE;
frh = nlmsg_data(nlh); frh->family = ops->family; frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) goto nla_put_failure; frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; frh->flags = rule->flags;
if (nla_put_u8(skb, FRA_PROTOCOL, rule->proto)) goto nla_put_failure;
if (rule->action == FR_ACT_GOTO && rcu_access_pointer(rule->ctarget) == NULL) frh->flags |= FIB_RULE_UNRESOLVED;
if (rule->iifname[0]) { if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) goto nla_put_failure; if (READ_ONCE(rule->iifindex) == -1) frh->flags |= FIB_RULE_IIF_DETACHED; }
if (rule->oifname[0]) { if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) goto nla_put_failure; if (READ_ONCE(rule->oifindex) == -1) frh->flags |= FIB_RULE_OIF_DETACHED; }
if ((rule->pref && nla_put_u32(skb, FRA_PRIORITY, rule->pref)) || (rule->mark && nla_put_u32(skb, FRA_FWMARK, rule->mark)) || ((rule->mark_mask || rule->mark) && nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || (rule->target && nla_put_u32(skb, FRA_GOTO, rule->target)) || (rule->tun_id && nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) || (rule->l3mdev && nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) || (uid_range_set(&rule->uid_range) && nla_put_uid_range(skb, &rule->uid_range)) || (fib_rule_port_range_set(&rule->sport_range) && nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) || (rule->sport_mask && nla_put_u16(skb, FRA_SPORT_MASK, rule->sport_mask)) || (fib_rule_port_range_set(&rule->dport_range) && nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) || (rule->dport_mask && nla_put_u16(skb, FRA_DPORT_MASK, rule->dport_mask)) || (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto))) goto nla_put_failure;
if (rule->suppress_ifgroup != -1) { if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup)) goto nla_put_failure; }
if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure;
nlmsg_end(skb, nlh); return 0;
nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE;}
static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, struct fib_rules_ops *ops){ int idx = 0; struct fib_rule *rule; int err = 0;
rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip;
err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWRULE, NLM_F_MULTI, ops); if (err) break;skip: idx++; } rcu_read_unlock(); cb->args[1] = idx; rules_ops_put(ops);
return err;}
static int fib_valid_dumprule_req(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack){ struct fib_rule_hdr *frh;
frh = nlmsg_payload(nlh, sizeof(*frh)); if (!frh) { NL_SET_ERR_MSG(extack, "Invalid header for fib rule dump request"); return -EINVAL; }
if (frh->dst_len || frh->src_len || frh->tos || frh->table || frh->res1 || frh->res2 || frh->action || frh->flags) { NL_SET_ERR_MSG(extack, "Invalid values in header for fib rule dump request"); return -EINVAL; }
if (nlmsg_attrlen(nlh, sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid data after header in fib rule dump request"); return -EINVAL; }
return 0;}
static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb){ const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct fib_rules_ops *ops; int err, idx = 0, family;
if (cb->strict_check) { err = fib_valid_dumprule_req(nlh, cb->extack);
if (err < 0) return err; }
family = rtnl_msg_family(nlh); if (family != AF_UNSPEC) { /* Protocol specific dump request */ ops = lookup_rules_ops(net, family); if (ops == NULL) return -EAFNOSUPPORT;
return dump_rules(skb, cb, ops); }
err = 0; rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (idx < cb->args[0] || !try_module_get(ops->owner)) goto skip;
err = dump_rules(skb, cb, ops); if (err < 0) break;
cb->args[1] = 0;skip: idx++; } rcu_read_unlock(); cb->args[0] = idx;
return err;}
static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid){ struct net *net; struct sk_buff *skb; int err = -ENOMEM;
net = ops->fro_net; skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL); if (skb == NULL) goto errout;
err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops); if (err < 0) { /* -EMSGSIZE implies BUG in fib_rule_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; }
rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); return;errout: rtnl_set_sk_err(net, ops->nlgroup, err);}
static void attach_rules(struct list_head *rules, struct net_device *dev){ struct fib_rule *rule;
list_for_each_entry(rule, rules, list) { if (rule->iifindex == -1 && strcmp(dev->name, rule->iifname) == 0) { WRITE_ONCE(rule->iifindex, dev->ifindex); WRITE_ONCE(rule->iif_is_l3_master, netif_is_l3_master(dev)); } if (rule->oifindex == -1 && strcmp(dev->name, rule->oifname) == 0) { WRITE_ONCE(rule->oifindex, dev->ifindex); WRITE_ONCE(rule->oif_is_l3_master, netif_is_l3_master(dev)); } }}
static void detach_rules(struct list_head *rules, struct net_device *dev){ struct fib_rule *rule;
list_for_each_entry(rule, rules, list) { if (rule->iifindex == dev->ifindex) { WRITE_ONCE(rule->iifindex, -1); WRITE_ONCE(rule->iif_is_l3_master, false); } if (rule->oifindex == dev->ifindex) { WRITE_ONCE(rule->oifindex, -1); WRITE_ONCE(rule->oif_is_l3_master, false); } }}
static int fib_rules_event(struct notifier_block *this, unsigned long event, void *ptr){ struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct fib_rules_ops *ops;
ASSERT_RTNL();
switch (event) { case NETDEV_REGISTER: list_for_each_entry(ops, &net->rules_ops, list) attach_rules(&ops->rules_list, dev); break;
case NETDEV_CHANGENAME: list_for_each_entry(ops, &net->rules_ops, list) { detach_rules(&ops->rules_list, dev); attach_rules(&ops->rules_list, dev); } break;
case NETDEV_UNREGISTER: list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); break; }
return NOTIFY_DONE;}
static struct notifier_block fib_rules_notifier = { .notifier_call = fib_rules_event,};
static int __net_init fib_rules_net_init(struct net *net){ INIT_LIST_HEAD(&net->rules_ops); spin_lock_init(&net->rules_mod_lock); return 0;}
static void __net_exit fib_rules_net_exit(struct net *net){ WARN_ON_ONCE(!list_empty(&net->rules_ops));}
static struct pernet_operations fib_rules_net_ops = { .init = fib_rules_net_init, .exit = fib_rules_net_exit,};
static const struct rtnl_msg_handler fib_rules_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_NEWRULE, .doit = fib_nl_newrule, .flags = RTNL_FLAG_DOIT_PERNET}, {.msgtype = RTM_DELRULE, .doit = fib_nl_delrule, .flags = RTNL_FLAG_DOIT_PERNET}, {.msgtype = RTM_GETRULE, .dumpit = fib_nl_dumprule, .flags = RTNL_FLAG_DUMP_UNLOCKED},};
static int __init fib_rules_init(void){ int err;
rtnl_register_many(fib_rules_rtnl_msg_handlers);
err = register_pernet_subsys(&fib_rules_net_ops); if (err < 0) goto fail;
err = register_netdevice_notifier(&fib_rules_notifier); if (err < 0) goto fail_unregister;
return 0;
fail_unregister: unregister_pernet_subsys(&fib_rules_net_ops);fail: rtnl_unregister_many(fib_rules_rtnl_msg_handlers); return err;}
subsys_initcall(fib_rules_init);