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.
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993// SPDX-License-Identifier: GPL-2.0/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */
#include <linux/bpf.h>#include <linux/btf_ids.h>#include <linux/filter.h>#include <linux/errno.h>#include <linux/file.h>#include <linux/net.h>#include <linux/workqueue.h>#include <linux/skmsg.h>#include <linux/list.h>#include <linux/jhash.h>#include <linux/sock_diag.h>#include <net/udp.h>
struct bpf_stab { struct bpf_map map; struct sock **sks; struct sk_psock_progs progs; spinlock_t lock;};
#define SOCK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
/* This mutex is used to * - protect race between prog/link attach/detach and link prog update, and * - protect race between releasing and accessing map in bpf_link. * A single global mutex lock is used since it is expected contention is low. */static DEFINE_MUTEX(sockmap_mutex);
static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, struct bpf_link *link, u32 which);static struct sk_psock_progs *sock_map_progs(struct bpf_map *map);
static struct bpf_map *sock_map_alloc(union bpf_attr *attr){ struct bpf_stab *stab;
if (attr->max_entries == 0 || attr->key_size != 4 || (attr->value_size != sizeof(u32) && attr->value_size != sizeof(u64)) || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL);
stab = bpf_map_area_alloc(sizeof(*stab), NUMA_NO_NODE); if (!stab) return ERR_PTR(-ENOMEM);
bpf_map_init_from_attr(&stab->map, attr); spin_lock_init(&stab->lock);
stab->sks = bpf_map_area_alloc((u64) stab->map.max_entries * sizeof(struct sock *), stab->map.numa_node); if (!stab->sks) { bpf_map_area_free(stab); return ERR_PTR(-ENOMEM); }
return &stab->map;}
int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog){ struct bpf_map *map; int ret;
if (attr->attach_flags || attr->replace_bpf_fd) return -EINVAL;
CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); mutex_lock(&sockmap_mutex); ret = sock_map_prog_update(map, prog, NULL, NULL, attr->attach_type); mutex_unlock(&sockmap_mutex); return ret;}
int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype){ struct bpf_prog *prog; struct bpf_map *map; int ret;
if (attr->attach_flags || attr->replace_bpf_fd) return -EINVAL;
CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map);
prog = bpf_prog_get(attr->attach_bpf_fd); if (IS_ERR(prog)) return PTR_ERR(prog);
if (prog->type != ptype) { ret = -EINVAL; goto put_prog; }
mutex_lock(&sockmap_mutex); ret = sock_map_prog_update(map, NULL, prog, NULL, attr->attach_type); mutex_unlock(&sockmap_mutex);put_prog: bpf_prog_put(prog); return ret;}
static void sock_map_sk_acquire(struct sock *sk) __acquires(&sk->sk_lock.slock){ lock_sock(sk); rcu_read_lock();}
static void sock_map_sk_release(struct sock *sk) __releases(&sk->sk_lock.slock){ rcu_read_unlock(); release_sock(sk);}
static void sock_map_add_link(struct sk_psock *psock, struct sk_psock_link *link, struct bpf_map *map, void *link_raw){ link->link_raw = link_raw; link->map = map; spin_lock_bh(&psock->link_lock); list_add_tail(&link->list, &psock->link); spin_unlock_bh(&psock->link_lock);}
static void sock_map_del_link(struct sock *sk, struct sk_psock *psock, void *link_raw){ bool strp_stop = false, verdict_stop = false; struct sk_psock_link *link, *tmp;
spin_lock_bh(&psock->link_lock); list_for_each_entry_safe(link, tmp, &psock->link, list) { if (link->link_raw == link_raw) { struct bpf_map *map = link->map; struct sk_psock_progs *progs = sock_map_progs(map);
if (psock->saved_data_ready && progs->stream_parser) strp_stop = true; if (psock->saved_data_ready && progs->stream_verdict) verdict_stop = true; if (psock->saved_data_ready && progs->skb_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); break; } } spin_unlock_bh(&psock->link_lock); if (strp_stop || verdict_stop) { write_lock_bh(&sk->sk_callback_lock); if (strp_stop) sk_psock_stop_strp(sk, psock); if (verdict_stop) sk_psock_stop_verdict(sk, psock);
if (psock->psock_update_sk_prot) psock->psock_update_sk_prot(sk, psock, false); write_unlock_bh(&sk->sk_callback_lock); }}
static void sock_map_unref(struct sock *sk, void *link_raw){ struct sk_psock *psock = sk_psock(sk);
if (likely(psock)) { sock_map_del_link(sk, psock, link_raw); sk_psock_put(sk, psock); }}
static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock){ if (!sk->sk_prot->psock_update_sk_prot) return -EINVAL; psock->psock_update_sk_prot = sk->sk_prot->psock_update_sk_prot; return sk->sk_prot->psock_update_sk_prot(sk, psock, false);}
static struct sk_psock *sock_map_psock_get_checked(struct sock *sk){ struct sk_psock *psock;
rcu_read_lock(); psock = sk_psock(sk); if (psock) { if (sk->sk_prot->close != sock_map_close) { psock = ERR_PTR(-EBUSY); goto out; }
if (!refcount_inc_not_zero(&psock->refcnt)) psock = ERR_PTR(-EBUSY); }out: rcu_read_unlock(); return psock;}
static int sock_map_link(struct bpf_map *map, struct sock *sk){ struct sk_psock_progs *progs = sock_map_progs(map); struct bpf_prog *stream_verdict = NULL; struct bpf_prog *stream_parser = NULL; struct bpf_prog *skb_verdict = NULL; struct bpf_prog *msg_parser = NULL; struct sk_psock *psock; int ret;
stream_verdict = READ_ONCE(progs->stream_verdict); if (stream_verdict) { stream_verdict = bpf_prog_inc_not_zero(stream_verdict); if (IS_ERR(stream_verdict)) return PTR_ERR(stream_verdict); }
stream_parser = READ_ONCE(progs->stream_parser); if (stream_parser) { stream_parser = bpf_prog_inc_not_zero(stream_parser); if (IS_ERR(stream_parser)) { ret = PTR_ERR(stream_parser); goto out_put_stream_verdict; } }
msg_parser = READ_ONCE(progs->msg_parser); if (msg_parser) { msg_parser = bpf_prog_inc_not_zero(msg_parser); if (IS_ERR(msg_parser)) { ret = PTR_ERR(msg_parser); goto out_put_stream_parser; } }
skb_verdict = READ_ONCE(progs->skb_verdict); if (skb_verdict) { skb_verdict = bpf_prog_inc_not_zero(skb_verdict); if (IS_ERR(skb_verdict)) { ret = PTR_ERR(skb_verdict); goto out_put_msg_parser; } }
psock = sock_map_psock_get_checked(sk); if (IS_ERR(psock)) { ret = PTR_ERR(psock); goto out_progs; }
if (psock) { if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) || (stream_parser && READ_ONCE(psock->progs.stream_parser)) || (skb_verdict && READ_ONCE(psock->progs.skb_verdict)) || (skb_verdict && READ_ONCE(psock->progs.stream_verdict)) || (stream_verdict && READ_ONCE(psock->progs.skb_verdict)) || (stream_verdict && READ_ONCE(psock->progs.stream_verdict))) { sk_psock_put(sk, psock); ret = -EBUSY; goto out_progs; } } else { psock = sk_psock_init(sk, map->numa_node); if (IS_ERR(psock)) { ret = PTR_ERR(psock); goto out_progs; } }
if (msg_parser) psock_set_prog(&psock->progs.msg_parser, msg_parser); if (stream_parser) psock_set_prog(&psock->progs.stream_parser, stream_parser); if (stream_verdict) psock_set_prog(&psock->progs.stream_verdict, stream_verdict); if (skb_verdict) psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
/* msg_* and stream_* programs references tracked in psock after this * point. Reference dec and cleanup will occur through psock destructor */ ret = sock_map_init_proto(sk, psock); if (ret < 0) { sk_psock_put(sk, psock); goto out; }
write_lock_bh(&sk->sk_callback_lock); if (stream_parser && stream_verdict && !psock->saved_data_ready) { if (sk_is_tcp(sk)) ret = sk_psock_init_strp(sk, psock); else ret = -EOPNOTSUPP; if (ret) { write_unlock_bh(&sk->sk_callback_lock); sk_psock_put(sk, psock); goto out; } sk_psock_start_strp(sk, psock); } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) { sk_psock_start_verdict(sk,psock); } else if (!stream_verdict && skb_verdict && !psock->saved_data_ready) { sk_psock_start_verdict(sk, psock); } write_unlock_bh(&sk->sk_callback_lock); return 0;out_progs: if (skb_verdict) bpf_prog_put(skb_verdict);out_put_msg_parser: if (msg_parser) bpf_prog_put(msg_parser);out_put_stream_parser: if (stream_parser) bpf_prog_put(stream_parser);out_put_stream_verdict: if (stream_verdict) bpf_prog_put(stream_verdict);out: return ret;}
static void sock_map_free(struct bpf_map *map){ struct bpf_stab *stab = container_of(map, struct bpf_stab, map); int i;
/* After the sync no updates or deletes will be in-flight so it * is safe to walk map and remove entries without risking a race * in EEXIST update case. */ synchronize_rcu(); for (i = 0; i < stab->map.max_entries; i++) { struct sock **psk = &stab->sks[i]; struct sock *sk;
sk = xchg(psk, NULL); if (sk) { sock_hold(sk); lock_sock(sk); rcu_read_lock(); sock_map_unref(sk, psk); rcu_read_unlock(); release_sock(sk); sock_put(sk); } }
/* wait for psock readers accessing its map link */ synchronize_rcu();
bpf_map_area_free(stab->sks); bpf_map_area_free(stab);}
static void sock_map_release_progs(struct bpf_map *map){ psock_progs_drop(&container_of(map, struct bpf_stab, map)->progs);}
static struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key){ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
WARN_ON_ONCE(!rcu_read_lock_held());
if (unlikely(key >= map->max_entries)) return NULL; return READ_ONCE(stab->sks[key]);}
static void *sock_map_lookup(struct bpf_map *map, void *key){ struct sock *sk;
sk = __sock_map_lookup_elem(map, *(u32 *)key); if (!sk) return NULL; if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; return sk;}
static void *sock_map_lookup_sys(struct bpf_map *map, void *key){ struct sock *sk;
if (map->value_size != sizeof(u64)) return ERR_PTR(-ENOSPC);
sk = __sock_map_lookup_elem(map, *(u32 *)key); if (!sk) return ERR_PTR(-ENOENT);
__sock_gen_cookie(sk); return &sk->sk_cookie;}
static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock **psk){ struct sock *sk = NULL; int err = 0;
spin_lock_bh(&stab->lock); if (!sk_test || sk_test == *psk) sk = xchg(psk, NULL);
if (likely(sk)) sock_map_unref(sk, psk); else err = -EINVAL;
spin_unlock_bh(&stab->lock); return err;}
static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk, void *link_raw){ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
__sock_map_delete(stab, sk, link_raw);}
static long sock_map_delete_elem(struct bpf_map *map, void *key){ struct bpf_stab *stab = container_of(map, struct bpf_stab, map); u32 i = *(u32 *)key; struct sock **psk;
if (unlikely(i >= map->max_entries)) return -EINVAL;
psk = &stab->sks[i]; return __sock_map_delete(stab, NULL, psk);}
static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next){ struct bpf_stab *stab = container_of(map, struct bpf_stab, map); u32 i = key ? *(u32 *)key : U32_MAX; u32 *key_next = next;
if (i == stab->map.max_entries - 1) return -ENOENT; if (i >= stab->map.max_entries) *key_next = 0; else *key_next = i + 1; return 0;}
static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags){ struct bpf_stab *stab = container_of(map, struct bpf_stab, map); struct sk_psock_link *link; struct sk_psock *psock; struct sock *osk; int ret;
WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(flags > BPF_EXIST)) return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG;
link = sk_psock_init_link(); if (!link) return -ENOMEM;
ret = sock_map_link(map, sk); if (ret < 0) goto out_free;
psock = sk_psock(sk); WARN_ON_ONCE(!psock);
spin_lock_bh(&stab->lock); osk = stab->sks[idx]; if (osk && flags == BPF_NOEXIST) { ret = -EEXIST; goto out_unlock; } else if (!osk && flags == BPF_EXIST) { ret = -ENOENT; goto out_unlock; }
sock_map_add_link(psock, link, map, &stab->sks[idx]); stab->sks[idx] = sk; if (osk) sock_map_unref(osk, &stab->sks[idx]); spin_unlock_bh(&stab->lock); return 0;out_unlock: spin_unlock_bh(&stab->lock); if (psock) sk_psock_put(sk, psock);out_free: sk_psock_free_link(link); return ret;}
static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops){ return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB || ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB || ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB;}
static bool sock_map_redirect_allowed(const struct sock *sk){ if (sk_is_tcp(sk)) return sk->sk_state != TCP_LISTEN; else return READ_ONCE(sk->sk_state) == TCP_ESTABLISHED;}
static bool sock_map_sk_is_suitable(const struct sock *sk){ return !!sk->sk_prot->psock_update_sk_prot;}
static bool sock_map_sk_state_allowed(const struct sock *sk){ if (sk_is_tcp(sk)) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); if (sk_is_udp(sk)) return sk_hashed(sk); if (sk_is_stream_unix(sk)) return (1 << READ_ONCE(sk->sk_state)) & TCPF_ESTABLISHED; if (sk_is_vsock(sk) && (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true;}
static int sock_hash_update_common(struct bpf_map *map, void *key, struct sock *sk, u64 flags);
int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags){ struct socket *sock; struct sock *sk; int ret; u64 ufd;
if (map->value_size == sizeof(u64)) ufd = *(u64 *)value; else ufd = *(u32 *)value; if (ufd > S32_MAX) return -EINVAL;
sock = sockfd_lookup(ufd, &ret); if (!sock) return ret; sk = sock->sk; if (!sk) { ret = -EINVAL; goto out; } if (!sock_map_sk_is_suitable(sk)) { ret = -EOPNOTSUPP; goto out; }
sock_map_sk_acquire(sk); if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) ret = sock_map_update_common(map, *(u32 *)key, sk, flags); else ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk);out: sockfd_put(sock); return ret;}
static long sock_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags){ struct sock *sk = (struct sock *)value; int ret;
if (unlikely(!sk || !sk_fullsock(sk))) return -EINVAL;
if (!sock_map_sk_is_suitable(sk)) return -EOPNOTSUPP;
local_bh_disable(); bh_lock_sock(sk); if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) ret = sock_map_update_common(map, *(u32 *)key, sk, flags); else ret = sock_hash_update_common(map, key, sk, flags); bh_unlock_sock(sk); local_bh_enable(); return ret;}
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, sops, struct bpf_map *, map, void *, key, u64, flags){ WARN_ON_ONCE(!rcu_read_lock_held());
if (likely(sock_map_sk_is_suitable(sops->sk) && sock_map_op_okay(sops))) return sock_map_update_common(map, *(u32 *)key, sops->sk, flags); return -EOPNOTSUPP;}
const struct bpf_func_proto bpf_sock_map_update_proto = { .func = bpf_sock_map_update, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING,};
BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, struct bpf_map *, map, u32, key, u64, flags){ struct sock *sk;
if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP;
sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; if ((flags & BPF_F_INGRESS) && sk_is_vsock(sk)) return SK_DROP;
skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS;}
const struct bpf_func_proto bpf_sk_redirect_map_proto = { .func = bpf_sk_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING,};
BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, struct bpf_map *, map, u32, key, u64, flags){ struct sock *sk;
if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP;
sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) return SK_DROP; if (sk_is_vsock(sk)) return SK_DROP;
msg->flags = flags; msg->sk_redir = sk; return SK_PASS;}
const struct bpf_func_proto bpf_msg_redirect_map_proto = { .func = bpf_msg_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING,};
struct sock_map_seq_info { struct bpf_map *map; struct sock *sk; u32 index;};
struct bpf_iter__sockmap { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(void *, key); __bpf_md_ptr(struct sock *, sk);};
DEFINE_BPF_ITER_FUNC(sockmap, struct bpf_iter_meta *meta, struct bpf_map *map, void *key, struct sock *sk)
static void *sock_map_seq_lookup_elem(struct sock_map_seq_info *info){ if (unlikely(info->index >= info->map->max_entries)) return NULL;
info->sk = __sock_map_lookup_elem(info->map, info->index);
/* can't return sk directly, since that might be NULL */ return info;}
static void *sock_map_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu){ struct sock_map_seq_info *info = seq->private;
if (*pos == 0) ++*pos;
/* pairs with sock_map_seq_stop */ rcu_read_lock(); return sock_map_seq_lookup_elem(info);}
static void *sock_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) __must_hold(rcu){ struct sock_map_seq_info *info = seq->private;
++*pos; ++info->index;
return sock_map_seq_lookup_elem(info);}
static int sock_map_seq_show(struct seq_file *seq, void *v) __must_hold(rcu){ struct sock_map_seq_info *info = seq->private; struct bpf_iter__sockmap ctx = {}; struct bpf_iter_meta meta; struct bpf_prog *prog;
meta.seq = seq; prog = bpf_iter_get_info(&meta, !v); if (!prog) return 0;
ctx.meta = &meta; ctx.map = info->map; if (v) { ctx.key = &info->index; ctx.sk = info->sk; }
return bpf_iter_run_prog(prog, &ctx);}
static void sock_map_seq_stop(struct seq_file *seq, void *v) __releases(rcu){ if (!v) (void)sock_map_seq_show(seq, NULL);
/* pairs with sock_map_seq_start */ rcu_read_unlock();}
static const struct seq_operations sock_map_seq_ops = { .start = sock_map_seq_start, .next = sock_map_seq_next, .stop = sock_map_seq_stop, .show = sock_map_seq_show,};
static int sock_map_init_seq_private(void *priv_data, struct bpf_iter_aux_info *aux){ struct sock_map_seq_info *info = priv_data;
bpf_map_inc_with_uref(aux->map); info->map = aux->map; return 0;}
static void sock_map_fini_seq_private(void *priv_data){ struct sock_map_seq_info *info = priv_data;
bpf_map_put_with_uref(info->map);}
static u64 sock_map_mem_usage(const struct bpf_map *map){ u64 usage = sizeof(struct bpf_stab);
usage += (u64)map->max_entries * sizeof(struct sock *); return usage;}
static const struct bpf_iter_seq_info sock_map_iter_seq_info = { .seq_ops = &sock_map_seq_ops, .init_seq_private = sock_map_init_seq_private, .fini_seq_private = sock_map_fini_seq_private, .seq_priv_size = sizeof(struct sock_map_seq_info),};
BTF_ID_LIST_SINGLE(sock_map_btf_ids, struct, bpf_stab)const struct bpf_map_ops sock_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_map_alloc, .map_free = sock_map_free, .map_get_next_key = sock_map_get_next_key, .map_lookup_elem_sys_only = sock_map_lookup_sys, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_map_delete_elem, .map_lookup_elem = sock_map_lookup, .map_release_uref = sock_map_release_progs, .map_check_btf = map_check_no_btf, .map_mem_usage = sock_map_mem_usage, .map_btf_id = &sock_map_btf_ids[0], .iter_seq_info = &sock_map_iter_seq_info,};
struct bpf_shtab_elem { struct rcu_head rcu; u32 hash; struct sock *sk; struct hlist_node node; u8 key[];};
struct bpf_shtab_bucket { struct hlist_head head; spinlock_t lock;};
struct bpf_shtab { struct bpf_map map; struct bpf_shtab_bucket *buckets; u32 buckets_num; u32 elem_size; struct sk_psock_progs progs; atomic_t count;};
static inline u32 sock_hash_bucket_hash(const void *key, u32 len){ return jhash(key, len, 0);}
static struct bpf_shtab_bucket *sock_hash_select_bucket(struct bpf_shtab *htab, u32 hash){ return &htab->buckets[hash & (htab->buckets_num - 1)];}
static struct bpf_shtab_elem *sock_hash_lookup_elem_raw(struct hlist_head *head, u32 hash, void *key, u32 key_size){ struct bpf_shtab_elem *elem;
hlist_for_each_entry_rcu(elem, head, node) { if (elem->hash == hash && !memcmp(&elem->key, key, key_size)) return elem; }
return NULL;}
static struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key){ struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u32 key_size = map->key_size, hash; struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem;
WARN_ON_ONCE(!rcu_read_lock_held());
hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size);
return elem ? elem->sk : NULL;}
static void sock_hash_free_elem(struct bpf_shtab *htab, struct bpf_shtab_elem *elem){ atomic_dec(&htab->count); kfree_rcu(elem, rcu);}
static void sock_hash_delete_from_link(struct bpf_map *map, struct sock *sk, void *link_raw){ struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); struct bpf_shtab_elem *elem_probe, *elem = link_raw; struct bpf_shtab_bucket *bucket;
WARN_ON_ONCE(!rcu_read_lock_held()); bucket = sock_hash_select_bucket(htab, elem->hash);
/* elem may be deleted in parallel from the map, but access here * is okay since it's going away only after RCU grace period. * However, we need to check whether it's still present. */ spin_lock_bh(&bucket->lock); elem_probe = sock_hash_lookup_elem_raw(&bucket->head, elem->hash, elem->key, map->key_size); if (elem_probe && elem_probe == elem) { hlist_del_rcu(&elem->node); sock_map_unref(elem->sk, elem); sock_hash_free_elem(htab, elem); } spin_unlock_bh(&bucket->lock);}
static long sock_hash_delete_elem(struct bpf_map *map, void *key){ struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u32 hash, key_size = map->key_size; struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem; int ret = -ENOENT;
hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash);
spin_lock_bh(&bucket->lock); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); if (elem) { hlist_del_rcu(&elem->node); sock_map_unref(elem->sk, elem); sock_hash_free_elem(htab, elem); ret = 0; } spin_unlock_bh(&bucket->lock); return ret;}
static struct bpf_shtab_elem *sock_hash_alloc_elem(struct bpf_shtab *htab, void *key, u32 key_size, u32 hash, struct sock *sk, struct bpf_shtab_elem *old){ struct bpf_shtab_elem *new;
if (atomic_inc_return(&htab->count) > htab->map.max_entries) { if (!old) { atomic_dec(&htab->count); return ERR_PTR(-E2BIG); } }
new = bpf_map_kmalloc_node(&htab->map, htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); if (!new) { atomic_dec(&htab->count); return ERR_PTR(-ENOMEM); } memcpy(new->key, key, key_size); new->sk = sk; new->hash = hash; return new;}
static int sock_hash_update_common(struct bpf_map *map, void *key, struct sock *sk, u64 flags){ struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u32 key_size = map->key_size, hash; struct bpf_shtab_elem *elem, *elem_new; struct bpf_shtab_bucket *bucket; struct sk_psock_link *link; struct sk_psock *psock; int ret;
WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(flags > BPF_EXIST)) return -EINVAL;
link = sk_psock_init_link(); if (!link) return -ENOMEM;
ret = sock_map_link(map, sk); if (ret < 0) goto out_free;
psock = sk_psock(sk); WARN_ON_ONCE(!psock);
hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash);
spin_lock_bh(&bucket->lock); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); if (elem && flags == BPF_NOEXIST) { ret = -EEXIST; goto out_unlock; } else if (!elem && flags == BPF_EXIST) { ret = -ENOENT; goto out_unlock; }
elem_new = sock_hash_alloc_elem(htab, key, key_size, hash, sk, elem); if (IS_ERR(elem_new)) { ret = PTR_ERR(elem_new); goto out_unlock; }
sock_map_add_link(psock, link, map, elem_new); /* Add new element to the head of the list, so that * concurrent search will find it before old elem. */ hlist_add_head_rcu(&elem_new->node, &bucket->head); if (elem) { hlist_del_rcu(&elem->node); sock_map_unref(elem->sk, elem); sock_hash_free_elem(htab, elem); } spin_unlock_bh(&bucket->lock); return 0;out_unlock: spin_unlock_bh(&bucket->lock); sk_psock_put(sk, psock);out_free: sk_psock_free_link(link); return ret;}
static int sock_hash_get_next_key(struct bpf_map *map, void *key, void *key_next){ struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); struct bpf_shtab_elem *elem, *elem_next; u32 hash, key_size = map->key_size; struct hlist_head *head; int i = 0;
if (!key) goto find_first_elem; hash = sock_hash_bucket_hash(key, key_size); head = &sock_hash_select_bucket(htab, hash)->head; elem = sock_hash_lookup_elem_raw(head, hash, key, key_size); if (!elem) goto find_first_elem;
elem_next = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&elem->node)), struct bpf_shtab_elem, node); if (elem_next) { memcpy(key_next, elem_next->key, key_size); return 0; }
i = hash & (htab->buckets_num - 1); i++;find_first_elem: for (; i < htab->buckets_num; i++) { head = &sock_hash_select_bucket(htab, i)->head; elem_next = hlist_entry_safe(rcu_dereference(hlist_first_rcu(head)), struct bpf_shtab_elem, node); if (elem_next) { memcpy(key_next, elem_next->key, key_size); return 0; } }
return -ENOENT;}
static struct bpf_map *sock_hash_alloc(union bpf_attr *attr){ struct bpf_shtab *htab; int i, err;
if (attr->max_entries == 0 || attr->key_size == 0 || (attr->value_size != sizeof(u32) && attr->value_size != sizeof(u64)) || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->key_size > MAX_BPF_STACK) return ERR_PTR(-E2BIG);
htab = bpf_map_area_alloc(sizeof(*htab), NUMA_NO_NODE); if (!htab) return ERR_PTR(-ENOMEM);
bpf_map_init_from_attr(&htab->map, attr);
htab->buckets_num = roundup_pow_of_two(htab->map.max_entries); htab->elem_size = sizeof(struct bpf_shtab_elem) + round_up(htab->map.key_size, 8); if (htab->buckets_num == 0 || htab->buckets_num > U32_MAX / sizeof(struct bpf_shtab_bucket)) { err = -EINVAL; goto free_htab; }
htab->buckets = bpf_map_area_alloc(htab->buckets_num * sizeof(struct bpf_shtab_bucket), htab->map.numa_node); if (!htab->buckets) { err = -ENOMEM; goto free_htab; }
for (i = 0; i < htab->buckets_num; i++) { INIT_HLIST_HEAD(&htab->buckets[i].head); spin_lock_init(&htab->buckets[i].lock); }
return &htab->map;free_htab: bpf_map_area_free(htab); return ERR_PTR(err);}
static void sock_hash_free(struct bpf_map *map){ struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); struct bpf_shtab_bucket *bucket; struct hlist_head unlink_list; struct bpf_shtab_elem *elem; struct hlist_node *node; int i;
/* After the sync no updates or deletes will be in-flight so it * is safe to walk map and remove entries without risking a race * in EEXIST update case. */ synchronize_rcu(); for (i = 0; i < htab->buckets_num; i++) { bucket = sock_hash_select_bucket(htab, i);
/* We are racing with sock_hash_delete_from_link to * enter the spin-lock critical section. Every socket on * the list is still linked to sockhash. Since link * exists, psock exists and holds a ref to socket. That * lets us to grab a socket ref too. */ spin_lock_bh(&bucket->lock); hlist_for_each_entry(elem, &bucket->head, node) sock_hold(elem->sk); hlist_move_list(&bucket->head, &unlink_list); spin_unlock_bh(&bucket->lock);
/* Process removed entries out of atomic context to * block for socket lock before deleting the psock's * link to sockhash. */ hlist_for_each_entry_safe(elem, node, &unlink_list, node) { hlist_del(&elem->node); lock_sock(elem->sk); rcu_read_lock(); sock_map_unref(elem->sk, elem); rcu_read_unlock(); release_sock(elem->sk); sock_put(elem->sk); sock_hash_free_elem(htab, elem); } cond_resched(); }
/* wait for psock readers accessing its map link */ synchronize_rcu();
bpf_map_area_free(htab->buckets); bpf_map_area_free(htab);}
static void *sock_hash_lookup_sys(struct bpf_map *map, void *key){ struct sock *sk;
if (map->value_size != sizeof(u64)) return ERR_PTR(-ENOSPC);
sk = __sock_hash_lookup_elem(map, key); if (!sk) return ERR_PTR(-ENOENT);
__sock_gen_cookie(sk); return &sk->sk_cookie;}
static void *sock_hash_lookup(struct bpf_map *map, void *key){ struct sock *sk;
sk = __sock_hash_lookup_elem(map, key); if (!sk) return NULL; if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; return sk;}
static void sock_hash_release_progs(struct bpf_map *map){ psock_progs_drop(&container_of(map, struct bpf_shtab, map)->progs);}
BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, sops, struct bpf_map *, map, void *, key, u64, flags){ WARN_ON_ONCE(!rcu_read_lock_held());
if (likely(sock_map_sk_is_suitable(sops->sk) && sock_map_op_okay(sops))) return sock_hash_update_common(map, key, sops->sk, flags); return -EOPNOTSUPP;}
const struct bpf_func_proto bpf_sock_hash_update_proto = { .func = bpf_sock_hash_update, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING,};
BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, struct bpf_map *, map, void *, key, u64, flags){ struct sock *sk;
if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP;
sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; if ((flags & BPF_F_INGRESS) && sk_is_vsock(sk)) return SK_DROP;
skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS;}
const struct bpf_func_proto bpf_sk_redirect_hash_proto = { .func = bpf_sk_redirect_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING,};
BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, struct bpf_map *, map, void *, key, u64, flags){ struct sock *sk;
if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP;
sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) return SK_DROP; if (sk_is_vsock(sk)) return SK_DROP;
msg->flags = flags; msg->sk_redir = sk; return SK_PASS;}
const struct bpf_func_proto bpf_msg_redirect_hash_proto = { .func = bpf_msg_redirect_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING,};
struct sock_hash_seq_info { struct bpf_map *map; struct bpf_shtab *htab; u32 bucket_id;};
static void *sock_hash_seq_find_next(struct sock_hash_seq_info *info, struct bpf_shtab_elem *prev_elem){ const struct bpf_shtab *htab = info->htab; struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem; struct hlist_node *node;
/* try to find next elem in the same bucket */ if (prev_elem) { node = rcu_dereference(hlist_next_rcu(&prev_elem->node)); elem = hlist_entry_safe(node, struct bpf_shtab_elem, node); if (elem) return elem;
/* no more elements, continue in the next bucket */ info->bucket_id++; }
for (; info->bucket_id < htab->buckets_num; info->bucket_id++) { bucket = &htab->buckets[info->bucket_id]; node = rcu_dereference(hlist_first_rcu(&bucket->head)); elem = hlist_entry_safe(node, struct bpf_shtab_elem, node); if (elem) return elem; }
return NULL;}
static void *sock_hash_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu){ struct sock_hash_seq_info *info = seq->private;
if (*pos == 0) ++*pos;
/* pairs with sock_hash_seq_stop */ rcu_read_lock(); return sock_hash_seq_find_next(info, NULL);}
static void *sock_hash_seq_next(struct seq_file *seq, void *v, loff_t *pos) __must_hold(rcu){ struct sock_hash_seq_info *info = seq->private;
++*pos; return sock_hash_seq_find_next(info, v);}
static int sock_hash_seq_show(struct seq_file *seq, void *v) __must_hold(rcu){ struct sock_hash_seq_info *info = seq->private; struct bpf_iter__sockmap ctx = {}; struct bpf_shtab_elem *elem = v; struct bpf_iter_meta meta; struct bpf_prog *prog;
meta.seq = seq; prog = bpf_iter_get_info(&meta, !elem); if (!prog) return 0;
ctx.meta = &meta; ctx.map = info->map; if (elem) { ctx.key = elem->key; ctx.sk = elem->sk; }
return bpf_iter_run_prog(prog, &ctx);}
static void sock_hash_seq_stop(struct seq_file *seq, void *v) __releases(rcu){ if (!v) (void)sock_hash_seq_show(seq, NULL);
/* pairs with sock_hash_seq_start */ rcu_read_unlock();}
static const struct seq_operations sock_hash_seq_ops = { .start = sock_hash_seq_start, .next = sock_hash_seq_next, .stop = sock_hash_seq_stop, .show = sock_hash_seq_show,};
static int sock_hash_init_seq_private(void *priv_data, struct bpf_iter_aux_info *aux){ struct sock_hash_seq_info *info = priv_data;
bpf_map_inc_with_uref(aux->map); info->map = aux->map; info->htab = container_of(aux->map, struct bpf_shtab, map); return 0;}
static void sock_hash_fini_seq_private(void *priv_data){ struct sock_hash_seq_info *info = priv_data;
bpf_map_put_with_uref(info->map);}
static u64 sock_hash_mem_usage(const struct bpf_map *map){ struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u64 usage = sizeof(*htab);
usage += htab->buckets_num * sizeof(struct bpf_shtab_bucket); usage += atomic_read(&htab->count) * (u64)htab->elem_size; return usage;}
static const struct bpf_iter_seq_info sock_hash_iter_seq_info = { .seq_ops = &sock_hash_seq_ops, .init_seq_private = sock_hash_init_seq_private, .fini_seq_private = sock_hash_fini_seq_private, .seq_priv_size = sizeof(struct sock_hash_seq_info),};
BTF_ID_LIST_SINGLE(sock_hash_map_btf_ids, struct, bpf_shtab)const struct bpf_map_ops sock_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_hash_alloc, .map_free = sock_hash_free, .map_get_next_key = sock_hash_get_next_key, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_hash_delete_elem, .map_lookup_elem = sock_hash_lookup, .map_lookup_elem_sys_only = sock_hash_lookup_sys, .map_release_uref = sock_hash_release_progs, .map_check_btf = map_check_no_btf, .map_mem_usage = sock_hash_mem_usage, .map_btf_id = &sock_hash_map_btf_ids[0], .iter_seq_info = &sock_hash_iter_seq_info,};
static struct sk_psock_progs *sock_map_progs(struct bpf_map *map){ switch (map->map_type) { case BPF_MAP_TYPE_SOCKMAP: return &container_of(map, struct bpf_stab, map)->progs; case BPF_MAP_TYPE_SOCKHASH: return &container_of(map, struct bpf_shtab, map)->progs; default: break; }
return NULL;}
static int sock_map_prog_link_lookup(struct bpf_map *map, struct bpf_prog ***pprog, struct bpf_link ***plink, u32 which){ struct sk_psock_progs *progs = sock_map_progs(map); struct bpf_prog **cur_pprog; struct bpf_link **cur_plink;
if (!progs) return -EOPNOTSUPP;
switch (which) { case BPF_SK_MSG_VERDICT: cur_pprog = &progs->msg_parser; cur_plink = &progs->msg_parser_link; break;#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) case BPF_SK_SKB_STREAM_PARSER: cur_pprog = &progs->stream_parser; cur_plink = &progs->stream_parser_link; break;#endif case BPF_SK_SKB_STREAM_VERDICT: if (progs->skb_verdict) return -EBUSY; cur_pprog = &progs->stream_verdict; cur_plink = &progs->stream_verdict_link; break; case BPF_SK_SKB_VERDICT: if (progs->stream_verdict) return -EBUSY; cur_pprog = &progs->skb_verdict; cur_plink = &progs->skb_verdict_link; break; default: return -EOPNOTSUPP; }
*pprog = cur_pprog; if (plink) *plink = cur_plink; return 0;}
static int sock_map_prog_attach_check(enum bpf_attach_type attach_type, struct bpf_prog *prog){ /* A stream parser must not modify the skb, only measure it. */ if (prog && attach_type == BPF_SK_SKB_STREAM_PARSER && prog->aux->changes_pkt_data) return -EINVAL;
return 0;}
/* Handle the following four cases: * prog_attach: prog != NULL, old == NULL, link == NULL * prog_detach: prog == NULL, old != NULL, link == NULL * link_attach: prog != NULL, old == NULL, link != NULL * link_detach: prog == NULL, old != NULL, link != NULL */static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, struct bpf_link *link, u32 which){ struct bpf_prog **pprog; struct bpf_link **plink; int ret;
ret = sock_map_prog_link_lookup(map, &pprog, &plink, which); if (ret) return ret;
ret = sock_map_prog_attach_check(which, prog); if (ret) return ret;
/* for prog_attach/prog_detach/link_attach, return error if a bpf_link * exists for that prog. */ if ((!link || prog) && *plink) return -EBUSY;
if (old) { ret = psock_replace_prog(pprog, prog, old); if (!ret) *plink = NULL; } else { psock_set_prog(pprog, prog); if (link) *plink = link; }
return ret;}
int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr){ __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); u32 prog_cnt = 0, flags = 0; struct bpf_prog **pprog; struct bpf_prog *prog; struct bpf_map *map; u32 id = 0; int ret;
if (attr->query.query_flags) return -EINVAL;
CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map);
rcu_read_lock();
ret = sock_map_prog_link_lookup(map, &pprog, NULL, attr->query.attach_type); if (ret) goto end;
prog = *pprog; prog_cnt = !prog ? 0 : 1;
if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) goto end;
/* we do not hold the refcnt, the bpf prog may be released * asynchronously and the id would be set to 0. */ id = data_race(prog->aux->id); if (id == 0) prog_cnt = 0;
end: rcu_read_unlock();
if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)) || (id != 0 && copy_to_user(prog_ids, &id, sizeof(u32))) || copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) ret = -EFAULT;
return ret;}
static void sock_map_unlink(struct sock *sk, struct sk_psock_link *link){ switch (link->map->map_type) { case BPF_MAP_TYPE_SOCKMAP: return sock_map_delete_from_link(link->map, sk, link->link_raw); case BPF_MAP_TYPE_SOCKHASH: return sock_hash_delete_from_link(link->map, sk, link->link_raw); default: break; }}
static void sock_map_remove_links(struct sock *sk, struct sk_psock *psock){ struct sk_psock_link *link;
while ((link = sk_psock_link_pop(psock))) { sock_map_unlink(sk, link); sk_psock_free_link(link); }}
void sock_map_unhash(struct sock *sk){ void (*saved_unhash)(struct sock *sk); struct sk_psock *psock;
retry: rcu_read_lock(); psock = sk_psock(sk); if (unlikely(!psock)) { rcu_read_unlock(); saved_unhash = READ_ONCE(sk->sk_prot)->unhash; if (unlikely(saved_unhash == sock_map_unhash)) goto retry; } else { saved_unhash = psock->saved_unhash; sock_map_remove_links(sk, psock); rcu_read_unlock();
if (WARN_ON_ONCE(saved_unhash == sock_map_unhash)) return; }
if (saved_unhash) saved_unhash(sk);}EXPORT_SYMBOL_GPL(sock_map_unhash);
void sock_map_destroy(struct sock *sk){ void (*saved_destroy)(struct sock *sk); struct sk_psock *psock;
retry: rcu_read_lock(); psock = sk_psock_get(sk); if (unlikely(!psock)) { rcu_read_unlock(); saved_destroy = READ_ONCE(sk->sk_prot)->destroy; if (unlikely(saved_destroy == sock_map_destroy)) goto retry; } else { saved_destroy = psock->saved_destroy; sock_map_remove_links(sk, psock); rcu_read_unlock(); sk_psock_stop(psock); sk_psock_put(sk, psock);
if (WARN_ON_ONCE(saved_destroy == sock_map_destroy)) return; }
if (saved_destroy) saved_destroy(sk);}EXPORT_SYMBOL_GPL(sock_map_destroy);
void sock_map_close(struct sock *sk, long timeout){ void (*saved_close)(struct sock *sk, long timeout); struct sk_psock *psock;
retry: lock_sock(sk); rcu_read_lock(); psock = sk_psock_get(sk); if (likely(psock)) { saved_close = psock->saved_close; sock_map_remove_links(sk, psock); rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock);
/* Make sure we do not recurse. This is a bug. * Leak the socket instead of crashing on a stack overflow. */ if (WARN_ON_ONCE(saved_close == sock_map_close)) return; } else { saved_close = READ_ONCE(sk->sk_prot)->close; rcu_read_unlock(); release_sock(sk);
if (unlikely(saved_close == sock_map_close)) goto retry; }
saved_close(sk, timeout);}EXPORT_SYMBOL_GPL(sock_map_close);
struct sockmap_link { struct bpf_link link; struct bpf_map *map;};
static void sock_map_link_release(struct bpf_link *link){ struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link);
mutex_lock(&sockmap_mutex); if (!sockmap_link->map) goto out;
WARN_ON_ONCE(sock_map_prog_update(sockmap_link->map, NULL, link->prog, link, link->attach_type));
bpf_map_put_with_uref(sockmap_link->map); sockmap_link->map = NULL;out: mutex_unlock(&sockmap_mutex);}
static int sock_map_link_detach(struct bpf_link *link){ sock_map_link_release(link); return 0;}
static void sock_map_link_dealloc(struct bpf_link *link){ kfree(link);}
/* Handle the following two cases: * case 1: link != NULL, prog != NULL, old != NULL * case 2: link != NULL, prog != NULL, old == NULL */static int sock_map_link_update_prog(struct bpf_link *link, struct bpf_prog *prog, struct bpf_prog *old){ const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); struct bpf_prog **pprog, *old_link_prog; struct bpf_link **plink; int ret = 0;
mutex_lock(&sockmap_mutex);
/* If old prog is not NULL, ensure old prog is the same as link->prog. */ if (old && link->prog != old) { ret = -EPERM; goto out; } /* Ensure link->prog has the same type/attach_type as the new prog. */ if (link->prog->type != prog->type || link->prog->expected_attach_type != prog->expected_attach_type) { ret = -EINVAL; goto out; }
ret = sock_map_prog_attach_check(link->attach_type, prog); if (ret) goto out;
if (!sockmap_link->map) { ret = -ENOLINK; goto out; }
ret = sock_map_prog_link_lookup(sockmap_link->map, &pprog, &plink, link->attach_type); if (ret) goto out;
/* return error if the stored bpf_link does not match the incoming bpf_link. */ if (link != *plink) { ret = -EBUSY; goto out; }
if (old) { ret = psock_replace_prog(pprog, prog, old); if (ret) goto out; } else { psock_set_prog(pprog, prog); }
bpf_prog_inc(prog); old_link_prog = xchg(&link->prog, prog); bpf_prog_put(old_link_prog);
out: mutex_unlock(&sockmap_mutex); return ret;}
static u32 sock_map_link_get_map_id(const struct sockmap_link *sockmap_link){ u32 map_id = 0;
mutex_lock(&sockmap_mutex); if (sockmap_link->map) map_id = sockmap_link->map->id; mutex_unlock(&sockmap_mutex); return map_id;}
static int sock_map_link_fill_info(const struct bpf_link *link, struct bpf_link_info *info){ const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); u32 map_id = sock_map_link_get_map_id(sockmap_link);
info->sockmap.map_id = map_id; info->sockmap.attach_type = link->attach_type; return 0;}
static void sock_map_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq){ const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); u32 map_id = sock_map_link_get_map_id(sockmap_link);
seq_printf(seq, "map_id:\t%u\n", map_id); seq_printf(seq, "attach_type:\t%u\n", link->attach_type);}
static const struct bpf_link_ops sock_map_link_ops = { .release = sock_map_link_release, .dealloc = sock_map_link_dealloc, .detach = sock_map_link_detach, .update_prog = sock_map_link_update_prog, .fill_link_info = sock_map_link_fill_info, .show_fdinfo = sock_map_link_show_fdinfo,};
int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog){ struct bpf_link_primer link_primer; struct sockmap_link *sockmap_link; enum bpf_attach_type attach_type; struct bpf_map *map; int ret;
if (attr->link_create.flags) return -EINVAL;
map = bpf_map_get_with_uref(attr->link_create.target_fd); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) { ret = -EINVAL; goto out; }
sockmap_link = kzalloc_obj(*sockmap_link, GFP_USER); if (!sockmap_link) { ret = -ENOMEM; goto out; }
attach_type = attr->link_create.attach_type; bpf_link_init(&sockmap_link->link, BPF_LINK_TYPE_SOCKMAP, &sock_map_link_ops, prog, attach_type); sockmap_link->map = map;
ret = bpf_link_prime(&sockmap_link->link, &link_primer); if (ret) { kfree(sockmap_link); goto out; }
mutex_lock(&sockmap_mutex); ret = sock_map_prog_update(map, prog, NULL, &sockmap_link->link, attach_type); mutex_unlock(&sockmap_mutex); if (ret) { bpf_link_cleanup(&link_primer); goto out; }
/* Increase refcnt for the prog since when old prog is replaced with * psock_replace_prog() and psock_set_prog() its refcnt will be decreased. * * Actually, we do not need to increase refcnt for the prog since bpf_link * will hold a reference. But in order to have less complexity w.r.t. * replacing/setting prog, let us increase the refcnt to make things simpler. */ bpf_prog_inc(prog);
return bpf_link_settle(&link_primer);
out: bpf_map_put_with_uref(map); return ret;}
static int sock_map_iter_attach_target(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux){ struct bpf_map *map; int err = -EINVAL;
if (!linfo->map.map_fd) return -EBADF;
map = bpf_map_get_with_uref(linfo->map.map_fd); if (IS_ERR(map)) return PTR_ERR(map);
if (map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) goto put_map;
if (prog->aux->max_rdonly_access > map->key_size) { err = -EACCES; goto put_map; }
aux->map = map; return 0;
put_map: bpf_map_put_with_uref(map); return err;}
static void sock_map_iter_detach_target(struct bpf_iter_aux_info *aux){ bpf_map_put_with_uref(aux->map);}
static struct bpf_iter_reg sock_map_iter_reg = { .target = "sockmap", .attach_target = sock_map_iter_attach_target, .detach_target = sock_map_iter_detach_target, .show_fdinfo = bpf_iter_map_show_fdinfo, .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__sockmap, key), PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY }, { offsetof(struct bpf_iter__sockmap, sk), PTR_TO_BTF_ID_OR_NULL }, },};
static int __init bpf_sockmap_iter_init(void){ sock_map_iter_reg.ctx_arg_info[1].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK]; return bpf_iter_reg_target(&sock_map_iter_reg);}late_initcall(bpf_sockmap_iter_init);