// 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)) sock_hold(sk); 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;Lines 1–500 of 1992. Load more
// 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)) sock_hold(sk); 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;