diff options
Diffstat (limited to 'net/mptcp')
| -rw-r--r-- | net/mptcp/options.c | 3 | ||||
| -rw-r--r-- | net/mptcp/pm_netlink.c | 89 | ||||
| -rw-r--r-- | net/mptcp/pm_userspace.c | 5 | ||||
| -rw-r--r-- | net/mptcp/protocol.c | 112 | ||||
| -rw-r--r-- | net/mptcp/protocol.h | 8 | ||||
| -rw-r--r-- | net/mptcp/sockopt.c | 14 | ||||
| -rw-r--r-- | net/mptcp/subflow.c | 143 | ||||
| -rw-r--r-- | net/mptcp/token.c | 14 | ||||
| -rw-r--r-- | net/mptcp/token_test.c | 3 |
9 files changed, 208 insertions, 183 deletions
diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 5ded85e2c374..b30cea2fbf3f 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1594,8 +1594,7 @@ mp_rst: TCPOLEN_MPTCP_PRIO, opts->backup, TCPOPT_NOP); - MPTCP_INC_STATS(sock_net((const struct sock *)tp), - MPTCP_MIB_MPPRIOTX); + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPPRIOTX); } mp_capable_done: diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 2ea7eae43bdb..5c8dea49626c 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -152,7 +152,6 @@ static struct mptcp_pm_addr_entry * select_local_address(const struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) { - const struct sock *sk = (const struct sock *)msk; struct mptcp_pm_addr_entry *entry, *ret = NULL; msk_owned_by_me(msk); @@ -165,16 +164,6 @@ select_local_address(const struct pm_nl_pernet *pernet, if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue; - if (entry->addr.family != sk->sk_family) { -#if IS_ENABLED(CONFIG_MPTCP_IPV6) - if ((entry->addr.family == AF_INET && - !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) || - (sk->sk_family == AF_INET && - !ipv6_addr_v4mapped(&entry->addr.addr6))) -#endif - continue; - } - ret = entry; break; } @@ -423,7 +412,9 @@ static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned /* Fill all the remote addresses into the array addrs[], * and return the array size. */ -static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh, +static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, + struct mptcp_addr_info *local, + bool fullmesh, struct mptcp_addr_info *addrs) { bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0); @@ -443,6 +434,9 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm if (deny_id0) return 0; + if (!mptcp_pm_addr_families_match(sk, local, &remote)) + return 0; + msk->pm.subflows++; addrs[i++] = remote; } else { @@ -453,6 +447,9 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm if (deny_id0 && !addrs[i].id) continue; + if (!mptcp_pm_addr_families_match(sk, local, &addrs[i])) + continue; + if (!lookup_address_in_vec(addrs, i, &addrs[i]) && msk->pm.subflows < subflows_max) { msk->pm.subflows++; @@ -603,9 +600,11 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); msk->pm.local_addr_used++; - nr = fill_remote_addresses_vec(msk, fullmesh, addrs); - if (nr) - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); + __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); + nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs); + if (nr == 0) + continue; + spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) __mptcp_subflow_connect(sk, &local->addr, &addrs[i]); @@ -628,11 +627,11 @@ static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk) * and return the array size. */ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, + struct mptcp_addr_info *remote, struct mptcp_addr_info *addrs) { struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *entry; - struct mptcp_addr_info local; struct pm_nl_pernet *pernet; unsigned int subflows_max; int i = 0; @@ -645,15 +644,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH)) continue; - if (entry->addr.family != sk->sk_family) { -#if IS_ENABLED(CONFIG_MPTCP_IPV6) - if ((entry->addr.family == AF_INET && - !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) || - (sk->sk_family == AF_INET && - !ipv6_addr_v4mapped(&entry->addr.addr6))) -#endif - continue; - } + if (!mptcp_pm_addr_families_match(sk, &entry->addr, remote)) + continue; if (msk->pm.subflows < subflows_max) { msk->pm.subflows++; @@ -666,8 +658,18 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, * 'IPADDRANY' local address */ if (!i) { + struct mptcp_addr_info local; + memset(&local, 0, sizeof(local)); - local.family = msk->pm.remote.family; + local.family = +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + remote->family == AF_INET6 && + ipv6_addr_v4mapped(&remote->addr6) ? AF_INET : +#endif + remote->family; + + if (!mptcp_pm_addr_families_match(sk, &local, remote)) + return 0; msk->pm.subflows++; addrs[i++] = local; @@ -706,7 +708,9 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) /* connect to the specified remote address, using whatever * local address the routing configuration will pick. */ - nr = fill_local_addresses_vec(msk, addrs); + nr = fill_local_addresses_vec(msk, &remote, addrs); + if (nr == 0) + return; msk->pm.add_addr_accepted++; if (msk->pm.add_addr_accepted >= add_addr_accept_max || @@ -993,13 +997,17 @@ out: return ret; } +static struct lock_class_key mptcp_slock_keys[2]; +static struct lock_class_key mptcp_keys[2]; + static int mptcp_pm_nl_create_listen_socket(struct sock *sk, struct mptcp_pm_addr_entry *entry) { + bool is_ipv6 = sk->sk_family == AF_INET6; int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; - struct mptcp_sock *msk; struct socket *ssock; + struct sock *newsk; int backlog = 1024; int err; @@ -1008,11 +1016,25 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; - msk = mptcp_sk(entry->lsk->sk); - if (!msk) + newsk = entry->lsk->sk; + if (!newsk) return -EINVAL; - ssock = __mptcp_nmpc_socket(msk); + /* The subflow socket lock is acquired in a nested to the msk one + * in several places, even by the TCP stack, and this msk is a kernel + * socket: lockdep complains. Instead of propagating the _nested + * modifiers in several places, re-init the lock class for the msk + * socket to an mptcp specific one. + */ + sock_lock_init_class_and_name(newsk, + is_ipv6 ? "mlock-AF_INET6" : "mlock-AF_INET", + &mptcp_slock_keys[is_ipv6], + is_ipv6 ? "msk_lock-AF_INET6" : "msk_lock-AF_INET", + &mptcp_keys[is_ipv6]); + + lock_sock(newsk); + ssock = __mptcp_nmpc_socket(mptcp_sk(newsk)); + release_sock(newsk); if (!ssock) return -EINVAL; @@ -1143,7 +1165,7 @@ void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ss if (!tcp_rtx_and_write_queues_empty(ssk)) { subflow->stale = 1; __mptcp_retransmit_pending_data(sk); - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_SUBFLOWSTALE); + MPTCP_INC_STATS(net, MPTCP_MIB_SUBFLOWSTALE); } unlock_sock_fast(ssk, slow); @@ -1903,8 +1925,7 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) } if (token) - return mptcp_userspace_pm_set_flags(sock_net(skb->sk), - token, &addr, &remote, bkup); + return mptcp_userspace_pm_set_flags(net, token, &addr, &remote, bkup); spin_lock_bh(&pernet->lock); entry = __lookup_addr(pernet, &addr.addr, lookup_by_id); diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index ea6ad9da7493..a02d3cbf2a1b 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -59,8 +59,8 @@ int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, */ e = sock_kmalloc(sk, sizeof(*e), GFP_ATOMIC); if (!e) { - spin_unlock_bh(&msk->pm.lock); - return -ENOMEM; + ret = -ENOMEM; + goto append_err; } *e = *entry; @@ -74,6 +74,7 @@ int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, ret = entry->addr.id; } +append_err: spin_unlock_bh(&msk->pm.lock); return ret; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8cd6cc67c2c5..60b23b2716c4 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -825,7 +825,6 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) if (sk->sk_socket && !ssk->sk_socket) mptcp_sock_graft(ssk, sk->sk_socket); - mptcp_propagate_sndbuf((struct sock *)msk, ssk); mptcp_sockopt_sync_locked(msk, ssk); return true; } @@ -923,9 +922,8 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk) static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; - struct sock *sk = (struct sock *)msk; - sock_owned_by_me(sk); + msk_owned_by_me(msk); mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->data_avail)) @@ -1408,7 +1406,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) u64 linger_time; long tout = 0; - sock_owned_by_me(sk); + msk_owned_by_me(msk); if (__mptcp_check_fallback(msk)) { if (!msk->first) @@ -1890,7 +1888,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) u32 time, advmss = 1; u64 rtt_us, mstamp; - sock_owned_by_me(sk); + msk_owned_by_me(msk); if (copied <= 0) return; @@ -2217,7 +2215,7 @@ static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) struct mptcp_subflow_context *subflow; int min_stale_count = INT_MAX; - sock_owned_by_me((const struct sock *)msk); + msk_owned_by_me(msk); if (__mptcp_check_fallback(msk)) return NULL; @@ -2344,7 +2342,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, goto out; } - sock_orphan(ssk); subflow->disposable = 1; /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops @@ -2352,15 +2349,25 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, * reference owned by msk; */ if (!inet_csk(ssk)->icsk_ulp_ops) { + WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD)); kfree_rcu(subflow, rcu); + } else if (msk->in_accept_queue && msk->first == ssk) { + /* if the first subflow moved to a close state, e.g. due to + * incoming reset and we reach here before inet_child_forget() + * the TCP stack could later try to close it via + * inet_csk_listen_stop(), or deliver it to the user space via + * accept(). + * We can't delete the subflow - or risk a double free - nor let + * the msk survive - or will be leaked in the non accept scenario: + * fallback and let TCP cope with the subflow cleanup. + */ + WARN_ON_ONCE(sock_flag(ssk, SOCK_DEAD)); + mptcp_subflow_drop_ctx(ssk); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ - if (ssk->sk_state == TCP_LISTEN) { - tcp_set_state(ssk, TCP_CLOSE); - mptcp_subflow_queue_clean(sk, ssk); - inet_csk_listen_stop(ssk); + if (ssk->sk_state == TCP_LISTEN) mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); - } + __tcp_close(ssk, 0); /* close acquired an extra ref */ @@ -2400,9 +2407,10 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) return 0; } -static void __mptcp_close_subflow(struct mptcp_sock *msk) +static void __mptcp_close_subflow(struct sock *sk) { struct mptcp_subflow_context *subflow, *tmp; + struct mptcp_sock *msk = mptcp_sk(sk); might_sleep(); @@ -2416,7 +2424,15 @@ static void __mptcp_close_subflow(struct mptcp_sock *msk) if (!skb_queue_empty_lockless(&ssk->sk_receive_queue)) continue; - mptcp_close_ssk((struct sock *)msk, ssk, subflow); + mptcp_close_ssk(sk, ssk, subflow); + } + + /* if the MPC subflow has been closed before the msk is accepted, + * msk will never be accept-ed, close it now + */ + if (!msk->first && msk->in_accept_queue) { + sock_set_flag(sk, SOCK_DEAD); + inet_sk_state_store(sk, TCP_CLOSE); } } @@ -2625,6 +2641,9 @@ static void mptcp_worker(struct work_struct *work) __mptcp_check_send_data_fin(sk); mptcp_check_data_fin(sk); + if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + __mptcp_close_subflow(sk); + /* There is no point in keeping around an orphaned sk timedout or * closed, but we need the msk around to reply to incoming DATA_FIN, * even if it is orphaned and in FIN_WAIT2 state @@ -2640,9 +2659,6 @@ static void mptcp_worker(struct work_struct *work) } } - if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) - __mptcp_close_subflow(msk); - if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) __mptcp_retrans(sk); @@ -2724,8 +2740,8 @@ static int mptcp_init_sock(struct sock *sk) mptcp_ca_reset(sk); sk_sockets_allocated_inc(sk); - sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]); - sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]); + sk->sk_rcvbuf = READ_ONCE(net->ipv4.sysctl_tcp_rmem[1]); + sk->sk_sndbuf = READ_ONCE(net->ipv4.sysctl_tcp_wmem[1]); return 0; } @@ -2876,7 +2892,6 @@ static void __mptcp_destroy_sock(struct sock *sk) sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); - sk_refcnt_debug_release(sk); sock_put(sk); } @@ -2892,15 +2907,23 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk) return EPOLLIN | EPOLLRDNORM; } +static void mptcp_listen_inuse_dec(struct sock *sk) +{ + if (inet_sk_state_load(sk) == TCP_LISTEN) + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); +} + bool __mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; + int subflows_alive = 0; sk->sk_shutdown = SHUTDOWN_MASK; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { + mptcp_listen_inuse_dec(sk); inet_sk_state_store(sk, TCP_CLOSE); goto cleanup; } @@ -2922,6 +2945,8 @@ cleanup: struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); + subflows_alive += ssk->sk_state != TCP_CLOSE; + /* since the close timeout takes precedence on the fail one, * cancel the latter */ @@ -2937,6 +2962,12 @@ cleanup: } sock_orphan(sk); + /* all the subflows are closed, only timeout can change the msk + * state, let's not keep resources busy for no reasons + */ + if (subflows_alive == 0) + inet_sk_state_store(sk, TCP_CLOSE); + sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); if (msk->token) @@ -3001,6 +3032,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) if (msk->fastopening) return 0; + mptcp_listen_inuse_dec(sk); inet_sk_state_store(sk, TCP_CLOSE); mptcp_stop_timer(sk); @@ -3064,6 +3096,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; msk->subflow = NULL; + msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) WRITE_ONCE(msk->csum_enabled, true); @@ -3081,8 +3114,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, security_inet_csk_clone(nsk, req); bh_unlock_sock(nsk); - /* keep a single reference */ - __sock_put(nsk); + /* note: the newly allocated socket refcount is 2 now */ return nsk; } @@ -3138,8 +3170,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, goto out; } - /* acquire the 2nd reference for the owning socket */ - sock_hold(new_mptcp_sock); newsk = new_mptcp_sock; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK); } else { @@ -3639,12 +3669,13 @@ static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); + struct sock *sk = sock->sk; struct socket *ssock; int err; pr_debug("msk=%p", msk); - lock_sock(sock->sk); + lock_sock(sk); ssock = __mptcp_nmpc_socket(msk); if (!ssock) { err = -EINVAL; @@ -3652,18 +3683,20 @@ static int mptcp_listen(struct socket *sock, int backlog) } mptcp_token_destroy(msk); - inet_sk_state_store(sock->sk, TCP_LISTEN); - sock_set_flag(sock->sk, SOCK_RCU_FREE); + inet_sk_state_store(sk, TCP_LISTEN); + sock_set_flag(sk, SOCK_RCU_FREE); err = ssock->ops->listen(ssock, backlog); - inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); - if (!err) - mptcp_copy_inaddrs(sock->sk, ssock->sk); + inet_sk_state_store(sk, inet_sk_state_load(ssock->sk)); + if (!err) { + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + mptcp_copy_inaddrs(sk, ssock->sk); + } mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED); unlock: - release_sock(sock->sk); + release_sock(sk); return err; } @@ -3687,25 +3720,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, struct sock *newsk = newsock->sk; set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); + msk->in_accept_queue = 0; lock_sock(newsk); - /* PM/worker can now acquire the first subflow socket - * lock without racing with listener queue cleanup, - * we can notify it, if needed. - * - * Even if remote has reset the initial subflow by now - * the refcnt is still at least one. - */ - subflow = mptcp_subflow_ctx(msk->first); - list_add(&subflow->node, &msk->conn_list); - sock_hold(msk->first); - if (mptcp_is_fully_established(newsk)) - mptcp_pm_fully_established(msk, msk->first, GFP_KERNEL); - - mptcp_rcv_space_init(msk, msk->first); - mptcp_propagate_sndbuf(newsk, msk->first); - /* set ssk->sk_socket of accept()ed flows to mptcp socket. * This is needed so NOSPACE flag can be set from tcp stack. */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 601469249da8..339a6f072989 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -295,7 +295,8 @@ struct mptcp_sock { u8 recvmsg_inq:1, cork:1, nodelay:1, - fastopening:1; + fastopening:1, + in_accept_queue:1; int connect_flags; struct work_struct work; struct sk_buff *ooo_last_skb; @@ -628,7 +629,6 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow); void __mptcp_subflow_send_ack(struct sock *ssk); void mptcp_subflow_reset(struct sock *ssk); -void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); bool __mptcp_close(struct sock *sk, long timeout); @@ -666,6 +666,8 @@ void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow); bool mptcp_subflow_active(struct mptcp_subflow_context *subflow); +void mptcp_subflow_drop_ctx(struct sock *ssk); + static inline void mptcp_subflow_tcp_fallback(struct sock *sk, struct mptcp_subflow_context *ctx) { @@ -755,7 +757,7 @@ static inline void mptcp_token_init_request(struct request_sock *req) int mptcp_token_new_request(struct request_sock *req); void mptcp_token_destroy_request(struct request_sock *req); -int mptcp_token_new_connect(struct sock *sk); +int mptcp_token_new_connect(struct sock *ssk); void mptcp_token_accept(struct mptcp_subflow_request_sock *r, struct mptcp_sock *msk); bool mptcp_token_exists(u32 token); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index d4b1e6ec1b36..8a9656248b0f 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -18,7 +18,7 @@ static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk) { - sock_owned_by_me((const struct sock *)msk); + msk_owned_by_me(msk); if (likely(!__mptcp_check_fallback(msk))) return NULL; @@ -760,14 +760,21 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname, static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname, sockptr_t optval, unsigned int optlen) { + struct sock *sk = (struct sock *)msk; struct socket *sock; + int ret = -EINVAL; /* Limit to first subflow, before the connection establishment */ + lock_sock(sk); sock = __mptcp_nmpc_socket(msk); if (!sock) - return -EINVAL; + goto unlock; + + ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen); - return tcp_setsockopt(sock->sk, level, optname, optval, optlen); +unlock: + release_sock(sk); + return ret; } static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, @@ -1255,6 +1262,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) ssk->sk_priority = sk->sk_priority; ssk->sk_bound_dev_if = sk->sk_bound_dev_if; ssk->sk_incoming_cpu = sk->sk_incoming_cpu; + ssk->sk_ipv6only = sk->sk_ipv6only; __ip_sock_set_tos(ssk, inet_sk(sk)->tos); if (sk->sk_userlocks & tx_rx_locks) { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ec54413fb31f..a0041360ee9d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -26,6 +26,7 @@ #include "mib.h" #include <trace/events/mptcp.h> +#include <trace/events/sock.h> static void mptcp_subflow_ops_undo_override(struct sock *ssk); @@ -396,10 +397,15 @@ void mptcp_subflow_reset(struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; + /* mptcp_mp_fail_no_response() can reach here on an already closed + * socket + */ + if (ssk->sk_state == TCP_CLOSE) + return; + /* must hold: tcp_done() could drop last reference on parent */ sock_hold(sk); - tcp_set_state(ssk, TCP_CLOSE); tcp_send_active_reset(ssk, GFP_ATOMIC); tcp_done(ssk); if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) && @@ -621,7 +627,7 @@ static struct request_sock_ops mptcp_subflow_v6_request_sock_ops __ro_after_init static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init; static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init; static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init; -static struct proto tcpv6_prot_override; +static struct proto tcpv6_prot_override __ro_after_init; static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) { @@ -692,9 +698,10 @@ static bool subflow_hmac_valid(const struct request_sock *req, static void mptcp_force_close(struct sock *sk) { - /* the msk is not yet exposed to user-space */ + /* the msk is not yet exposed to user-space, and refcount is 2 */ inet_sk_state_store(sk, TCP_CLOSE); sk_common_release(sk); + sock_put(sk); } static void subflow_ulp_fallback(struct sock *sk, @@ -710,7 +717,7 @@ static void subflow_ulp_fallback(struct sock *sk, mptcp_subflow_ops_undo_override(sk); } -static void subflow_drop_ctx(struct sock *ssk) +void mptcp_subflow_drop_ctx(struct sock *ssk) { struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk); @@ -749,6 +756,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct mptcp_options_received mp_opt; bool fallback, fallback_is_fatal; struct sock *new_msk = NULL; + struct mptcp_sock *owner; struct sock *child; pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); @@ -815,7 +823,7 @@ create_child: if (new_msk) mptcp_copy_inaddrs(new_msk, child); - subflow_drop_ctx(child); + mptcp_subflow_drop_ctx(child); goto out; } @@ -823,6 +831,8 @@ create_child: ctx->setsockopt_seq = listener->setsockopt_seq; if (ctx->mp_capable) { + owner = mptcp_sk(new_msk); + /* this can't race with mptcp_close(), as the msk is * not yet exposted to user-space */ @@ -831,14 +841,14 @@ create_child: /* record the newly created socket as the first msk * subflow, but don't link it yet into conn_list */ - WRITE_ONCE(mptcp_sk(new_msk)->first, child); + WRITE_ONCE(owner->first, child); /* new mpc subflow takes ownership of the newly * created mptcp socket */ mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq; - mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1); - mptcp_token_accept(subflow_req, mptcp_sk(new_msk)); + mptcp_pm_new_connection(owner, child, 1); + mptcp_token_accept(subflow_req, owner); ctx->conn = new_msk; new_msk = NULL; @@ -846,15 +856,21 @@ create_child: * uses the correct data */ mptcp_copy_inaddrs(ctx->conn, child); + mptcp_propagate_sndbuf(ctx->conn, child); + + mptcp_rcv_space_init(owner, child); + list_add(&ctx->node, &owner->conn_list); + sock_hold(child); /* with OoO packets we can reach here without ingress * mpc option */ - if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) + if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) { mptcp_subflow_fully_established(ctx, &mp_opt); + mptcp_pm_fully_established(owner, child, GFP_ATOMIC); + ctx->pm_notified = 1; + } } else if (ctx->mp_join) { - struct mptcp_sock *owner; - owner = subflow_req->msk; if (!owner) { subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); @@ -898,7 +914,7 @@ out: return child; dispose_child: - subflow_drop_ctx(child); + mptcp_subflow_drop_ctx(child); tcp_rsk(req)->drop_req = true; inet_csk_prepare_for_destroy_sock(child); tcp_done(child); @@ -909,7 +925,7 @@ dispose_child: } static struct inet_connection_sock_af_ops subflow_specific __ro_after_init; -static struct proto tcp_prot_override; +static struct proto tcp_prot_override __ro_after_init; enum mapping_status { MAPPING_OK, @@ -1399,6 +1415,7 @@ void __mptcp_error_report(struct sock *sk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int err = sock_error(ssk); + int ssk_state; if (!err) continue; @@ -1409,7 +1426,14 @@ void __mptcp_error_report(struct sock *sk) if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) continue; - inet_sk_state_store(sk, inet_sk_state_load(ssk)); + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); sk->sk_err = -err; /* This barrier is coupled with smp_rmb() in mptcp_poll() */ @@ -1423,6 +1447,13 @@ static void subflow_error_report(struct sock *ssk) { struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + /* bail early if this is a no-op, so that we avoid introducing a + * problematic lockdep dependency between TCP accept queue lock + * and msk socket spinlock + */ + if (!sk->sk_socket) + return; + mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_error_report(sk); @@ -1438,6 +1469,8 @@ static void subflow_data_ready(struct sock *sk) struct sock *parent = subflow->conn; struct mptcp_sock *msk; + trace_sk_data_ready(sk); + msk = mptcp_sk(parent); if (state & TCPF_LISTEN) { /* MPJ subflow are removed from accept queue before reaching here, @@ -1679,7 +1712,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, if (err) return err; - lock_sock(sf->sk); + lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING); /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); @@ -1792,79 +1825,6 @@ static void subflow_state_change(struct sock *sk) } } -void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) -{ - struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; - struct mptcp_sock *msk, *next, *head = NULL; - struct request_sock *req; - - /* build a list of all unaccepted mptcp sockets */ - spin_lock_bh(&queue->rskq_lock); - for (req = queue->rskq_accept_head; req; req = req->dl_next) { - struct mptcp_subflow_context *subflow; - struct sock *ssk = req->sk; - struct mptcp_sock *msk; - - if (!sk_is_mptcp(ssk)) - continue; - - subflow = mptcp_subflow_ctx(ssk); - if (!subflow || !subflow->conn) - continue; - - /* skip if already in list */ - msk = mptcp_sk(subflow->conn); - if (msk->dl_next || msk == head) - continue; - - msk->dl_next = head; - head = msk; - } - spin_unlock_bh(&queue->rskq_lock); - if (!head) - return; - - /* can't acquire the msk socket lock under the subflow one, - * or will cause ABBA deadlock - */ - release_sock(listener_ssk); - - for (msk = head; msk; msk = next) { - struct sock *sk = (struct sock *)msk; - bool do_cancel_work; - - sock_hold(sk); - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - next = msk->dl_next; - msk->first = NULL; - msk->dl_next = NULL; - - do_cancel_work = __mptcp_close(sk, 0); - release_sock(sk); - if (do_cancel_work) { - /* lockdep will report a false positive ABBA deadlock - * between cancel_work_sync and the listener socket. - * The involved locks belong to different sockets WRT - * the existing AB chain. - * Using a per socket key is problematic as key - * deregistration requires process context and must be - * performed at socket disposal time, in atomic - * context. - * Just tell lockdep to consider the listener socket - * released here. - */ - mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_); - mptcp_cancel_work(sk); - mutex_acquire(&listener_sk->sk_lock.dep_map, - SINGLE_DEPTH_NESTING, 0, _RET_IP_); - } - sock_put(sk); - } - - /* we are still under the listener msk socket lock */ - lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); -} - static int subflow_ulp_init(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -1921,6 +1881,13 @@ static void subflow_ulp_release(struct sock *ssk) * when the subflow is still unaccepted */ release = ctx->disposable || list_empty(&ctx->node); + + /* inet_child_forget() does not call sk_state_change(), + * explicitly trigger the socket close machinery + */ + if (!release && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, + &mptcp_sk(sk)->flags)) + mptcp_schedule_work(sk); sock_put(sk); } diff --git a/net/mptcp/token.c b/net/mptcp/token.c index 65430f314a68..5bb924534387 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -134,7 +134,7 @@ int mptcp_token_new_request(struct request_sock *req) /** * mptcp_token_new_connect - create new key/idsn/token for subflow - * @sk: the socket that will initiate a connection + * @ssk: the socket that will initiate a connection * * This function is called when a new outgoing mptcp connection is * initiated. @@ -148,11 +148,12 @@ int mptcp_token_new_request(struct request_sock *req) * * returns 0 on success. */ -int mptcp_token_new_connect(struct sock *sk) +int mptcp_token_new_connect(struct sock *ssk) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); int retries = MPTCP_TOKEN_MAX_RETRIES; + struct sock *sk = subflow->conn; struct token_bucket *bucket; again: @@ -169,12 +170,13 @@ again: } pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n", - sk, subflow->local_key, subflow->token, subflow->idsn); + ssk, subflow->local_key, subflow->token, subflow->idsn); WRITE_ONCE(msk->token, subflow->token); __sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain); bucket->chain_len++; spin_unlock_bh(&bucket->lock); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); return 0; } @@ -190,8 +192,10 @@ void mptcp_token_accept(struct mptcp_subflow_request_sock *req, struct mptcp_sock *msk) { struct mptcp_subflow_request_sock *pos; + struct sock *sk = (struct sock *)msk; struct token_bucket *bucket; + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); bucket = token_bucket(req->token); spin_lock_bh(&bucket->lock); @@ -370,12 +374,14 @@ void mptcp_token_destroy_request(struct request_sock *req) */ void mptcp_token_destroy(struct mptcp_sock *msk) { + struct sock *sk = (struct sock *)msk; struct token_bucket *bucket; struct mptcp_sock *pos; if (sk_unhashed((struct sock *)msk)) return; + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); bucket = token_bucket(msk->token); spin_lock_bh(&bucket->lock); pos = __token_lookup_msk(bucket, msk->token); diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c index 5d984bec1cd8..0758865ab658 100644 --- a/net/mptcp/token_test.c +++ b/net/mptcp/token_test.c @@ -57,6 +57,9 @@ static struct mptcp_sock *build_msk(struct kunit *test) KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk); refcount_set(&((struct sock *)msk)->sk_refcnt, 1); sock_net_set((struct sock *)msk, &init_net); + + /* be sure the token helpers can dereference sk->sk_prot */ + ((struct sock *)msk)->sk_prot = &tcp_prot; return msk; } |