From e3d9387f002612093dbeaa272f7930ce5108033f Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 20 Apr 2023 19:17:13 +0200 Subject: security, lsm: Introduce security_mptcp_add_subflow() MPTCP can create subflows in kernel context, and later indirectly expose them to user-space, via the owning MPTCP socket. As discussed in the reported link, the above causes unexpected failures for server, MPTCP-enabled applications. Let's introduce a new LSM hook to allow the security module to relabel the subflow according to the owning user-space process, via the MPTCP socket owning the subflow. Note that the new hook requires both the MPTCP socket and the new subflow. This could allow future extensions, e.g. explicitly validating the MPTCP <-> subflow linkage. Link: https://lore.kernel.org/mptcp/CAHC9VhTNh-YwiyTds=P1e3rixEDqbRTFj22bpya=+qJqfcaMfg@mail.gmail.com/ Signed-off-by: Paolo Abeni Acked-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Paul Moore --- net/mptcp/subflow.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/mptcp/subflow.c') diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ba065b66551a..76952cf74fc0 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1694,6 +1694,10 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING); + err = security_mptcp_add_subflow(sk, sf->sk); + if (err) + goto release_ssk; + /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); @@ -1706,6 +1710,8 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); err = tcp_set_ulp(sf->sk, "mptcp"); + +release_ssk: release_sock(sf->sk); if (err) { -- cgit v1.2.3 From 7e8b88ec35eef363040e08d99536d2bebef83774 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 31 May 2023 12:37:05 -0700 Subject: mptcp: consolidate passive msk socket initialization When the msk socket is cloned at MPC handshake time, a few fields are initialized in a racy way outside mptcp_sk_clone() and the msk socket lock. The above is due historical reasons: before commit a88d0092b24b ("mptcp: simplify subflow_syn_recv_sock()") as the first subflow socket carrying all the needed date was not available yet at msk creation time We can now refactor the code moving the missing initialization bit under the socket lock, removing the init race and avoiding some code duplication. This will also simplify the next patch, as all msk->first write access are now under the msk socket lock. Fixes: 0397c6d85f9c ("mptcp: keep unaccepted MPC subflow into join list") Reviewed-by: Mat Martineau Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 35 ++++++++++++++++++++++++++++------- net/mptcp/protocol.h | 8 ++++---- net/mptcp/subflow.c | 28 +--------------------------- 3 files changed, 33 insertions(+), 38 deletions(-) (limited to 'net/mptcp/subflow.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index ce9de2c946b0..2ecd0117ab1b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3038,7 +3038,7 @@ static void mptcp_close(struct sock *sk, long timeout) sock_put(sk); } -void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) +static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) const struct ipv6_pinfo *ssk6 = inet6_sk(ssk); @@ -3115,9 +3115,10 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) } #endif -struct sock *mptcp_sk_clone(const struct sock *sk, - const struct mptcp_options_received *mp_opt, - struct request_sock *req) +struct sock *mptcp_sk_clone_init(const struct sock *sk, + const struct mptcp_options_received *mp_opt, + struct sock *ssk, + struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); @@ -3149,10 +3150,30 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; sock_reset_flag(nsk, SOCK_RCU_FREE); - /* will be fully established after successful MPC subflow creation */ - inet_sk_state_store(nsk, TCP_SYN_RECV); - security_inet_csk_clone(nsk, req); + + /* this can't race with mptcp_close(), as the msk is + * not yet exposted to user-space + */ + inet_sk_state_store(nsk, TCP_ESTABLISHED); + + /* The msk maintain a ref to each subflow in the connections list */ + WRITE_ONCE(msk->first, ssk); + list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list); + sock_hold(ssk); + + /* new mpc subflow takes ownership of the newly + * created mptcp socket + */ + mptcp_token_accept(subflow_req, msk); + + /* set msk addresses early to ensure mptcp_pm_get_local_id() + * uses the correct data + */ + mptcp_copy_inaddrs(nsk, ssk); + mptcp_propagate_sndbuf(nsk, ssk); + + mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7a1a3c35470f..c5255258bfb3 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -616,7 +616,6 @@ int mptcp_is_checksum_enabled(const struct net *net); int mptcp_allow_join_id0(const struct net *net); unsigned int mptcp_stale_loss_cnt(const struct net *net); int mptcp_get_pm_type(const struct net *net); -void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); @@ -686,9 +685,10 @@ void __init mptcp_proto_init(void); int __init mptcp_proto_v6_init(void); #endif -struct sock *mptcp_sk_clone(const struct sock *sk, - const struct mptcp_options_received *mp_opt, - struct request_sock *req); +struct sock *mptcp_sk_clone_init(const struct sock *sk, + const struct mptcp_options_received *mp_opt, + struct sock *ssk, + struct request_sock *req); void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ba065b66551a..4688daa6b38b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -815,38 +815,12 @@ create_child: ctx->setsockopt_seq = listener->setsockopt_seq; if (ctx->mp_capable) { - ctx->conn = mptcp_sk_clone(listener->conn, &mp_opt, req); + ctx->conn = mptcp_sk_clone_init(listener->conn, &mp_opt, child, req); if (!ctx->conn) goto fallback; owner = mptcp_sk(ctx->conn); - - /* this can't race with mptcp_close(), as the msk is - * not yet exposted to user-space - */ - inet_sk_state_store(ctx->conn, TCP_ESTABLISHED); - - /* record the newly created socket as the first msk - * subflow, but don't link it yet into conn_list - */ - WRITE_ONCE(owner->first, child); - - /* new mpc subflow takes ownership of the newly - * created mptcp socket - */ - owner->setsockopt_seq = ctx->setsockopt_seq; mptcp_pm_new_connection(owner, child, 1); - mptcp_token_accept(subflow_req, owner); - - /* set msk addresses early to ensure mptcp_pm_get_local_id() - * 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 -- cgit v1.2.3 From 81c1d029016001f994ce1c46849c5e9900d8eab8 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Jun 2023 18:24:21 +0200 Subject: mptcp: consolidate fallback and non fallback state machine An orphaned msk releases the used resources via the worker, when the latter first see the msk in CLOSED status. If the msk status transitions to TCP_CLOSE in the release callback invoked by the worker's final release_sock(), such instance of the workqueue will not take any action. Additionally the MPTCP code prevents scheduling the worker once the socket reaches the CLOSE status: such msk resources will be leaked. The only code path that can trigger the above scenario is the __mptcp_check_send_data_fin() in fallback mode. Address the issue removing the special handling of fallback socket in __mptcp_check_send_data_fin(), consolidating the state machine for fallback and non fallback socket. Since non-fallback sockets do not send and do not receive data_fin, the mptcp code can update the msk internal status to match the next step in the SM every time data fin (ack) should be generated or received. As a consequence we can remove a bunch of checks for fallback from the fastpath. Fixes: 6e628cd3a8f7 ("mptcp: use mptcp release_cb for delayed tasks") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 41 +++++++++++++++-------------------------- net/mptcp/subflow.c | 17 ++++++++++------- 2 files changed, 25 insertions(+), 33 deletions(-) (limited to 'net/mptcp/subflow.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 9a40dae31cec..27d206f7af62 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -44,7 +44,7 @@ enum { static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp; static void __mptcp_destroy_sock(struct sock *sk); -static void __mptcp_check_send_data_fin(struct sock *sk); +static void mptcp_check_send_data_fin(struct sock *sk); DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); static struct net_device mptcp_napi_dev; @@ -424,8 +424,7 @@ static bool mptcp_pending_data_fin_ack(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - return !__mptcp_check_fallback(msk) && - ((1 << sk->sk_state) & + return ((1 << sk->sk_state) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) && msk->write_seq == READ_ONCE(msk->snd_una); } @@ -583,9 +582,6 @@ static bool mptcp_check_data_fin(struct sock *sk) u64 rcv_data_fin_seq; bool ret = false; - if (__mptcp_check_fallback(msk)) - return ret; - /* Need to ack a DATA_FIN received from a peer while this side * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2. * msk->rcv_data_fin was set when parsing the incoming options @@ -623,7 +619,8 @@ static bool mptcp_check_data_fin(struct sock *sk) } ret = true; - mptcp_send_ack(msk); + if (!__mptcp_check_fallback(msk)) + mptcp_send_ack(msk); mptcp_close_wake_up(sk); } return ret; @@ -1609,7 +1606,7 @@ out: if (!mptcp_timer_pending(sk)) mptcp_reset_timer(sk); if (do_check_data_fin) - __mptcp_check_send_data_fin(sk); + mptcp_check_send_data_fin(sk); } static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first) @@ -2680,8 +2677,6 @@ static void mptcp_worker(struct work_struct *work) if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock; - mptcp_check_data_fin_ack(sk); - mptcp_check_fastclose(msk); mptcp_pm_nl_work(msk); @@ -2689,7 +2684,8 @@ static void mptcp_worker(struct work_struct *work) if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags)) mptcp_check_for_eof(msk); - __mptcp_check_send_data_fin(sk); + mptcp_check_send_data_fin(sk); + mptcp_check_data_fin_ack(sk); mptcp_check_data_fin(sk); if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) @@ -2828,6 +2824,12 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) pr_debug("Fallback"); ssk->sk_shutdown |= how; tcp_shutdown(ssk, how); + + /* simulate the data_fin ack reception to let the state + * machine move forward + */ + WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt); + mptcp_schedule_work(sk); } else { pr_debug("Sending DATA_FIN on subflow %p", ssk); tcp_send_ack(ssk); @@ -2867,7 +2869,7 @@ static int mptcp_close_state(struct sock *sk) return next & TCP_ACTION_FIN; } -static void __mptcp_check_send_data_fin(struct sock *sk) +static void mptcp_check_send_data_fin(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); @@ -2885,19 +2887,6 @@ static void __mptcp_check_send_data_fin(struct sock *sk) WRITE_ONCE(msk->snd_nxt, msk->write_seq); - /* fallback socket will not get data_fin/ack, can move to the next - * state now - */ - if (__mptcp_check_fallback(msk)) { - WRITE_ONCE(msk->snd_una, msk->write_seq); - if ((1 << sk->sk_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { - inet_sk_state_store(sk, TCP_CLOSE); - mptcp_close_wake_up(sk); - } else if (sk->sk_state == TCP_FIN_WAIT1) { - inet_sk_state_store(sk, TCP_FIN_WAIT2); - } - } - mptcp_for_each_subflow(msk, subflow) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); @@ -2917,7 +2906,7 @@ static void __mptcp_wr_shutdown(struct sock *sk) WRITE_ONCE(msk->write_seq, msk->write_seq + 1); WRITE_ONCE(msk->snd_data_fin_enable, 1); - __mptcp_check_send_data_fin(sk); + mptcp_check_send_data_fin(sk); } static void __mptcp_destroy_sock(struct sock *sk) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 4688daa6b38b..d9c8b21c6076 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1749,14 +1749,16 @@ static void subflow_state_change(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct sock *parent = subflow->conn; + struct mptcp_sock *msk; __subflow_state_change(sk); + msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { mptcp_propagate_sndbuf(parent, sk); mptcp_do_fallback(sk); - mptcp_rcv_space_init(mptcp_sk(parent), sk); - pr_fallback(mptcp_sk(parent)); + mptcp_rcv_space_init(msk, sk); + pr_fallback(msk); subflow->conn_finished = 1; mptcp_set_connected(parent); } @@ -1772,11 +1774,12 @@ static void subflow_state_change(struct sock *sk) subflow_sched_work_if_closed(mptcp_sk(parent), sk); - if (__mptcp_check_fallback(mptcp_sk(parent)) && - !subflow->rx_eof && subflow_is_done(sk)) { - subflow->rx_eof = 1; - mptcp_subflow_eof(parent); - } + /* when the fallback subflow closes the rx side, trigger a 'dummy' + * ingress data fin, so that the msk state will follow along + */ + if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk && + mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true)) + mptcp_schedule_work(parent); } void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) -- cgit v1.2.3 From 6f06b4d4d1cc676a3f9d947f931ec3866b6c4f6c Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Jun 2023 18:30:17 +0200 Subject: mptcp: add subflow unique id The user-space need to properly account the data received/sent by individual subflows. When additional subflows are created and/or closed during the MPTCP socket lifetime, the information currently exposed via MPTCP_TCPINFO are not enough: subflows are identified only by the sequential position inside the info dumps, and that will change with the above mentioned events. To solve the above problem, this patch introduces a new subflow identifier that is unique inside the given MPTCP socket scope. The initial subflow get the id 1 and the other subflows get incremental values at join time. Link: https://github.com/multipath-tcp/mptcp_net-next/issues/388 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 6 ++++++ net/mptcp/protocol.h | 5 ++++- net/mptcp/subflow.c | 2 ++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'net/mptcp/subflow.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index d5b8e488bce1..4ebd6e9aa949 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -96,6 +96,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); subflow->request_mptcp = 1; + subflow->subflow_id = msk->subflow_id++; /* This is the first subflow, always with id 0 */ subflow->local_id_valid = 1; @@ -847,6 +848,7 @@ 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_subflow_ctx(ssk)->subflow_id = msk->subflow_id++; mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); return true; @@ -2732,6 +2734,7 @@ static int __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); WRITE_ONCE(msk->allow_infinite_fallback, true); msk->recovery = false; + msk->subflow_id = 1; mptcp_pm_data_init(msk); @@ -3160,6 +3163,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd; msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; + /* passive msk is created after the first/MPC subflow */ + msk->subflow_id = 2; + sock_reset_flag(nsk, SOCK_RCU_FREE); security_inet_csk_clone(nsk, req); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 27adfcc5aaa2..bb4cacd92778 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -323,7 +323,8 @@ struct mptcp_sock { u64 rtt_us; /* last maximum rtt of subflows */ } rcvq_space; - u32 setsockopt_seq; + u32 subflow_id; + u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; struct mptcp_sock *dl_next; }; @@ -504,6 +505,8 @@ struct mptcp_subflow_context { u8 reset_reason:4; u8 stale_count; + u32 subflow_id; + long delegated_status; unsigned long fail_tout; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 4688daa6b38b..222dfcdadf2e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -819,6 +819,7 @@ create_child: if (!ctx->conn) goto fallback; + ctx->subflow_id = 1; owner = mptcp_sk(ctx->conn); mptcp_pm_new_connection(owner, child, 1); @@ -1574,6 +1575,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, subflow->remote_id = remote_id; subflow->request_join = 1; subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); + subflow->subflow_id = msk->subflow_id++; mptcp_info2sockaddr(remote, &addr, ssk->sk_family); sock_hold(ssk); -- cgit v1.2.3