From b7a679ba7c652587b85294f4953f33ac0b756d40 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 9 Mar 2023 15:49:57 +0100 Subject: mptcp: fix possible deadlock in subflow_error_report Christoph reported a possible deadlock while the TCP stack destroys an unaccepted subflow due to an incoming reset: the MPTCP socket error path tries to acquire the msk-level socket lock while TCP still owns the listener socket accept queue spinlock, and the reverse dependency already exists in the TCP stack. Note that the above is actually a lockdep false positive, as the chain involves two separate sockets. A different per-socket lockdep key will address the issue, but such a change will be quite invasive. Instead, we can simply stop earlier the socket error handling for orphaned or unaccepted subflows, breaking the critical lockdep chain. Error handling in such a scenario is a no-op. Reported-and-tested-by: Christoph Paasch Fixes: 15cc10453398 ("mptcp: deliver ssk errors to msk") Cc: stable@vger.kernel.org Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/355 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/subflow.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net/mptcp') diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 4ae1a7304cf0..5070dc33675d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1432,6 +1432,13 @@ 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); -- cgit v1.2.3 From 3a236aef280ed5122b2d47087eb514d0921ae033 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 9 Mar 2023 15:49:58 +0100 Subject: mptcp: refactor passive socket initialization After commit 30e51b923e43 ("mptcp: fix unreleased socket in accept queue") unaccepted msk sockets go throu complete shutdown, we don't need anymore to delay inserting the first subflow into the subflow lists. The reference counting deserve some extra care, as __mptcp_close() is unaware of the request socket linkage to the first subflow. Please note that this is more a refactoring than a fix but because this modification is needed to include other corrections, see the following commits. Then a Fixes tag has been added here to help the stable team. Fixes: 30e51b923e43 ("mptcp: fix unreleased socket in accept queue") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Tested-by: Christoph Paasch Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 17 ----------------- net/mptcp/subflow.c | 27 +++++++++++++++++++++------ 2 files changed, 21 insertions(+), 23 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3ad9c46202fc..447641d34c2c 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; } @@ -3708,22 +3707,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, 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/subflow.c b/net/mptcp/subflow.c index 5070dc33675d..a631a5e6fc7b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -397,6 +397,12 @@ 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); @@ -750,6 +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); @@ -824,6 +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 */ @@ -832,14 +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; @@ -847,15 +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); -- cgit v1.2.3 From b6985b9b82954caa53f862d6059d06c0526254f0 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 9 Mar 2023 15:49:59 +0100 Subject: mptcp: use the workqueue to destroy unaccepted sockets Christoph reported a UaF at token lookup time after having refactored the passive socket initialization part: BUG: KASAN: use-after-free in __token_bucket_busy+0x253/0x260 Read of size 4 at addr ffff88810698d5b0 by task syz-executor653/3198 CPU: 1 PID: 3198 Comm: syz-executor653 Not tainted 6.2.0-rc59af4eaa31c1f6c00c8f1e448ed99a45c66340dd5 #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x6e/0x91 print_report+0x16a/0x46f kasan_report+0xad/0x130 __token_bucket_busy+0x253/0x260 mptcp_token_new_connect+0x13d/0x490 mptcp_connect+0x4ed/0x860 __inet_stream_connect+0x80e/0xd90 tcp_sendmsg_fastopen+0x3ce/0x710 mptcp_sendmsg+0xff1/0x1a20 inet_sendmsg+0x11d/0x140 __sys_sendto+0x405/0x490 __x64_sys_sendto+0xdc/0x1b0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc We need to properly clean-up all the paired MPTCP-level resources and be sure to release the msk last, even when the unaccepted subflow is destroyed by the TCP internals via inet_child_forget(). We can re-use the existing MPTCP_WORK_CLOSE_SUBFLOW infra, explicitly checking that for the critical scenario: the closed subflow is the MPC one, the msk is not accepted and eventually going through full cleanup. With such change, __mptcp_destroy_sock() is always called on msk sockets, even on accepted ones. We don't need anymore to transiently drop one sk reference at msk clone time. Please note this commit depends on the parent one: mptcp: refactor passive socket initialization Fixes: 58b09919626b ("mptcp: create msk early") Cc: stable@vger.kernel.org Reported-and-tested-by: Christoph Paasch Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/347 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 40 ++++++++++++++++++++++++++++++---------- net/mptcp/protocol.h | 5 ++++- net/mptcp/subflow.c | 17 ++++++++++++----- 3 files changed, 46 insertions(+), 16 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 447641d34c2c..2a2093d61835 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2342,7 +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 @@ -2350,7 +2349,20 @@ 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) { @@ -2398,9 +2410,10 @@ 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(); @@ -2414,7 +2427,15 @@ 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); } } @@ -2623,6 +2644,9 @@ 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 @@ -2638,9 +2662,6 @@ 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); @@ -3078,6 +3099,7 @@ 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); @@ -3095,8 +3117,7 @@ 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; } @@ -3152,8 +3173,6 @@ 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 { @@ -3704,6 +3723,7 @@ 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); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 61fd8eabfca2..3a2db1b862dd 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; @@ -666,6 +667,8 @@ 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) { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index a631a5e6fc7b..932a3e0eb22d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -699,9 +699,10 @@ 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, @@ -717,7 +718,7 @@ 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); @@ -823,7 +824,7 @@ create_child: if (new_msk) mptcp_copy_inaddrs(new_msk, child); - subflow_drop_ctx(child); + mptcp_subflow_drop_ctx(child); goto out; } @@ -914,7 +915,7 @@ 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); @@ -1866,7 +1867,6 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s 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; @@ -1954,6 +1954,13 @@ 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); } -- cgit v1.2.3 From 0a3f4f1f9c27215e4ddcd312558342e57b93e518 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 9 Mar 2023 15:50:00 +0100 Subject: mptcp: fix UaF in listener shutdown As reported by Christoph after having refactored the passive socket initialization, the mptcp listener shutdown path is prone to an UaF issue. BUG: KASAN: use-after-free in _raw_spin_lock_bh+0x73/0xe0 Write of size 4 at addr ffff88810cb23098 by task syz-executor731/1266 CPU: 1 PID: 1266 Comm: syz-executor731 Not tainted 6.2.0-rc59af4eaa31c1f6c00c8f1e448ed99a45c66340dd5 #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x6e/0x91 print_report+0x16a/0x46f kasan_report+0xad/0x130 kasan_check_range+0x14a/0x1a0 _raw_spin_lock_bh+0x73/0xe0 subflow_error_report+0x6d/0x110 sk_error_report+0x3b/0x190 tcp_disconnect+0x138c/0x1aa0 inet_child_forget+0x6f/0x2e0 inet_csk_listen_stop+0x209/0x1060 __mptcp_close_ssk+0x52d/0x610 mptcp_destroy_common+0x165/0x640 mptcp_destroy+0x13/0x80 __mptcp_destroy_sock+0xe7/0x270 __mptcp_close+0x70e/0x9b0 mptcp_close+0x2b/0x150 inet_release+0xe9/0x1f0 __sock_release+0xd2/0x280 sock_close+0x15/0x20 __fput+0x252/0xa20 task_work_run+0x169/0x250 exit_to_user_mode_prepare+0x113/0x120 syscall_exit_to_user_mode+0x1d/0x40 do_syscall_64+0x48/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc The msk grace period can legitly expire in between the last reference count dropped in mptcp_subflow_queue_clean() and the later eventual access in inet_csk_listen_stop() After the previous patch we don't need anymore special-casing msk listener socket cleanup: the mptcp worker will process each of the unaccepted msk sockets. Just drop the now unnecessary code. Please note this commit depends on the two parent ones: mptcp: refactor passive socket initialization mptcp: use the workqueue to destroy unaccepted sockets Fixes: 6aeed9045071 ("mptcp: fix race on unaccepted mptcp sockets") Cc: stable@vger.kernel.org Reported-and-tested-by: Christoph Paasch Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/346 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 7 ++--- net/mptcp/protocol.h | 1 - net/mptcp/subflow.c | 72 ---------------------------------------------------- 3 files changed, 2 insertions(+), 78 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2a2093d61835..60b23b2716c4 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2365,12 +2365,9 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, 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 */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3a2db1b862dd..339a6f072989 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -629,7 +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); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 932a3e0eb22d..9c57575df84c 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1826,78 +1826,6 @@ 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; - - 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); -- cgit v1.2.3 From 822467a48e938e661965d09df5fcac66f7291050 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 9 Mar 2023 15:50:02 +0100 Subject: mptcp: add ro_after_init for tcp{,v6}_prot_override Add __ro_after_init labels for the variables tcp_prot_override and tcpv6_prot_override, just like other variables adjacent to them, to indicate that they are initialised from the init hooks and no writes occur afterwards. Fixes: b19bc2945b40 ("mptcp: implement delegated actions") Cc: stable@vger.kernel.org Fixes: 51fa7f8ebf0e ("mptcp: mark ops structures as ro_after_init") Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/subflow.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9c57575df84c..2aadc8733369 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -628,7 +628,7 @@ 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) { @@ -926,7 +926,7 @@ 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, -- cgit v1.2.3 From 3ba14528684f528566fb7d956bfbfb958b591d86 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Thu, 9 Mar 2023 15:50:03 +0100 Subject: mptcp: avoid setting TCP_CLOSE state twice tcp_set_state() is called from tcp_done() already. There is then no need to first set the state to TCP_CLOSE, then call tcp_done(). Fixes: d582484726c4 ("mptcp: fix fallback for MP_JOIN subflows") Cc: stable@vger.kernel.org Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/362 Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/subflow.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net/mptcp') diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 2aadc8733369..a0041360ee9d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -406,7 +406,6 @@ void mptcp_subflow_reset(struct sock *ssk) /* 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) && -- cgit v1.2.3 From cee4034a3db1d30c3243dd51506a9d4ab1a849fa Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 9 Mar 2023 15:50:04 +0100 Subject: mptcp: fix lockdep false positive in mptcp_pm_nl_create_listen_socket() Christoph reports a lockdep splat in the mptcp_subflow_create_socket() error path, when such function is invoked by mptcp_pm_nl_create_listen_socket(). Such code path acquires two separates, nested socket lock, with the internal lock operation lacking the "nested" annotation. Adding that in sock_release() for mptcp's sake only could be confusing. Instead just add a new lockclass to the in-kernel msk socket, re-initializing the lockdep infra after the socket creation. Fixes: ad2171009d96 ("mptcp: fix locking for in-kernel listener creation") Cc: stable@vger.kernel.org Reported-by: Christoph Paasch Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/354 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Tested-by: Christoph Paasch Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'net/mptcp') diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 56628b52d100..5c8dea49626c 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -997,9 +997,13 @@ 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 socket *ssock; @@ -1016,6 +1020,18 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (!newsk) return -EINVAL; + /* 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); -- cgit v1.2.3