From 013e3179dbd2bc756ce1dd90354abac62f65b739 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 8 Feb 2024 19:03:50 +0100 Subject: mptcp: fix rcv space initialization mptcp_rcv_space_init() is supposed to happen under the msk socket lock, but active msk socket does that without such protection. Leverage the existing mptcp_propagate_state() helper to that extent. We need to ensure mptcp_rcv_space_init will happen before mptcp_rcv_space_adjust(), and the release_cb does not assure that: explicitly check for such condition. While at it, move the wnd_end initialization out of mptcp_rcv_space_init(), it never belonged there. Note that the race does not produce ill effect in practice, but change allows cleaning-up and defying better the locking model. Fixes: a6b118febbab ("mptcp: add receive buffer auto-tuning") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- net/mptcp/subflow.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/mptcp/subflow.c') diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 0dcb721c89d1..56b2ac2f2f22 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -424,6 +424,8 @@ void __mptcp_sync_state(struct sock *sk, int state) struct mptcp_sock *msk = mptcp_sk(sk); __mptcp_propagate_sndbuf(sk, msk->first); + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); if (sk->sk_state == TCP_SYN_SENT) { mptcp_set_state(sk, state); sk->sk_state_change(sk); @@ -545,7 +547,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } } else if (mptcp_check_fallback(sk)) { fallback: - mptcp_rcv_space_init(msk, sk); mptcp_propagate_state(parent, sk); } return; @@ -1744,7 +1745,6 @@ static void subflow_state_change(struct sock *sk) msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { mptcp_do_fallback(sk); - mptcp_rcv_space_init(msk, sk); pr_fallback(msk); subflow->conn_finished = 1; mptcp_propagate_state(parent, sk); -- cgit v1.2.3 From 3f83d8a77eeeb47011b990fd766a421ee64f1d73 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 8 Feb 2024 19:03:51 +0100 Subject: mptcp: fix more tx path fields initialization The 'msk->write_seq' and 'msk->snd_nxt' are always updated under the msk socket lock, except at MPC handshake completiont time. Builds-up on the previous commit to move such init under the relevant lock. There are no known problems caused by the potential race, the primary goal is consistency. Fixes: 6d0060f600ad ("mptcp: Write MPTCP DSS headers to outgoing data packets") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 6 ++---- net/mptcp/subflow.c | 13 +++++++++++-- 2 files changed, 13 insertions(+), 6 deletions(-) (limited to 'net/mptcp/subflow.c') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7632eafb683b..8cb6a873dae9 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3478,10 +3478,8 @@ void mptcp_finish_connect(struct sock *ssk) * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); - WRITE_ONCE(msk->write_seq, subflow->idsn + 1); - WRITE_ONCE(msk->snd_nxt, msk->write_seq); - WRITE_ONCE(msk->snd_una, msk->write_seq); - WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); + WRITE_ONCE(msk->snd_una, subflow->idsn + 1); + WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); mptcp_pm_new_connection(msk, ssk, 0); } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 56b2ac2f2f22..c2df34ebcf28 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -421,12 +421,21 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc void __mptcp_sync_state(struct sock *sk, int state) { + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); + struct sock *ssk = msk->first; - __mptcp_propagate_sndbuf(sk, msk->first); + subflow = mptcp_subflow_ctx(ssk); + __mptcp_propagate_sndbuf(sk, ssk); if (!msk->rcvspace_init) - mptcp_rcv_space_init(msk, msk->first); + mptcp_rcv_space_init(msk, ssk); + if (sk->sk_state == TCP_SYN_SENT) { + /* subflow->idsn is always available is TCP_SYN_SENT state, + * even for the FASTOPEN scenarios + */ + WRITE_ONCE(msk->write_seq, subflow->idsn + 1); + WRITE_ONCE(msk->snd_nxt, msk->write_seq); mptcp_set_state(sk, state); sk->sk_state_change(sk); } -- cgit v1.2.3 From e4a0fa47e816e186f6b4c0055d07eeec42d11871 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 8 Feb 2024 19:03:52 +0100 Subject: mptcp: corner case locking for rx path fields initialization Most MPTCP-level related fields are under the mptcp data lock protection, but are written one-off without such lock at MPC complete time, both for the client and the server Leverage the mptcp_propagate_state() infrastructure to move such initialization under the proper lock client-wise. The server side critical init steps are done by mptcp_subflow_fully_established(): ensure the caller properly held the relevant lock, and avoid acquiring the same lock in the nested scopes. There are no real potential races, as write access to such fields is implicitly serialized by the MPTCP state machine; the primary goal is consistency. Fixes: d22f4988ffec ("mptcp: process MP_CAPABLE data option") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- net/mptcp/fastopen.c | 6 ++---- net/mptcp/options.c | 9 +++++---- net/mptcp/protocol.c | 9 ++++++--- net/mptcp/protocol.h | 9 +++++---- net/mptcp/subflow.c | 56 ++++++++++++++++++++++++++++++---------------------- 5 files changed, 50 insertions(+), 39 deletions(-) (limited to 'net/mptcp/subflow.c') diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index 74698582a285..ad28da655f8b 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -59,13 +59,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf mptcp_data_unlock(sk); } -void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt) +void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) { struct sock *sk = (struct sock *)msk; struct sk_buff *skb; - mptcp_data_lock(sk); skb = skb_peek_tail(&sk->sk_receive_queue); if (skb) { WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq); @@ -77,5 +76,4 @@ void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_ } pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq); - mptcp_data_unlock(sk); } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index d2527d189a79..e3e96a49f922 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -962,9 +962,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ - subflow->fully_established = 1; - WRITE_ONCE(msk->fully_established, true); - goto check_notify; + goto set_fully_established; } /* If the first established packet does not contain MP_CAPABLE + data @@ -986,7 +984,10 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, set_fully_established: if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); - mptcp_subflow_fully_established(subflow, mp_opt); + + mptcp_data_lock((struct sock *)msk); + __mptcp_subflow_fully_established(msk, subflow, mp_opt); + mptcp_data_unlock((struct sock *)msk); check_notify: /* if the subflow is not already linked into the conn_list, we can't diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8cb6a873dae9..8ef2927ebca2 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3186,6 +3186,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; if (!nsk) @@ -3226,7 +3227,8 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, /* 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); + subflow = mptcp_subflow_ctx(ssk); + list_add(&subflow->node, &msk->conn_list); sock_hold(ssk); /* new mpc subflow takes ownership of the newly @@ -3241,6 +3243,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); + + if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) + __mptcp_subflow_fully_established(msk, subflow, mp_opt); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ @@ -3478,8 +3483,6 @@ void mptcp_finish_connect(struct sock *ssk) * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); - WRITE_ONCE(msk->snd_una, subflow->idsn + 1); - WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); mptcp_pm_new_connection(msk, ssk, 0); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 9f5ee82e3473..fefcbf585411 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -622,8 +622,9 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net); unsigned int mptcp_close_timeout(const struct sock *sk); int mptcp_get_pm_type(const struct net *net); const char *mptcp_get_scheduler(const struct net *net); -void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt); +void __mptcp_subflow_fully_established(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); void mptcp_check_and_set_pending(struct sock *sk); void __mptcp_push_pending(struct sock *sk, unsigned int flags); @@ -952,8 +953,8 @@ void mptcp_event_pm_listener(const struct sock *ssk, enum mptcp_event_type event); bool mptcp_userspace_pm_active(const struct mptcp_sock *msk); -void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt); +void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt); void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index c2df34ebcf28..c34ecadee120 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -441,20 +441,6 @@ void __mptcp_sync_state(struct sock *sk, int state) } } -static void mptcp_propagate_state(struct sock *sk, struct sock *ssk) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - - mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) { - __mptcp_sync_state(sk, ssk->sk_state); - } else { - msk->pending_state = ssk->sk_state; - __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); - } - mptcp_data_unlock(sk); -} - static void subflow_set_remote_key(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt) @@ -476,6 +462,31 @@ static void subflow_set_remote_key(struct mptcp_sock *msk, atomic64_set(&msk->rcv_wnd_sent, subflow->iasn); } +static void mptcp_propagate_state(struct sock *sk, struct sock *ssk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_data_lock(sk); + if (mp_opt) { + /* Options are available only in the non fallback cases + * avoid updating rx path fields otherwise + */ + WRITE_ONCE(msk->snd_una, subflow->idsn + 1); + WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); + subflow_set_remote_key(msk, subflow, mp_opt); + } + + if (!sock_owned_by_user(sk)) { + __mptcp_sync_state(sk, ssk->sk_state); + } else { + msk->pending_state = ssk->sk_state; + __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); + } + mptcp_data_unlock(sk); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -510,10 +521,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (mp_opt.deny_join_id0) WRITE_ONCE(msk->pm.remote_deny_join_id0, true); subflow->mp_capable = 1; - subflow_set_remote_key(msk, subflow, &mp_opt); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, &mp_opt); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -556,7 +566,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } } else if (mptcp_check_fallback(sk)) { fallback: - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, NULL); } return; @@ -741,17 +751,16 @@ void mptcp_subflow_drop_ctx(struct sock *ssk) kfree_rcu(ctx, rcu); } -void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt) +void __mptcp_subflow_fully_established(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) { - struct mptcp_sock *msk = mptcp_sk(subflow->conn); - subflow_set_remote_key(msk, subflow, mp_opt); subflow->fully_established = 1; WRITE_ONCE(msk->fully_established, true); if (subflow->is_mptfo) - mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); + __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); } static struct sock *subflow_syn_recv_sock(const struct sock *sk, @@ -844,7 +853,6 @@ create_child: * mpc option */ if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) { - mptcp_subflow_fully_established(ctx, &mp_opt); mptcp_pm_fully_established(owner, child); ctx->pm_notified = 1; } @@ -1756,7 +1764,7 @@ static void subflow_state_change(struct sock *sk) mptcp_do_fallback(sk); pr_fallback(msk); subflow->conn_finished = 1; - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, NULL); } /* as recvmsg() does not acquire the subflow socket for ssk selection -- cgit v1.2.3