February 2024 - Linux-stable-mirror

FAILED: patch "[PATCH] mptcp: corner case locking for rx path fields initialization" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x e4a0fa47e816e186f6b4c0055d07eeec42d11871 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021905-routing-hurray-cc32@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: e4a0fa47e816 ("mptcp: corner case locking for rx path fields initialization") 3f83d8a77eee ("mptcp: fix more tx path fields initialization") 013e3179dbd2 ("mptcp: fix rcv space initialization") c693a8516429 ("mptcp: use mptcp_set_state") 4fd19a307016 ("mptcp: fix inconsistent state on fastopen race") d109a7767273 ("mptcp: fix possible NULL pointer dereference on close") 8005184fd1ca ("mptcp: refactor sndbuf auto-tuning") a5efdbcece83 ("mptcp: fix delegated action races") 27e5ccc2d5a5 ("mptcp: fix dangling connection hang-up") f6909dc1c1f4 ("mptcp: rename timer related helper to less confusing names") 9f1a98813b4b ("mptcp: process pending subflow error on close") d5fbeff1ab81 ("mptcp: move __mptcp_error_report in protocol.c") e3b2870b6d22 ("mptcp: add a new sysctl scheduler") ebc1e08f01eb ("mptcp: drop last_snd and MPTCP_RESET_SCHEDULER") e263691773cd ("mptcp: Remove unnecessary test for __mptcp_init_sock()") 39880bd808ad ("mptcp: get rid of msk->subflow") 3f326a821b99 ("mptcp: change the mpc check helper to return a sk") 3aa362494170 ("mptcp: avoid ssock usage in mptcp_pm_nl_create_listen_socket()") f0bc514bd5c1 ("mptcp: avoid additional indirection in sockopt") 40f56d0c7043 ("mptcp: avoid additional indirection in mptcp_listen()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e4a0fa47e816e186f6b4c0055d07eeec42d11871 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Thu, 8 Feb 2024 19:03:52 +0100 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> 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 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * 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

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] mptcp: corner case locking for rx path fields initialization" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x e4a0fa47e816e186f6b4c0055d07eeec42d11871 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021903-overshoot-stumbling-283f@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: e4a0fa47e816 ("mptcp: corner case locking for rx path fields initialization") 3f83d8a77eee ("mptcp: fix more tx path fields initialization") 013e3179dbd2 ("mptcp: fix rcv space initialization") c693a8516429 ("mptcp: use mptcp_set_state") 4fd19a307016 ("mptcp: fix inconsistent state on fastopen race") d109a7767273 ("mptcp: fix possible NULL pointer dereference on close") 8005184fd1ca ("mptcp: refactor sndbuf auto-tuning") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e4a0fa47e816e186f6b4c0055d07eeec42d11871 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Thu, 8 Feb 2024 19:03:52 +0100 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> 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 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * 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

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] mptcp: corner case locking for rx path fields initialization" failed to apply to 6.7-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.7-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.7.y git checkout FETCH_HEAD git cherry-pick -x e4a0fa47e816e186f6b4c0055d07eeec42d11871 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021902-askew-amnesty-5bca@gregkh' --subject-prefix 'PATCH 6.7.y' HEAD^.. Possible dependencies: e4a0fa47e816 ("mptcp: corner case locking for rx path fields initialization") 3f83d8a77eee ("mptcp: fix more tx path fields initialization") 013e3179dbd2 ("mptcp: fix rcv space initialization") c693a8516429 ("mptcp: use mptcp_set_state") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e4a0fa47e816e186f6b4c0055d07eeec42d11871 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Thu, 8 Feb 2024 19:03:52 +0100 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> 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 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * 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

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] mptcp: fix rcv space initialization" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 013e3179dbd2bc756ce1dd90354abac62f65b739 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021904-undertook-crushing-1de6@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: 013e3179dbd2 ("mptcp: fix rcv space initialization") 4fd19a307016 ("mptcp: fix inconsistent state on fastopen race") d109a7767273 ("mptcp: fix possible NULL pointer dereference on close") 8005184fd1ca ("mptcp: refactor sndbuf auto-tuning") a5efdbcece83 ("mptcp: fix delegated action races") 27e5ccc2d5a5 ("mptcp: fix dangling connection hang-up") f6909dc1c1f4 ("mptcp: rename timer related helper to less confusing names") ebc1e08f01eb ("mptcp: drop last_snd and MPTCP_RESET_SCHEDULER") e263691773cd ("mptcp: Remove unnecessary test for __mptcp_init_sock()") 39880bd808ad ("mptcp: get rid of msk->subflow") 17ebf8a4c38b ("mptcp: fix the incorrect judgment for msk->cb_flags") a7384f391875 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 013e3179dbd2bc756ce1dd90354abac62f65b739 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Thu, 8 Feb 2024 19:03:50 +0100 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2111819016af..7632eafb683b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1963,6 +1963,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (copied <= 0) return; + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); + msk->rcvq_space.copied += copied; mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); @@ -3160,6 +3163,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->bytes_received = 0; msk->bytes_sent = 0; msk->bytes_retrans = 0; + msk->rcvspace_init = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); @@ -3247,6 +3251,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) { const struct tcp_sock *tp = tcp_sk(ssk); + msk->rcvspace_init = 1; msk->rcvq_space.copied = 0; msk->rcvq_space.rtt_us = 0; @@ -3257,8 +3262,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) TCP_INIT_CWND * tp->advmss); if (msk->rcvq_space.space == 0) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; - - WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); } void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) @@ -3478,10 +3481,9 @@ void mptcp_finish_connect(struct sock *ssk) 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); mptcp_pm_new_connection(msk, ssk, 0); - - mptcp_rcv_space_init(msk, ssk); } void mptcp_sock_graft(struct sock *sk, struct socket *parent) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index b905f1868298..9f5ee82e3473 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -304,7 +304,8 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1, - free_first:1; + free_first:1, + rcvspace_init:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; 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);

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] mptcp: fix rcv space initialization" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 013e3179dbd2bc756ce1dd90354abac62f65b739 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021903-cohesive-swaddling-c9ab@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: 013e3179dbd2 ("mptcp: fix rcv space initialization") 4fd19a307016 ("mptcp: fix inconsistent state on fastopen race") d109a7767273 ("mptcp: fix possible NULL pointer dereference on close") 8005184fd1ca ("mptcp: refactor sndbuf auto-tuning") a5efdbcece83 ("mptcp: fix delegated action races") 27e5ccc2d5a5 ("mptcp: fix dangling connection hang-up") f6909dc1c1f4 ("mptcp: rename timer related helper to less confusing names") ebc1e08f01eb ("mptcp: drop last_snd and MPTCP_RESET_SCHEDULER") e263691773cd ("mptcp: Remove unnecessary test for __mptcp_init_sock()") 39880bd808ad ("mptcp: get rid of msk->subflow") 17ebf8a4c38b ("mptcp: fix the incorrect judgment for msk->cb_flags") a7384f391875 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 013e3179dbd2bc756ce1dd90354abac62f65b739 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Thu, 8 Feb 2024 19:03:50 +0100 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2111819016af..7632eafb683b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1963,6 +1963,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (copied <= 0) return; + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); + msk->rcvq_space.copied += copied; mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); @@ -3160,6 +3163,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->bytes_received = 0; msk->bytes_sent = 0; msk->bytes_retrans = 0; + msk->rcvspace_init = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); @@ -3247,6 +3251,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) { const struct tcp_sock *tp = tcp_sk(ssk); + msk->rcvspace_init = 1; msk->rcvq_space.copied = 0; msk->rcvq_space.rtt_us = 0; @@ -3257,8 +3262,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) TCP_INIT_CWND * tp->advmss); if (msk->rcvq_space.space == 0) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; - - WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); } void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) @@ -3478,10 +3481,9 @@ void mptcp_finish_connect(struct sock *ssk) 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); mptcp_pm_new_connection(msk, ssk, 0); - - mptcp_rcv_space_init(msk, ssk); } void mptcp_sock_graft(struct sock *sk, struct socket *parent) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index b905f1868298..9f5ee82e3473 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -304,7 +304,8 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1, - free_first:1; + free_first:1, + rcvspace_init:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; 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);

1 year, 9 months

1
0
0 0

[PATCH stable] mptcp: introduce explicit flag for first subflow disposal

by Christoph Paasch

From: Paolo Abeni <pabeni(a)redhat.com> This is a partial backport of the upstram commit 39880bd808ad ("mptcp: get rid of msk->subflow"). It's partial to avoid a long a complex dependency chain not suitable for stable. The only bit remaning from the original commit is the introduction of a new field avoid a race at close time causing an UaF: BUG: KASAN: use-after-free in mptcp_subflow_queue_clean+0x2c9/0x390 include/net/mptcp.h:104 Read of size 1 at addr ffff88803bf72884 by task syz-executor.6/23092 CPU: 0 PID: 23092 Comm: syz-executor.6 Not tainted 6.1.65-gc6114c845984 #50 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x125/0x18f lib/dump_stack.c:106 print_report+0x163/0x4f0 mm/kasan/report.c:284 kasan_report+0xc4/0x100 mm/kasan/report.c:495 mptcp_subflow_queue_clean+0x2c9/0x390 include/net/mptcp.h:104 mptcp_check_listen_stop+0x190/0x2a0 net/mptcp/protocol.c:3009 __mptcp_close+0x9a/0x970 net/mptcp/protocol.c:3024 mptcp_close+0x2a/0x130 net/mptcp/protocol.c:3089 inet_release+0x13d/0x190 net/ipv4/af_inet.c:429 sock_close+0xcf/0x230 net/socket.c:652 __fput+0x3a2/0x870 fs/file_table.c:320 task_work_run+0x24e/0x300 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop+0xa4/0xc0 kernel/entry/common.c:171 exit_to_user_mode_prepare+0x51/0x90 kernel/entry/common.c:204 syscall_exit_to_user_mode+0x26/0x140 kernel/entry/common.c:286 do_syscall_64+0x53/0xa0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x64/0xce RIP: 0033:0x41d791 Code: 75 14 b8 03 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 74 2a 00 00 c3 48 83 ec 08 e8 9a fc ff ff 48 89 04 24 b8 03 00 00 00 0f 05 <48> 8b 3c 24 48 89 c2 e8 e3 fc ff ff 48 89 d0 48 83 c4 08 48 3d 01 RSP: 002b:00000000008bfb90 EFLAGS: 00000293 ORIG_RAX: 0000000000000003 RAX: 0000000000000000 RBX: 0000000000000004 RCX: 000000000041d791 RDX: 0000001b33920000 RSI: ffffffff8139adff RDI: 0000000000000003 RBP: 000000000079d980 R08: 0000001b33d20000 R09: 0000000000000951 R10: 000000008139a955 R11: 0000000000000293 R12: 00000000000c739b R13: 000000000079bf8c R14: 00007fa301053000 R15: 00000000000c705a </TASK> Allocated by task 22528: kasan_save_stack mm/kasan/common.c:45 [inline] kasan_set_track+0x40/0x70 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:374 [inline] __kasan_kmalloc+0xa0/0xb0 mm/kasan/common.c:383 kasan_kmalloc include/linux/kasan.h:211 [inline] __do_kmalloc_node mm/slab_common.c:955 [inline] __kmalloc+0xaa/0x1c0 mm/slab_common.c:968 kmalloc include/linux/slab.h:558 [inline] sk_prot_alloc+0xac/0x200 net/core/sock.c:2038 sk_clone_lock+0x56/0x1090 net/core/sock.c:2236 inet_csk_clone_lock+0x26/0x420 net/ipv4/inet_connection_sock.c:1141 tcp_create_openreq_child+0x30/0x1910 net/ipv4/tcp_minisocks.c:474 tcp_v6_syn_recv_sock+0x413/0x1a90 net/ipv6/tcp_ipv6.c:1283 subflow_syn_recv_sock+0x621/0x1300 net/mptcp/subflow.c:730 tcp_get_cookie_sock+0xf0/0x5f0 net/ipv4/syncookies.c:201 cookie_v6_check+0x130f/0x1c50 net/ipv6/syncookies.c:261 tcp_v6_do_rcv+0x7e0/0x12b0 net/ipv6/tcp_ipv6.c:1147 tcp_v6_rcv+0x2494/0x2f50 net/ipv6/tcp_ipv6.c:1743 ip6_protocol_deliver_rcu+0xba3/0x1620 net/ipv6/ip6_input.c:438 ip6_input+0x1bc/0x470 net/ipv6/ip6_input.c:483 ipv6_rcv+0xef/0x2c0 include/linux/netfilter.h:302 __netif_receive_skb+0x1ea/0x6a0 net/core/dev.c:5525 process_backlog+0x353/0x660 net/core/dev.c:5967 __napi_poll+0xc6/0x5a0 net/core/dev.c:6534 net_rx_action+0x652/0xea0 net/core/dev.c:6601 __do_softirq+0x176/0x525 kernel/softirq.c:571 Freed by task 23093: kasan_save_stack mm/kasan/common.c:45 [inline] kasan_set_track+0x40/0x70 mm/kasan/common.c:52 kasan_save_free_info+0x2b/0x50 mm/kasan/generic.c:516 ____kasan_slab_free+0x13a/0x1b0 mm/kasan/common.c:236 kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1724 [inline] slab_free_freelist_hook mm/slub.c:1750 [inline] slab_free mm/slub.c:3661 [inline] __kmem_cache_free+0x1eb/0x340 mm/slub.c:3674 sk_prot_free net/core/sock.c:2074 [inline] __sk_destruct+0x4ad/0x620 net/core/sock.c:2160 tcp_v6_rcv+0x269c/0x2f50 net/ipv6/tcp_ipv6.c:1761 ip6_protocol_deliver_rcu+0xba3/0x1620 net/ipv6/ip6_input.c:438 ip6_input+0x1bc/0x470 net/ipv6/ip6_input.c:483 ipv6_rcv+0xef/0x2c0 include/linux/netfilter.h:302 __netif_receive_skb+0x1ea/0x6a0 net/core/dev.c:5525 process_backlog+0x353/0x660 net/core/dev.c:5967 __napi_poll+0xc6/0x5a0 net/core/dev.c:6534 net_rx_action+0x652/0xea0 net/core/dev.c:6601 __do_softirq+0x176/0x525 kernel/softirq.c:571 The buggy address belongs to the object at ffff88803bf72000 which belongs to the cache kmalloc-4k of size 4096 The buggy address is located 2180 bytes inside of 4096-byte region [ffff88803bf72000, ffff88803bf73000) The buggy address belongs to the physical page: page:00000000a72e4e51 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x3bf70 head:00000000a72e4e51 order:3 compound_mapcount:0 compound_pincount:0 flags: 0x100000000010200(slab|head|node=0|zone=1) raw: 0100000000010200 ffffea0000a0ea00 dead000000000002 ffff888100042140 raw: 0000000000000000 0000000000040004 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88803bf72780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88803bf72800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88803bf72880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88803bf72900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88803bf72980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Prevent the MPTCP worker from freeing the first subflow for unaccepted socket when such sockets transition to TCP_CLOSE state, and let that happen at accept() or listener close() time. Fixes: b6985b9b8295 ("mptcp: use the workqueue to destroy unaccepted sockets") Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Reported-by: Christoph Paasch <cpaasch(a)apple.com> Tested-by: Christoph Paasch <cpaasch(a)apple.com> --- Notes: This patch is targeted only for -stable and specifically v6.1.x The Fixes-tag is from the upstream tree. We can change that to the commit in the v6.1.x-tree if needed. net/mptcp/protocol.c | 9 ++++----- net/mptcp/protocol.h | 3 ++- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 76539d1004eb..db5369b6442d 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2422,7 +2422,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, goto out_release; } - dispose_it = !msk->subflow || ssk != msk->subflow->sk; + dispose_it = msk->free_first || ssk != msk->first; if (dispose_it) list_del(&subflow->node); @@ -2440,7 +2440,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { __mptcp_subflow_disconnect(ssk, subflow, flags); - msk->subflow->state = SS_UNCONNECTED; release_sock(ssk); goto out; @@ -3341,10 +3340,10 @@ static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - /* clears msk->subflow, allowing the following to close - * even the initial subflow - */ mptcp_dispose_initial_subflow(msk); + + /* allow the following to close even the initial subflow */ + msk->free_first = 1; mptcp_destroy_common(msk, 0); sk_sockets_allocated_dec(sk); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 4ec8e0a81b5a..e5d553dfc13f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -287,7 +287,8 @@ struct mptcp_sock { cork:1, nodelay:1, fastopening:1, - in_accept_queue:1; + in_accept_queue:1, + free_first:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; -- 2.32.3 (Apple Git-135)

1 year, 9 months

2
1
0 0

FAILED: patch "[PATCH] userfaultfd: fix mmap_changing checking in" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 67695f18d55924b2013534ef3bdc363bc9e14605 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021851-implement-sulfide-c5fa@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 67695f18d55924b2013534ef3bdc363bc9e14605 Mon Sep 17 00:00:00 2001 From: Lokesh Gidra <lokeshgidra(a)google.com> Date: Wed, 17 Jan 2024 14:37:29 -0800 Subject: [PATCH] userfaultfd: fix mmap_changing checking in mfill_atomic_hugetlb In mfill_atomic_hugetlb(), mmap_changing isn't being checked again if we drop mmap_lock and reacquire it. When the lock is not held, mmap_changing could have been incremented. This is also inconsistent with the behavior in mfill_atomic(). Link: https://lkml.kernel.org/r/20240117223729.1444522-1-lokeshgidra@google.com Fixes: df2cc96e77011 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races") Signed-off-by: Lokesh Gidra <lokeshgidra(a)google.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Brian Geffon <bgeffon(a)google.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Jann Horn <jannh(a)google.com> Cc: Kalesh Singh <kaleshsingh(a)google.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Nicolas Geoffray <ngeoffray(a)google.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 20e3b0d9cf7e..75fcf1f783bc 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -357,6 +357,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags) { struct mm_struct *dst_mm = dst_vma->vm_mm; @@ -472,6 +473,15 @@ static __always_inline ssize_t mfill_atomic_hugetlb( goto out; } mmap_read_lock(dst_mm); + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + if (mmap_changing && atomic_read(mmap_changing)) { + err = -EAGAIN; + break; + } dst_vma = NULL; goto retry; @@ -506,6 +516,7 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags); #endif /* CONFIG_HUGETLB_PAGE */ @@ -622,8 +633,8 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) - return mfill_atomic_hugetlb(dst_vma, dst_start, - src_start, len, flags); + return mfill_atomic_hugetlb(dst_vma, dst_start, src_start, + len, mmap_changing, flags); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock;

1 year, 9 months

2
1
0 0

FAILED: patch "[PATCH] userfaultfd: fix mmap_changing checking in" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 67695f18d55924b2013534ef3bdc363bc9e14605 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021849-backboned-clump-6dd4@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 67695f18d55924b2013534ef3bdc363bc9e14605 Mon Sep 17 00:00:00 2001 From: Lokesh Gidra <lokeshgidra(a)google.com> Date: Wed, 17 Jan 2024 14:37:29 -0800 Subject: [PATCH] userfaultfd: fix mmap_changing checking in mfill_atomic_hugetlb In mfill_atomic_hugetlb(), mmap_changing isn't being checked again if we drop mmap_lock and reacquire it. When the lock is not held, mmap_changing could have been incremented. This is also inconsistent with the behavior in mfill_atomic(). Link: https://lkml.kernel.org/r/20240117223729.1444522-1-lokeshgidra@google.com Fixes: df2cc96e77011 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races") Signed-off-by: Lokesh Gidra <lokeshgidra(a)google.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Brian Geffon <bgeffon(a)google.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Jann Horn <jannh(a)google.com> Cc: Kalesh Singh <kaleshsingh(a)google.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Nicolas Geoffray <ngeoffray(a)google.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 20e3b0d9cf7e..75fcf1f783bc 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -357,6 +357,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags) { struct mm_struct *dst_mm = dst_vma->vm_mm; @@ -472,6 +473,15 @@ static __always_inline ssize_t mfill_atomic_hugetlb( goto out; } mmap_read_lock(dst_mm); + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + if (mmap_changing && atomic_read(mmap_changing)) { + err = -EAGAIN; + break; + } dst_vma = NULL; goto retry; @@ -506,6 +516,7 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags); #endif /* CONFIG_HUGETLB_PAGE */ @@ -622,8 +633,8 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) - return mfill_atomic_hugetlb(dst_vma, dst_start, - src_start, len, flags); + return mfill_atomic_hugetlb(dst_vma, dst_start, src_start, + len, mmap_changing, flags); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock;

1 year, 9 months

2
1
0 0

FAILED: patch "[PATCH] userfaultfd: fix mmap_changing checking in" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 67695f18d55924b2013534ef3bdc363bc9e14605 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021848-spiny-glitzy-711f@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 67695f18d55924b2013534ef3bdc363bc9e14605 Mon Sep 17 00:00:00 2001 From: Lokesh Gidra <lokeshgidra(a)google.com> Date: Wed, 17 Jan 2024 14:37:29 -0800 Subject: [PATCH] userfaultfd: fix mmap_changing checking in mfill_atomic_hugetlb In mfill_atomic_hugetlb(), mmap_changing isn't being checked again if we drop mmap_lock and reacquire it. When the lock is not held, mmap_changing could have been incremented. This is also inconsistent with the behavior in mfill_atomic(). Link: https://lkml.kernel.org/r/20240117223729.1444522-1-lokeshgidra@google.com Fixes: df2cc96e77011 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races") Signed-off-by: Lokesh Gidra <lokeshgidra(a)google.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Brian Geffon <bgeffon(a)google.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Jann Horn <jannh(a)google.com> Cc: Kalesh Singh <kaleshsingh(a)google.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Nicolas Geoffray <ngeoffray(a)google.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 20e3b0d9cf7e..75fcf1f783bc 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -357,6 +357,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags) { struct mm_struct *dst_mm = dst_vma->vm_mm; @@ -472,6 +473,15 @@ static __always_inline ssize_t mfill_atomic_hugetlb( goto out; } mmap_read_lock(dst_mm); + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + if (mmap_changing && atomic_read(mmap_changing)) { + err = -EAGAIN; + break; + } dst_vma = NULL; goto retry; @@ -506,6 +516,7 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags); #endif /* CONFIG_HUGETLB_PAGE */ @@ -622,8 +633,8 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) - return mfill_atomic_hugetlb(dst_vma, dst_start, - src_start, len, flags); + return mfill_atomic_hugetlb(dst_vma, dst_start, src_start, + len, mmap_changing, flags); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock;

1 year, 9 months

2
1
0 0

FAILED: patch "[PATCH] userfaultfd: fix mmap_changing checking in" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 67695f18d55924b2013534ef3bdc363bc9e14605 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021847-glandular-distant-2033@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 67695f18d55924b2013534ef3bdc363bc9e14605 Mon Sep 17 00:00:00 2001 From: Lokesh Gidra <lokeshgidra(a)google.com> Date: Wed, 17 Jan 2024 14:37:29 -0800 Subject: [PATCH] userfaultfd: fix mmap_changing checking in mfill_atomic_hugetlb In mfill_atomic_hugetlb(), mmap_changing isn't being checked again if we drop mmap_lock and reacquire it. When the lock is not held, mmap_changing could have been incremented. This is also inconsistent with the behavior in mfill_atomic(). Link: https://lkml.kernel.org/r/20240117223729.1444522-1-lokeshgidra@google.com Fixes: df2cc96e77011 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races") Signed-off-by: Lokesh Gidra <lokeshgidra(a)google.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Brian Geffon <bgeffon(a)google.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Jann Horn <jannh(a)google.com> Cc: Kalesh Singh <kaleshsingh(a)google.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Nicolas Geoffray <ngeoffray(a)google.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 20e3b0d9cf7e..75fcf1f783bc 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -357,6 +357,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags) { struct mm_struct *dst_mm = dst_vma->vm_mm; @@ -472,6 +473,15 @@ static __always_inline ssize_t mfill_atomic_hugetlb( goto out; } mmap_read_lock(dst_mm); + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + if (mmap_changing && atomic_read(mmap_changing)) { + err = -EAGAIN; + break; + } dst_vma = NULL; goto retry; @@ -506,6 +516,7 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags); #endif /* CONFIG_HUGETLB_PAGE */ @@ -622,8 +633,8 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) - return mfill_atomic_hugetlb(dst_vma, dst_start, - src_start, len, flags); + return mfill_atomic_hugetlb(dst_vma, dst_start, src_start, + len, mmap_changing, flags); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock;

1 year, 9 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2024