diff options
author | Paolo Abeni <pabeni@redhat.com> | 2023-10-04 13:38:11 -0700 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2023-10-05 09:34:31 -0700 |
commit | a5efdbcece83af94180e8d7c0a6e22947318499d (patch) | |
tree | 5ff63443c2832ffd7b9b644e5fefbbbd22cf36d5 /net/mptcp/protocol.c | |
parent | 3eef8555891026628aa1cc6dbc01db86df88aa26 (diff) |
mptcp: fix delegated action races
The delegated action infrastructure is prone to the following
race: different CPUs can try to schedule different delegated
actions on the same subflow at the same time.
Each of them will check different bits via mptcp_subflow_delegate(),
and will try to schedule the action on the related per-cpu napi
instance.
Depending on the timing, both can observe an empty delegated list
node, causing the same entry to be added simultaneously on two different
lists.
The root cause is that the delegated actions infra does not provide
a single synchronization point. Address the issue reserving an additional
bit to mark the subflow as scheduled for delegation. Acquiring such bit
guarantee the caller to own the delegated list node, and being able to
safely schedule the subflow.
Clear such bit only when the subflow scheduling is completed, ensuring
proper barrier in place.
Additionally swap the meaning of the delegated_action bitmask, to allow
the usage of the existing helper to set multiple bit at once.
Fixes: bcd97734318d ("mptcp: use delegate action to schedule 3rd ack retrans")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231004-send-net-20231004-v1-1-28de4ac663ae@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/mptcp/protocol.c')
-rw-r--r-- | net/mptcp/protocol.c | 28 |
1 files changed, 14 insertions, 14 deletions
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e252539b1e19..c3b83cb390d9 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3425,24 +3425,21 @@ static void schedule_3rdack_retransmission(struct sock *ssk) sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout); } -void mptcp_subflow_process_delegated(struct sock *ssk) +void mptcp_subflow_process_delegated(struct sock *ssk, long status) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; - if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + if (status & BIT(MPTCP_DELEGATE_SEND)) { mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, true); else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); - mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND); } - if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) { + if (status & BIT(MPTCP_DELEGATE_ACK)) schedule_3rdack_retransmission(ssk); - mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK); - } } static int mptcp_hash(struct sock *sk) @@ -3968,14 +3965,17 @@ static int mptcp_napi_poll(struct napi_struct *napi, int budget) struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bh_lock_sock_nested(ssk); - if (!sock_owned_by_user(ssk) && - mptcp_subflow_has_delegated_action(subflow)) - mptcp_subflow_process_delegated(ssk); - /* ... elsewhere tcp_release_cb_override already processed - * the action or will do at next release_sock(). - * In both case must dequeue the subflow here - on the same - * CPU that scheduled it. - */ + if (!sock_owned_by_user(ssk)) { + mptcp_subflow_process_delegated(ssk, xchg(&subflow->delegated_status, 0)); + } else { + /* tcp_release_cb_override already processed + * the action or will do at next release_sock(). + * In both case must dequeue the subflow here - on the same + * CPU that scheduled it. + */ + smp_wmb(); + clear_bit(MPTCP_DELEGATE_SCHEDULED, &subflow->delegated_status); + } bh_unlock_sock(ssk); sock_put(ssk); |