If rxrpc_recvmsg() fails because MSG_DONTWAIT was specified but the call at the front of the recvmsg queue already has its mutex locked, it requeues the call - whether or not the call is already queued. The call may be on the queue because MSG_PEEK was also passed and so the call was not dequeued or because the I/O thread requeued it. The unconditional requeue may then corrupt the recvmsg queue, leading to things like UAFs or refcount underruns. Fix this by only requeuing the call if it isn't already on the queue - and moving it to the front if it is already queued. Also, MSG_PEEK doesn't dequeue the call so shouldn't call rxrpc_notify_socket() for the call if we didn't use up all the data on the queue, so fix that also. Fixes: 540b1c48c37a ("rxrpc: Fix deadlock between call creation and sendmsg/recvmsg") Reported-by: Faith Reported-by: Pumpkin Chang Signed-off-by: David Howells Acked-by: Marc Dionne cc: Nir Ohfeld cc: Willy Tarreau cc: "David S. Miller" cc: Eric Dumazet cc: Jakub Kicinski cc: Paolo Abeni cc: Simon Horman cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org cc: security@kernel.org cc: stable@kernel.org --- include/trace/events/rxrpc.h | 4 ++++ net/rxrpc/recvmsg.c | 15 ++++++++++++--- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index de6f6d25767c..869f97c9bf73 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -322,6 +322,7 @@ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ + EM(rxrpc_call_put_recvmsg_peek_nowait, "PUT peek-nwt") \ EM(rxrpc_call_put_release_recvmsg_q, "PUT rls-rcmq") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ @@ -340,6 +341,9 @@ EM(rxrpc_call_see_input, "SEE input ") \ EM(rxrpc_call_see_notify_released, "SEE nfy-rlsd") \ EM(rxrpc_call_see_recvmsg, "SEE recvmsg ") \ + EM(rxrpc_call_see_recvmsg_requeue, "SEE recv-rqu") \ + EM(rxrpc_call_see_recvmsg_requeue_first, "SEE recv-rqF") \ + EM(rxrpc_call_see_recvmsg_requeue_move, "SEE recv-rqM") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 7fa7e77f6bb9..2c42823f472b 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -518,7 +518,8 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (rxrpc_call_has_failed(call)) goto call_failed; - if (!skb_queue_empty(&call->recvmsg_queue)) + if (!(flags & MSG_PEEK) && + !skb_queue_empty(&call->recvmsg_queue)) rxrpc_notify_socket(call); goto not_yet_complete; @@ -549,11 +550,19 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, error_requeue_call: if (!(flags & MSG_PEEK)) { spin_lock_irq(&rx->recvmsg_lock); - list_add(&call->recvmsg_link, &rx->recvmsg_q); + if (list_empty(&call->recvmsg_link)) { + list_add(&call->recvmsg_link, &rx->recvmsg_q); + rxrpc_see_call(call, rxrpc_call_see_recvmsg_requeue); + } else if (list_is_first(&call->recvmsg_link, &rx->recvmsg_q)) { + rxrpc_see_call(call, rxrpc_call_see_recvmsg_requeue_first); + } else { + list_move(&call->recvmsg_link, &rx->recvmsg_q); + rxrpc_see_call(call, rxrpc_call_see_recvmsg_requeue_move); + } spin_unlock_irq(&rx->recvmsg_lock); trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_requeue, 0); } else { - rxrpc_put_call(call, rxrpc_call_put_recvmsg); + rxrpc_put_call(call, rxrpc_call_put_recvmsg_peek_nowait); } error_no_call: release_sock(&rx->sk);