rxrpc: Fix recvmsg() unconditional requeue

[ Upstream commit 2c28769 ]

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.  If we don't queue it, we
have to put the ref we obtained by dequeuing it.

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: 540b1c4 ("rxrpc: Fix deadlock between call creation and sendmsg/recvmsg")
Reported-by: Faith <faith@zellic.io>
Reported-by: Pumpkin Chang <pumpkin@devco.re>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Marc Dionne <marc.dionne@auristor.com>
cc: Nir Ohfeld <niro@wiz.io>
cc: Willy Tarreau <w@1wt.eu>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/95163.1768428203@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
[Use spin_unlock instead of spin_unlock_irq to maintain context consistency.]
Signed-off-by: Robert Garcia <rob_garcia@163.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Author: dhowells

include/trace/events/rxrpc.h

@@ -270,6 +270,7 @@
 	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_sock,		"PUT rls-sock") \
 	EM(rxrpc_call_put_release_sock_tba,	"PUT rls-sk-a") \
 	EM(rxrpc_call_put_sendmsg,		"PUT sendmsg ") \
@@ -287,6 +288,9 @@
 	EM(rxrpc_call_see_distribute_error,	"SEE dist-err") \
 	EM(rxrpc_call_see_input,		"SEE input   ") \
 	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  ") \

net/rxrpc/recvmsg.c

@@ -430,7 +430,8 @@ 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;
 
@@ -461,11 +462,21 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 error_requeue_call:
 	if (!(flags & MSG_PEEK)) {
 		spin_lock(&rx->recvmsg_lock);
-		list_add(&call->recvmsg_link, &rx->recvmsg_q);
-		spin_unlock(&rx->recvmsg_lock);
+		if (list_empty(&call->recvmsg_link)) {
+			list_add(&call->recvmsg_link, &rx->recvmsg_q);
+			rxrpc_see_call(call, rxrpc_call_see_recvmsg_requeue);
+			spin_unlock(&rx->recvmsg_lock);
+		} else if (list_is_first(&call->recvmsg_link, &rx->recvmsg_q)) {
+			spin_unlock(&rx->recvmsg_lock);
+			rxrpc_put_call(call, rxrpc_call_see_recvmsg_requeue_first);
+		} else {
+			list_move(&call->recvmsg_link, &rx->recvmsg_q);
+			spin_unlock(&rx->recvmsg_lock);
+			rxrpc_put_call(call, rxrpc_call_see_recvmsg_requeue_move);
+		}
 		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);