can: rx-offload: can_rx_offload_queue_sorted(): fix error handling, avoid skb mem...

If the rx-offload skb_queue is full can_rx_offload_queue_sorted() will
not queue the skb and return with an error.

None of the callers of this function, issue a kfree_skb() to free the
not queued skb. This results in a memory leak.

This patch fixes the problem by freeing the skb in case of a full queue.
The return value is adjusted to -ENOBUFS to better reflect the actual
problem.

The device stats handling is left to the callers, as this function might
be used in both the rx and tx path.

Fixes: 55059f2b7f86 ("can: rx-offload: introduce can_rx_offload_get_echo_skb() and can_rx_offload_queue_sorted() functions")
Cc: linux-stable <stable@vger.kernel.org>
Cc: Martin Hundebøll <martin@geanix.com>
Reported-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>

diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c
index e6a668ee77306a1859872cf543d68ef59cf8667d..663697439d1c7cae55b238fa0016d45ae9f06e36 100644 (file)
--- a/drivers/net/can/rx-offload.c
+++ b/drivers/net/can/rx-offload.c
@@ -207,8 +207,10 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload,
        unsigned long flags;
 
        if (skb_queue_len(&offload->skb_queue) >
-           offload->skb_queue_len_max)
-               return -ENOMEM;
+           offload->skb_queue_len_max) {
+               kfree_skb(skb);
+               return -ENOBUFS;
+       }
 
        cb = can_rx_offload_get_cb(skb);
        cb->timestamp = timestamp;