samples/bpf: Fix possible hang in xdpsock with multiple threads

Fix a possible hang in xdpsock that can occur when using multiple
threads. In this case, one or more of the threads might get stuck in
the while-loop in tx_only after the user has signaled the main thread
to stop execution. In this case, no more Tx packets will be sent, so a
thread might get stuck in the aforementioned while-loop. Fix this by
introducing a test inside the while-loop to check if the benchmark has
been terminated. If so, return from the function.

Fixes: cd9e72b6f210 ("samples/bpf: xdpsock: Add option to specify batch size")
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20201210163407.22066-1-magnus.karlsson@gmail.com

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 568f981..db0cb73 100644 (file)
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -1275,6 +1275,8 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size)
        while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) <
                                      batch_size) {
                complete_tx_only(xsk, batch_size);
+               if (benchmark_done)
+                       return;
        }
 
        for (i = 0; i < batch_size; i++) {