Blob Blame History Raw
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Thu, 10 Dec 2020 17:34:07 +0100
Subject: samples/bpf: Fix possible hang in xdpsock with multiple threads
Patch-mainline: v5.11-rc1
Git-commit: 092fde0f863b72b67c4d6dc03844f5658fc00a35
References: bsc#1155518

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
Acked-by: Gary Lin <glin@suse.com>
---
 samples/bpf/xdpsock_user.c |    2 ++
 1 file changed, 2 insertions(+)

--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -929,6 +929,8 @@ static void tx_only(struct xsk_socket_in
 	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++) {