From cc85d67f4fdc4fb89c74ff327d2bbe7803951a0f Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Wed, 9 Jul 2014 21:18:32 +0200 Subject: [PATCH] drbd: fix regression 'out of mem, failed to invoke fence-peer helper' commit bbc1c5e8ad6dfebf9d13b8a4ccdf66c92913eac9 upstream. Since linux kernel 3.13, kthread_run() internally uses wait_for_completion_killable(). We sometimes may use kthread_run() while we still have a signal pending, which we used to kick our threads out of potentially blocking network functions, causing kthread_run() to mistake that as a new fatal signal and fail. Fix: flush_signals() before kthread_run(). Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/drbd/drbd_nl.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index c706d50..8c16c2f 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -525,6 +525,12 @@ void conn_try_outdate_peer_async(struct drbd_tconn *tconn) struct task_struct *opa; kref_get(&tconn->kref); + /* We may just have force_sig()'ed this thread + * to get it out of some blocking network function. + * Clear signals; otherwise kthread_run(), which internally uses + * wait_on_completion_killable(), will mistake our pending signal + * for a new fatal signal and fail. */ + flush_signals(current); opa = kthread_run(_try_outdate_peer_async, tconn, "drbd_async_h"); if (IS_ERR(opa)) { conn_err(tconn, "out of mem, failed to invoke fence-peer helper\n"); -- 2.7.4