From 340cd44451fb0bfa542365e6b4b565bbd44836e2 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 9 Apr 2009 00:27:17 +0100 Subject: [PATCH] dm kcopyd: fix callback race If the thread calling dm_kcopyd_copy is delayed due to scheduling inside split_job/segment_complete and the subjobs complete before the loop in split_job completes, the kcopyd callback could be invoked from the thread that called dm_kcopyd_copy instead of the kcopyd workqueue. dm_kcopyd_copy -> split_job -> segment_complete -> job->fn() Snapshots depend on the fact that callbacks are called from the singlethreaded kcopyd workqueue and expect that there is no racing between individual callbacks. The racing between callbacks can lead to corruption of exception store and it can also mean that exception store callbacks are called twice for the same exception - a likely reason for crashes reported inside pending_complete() / remove_exception(). This patch fixes two problems: 1. job->fn being called from the thread that submitted the job (see above). - Fix: hand over the completion callback to the kcopyd thread. 2. job->fn(read_err, write_err, job->context); in segment_complete reports the error of the last subjob, not the union of all errors. - Fix: pass job->write_err to the callback to report all error bits (it is done already in run_complete_job) Cc: stable@kernel.org Signed-off-by: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- drivers/md/dm-kcopyd.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 9d37907..3e3fc06 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -511,13 +511,16 @@ static void segment_complete(int read_err, unsigned long write_err, } else if (atomic_dec_and_test(&job->sub_jobs)) { /* - * To avoid a race we must keep the job around - * until after the notify function has completed. - * Otherwise the client may try and stop the job - * after we've completed. + * Queue the completion callback to the kcopyd thread. + * + * Some callers assume that all the completions are called + * from a single thread and don't race with each other. + * + * We must not call the callback directly here because this + * code may not be executing in the thread. */ - job->fn(read_err, write_err, job->context); - mempool_free(job, job->kc->job_pool); + push(&kc->complete_jobs, job); + wake(kc); } } @@ -530,6 +533,8 @@ static void split_job(struct kcopyd_job *job) { int i; + atomic_inc(&job->kc->nr_jobs); + atomic_set(&job->sub_jobs, SPLIT_COUNT); for (i = 0; i < SPLIT_COUNT; i++) segment_complete(0, 0u, job); -- 2.7.4