[PATCH block/for-3.3/core] block: an exiting task should be allowedto create io_context

From: Tejun Heo
Date: Sat Dec 24 2011 - 20:03:11 EST

While fixing io_context creation / task exit race condition,
6e736be7f2 "block: make ioc get/put interface more conventional and
fix race on alloction" also prevented an exiting (%PF_EXITING) task
from creating its own io_context. This is incorrect as exit path may
issue IOs, e.g. from exit_files(), and if those IOs are the first ones
issued by the task, io_context needs to be created to process the IOs.

Combined with the existing problem of io_context / io_cq creation
failure having the possibility of stalling IO, this problem results in
deterministic full IO lockup with certain workloads.

Fix it by allowing io_context creation regardless of %PF_EXITING for

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Reported-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Reported-by: Hugh Dickins <hughd@xxxxxxxxxx>
Thanks a lot for the hint, Hugh. My testing stuff (fio, dd and some
adhoc rawio testing programs) was issuing IOs before exiting, so I
didn't hit the problem and I suspect the reason why I didn't see the
boot failure Andrew was seeing was because of systemd - boot process
used to be dominated by lots of short-lived programs, many of which
touching/modifying files, and thus it triggered the first IO on exit
paths with Andrew's old userland. With systemd, most of those are
gone, so...


block/blk-ioc.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index ce9b35a..33fae7d 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -281,9 +281,16 @@ void create_io_context_slowpath(struct task_struct *task, gfp_t gfp_flags,
INIT_WORK(&ioc->release_work, ioc_release_fn);

- /* try to install, somebody might already have beaten us to it */
+ /*
+ * Try to install. ioc shouldn't be installed if someone else
+ * already did or @task, which isn't %current, is exiting. Note
+ * that we need to allow ioc creation on exiting %current as exit
+ * path may issue IOs from e.g. exit_files(). The exit path is
+ * responsible for not issuing IO after exit_io_context().
+ */
- if (!task->io_context && !(task->flags & PF_EXITING))
+ if (!task->io_context &&
+ (task == current || !(task->flags & PF_EXITING)))
task->io_context = ioc;
kmem_cache_free(iocontext_cachep, ioc);
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/