io_uring: fix bug in slow unregistering of nodes
authorDylan Yudaken <dylany@fb.com>
Fri, 21 Jan 2022 12:38:56 +0000 (04:38 -0800)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Tue, 1 Feb 2022 16:27:11 +0000 (17:27 +0100)
commit82cc3382e34e2254453cdfc0e0c3190357e27eed
tree24d8dbe87a8adbcceaffd1a0ce5e8866e3c1e6f6
parentfa005a5c5d4dc1eb1bcf99761fc1f678bfd46a08
io_uring: fix bug in slow unregistering of nodes

[ Upstream commit b36a2050040b2d839bdc044007cdd57101d7f881 ]

In some cases io_rsrc_ref_quiesce will call io_rsrc_node_switch_start,
and then immediately flush the delayed work queue &ctx->rsrc_put_work.

However the percpu_ref_put does not immediately destroy the node, it
will be called asynchronously via RCU. That ends up with
io_rsrc_node_ref_zero only being called after rsrc_put_work has been
flushed, and so the process ends up sleeping for 1 second unnecessarily.

This patch executes the put code immediately if we are busy
quiescing.

Fixes: 4a38aed2a0a7 ("io_uring: batch reap of dead file registrations")
Signed-off-by: Dylan Yudaken <dylany@fb.com>
Link: https://lore.kernel.org/r/20220121123856.3557884-1-dylany@fb.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
fs/io_uring.c