Sagi Grimberg b6bb1722f3 nvme-rdma: fix possible use-after-free in transport error_recovery work
While nvme_rdma_submit_async_event_work is checking the ctrl and queue
state before preparing the AER command and scheduling io_work, in order
to fully prevent a race where this check is not reliable the error
recovery work must flush async_event_work before continuing to destroy
the admin queue after setting the ctrl state to RESETTING such that
there is no race .submit_async_event and the error recovery handler
itself changing the ctrl state.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
2022-02-02 09:19:07 +01:00
..
2021-10-20 19:16:02 +02:00
2021-11-01 09:27:38 -07:00
2021-08-14 15:54:09 -06:00
2021-08-14 15:54:09 -06:00
2022-01-12 10:35:23 -08:00
2022-01-12 10:35:23 -08:00
2021-08-16 14:42:23 +02:00