freebsd-skq/sys/dev/nvme
Jim Harris 43e35466de Revert r244549.
This change was originally intended to account for test kthreads under
the nvmecontrol process, but jhb indicated it may not be safe to
associate kthreads with userland processes and this could have
unintended consequences.

I did not observe any problems with this change, but my testing didn't
exhaust the kinds of corner cases that could cause problems.  It is not
that important to account for these test threads under nvmecontrol, so I
am just reverting this change for now.

On a related note, the part of this patch for <= 7.x fails compilation
so reverting this fixes that too.

Suggested by: jhb
2013-01-07 21:35:25 +00:00
..
nvme_ctrlr_cmd.c Add nvme_ctrlr_submit_[admin|io]_request functions which consolidates 2012-10-18 00:39:29 +00:00
nvme_ctrlr.c Map BAR 4/5, because NVMe spec says devices may place the MSI-X table 2012-12-18 23:27:18 +00:00
nvme_ns_cmd.c Add nvme_ctrlr_submit_[admin|io]_request functions which consolidates 2012-10-18 00:39:29 +00:00
nvme_ns.c Add return codes to all functions used for submitting commands to I/O 2012-10-18 00:32:07 +00:00
nvme_private.h Map BAR 4/5, because NVMe spec says devices may place the MSI-X table 2012-12-18 23:27:18 +00:00
nvme_qpair.c Use callout_reset_curcpu to allow the callout to be handled by the 2012-10-31 23:44:19 +00:00
nvme_sysctl.c Preallocate a limited number of nvme_tracker objects per qpair, rather 2012-10-18 00:44:39 +00:00
nvme_test.c Revert r244549. 2013-01-07 21:35:25 +00:00
nvme_uio.c Cleanup uio-related code to use struct nvme_request and 2012-10-18 00:40:40 +00:00
nvme.c Map BAR 4/5, because NVMe spec says devices may place the MSI-X table 2012-12-18 23:27:18 +00:00
nvme.h Add ability to queue nvme_request objects if no nvme_trackers are available. 2012-10-18 00:45:53 +00:00