summaryrefslogtreecommitdiffstats
path: root/sys/dev/nvme
Commit message (Expand)AuthorAgeFilesLines
...
* Add a mutex to each namespace, for general locking operations on the namespace.jimharris2013-04-122-0/+12
* Rename the controller's fail_req_lock, so that it can be used for otherjimharris2013-04-122-7/+8
* Do not panic when a busdma mapping operation fails.jimharris2013-04-122-5/+28
* Add unmapped bio support to nvme(4) and nvd(4).jimharris2013-04-015-10/+114
* Add "type" to nvme_request, signifying if its payload is a VADDR, UIO, orjimharris2013-03-295-37/+63
* Remove obsolete comment. This code has now been tested with the QEMUjimharris2013-03-281-4/+0
* Delete extra IO qpairs allocated based on number of MSI-X vectors, butjimharris2013-03-281-6/+14
* Fix printf format issue on i386.jimharris2013-03-271-2/+3
* Clean up debug prints.jimharris2013-03-265-43/+254
* Move common code from the different nvme_allocate_request functions into ajimharris2013-03-261-18/+21
* Change a number of malloc(9) calls to use M_WAITOK instead ofjimharris2013-03-264-20/+10
* Replace usages of mtx_pool_find used for admin commands with a pollingjimharris2013-03-264-103/+71
* Abort and do not retry any outstanding admin commands left over afterjimharris2013-03-261-0/+15
* Add the ability to internally mark a controller as failed, if it is unable tojimharris2013-03-265-21/+192
* Just disable the controller instead of deleting IO queues during detach.jimharris2013-03-262-59/+17
* Set Pre-boot Software Load Count to 0 at the end of the controllerjimharris2013-03-261-0/+10
* Remove the is_started flag from struct nvme_controller.jimharris2013-03-264-60/+46
* Ensure the controller's MDTS is accounted for in max_xfer_size.jimharris2013-03-262-0/+13
* Cap the number of retry attempts to a configurable number. This ensuresjimharris2013-03-264-12/+39
* Pass associated log page data to async event consumers, if requested.jimharris2013-03-264-11/+32
* When an asynchronous event request is completed, automatically fetch thejimharris2013-03-262-9/+83
* Add structure definitions and controller command function for firmwarejimharris2013-03-263-0/+26
* Add structure definitions and a controller command function forjimharris2013-03-263-0/+37
* Create struct nvme_status.jimharris2013-03-267-40/+41
* Make nvme_ctrlr_reset a nop if a reset is already in progress.jimharris2013-03-263-5/+29
* By default, always escalate to controller reset when an I/O times out.jimharris2013-03-263-21/+33
* Add a tunable for the I/O timeout interval. Default is still 30 seconds,jimharris2013-03-264-11/+50
* Add handling for controller fatal status (csts.cfs).jimharris2013-03-263-3/+37
* Add API for nvme consumers to access controller and namespace identify data.jimharris2013-03-263-0/+18
* Add controller reset capability to nvme(4) and ability to explicitlyjimharris2013-03-266-99/+214
* Keep a doubly-linked list of outstanding trackers.jimharris2013-03-262-10/+14
* Create a generic nvme_ctrlr_cmd_get_log_page function, and change thejimharris2013-03-262-6/+21
* Expose the get/set features API to nvme consumers.jimharris2013-03-262-8/+10
* Add an interface for nvme shim drivers (i.e. nvd) to register forjimharris2013-03-264-17/+75
* Enable asynchronous event requests on non-Chatham devices.jimharris2013-03-265-77/+141
* Move controller destruction code from nvme_detach() to new nvme_ctrlr_destruct()jimharris2013-03-263-46/+53
* Specify command timeout interval on a per-command type basis.jimharris2013-03-263-3/+13
* Explicitly abort a timed out command, if the ABORT command sent to thejimharris2013-03-261-1/+29
* Break out the code for completing an nvme_tracker object into a separatejimharris2013-03-261-43/+59
* Add support for ABORT commands, including issuing these commands whenjimharris2013-03-263-5/+24
* Add an internal _nvme_qpair_submit_request function, which performsjimharris2013-03-261-6/+15
* Make the DSM range count 0-based. Previously we were deallocating one morejimharris2013-03-261-1/+1
* Do not look at the namespace's thin provisioning field to determine if DSMjimharris2013-03-261-1/+1
* Fix GCC build:obrien2013-03-072-7/+5
* Revert r244549.jimharris2013-01-071-2/+2
* Put kthreads under curproc so they are attached to nvmecontrol ratherjimharris2012-12-211-2/+2
* Map BAR 4/5, because NVMe spec says devices may place the MSI-X tablejimharris2012-12-183-0/+24
* Simplify module definition by adding nvme_modevent to DRIVER_MODULE()jimharris2012-12-181-9/+2
* Do not use taskqueue to defer completion work when using INTx. INTx nowjimharris2012-12-183-24/+3
* Add PCI device ID for 8-channel IDT NVMe controller, and clarify that thejimharris2012-12-062-2/+4
OpenPOWER on IntegriCloud