| Age | Commit message (Expand) | Author |
|---|
| 2013-01-18 | data transfers suit STREAMING dma maps. | David Gwynne |
| 2013-01-17 | mikeb pointed at that the interrupt status register read in mpi_intr was | David Gwynne |
| 2013-01-17 | we dont need to read the interrupt status register to know if we have | David Gwynne |
| 2013-01-17 | treat DVAs as 64bits all the time so we can avoid ugly casts and shifts in | David Gwynne |
| 2012-09-18 | several tweaks to make mpi(4) work for vmware emulated sas adapters. | David Gwynne |
| 2012-09-12 | Use sg_addr instead of sg_lo_addr, leftovers from last commit. | Christiano F. Haesbaert |
| 2012-09-12 | Make sure we don't sleep on autoconf. | Christiano F. Haesbaert |
| 2012-08-26 | htole64 works as good as htole32 twice for dma virtual addresses. | David Gwynne |
| 2012-01-16 | mpi_get_ccb and mpi_put_ccb are only called via iopools now, so change | David Gwynne |
| 2011-07-17 | Backout a bunch of my SCSI commits from c2k11. At least one of these | Matthew Dempsky |
| 2011-07-08 | First batch of converting SCSI HBAs from setting saa_targets and | Matthew Dempsky |
| 2011-06-17 | M_WAITOK cleanup of two cases: | Michael Knudsen |
| 2011-04-27 | if getting the RAID header fails, dont stop the midlayer from trying to | David Gwynne |
| 2011-04-27 | configure fc controllers to fail io as fast as possible when cables are | David Gwynne |
| 2011-04-27 | return XS_RESET to the midlayer if the command was killed for some reason | David Gwynne |
| 2011-04-27 | rework the scanning of fibre channel ports to match how linux does it. | David Gwynne |
| 2011-03-04 | Peek at the interrupt status register before poking with the reply post | Mike Belopuhov |
| 2011-03-01 | back out r1.162, the one that bumps openings up on sas and fc | David Gwynne |
| 2010-09-24 | vol_list in mpi_get_raid is never used. | David Gwynne |
| 2010-09-21 | tweak the sas io unit to use 32 openings when talking to sata disks if the | David Gwynne |
| 2010-09-20 | Use SSD_ERRCODE_CURRENT instead of magic 0x70. | Kenneth R Westerback |
| 2010-09-14 | allow devices on fc and sas adapters to use all the openings the chip can | David Gwynne |
| 2010-09-13 | if a busy sas device is unplugged, the pending io on that device will | David Gwynne |
| 2010-09-13 | dont reuse the event notifications ccbs id for the acknowledgement. | David Gwynne |
| 2010-09-13 | im not convinced we only have one outstanding event to ack at a time. this | David Gwynne |
| 2010-09-10 | implement handling of rescan events on fc controllers. allows "hotplug" of | David Gwynne |
| 2010-08-27 | get some format strings and variables right in debug output | David Gwynne |
| 2010-08-07 | No "\n" needed at the end of panic() strings. | Kenneth R Westerback |
| 2010-07-06 | if we get an event notification that requires acknowledgement while | David Gwynne |
| 2010-07-06 | move the last direct users of mpi_{get,put}_ccb over to using the scsi | David Gwynne |
| 2010-07-01 | Change scsibus(4)'s scsi_link array to an SLIST to save memory on | Matthew Dempsky |
| 2010-06-28 | Remove all adapter-specific 'struct scsi_device's. They are never used. First | Kenneth R Westerback |
| 2010-06-15 | rearrange attach so that the SDEV_VIRTUAL flag is set during scsi_probe, | David Gwynne |
| 2010-06-15 | dont pass the dev_t from the scsi device drivers into the midlayer for | David Gwynne |
| 2010-05-19 | the virtual scsi disks that mpi(4) presents dont grok modifications to the | David Gwynne |
| 2010-05-16 | Use a temporary variable for now to sidestep -Wbounded checking when | Nicholas Marriott |
| 2010-05-09 | back out 1.143, it causes data corruption on the mpis in sun v20z boxes, | David Gwynne |
| 2010-04-28 | Fix gcc4 warning | Marco Peereboom |
| 2010-04-22 | use BUS_DMA_ZERO on alloc instead of bzeroing after. | Owain Ainsworth |
| 2010-04-22 | Fix cut 'n paste typo | Marco Peereboom |
| 2010-04-19 | i thought mpi gave each device all the openings on the bus, which was a | David Gwynne |
| 2010-04-16 | byteswap the number of blocks on physical disks for bioctl correctly. | David Gwynne |
| 2010-04-16 | if there is no raid, do not allocate a 0-sized structure for sensors | Theo de Raadt |
| 2010-04-12 | dont need to call scsi_done with splbio. the midlayer protects | David Gwynne |
| 2010-04-09 | fix double free in an error path. the midlayer gets the ccb for scsi io | David Gwynne |
| 2010-04-06 | use SLISTs for managing the ccb free list rather than TAILQs. | David Gwynne |
| 2010-04-06 | modify mpi to provide an iopool as a way for the midlayer to manage access | David Gwynne |
| 2010-04-03 | dont allocate with M_TEMP and then free with M_DEVBUF. made even worse that | David Gwynne |
| 2010-03-23 | Change the scsi_cmd function member of scsi_adapter from int to | Kenneth R Westerback |
| 2010-01-11 | rework the polling code to use the semantic krw@ proposed. | David Gwynne |
