index
:
src
cvs/HEAD
kms/intel
kms/radeon
master
OpenBSD base system
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
sys
Age
Commit message (
Expand
)
Author
2016-04-14
dont attach if the min nvme page size is bigger than the cpu page size
David Gwynne
2016-04-14
dont complete scsi writes twice
David Gwynne
2016-04-14
WAITOK for the dmamap create for ccbs too
David Gwynne
2016-04-14
cut the memory for io buffers up into page sized chunks
David Gwynne
2016-04-14
check both the admin and io queue for completions in the interrupt handler
David Gwynne
2016-04-14
dont put names in arguments.
David Gwynne
2016-04-14
tabs, not spaces
David Gwynne
2016-04-13
implement handling of scsi reads and writes
David Gwynne
2016-04-13
enable interrupts before attaching the scsibus
David Gwynne
2016-04-13
allocate a queue for io commands and tell the chip about it.
David Gwynne
2016-04-13
nvme_q_create() issues the commands to tell the chip about io queues
David Gwynne
2016-04-13
stub out handling of TEST_UNIT_READY, PREVENT_ALLOW, and START_STOP
David Gwynne
2016-04-13
implement handling of scsi read capacity commands
David Gwynne
2016-04-13
implement basic scsi inquiry handling
David Gwynne
2016-04-13
provide variants of the sqe struct for q creation and io operations
David Gwynne
2016-04-13
implement the guts of the scsi probe and free function
David Gwynne
2016-04-13
implement the namespace identify structure
David Gwynne
2016-04-13
the io command set
David Gwynne
2016-04-13
wire up the scsi midlayer. scsibus should appear after this.
David Gwynne
2016-04-13
allocate an array of things to hold info about namespaces
David Gwynne
2016-04-13
stash the controller identify and number of namespaces in the softc.
David Gwynne
2016-04-13
make a place for q_id to go
David Gwynne
2016-04-13
provide an scsi_adapter and stub functions for emulation to sit in
David Gwynne
2016-04-13
nvme_sqe_fill will post a copy of an sqe from a caller
David Gwynne
2016-04-13
poll for command completion on the cqe itll be of calling nvme_intr
David Gwynne
2016-04-13
make nvme_poll return the flags from the completion queue entry
David Gwynne
2016-04-13
keep track of the queue id in nvme_queue.
David Gwynne
2016-04-13
rename idx to id in nvme_q_alloc
David Gwynne
2016-04-13
nvme_dmamem_alloc runs in autoconf or process context, so it can sleep
David Gwynne
2016-04-13
We're always ready! So send IFQ_SET_READY() to the bitbucket.
Martin Pieuchot
2016-04-13
G/C IFQ_SET_READY().
Martin Pieuchot
2016-04-13
G/C IFQ_SET_READY().
Martin Pieuchot
2016-04-13
G/C IFQ_SET_READY().
Martin Pieuchot
2016-04-13
G/C IFQ_SET_READY().
Martin Pieuchot
2016-04-13
G/C IFQ_SET_READY().
Martin Pieuchot
2016-04-13
Keep all pools in the same place.
Martin Pieuchot
2016-04-13
Remove extra parenthesis around comparison.
Vincent Gross
2016-04-13
add missing arguments to debug printf
Mike Larkin
2016-04-12
Simplify amap traversal in amap_swap_off.
Stefan Kempf
2016-04-12
No need to rescan chunks in each discipline to find appropriate
Kenneth R Westerback
2016-04-12
Unbreak tree. Put 'laddr6' declaration inside #ifdef INET6/#endif.
Kenneth R Westerback
2016-04-12
Call if_enqueue() and if_start() instead of dereferencing the ifp
Martin Pieuchot
2016-04-12
shuffle attach so we read chip capabilities before operating on it
David Gwynne
2016-04-12
Call ether_fakeaddr() instead of faking Ethernet addresses manually.
Martin Pieuchot
2016-04-12
Call debug register dump functions in error conditions (if VMM_DEBUG set)
Mike Larkin
2016-04-12
Remove unneeded art_free().
Martin Pieuchot
2016-04-12
Set bridge(4)'s if_output to a dummy function returning EAFNOSUPPORT as
Martin Pieuchot
2016-04-12
Only build the vcpu register dump functions if VMM_DEBUG is enabled, no
Mike Larkin
2016-04-11
Simplify in_pcblookup_local() logic.
Vincent Gross
2016-04-11
Rename in_pcblookup() to in_pcblookup_local() and change its prototype
Vincent Gross
[next]