when getting a reply from the hw, only sync the dmamem for that one reply
rather than all the replies.

switch mpi from using splbio to protect itself over to mutexes.

mpi only needs two mutexes, one for the list of free ccbs, and another to
protect the reply doorbell. the latter is necessary to allow

switch mpi from using splbio to protect itself over to mutexes.

mpi only needs two mutexes, one for the list of free ccbs, and another to
protect the reply doorbell. the latter is necessary to allow polling for
command completion to work in smp systems.

tested on sas and fc hbas. this diff was written over 2 years ago now with
surprisingly few tweaks to handle changes that have occurred since then.

show more ...

remove dead assignment and newly created unused variable.

Found by LLVM/Clang Static Analyzer.

ok dlg@ marco@

Stop spamming dmesg when raid isn't available.

put the midlayer changes back in.

the two issues affecting it last time are gone. the first, mishandling of
TRY_AGAIN_LATER is not relevant now that krw got rid of TRY_AGAIN_LATER.
the second, the m

put the midlayer changes back in.

the two issues affecting it last time are gone. the first, mishandling of
TRY_AGAIN_LATER is not relevant now that krw got rid of TRY_AGAIN_LATER.
the second, the misbehaving IBM disk was found to be a problem with siop
using ordered tags on most ops combined with the speed of the new code.

putting this in so we can move forward.

ok krw@ "commit please" marco@

show more ...

revert midlayer back to it was before i put my big rewrite in. this is
causing a weird problems on an alpha and also appears responsible for
isp(4) weirdness i havent had a chance to examine yet.

si

revert midlayer back to it was before i put my big rewrite in. this is
causing a weird problems on an alpha and also appears responsible for
isp(4) weirdness i havent had a chance to examine yet.

sigh, this makes me sad.

show more ...

backout the backout marco did of my code because of the NO_CCB breakage.
the fix for the NO_CCB breakage will follow shortly.

tested by krw@ marco@ johan@
ok krw@ marco@

bump copyrights

The big diff dlg committed to the midlayer breaks NO_CCB and
TRY_AGAIN_LATER. NO_CCB is a timer based mechanism that can trivially
be made to fail by running IO to two or more disks simultaneously.

The big diff dlg committed to the midlayer breaks NO_CCB and
TRY_AGAIN_LATER. NO_CCB is a timer based mechanism that can trivially
be made to fail by running IO to two or more disks simultaneously. The
TRY_AGAIN_LATER thing is more subtle because it now is a permanent
failure instead of transient however this is much harder to hit because
something must have gone wrong before it hits.

ok deraadt krw miod

show more ...

Don't write bogus values to reply_fifo_host_signalling_addr. This register
should remain untouched because it is only for interruptless drivers.

Honor reply queue depth per the spec instead of clip

Don't write bogus values to reply_fifo_host_signalling_addr. This register
should remain untouched because it is only for interruptless drivers.

Honor reply queue depth per the spec instead of clipping it at 32.

ok dlg

show more ...

enable event handling on sas hbas and ignore unhandled events. this turns
on sas hotplug. you can add and remove drives and the kernel will handle it
now.

if you're attempting to detach multiple devices (eg, many targets,
many luns, or the entire bus), dont report ENXIO as an error to the
caller. this broke autoconf when it tried to forcefully remove a

if you're attempting to detach multiple devices (eg, many targets,
many luns, or the entire bus), dont report ENXIO as an error to the
caller. this broke autoconf when it tried to forcefully remove a
bus such as umass and it thought there was a failure.

this introduces a way for scsi hbas to call activate/deactivate on
a device based on its target/lun address via a call to scsi_activate().
they can then schedule the actual detach/attach in a thread later via
scsi_req_probe/detach.

the mpi changes tweak the sas event handling code to use these apis
to properly handle attaches and detaches of disks. event handling
is still disabled till i can make it less chatty.

umass breakage reported by form@

show more ...

disable interrupt coalescing (aka mitigation) if the chip comes up with it
turned on. mitigation on io only slows us down.

developed on hardware donated by fox-it.

let page requests sleep instead of polling for completion. not used just
yet...

always mark an xs complete if we're about to return COMPLETE to the
midlayer. always call scsi_done on the xs too.

if the port is fc, populate the adapters scsi_link structure with the wwpn
and wwnn so scsibus can use it.

requested by and ok deraadt@

Bring NO_CCB to mpi.

ok marco@

Extend the scsi_adapter minphys() callback to take a struct scsi_link *
as additional argument. This will allow intermediate layers between
scsi devices such as sd and scsi host adapters to take appr

Extend the scsi_adapter minphys() callback to take a struct scsi_link *
as additional argument. This will allow intermediate layers between
scsi devices such as sd and scsi host adapters to take appropriate
action if necessary.

show more ...

missing braces; ok marco

enable bio

ok dlg

sizeofa is now nitems in param.h, so dont declare my own in mpi.c it was
unused there anyway. use nitems in mpi_pci_match.

Remove dup proto from <alexey.suslikov@gmail.com>

Don't attach bio unless we do RAID.

Add sensors

Fix bogus shift.