from the pc532 "ncr" driver.
This gets me up to 300 KB/s from /dev/rsd0a on my A310. I think
bus_space_{read,write}_multi_1 and copy{in,out} are the bottlenecks now.
Handle special case for IFF_PROMISC. If only IFF_PROMISC
flag is changed, do not call an_init() to avoid initiating
reassociation to another access point. It is really
helpful for tcpdump(8).
way of doing business- modulo some startup spasms and peculiarities
of the way kthreads are started (*after* configuration, weird) and
some strangeness with the freeze/thaw code, what now happens is
that any of Loop Down, LIP, Loop Reset or Port Datbase or Name
Server Database Changed ASYNC events cause the queues to freeze
for this channel. The arrival of a Loop UP is not relevant.
What *is* relevant is that the Port Datbase or Name Server Changed
async event indicate that it's okay to go and (re)evaluate the
state of the FC link and (re)probe local loop and fabric membership.
We have a kthread do this because it's *sooooo* much nicer to be
able to sleep while doing the 130-250 mailbox commands it'll take
to re-evaluate things.
When the state is well known again, we can unfreeze the channel
queues. Then, as commands start arriving, we simply can start them
or bounce them with XS_SELTIMEOUT (if the device in question has
gone away). Previously, we did lazy evaluation, which meant that
if a change occurred, we would wait until the very *next* command
to go rebuild stuff.
The reason this is not sensible is:
a) Even with sleeping, you can hang up your system because you might be
making some poor stat(2) call pay the price of re-evaluating the whole
fabric.
b) If we ever really want to get to dynamic attachment/detachment, we
should find out sooner, rather than later, where things get to.
Split off ispminphys_1020 from ispminphys- a 1020 has a 24 bit limit-
not anything newer.
Re-enable LIPs and Loop Resets as async events- this allows the outer
layer to set policy about them.
Roll platform major && minor. Remove bogus waitq (no longer used).
Remove callout entry in softc (no longer used). Define some shorthands
for channels. Clean up a variety of cruft left over from the
thorpej_scsipi changeover.
Add SD_IO_TIMEOUT (an option in opt_scsi.h) also, which defaults to the
normal 60 * 1000 timeout for normal read/write commamds. This allows you
to shorten or lengthen the timeout as needed.
- Add some additional config block bits for the i82558/i82559.
- Change the config block template to only fill in the must-be-one
reserved bits, leave fxp_init() to fill in all the important things.
- On the i82558/i82559, we can use "Receive Long Frames" rather than
"Save Bad Frames" to support the VLAN MTU.
- Use 802.3x flow control on the i82558/i82559. This is all handled
transparently by the hardware. When in promiscuous mode, allow
wire-watchers to see the flow control frames.
- Use the Extended TxCB format on the i82558/i82559. This places two
Transmit Buffer Descriptors directly in the TxCB, which should cover
the vast majority of packets transmitted. This saves PCI transactions
that would otherwise be required to fetch the TBD list.
With the tansmit queue length changes from yesterday, this gets us up to
11.5MB/s TCP transmit speed, out of an absolute maximum of 12MB/s possible
on a 100Mb/s link.
some devices can't handle tag number larger than some values and always
reject commands with QUEUE FULL if the tag number is larger than this.
Under some circonstances the scsipi system may not decrease periph_openings
(as a workaround of other odd behavior) and we may end up requeuing the command
with a hight tag value again, and the driver could loop on this.
Workaround: in case of queue full, decrease periph_openings to
min(periph_active - 1, periph_openings - 1) so that, after some iteration,
periph_openings is less than the max tag value acceptable by the device.
Solves the problem with tagged queuing on ncr53c9x for me.
SIP_EVENT_COUNTERS.
- Decrease SIP_NTXSEGS to 8 and increase SIP_TXQUEUELEN to 256.
This gives us 256 transmit jobs with only twice the descriptor
memory footprint. This prevents stalling transmissions due to
lack of transmit jobs under heavy load.
- Increase SIP_NRXDESC to 128 so we don't run out of receive descriptors
under extreme load.
- As recommended by the manual, leave one descriptor in the transmit ring
with OWN clear to prevent wrap-around.
- Even though the manual claims that driver software must initialize
TXDP if there are no pending transmissions when a new transmission
is to be initialized, doing so causes serious performance degredation
on the DP83820 under heavy load. Not initializing TXDP also increases
performance on the DP83815.
All of this gets us up to ~90Mb/s on both the DP83820 and DP83815 when
connected to a 100base network.
This fixes a `hang' on shutdown when the `Synchronise Cache' command
is sent to a disk. (It uses polled mode because it is called from inside
a shutdown hook).
interrupt priority, to avoid allocating additional mbufs on
splsched(). Move some other misc bits out of splched()-guarded
section. This should make the code a bit more friendly wrt e.g.
clock interrupts. Sligh performance improvement was observed with
this change (like 1-2% on slow machine), even.
This also fixes ancient kern/2478 by Bill Sommerfeld.
keeps us from stomping on ourselves.
Say we're in the middle of re-evaluating a loop (and sleeping) when a
command completes, or a timer refires, and this *other* thread decides
*it* wants to start re-evaluating the loop. Bad news.
We have to be a bit careful- if we can't acquire the MBOX semaphore at
interrupt level, we will simulate a host interface error. This is a bit
of a temp workaround. There's some work underway driven by a NetBSD
commercial user that will try and force most mailbox stuff into a
part A/part B interrupt driven model.
0xfe on my gateway 2000 circa 1993). That should not affect broken controllers
that choke on the kbc_auxtest, because for those the write/read test succeeds.
Clean up one bug in a DPRINTF in arrs_input which could panic on some packets.
Gut the ack/response functionality and clean it up so all packets get checked
correctly and the abuf struct isn't used once the ab_cb has happened (there
still could be ack packets waiting to be processed at that time).
Finally, add some documentation explaining read/write/inreg and their
purpose/argument calling.
Although WEP is used in Windows also in an old firm,
because WEP is processed by the windows driver side.
If Prism2 Firm version is more than 0.8.3, WEP does work without 'Promiscuous ON'.
Roaming mode can change value into 'firm mode' and disable.
Authentication mode can change into 'Open System authentication'
and 'Shared Key Authentication' with Prism2 chip.
wi_get_id() was introduced in order that chip might judge automatically
whether it is Prism2 chip. Therefore, a pp_prism2 entry in
"struct wi_pcmcia_product" became unnecessary.
DP83820. The DP83820 definitions are wrapped in #ifdef DP83820, since
there are enough differences that a single binary object would not be
able to efficiently drive both the DP83815 and DP83820.
DIAGNOSTIC/DEBUG from the kernel. This helped to boost the performance
on my test machine from ~5KB/s to like 800KB/s for ftp test, and
to like 700KB/s for netio test. I wouldn't have imagined the options
are THAT costly ....
done when the command-in-progress bit has been cleared. The 1ms
time that is mentioned also seems wrong; 20,000us is not enough
on at least one machine. So, do a delay(100000) in ex_reset.
Fortunately, this function is only called when the card is
attached or when hardware failure is suspected.
While here, only mask one 1 bit in the 'reset hack' case.