Commit Graph

1667 Commits

Author SHA1 Message Date
Luigi Rizzo
aec846d484 Per jlemon request, reintroduce some printf() when an
mbuf allocation fails, and fix (i hope) a couple of style bugs.

I believe these printf() are extremely dangerous because now they can
occur on every incoming packet and are not rate limited. They were
meant to warn the sysadmin about lack of resources, but now they
can become a nice way to panic your system under load.

Other drivers (e.g. the fxp driver) have nothing like this.

There is a pending discussion on putting this kind of warnings
elsewhere, and I hope we can fix this soon.
2001-11-29 23:47:47 +00:00
Luigi Rizzo
01faf54bb0 For i386 architecture, remove an expensive m_devget() (and the
underlying unaligned bcopy) on incoming packets that are already
available (albeit unaligned) in a buffer.
The performance improvement varies, depending on CPU and memory
speed, but can be quite large especially on slow CPUs. I have seen
over 50% increase on forwarding speed on the sis driver for the
486/133 (embedded systems), which does exactly the same thing.

The behaviour is controlled by a sysctl variable, hw.dc_quick which
defaults to 1. Set it to 0 to restore the old behaviour.

After running a few experiments (in userland, though) I am convinced
that doing the m_devget() is detrimental to performance in almost
all cases.

Even if your CPU has degraded performance with misaligned data,
the bcopy() in the driver has the same overhead due to misaligment
as the one that you save in the uiomove(), plus you do one extra
copy and pollute the cache.

But more often than not, you do not even have to touch the payload,
e.g. when you are forwarding packets, and even in the often-cited
case of NFS, you often end up passing a pointer to the payload to
the disk controller.

In any case, you can play with the sysctl variable to toggle between
the two behaviours, and see if it makes a difference.

MFC-after: 3 days
2001-11-29 22:46:48 +00:00
Luigi Rizzo
920dcd3fcb Remove the need for an expensive m_devget on the i386, which does not
have alignment problems.

On small boxes (e.g. the net4501 from Soekris, featuring a 486/133)
this provides huge performance benefits: the peak forwarding rate
with avg.sized packets goes up by 50-70% because of this change
alone. Faster CPUs might benefit less from this change, but in any
case the CPU has better things to do than waste time on useless
memory-to-memory copies.

Several drivers (for Tulip-like cards) might benefit from a similar
change.

Right now the new behaviour is controlled by a sysctl variable,
hw.sis_quick which defaults to 1 (on), you can set it to 0 to
reintroduce the old behaviour (and compare the results).  The
variable is only there to show how much you can gain with this
change, it will go away soon.

Also, slightly simplify the code to initialize the ring buffers,
and remove a couple of dangerous printf's which could trigger on
any packet in case of mbuf shortage.

MFC-after: 3 days
2001-11-28 16:10:37 +00:00
Luigi Rizzo
49a79b6661 Fix a bug in the driver -- under load, the receive unit could become
idle and the driver would not detect the event, requiring userland
to cycle the interface to bring it up again.
The fix consists in adding SIS_IMR_RX_IDLE to the interrupt mask and
add a command in sis_intr() to restart the receiver when this happens.

While at it, make the test of status bits more efficient.
2001-11-27 16:29:11 +00:00
Ruslan Ermilov
3e0cee70d7 Don't automatically unbind/deallocate memory when releasing.
This fixes the VT switching problem with the i810 X driver.

Explained by:	David Dawes <dawes@XFree86.Org>
Reviewed by:	dfr
2001-11-27 14:12:21 +00:00
Mitsuru IWASAKI
0c66d318dd Add suspend/resume code mostly merged from fxp driver. 2001-11-23 14:27:33 +00:00
John Baldwin
99efe4f0f8 Remove ifnet.if_mpsafe for now. If this is needed, it won't be needed
until much later when the network stack locking is farther along.

Approved by:	jlemon
2001-11-14 18:36:37 +00:00
Jun Kuriyama
6183dc49fb Add support for Intel's i820/i840/i845/i850/i860 chipset.
Submitted by:	nork@cityfujisawa.ne.jp (Norikatsu Shigemura)
PR:		kern/31559, kern/31825
MFC after:	1 week
2001-11-08 16:03:23 +00:00
Peter Wemm
da73fe05e1 Add AMD766 OHCI USB controller. Remove unused VENDORID lists. 2001-11-06 23:44:03 +00:00
Poul-Henning Kamp
45f40c7569 This file was part of something grander, which doesn't seem to be
around anymore.
2001-11-06 07:26:21 +00:00
Poul-Henning Kamp
4bdc9660e5 Remove unneeded call to cdevsw_add() 2001-11-04 08:44:49 +00:00
Peter Wemm
84e5eebd09 No FreeBSD/vax here either. 2001-11-03 08:32:28 +00:00
Peter Wemm
d5f6245f80 Add ICH3 (82801CA/CAM) and 460GX 2001-11-03 05:03:00 +00:00
Luigi Rizzo
935fe01014 Enable round-robin arbitration between transmit and receive unit
in the 21143, instead of giving priority to the receive unit.
This gives a 10-15% performance improvement in the forwarding rate
under heavy load.

Reviewed-by: Bill Paul
2001-10-27 00:59:17 +00:00
Luigi Rizzo
617b3dd758 Defs for three (unused so far) bits in PCI command/status register
were off by one bit.
2001-10-25 17:43:26 +00:00
Alan Cox
eab754b91d Implement TCP/IP checksum off-loading on send for the 3c905B and later
generation cards.
2001-10-22 06:45:42 +00:00
Matt Jacob
f2465b0df3 Remove this driver from FreeBSD.
Jonathon Lemon's driver (gx) is at least as fast and has more features
and is likely to be better supported.

It is also possible that Intel might support this chipset in FreeBSD
with their own driver. Somewhat secretive and furtive rumblings from
certain Yahoo employees have indicated that this might happen soon.

I'm a little unhappy at the lack of discussion on the net list about
this, or on developers, or on hackers, or the lack of mention on
audit. This then leaves me to try and figure out the right thing
to do.

I've concluded that the right thing to do is to remove wx from FreeBSD,
as this is probably best for FreeBSD.
2001-10-20 18:48:45 +00:00
Matt Jacob
819e7ffdf3 Whack on this soon to be deprecated driver.
What the heck, the OpenBSD version will benefit.

1. Add wx_txint_delay as a tunable (defaults to 5000 now, or ~5ms) and switch
to using delayed TXDW interrupts. Since the chip continues to reload the
TIDV with this value for each descriptor written back, this allows continued
deferral of the actual interrupt until the last packet completes (assuming
that 5ms between multiple packets transmitting is reasonable).

2. Add two other SYSCTL entities:

hw.wx.dump_stats
hw.wx.clear_stats

to be used, hackey hackey, to get the watchdog routine to dump/clear
the current softc statistics.

Usage would be:

	sysctl -w hw.wx.dump_stats=UNIT

to cause the current stats to be dumped for UNIT.

3. Attempt to clean up wx_detach routine so we don't panic. Well, things
still panic, but given that the code is just like other NIC drivers,
I suspect it's actually something elsewhere, like e1000phy, that's actually
blowing up.

4. Skip the entire test for runt packets- after doing somet thinking
and experimenting, I believe that the chip only doesn't like it if
the whole frame to xmit is < 16 bytes- each TFD can be some fragment
of that. This should improve performance a chunk because of all of the
(14 byte ETHERHEADER + DATA) mbuf chains.

5. Keep track of total frame length. Try not to xmit an odd byte frame-
this is supposed to get around some dumb Cisco switch problems.

6. On the last packet, also set Interrupt Delay && Report Packet Sent
(see #1 above)

7. Attempt to do xmit garbage collection *first* in order to avoid setting
IFF_OACTIVE if at all possible.

MFC after:	1 week
2001-10-15 06:59:41 +00:00
Matt Jacob
572ce00d3e Note that this driver is soon to be deprecated and removed from FreeBSD. 2001-10-09 00:14:41 +00:00
Matt Jacob
77049e810b Let's not kid ourselves- we don't *really* support jumbframes yet.
We only support the size of frame we are currently allocating, which
is MCLBYTES - sizeof (struct ether_header) usable, so don't set an
MTU that would go over this.
2001-10-02 22:36:49 +00:00
Matt Jacob
1c3903d23f Various fixes and improvements- some from the folks at Sitara Networks (thx) 2001-10-02 22:21:21 +00:00
Matt Jacob
4a5470eebd Remove all OpenBSD/NetBSD code. It was the right place to start from, but
it now really gets in the way.

This allows us to fix several problems- not least of which was problems
of ordering about when you'd have a device softc for an miibus child
available or not. Move some steps of things around.

Put the ifnet/arpcom structure at the head of the softc (PR 29249).

Don't do tx gc in the interrupt service routine- that seems to make
things a bit more efficient.

Enable jumbo support by default- but this version of 'jumbo' is broken
because it really is just using multiple tfd/rfd's to match a packet,
which will never be > CLSIZE anyway.

This should begin the first steps toward cleaning this driver up.

PR:		29249
MFC after:	1 week
2001-10-02 00:13:44 +00:00
Jonathan Lemon
cd62a9cb38 Do not call mii_pollstat() from within device tick routines; the status
information is updated by mii_tick().

Pointed out by: wpaul (a while back)
2001-09-29 19:28:31 +00:00
Luigi Rizzo
88f6feee74 Fix typo in a comment.
MFC-after: 3 days
2001-09-27 12:01:57 +00:00
Alan Cox
391fa6d3d4 Implement TCP/IP checksum off-loading on receive. Announce
rxcsum capabilities.

Reviewed by:	wpaul
2001-09-23 05:13:12 +00:00
Coleman Kane
57110f7604 Add probe line for the AMD 761 northbridge chip. At least it detects now,
seems to set up memory spaces correctly. This change actually did work for
me using -STABLE, XFree86 4.0.3 ~ some snapshot of DRI awhile back. I sent
mail to dfr to no avail, perhaps someone else would like to test it with
DRI.

Anyway, people have been nagging me about this change for awhile, so here's
the commit.
2001-09-20 05:13:12 +00:00
Jonathan Lemon
53de2fb09f Have the driver advertise that it is capable of hardware checksums, and
allow the user to control the setting.  (checksums are enabled by default)
2001-09-18 18:40:22 +00:00
Murray Stokely
c896039b9b SMBus support for the AMD 756 power management unit. See smbus(4),
amdpm(4) and smb(4).

This device can be used with userland programs such as sysutils/lmmon
to retrieve sensor information from the motherboard.

PR:		   kern/23989
Obtained from:	   Matthew C. Forman <mcf@dmu.ac.uk>
Based on:	   alpm(4)
2001-09-16 22:35:07 +00:00
Julian Elischer
b40ce4165d KSE Milestone 2
Note ALL MODULES MUST BE RECOMPILED
make the kernel aware that there are smaller units of scheduling than the
process. (but only allow one thread per process at this time).
This is functionally equivalent to teh previousl -current except
that there is a thread associated with each process.

Sorry john! (your next MFC will be a doosie!)

Reviewed by: peter@freebsd.org, dillon@freebsd.org

X-MFC after:    ha ha ha ha
2001-09-12 08:38:13 +00:00
Brooks Davis
5c88c82cf3 Update tx(4) to always enable vlan(4) support.
Approved by:		semenu
2001-09-05 23:04:53 +00:00
Brooks Davis
9d4fe4b2b0 Make vlan(4) loadable, unloadable, and clonable. As a side effect,
interfaces must now always enable VLAN support.

Reviewed by:	jlemon
MFC after:	3 weeks
2001-09-05 21:10:28 +00:00
Bill Paul
1af8bec768 Add support for Conexant LANfinity miniPCI controllers. People who have
laptops with this chip should test this and report back as I don't have
access to this hardware myself. People with -stable systems should try
the patch at:

	http://www.freebsd.org/~wpaul/conexant.patch.gz

Submitted by:	Phil Kernick <Phil@Kernick.org>
2001-09-04 17:10:11 +00:00
Søren Schmidt
38090f05c2 Remove long overdue obsolete file ide_pcireg.h 2001-09-04 15:52:00 +00:00
Jonathan Lemon
cf9d4cbfc6 The fxp driver has lived in dev/fxp for some time, remove old files. 2001-08-31 02:21:03 +00:00
Doug Rabson
7e59bf6765 Recognise VIA Apollo KT133A bridge.
PR:	30061
Submitted by:	John Merryweather Cooper <jmcoopr@webmail.bmi.net>
MFC after:	1 week
2001-08-30 14:17:48 +00:00
Bill Paul
d93d282620 Add support for the 3c656B cardbus adapter. This is one half of a
dual function card. It needs pretty much the same flags as the 656C,
except that it seems to need both the INVERT_MII_PWR and INVERT_LED_PWR
flags set. Tested with cardbus in -current as of today.

Also added support for the 3c656, which looks to be the same as
the 656B, except it doesn't need the EEPROM_8BIT flag. I think. This
one is untested, but the added support should not break any of the
other cards.
2001-08-28 00:40:18 +00:00
Matt Jacob
38db9454de John Polstra
bogus additional write to WXREG_IMASK that enabled *all* interrupt causes
while I was trying to disable the chip. Oops.
2001-08-24 23:08:13 +00:00
Bill Paul
645ed1a78b Fix a bug in the ste_setmulti() routine. The NIC has 4 16-bit multicast
hash registers, not 2 32-bit ones. This would prevent the multicasr filter
from being programmed correctly in some cases.
2001-08-23 18:22:55 +00:00
Bill Paul
d3ab0d02cf After one more day of testing, make what I hope are the final tweaks to
prevent/workaround TX lockups in this driver. The secret seems to be to
not let the TX DMA queue become too full. If we have too many packets
in the queue, we should wait for them to drain a bit before trying to
queue more. This should prevent the lockup from occurring, and if it
does occur, there is special code in sf_start() to kick the NIC in the
head and get it going again.

Special thanks to Glen Neff for helping me test this fix.
2001-08-16 20:15:16 +00:00
Bill Paul
fa97ab323c Still more changes to try to prevent TX lockups. Will wait for one more
night of testing before merging to -stable.

Also added to code to detect TX underruns and automatically increase the
TX threshold to avoid them. Carefully placed diagnostig printf() about
this under #ifdef DIAGNOSTIC to avoid getting any panicky e-mails from
confused users, like I always do with the xl and dc drivers.
2001-08-16 00:32:20 +00:00
Bill Paul
0a4b345e9f Tweak the interrupt handler so that we call the txeof handler more often,
to hopefully prevent the TX DMA queue from filling up and never getting
flushed.
2001-08-15 17:46:57 +00:00
Bill Paul
0219a42155 Convert the if_sis and if_rl drivers to use the bus_dma API instead of
calling vtophys() and contigmalloc()/contigfree() directly. Hopefully,
I have shaken out all of the problems with busdma on the alpha now.
(Everything seems to work as expected.)

Also, change the max RX DMA limit to 1024 bytes instead of "unlimited,"
as the latter seems not to work correctly on the alpha that I tested.
(At 100Mbps, all attempts to receive frames yield RX errors.)
2001-08-15 17:38:43 +00:00
Semen Ustimenko
395a636fb2 Fix an bug in FreeBSD attach routine - attaching MII interfaces before doing
common_attach is wrong as common attach initialize some fileds used by
mediainit routine. This was hard to notify because loading driver as kld
lead to mediainit routine being called after common_attach, though probe_phy
is called before.

MFC after:	1 week
2001-08-13 18:37:31 +00:00
Semen Ustimenko
2c9067b16f Add support for 802.1Q VLAN and oversized ethernet frames.
PR:		kern/29235
Submitted by:	Peter Jeremy <peter.jeremy@alcatel.com.au>
Reviewed by:	Yar Tikhiy <yar@FreeBSD.org>
MFC after:	1 week
2001-08-13 18:32:39 +00:00
Bill Paul
0a75b55602 Pacify users who get all bent out of shape when they see the "xl%d: command
never completed" message. The RX reset takes longer complete than it
used to, a lot longer in fact than xl_wait() is prepared to wait.
When we do the RX reset in xl_reset(), this cases xl_wait() to time out
and whine. We wait a little extra time now after the RX reset, which
should silence the warning.

Thanks to obrien for finally getting me a box with a NIC that
causes this problem for me to tinker with.
2001-07-27 20:55:45 +00:00
Brooks Davis
bbce7eba7f IFT_8021_VLAN -> IFT_L2VLAN per if_vlan_var.h rev 1.9. With this change
LINT compiles, but doesn't link.
2001-07-25 00:19:59 +00:00
Kris Kennaway
56bded8a29 s/adress/address/
Inspired by:    OpenBSD
MFC After:      1 week
2001-07-23 12:05:27 +00:00
Bill Paul
e7be9f9a1a Deal with the condition where we lose link in the middle of transmitting
a bunch of frames. In this case, the dc_link flag is cleared, and dc_start()
stops draining the if_snd send queue, which results in lots of 'no buffers
available' errors being reported to applications. The whole idea behind
not draining the send queue until the link comes up was to avoid having
the gratuitous ARP being lost while we're waiting for autoneg to complete
after the interface is first brought up. As an optimization, change the
test in dc_start() so that we only bail if dc_link is not set _and_ there
are less than 10 packets in the send queue. If the queue has many frames
in it, we need to drain them. If the queue has a small number of frames
in it, we can hold off on sending them until the link comes up.

MFC after: 1 week
2001-07-12 22:51:59 +00:00
Bill Paul
75ff968cd5 Apply patch supplied by Jonathan Chen: use the correct arguments to
pci_enable_io(). We need to use SYS_RES_IOPORT/SYS_RES_MEMORY instead
of PCIM_CMD_PORTEN/PCIM_CMD_MEMEN.
2001-07-09 17:58:42 +00:00
John Baldwin
52b3919d31 Make these compile again by adding proc.h include for GIANT_REQUIRED
that is in included vm headers.
2001-07-05 21:28:47 +00:00