Commit Graph

14 Commits

Author SHA1 Message Date
David S. Miller
49d85c502e [NET]: Fix interrupt semaphore corruption in Intel drivers.
Several of the Intel ethernet drivers keep an atomic counter used to
manage when to actually hit the hardware with a disable or an enable.

The way the net_rx_work() breakout logic works during a pending
napi_disable() is that it simply unschedules the poll even if it
still has work.

This can potentially leave interrupts disabled, but that is OK
because all of the drivers are about to disable interrupts
anyways in all such code paths that do a napi_disable().

Unfortunately, this trips up the semaphore used here in the Intel
drivers.  If you hit this case, when you try to bring the interface
back up it won't enable interrupts.  A reload of the driver module
fixes it of course.

So what we do is make sure all the sequences now go:

	napi_disable();
	atomic_set(&adapter->irq_sem, 0);
	*_irq_disable();

which makes sure the counter is always in the correct state.

Reported by Robert Olsson.

Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-20 20:31:39 -08:00
David S. Miller
d2c7ddd626 [NET]: Fix TX timeout regression in Intel drivers.
This fixes a regression added by changeset
53e52c729c ("[NET]: Make ->poll()
breakout consistent in Intel ethernet drivers.")

As pointed out by Jesse Brandeburg, for three of the drivers edited
above there is breakout logic in the *_clean_tx_irq() code to prevent
running TX reclaim forever.  If this occurs, we have to elide NAPI
poll completion or else those TX events will never be serviced.

Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
2008-01-17 01:49:29 -08:00
David S. Miller
53e52c729c [NET]: Make ->poll() breakout consistent in Intel ethernet drivers.
This makes the ->poll() routines of the E100, E1000, E1000E, IXGB, and
IXGBE drivers complete ->poll() consistently.

Now they will all break out when the amount of RX work done is less
than 'budget'.

At a later time, we may want put back code to include the TX work as
well (as at least one other NAPI driver does, but by in large NAPI
drivers do not do this).  But if so, it should be done consistently
across the board to all of these drivers.

Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Auke Kok <auke-jan.h.kok@intel.com>
2008-01-08 23:30:14 -08:00
David S. Miller
4ec2411980 [NET]: Do not check netif_running() and carrier state in ->poll()
Drivers do this to try to break out of the ->poll()'ing loop
when the device is being brought administratively down.

Now that we have a napi_disable() "pending" state we are going
to solve that problem generically.

Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-08 23:30:09 -08:00
Auke Kok
f920c186be e1000e: Remove legacy jumbo frame receive code
The legacy jumbo frame receive code is no longer needed since all
hardware can do packet split and we're no longer offering a bypass
kernel config option to disable packet split. Remove the unused code.

Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-10-29 05:47:08 -04:00
Auke Kok
140a748028 e1000e: Re-enable SECRC - crc stripping
This workaround code performed software stripping instead of the
hardware which can do it much faster. None of the e1000e target
hardware has issues with this feature and should work fine. This
gives us some performance back on receive, and removes some
kludging stripping the 4 bytes.

Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-10-29 05:47:08 -04:00
Auke Kok
df762464ad e1000e: Fix PBA calculation for jumbo frame packets
Upon inspection the rx FIFO size calculation code was found to have
2 significant flaws: A superfluous minus sign resulting in the
wrong size to be used for jumbo frames on 82573 and ich9, as well
as that this code rewrote the read-only adapter->pba variable
resulting in different values at each run.

Without this patch jumbo's will work but performance will be
awkward since the TX size is not adequate for two whole frames.

Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-10-29 05:47:08 -04:00
Auke Kok
47f44e40a3 e1000e: Fix jumbo frame receive code.
Fix allocation and freeing of jumbo frames where several bugs
were recently introduced by cleanups after we forked this code
from e1000. This moves ps_pages to buffer_info where it really
belongs and makes it a dynamically allocated array. The penalty
is not that high since it's allocated outside of the buffer_info
struct anyway.

Without this patch all jumbo frames are completely broken and the
driver panics.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-10-29 05:47:08 -04:00
Auke Kok
309af40b5f e1000e: restore flow control settings properly
After a cable unplug the forced flow control settings were lost
accidentally and the flow control settings fell back to the default
EEPROM determined values. This breaks for people who want to
run without fc enabled - after a cable reset the driver would
refuse to run with fc disabled.

Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-10-10 16:55:25 -07:00
Auke Kok
4e6c709c5a e1000e: Simple optimizations in e1000_xmit_frame
After an e1000 patch from Krishna Kumar <krkumar2@in.ibm.com>.

Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-10-10 16:55:25 -07:00
Auke Kok
589c085f27 e1000e: fix debugging printout code
A small bug crawled in the -DDEBUG enabled code. Fix this to
properly call the backreference device name.

Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-10-10 16:54:42 -07:00
Krishna Kumar
7b5dfe1aa9 e1000e: Do not allow requeue of freed skb
Returning BUSY will make qdisc_restart enqueue the skb which was already
freed. The bad skb was correctly freed and we should return NETDEV_TX_OK.

First spotted by Jeff Garzik on 08/13/07.

Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-10-10 16:53:46 -07:00
Ralf Baechle
10d024c1b2 [NET]: Nuke SET_MODULE_OWNER macro.
It's been a useless no-op for long enough in 2.6 so I figured it's time to
remove it.  The number of people that could object because they're
maintaining unified 2.4 and 2.6 drivers is probably rather small.

[ Handled drivers added by netdev tree and some missed IRDA cases... -DaveM ]

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-10 16:51:13 -07:00
Auke Kok
bc7f75fa97 [E1000E]: New pci-express e1000 driver (currently for ICH9 devices only)
This driver implements support for the ICH9 on-board LAN ethernet
device. The device is similar to ICH8.

The driver encompasses code to support 82571/2/3, es2lan and ICH8
devices as well, but those device IDs are disabled and will be
"lifted" from the e1000 driver over one at a time once this driver
receives some more live time.

Changes to the last snapshot posted are exclusively in the internal
hardware API organization. Many thanks to Jeff Garzik for jumping in
and getting this organized with a keen eye on the future layout.

[ Integrated napi_struct patch from Auke as well... -DaveM ]

Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-10 16:50:40 -07:00