linux-stable.git/drivers/net/igb, branch linux-2.6.36.y

e100/e1000/igb/ixgb*: Add missing read memory barrier

2010-08-09T03:02:45+00:00

Based on patches from Sonny Rao and Milton Miller...

Combined the patches to fix up clean_tx_irq and clean_rx_irq.

The PowerPC architecture does not require loads to independent bytes
to be ordered without adding an explicit barrier.

In ixgbe_clean_rx_irq we load the status bit then load the packet data.
With packet split disabled if these loads go out of order we get a
stale packet, but we will notice the bad sequence numbers and drop it.

The problem occurs with packet split enabled where the TCP/IP header
and data are in different descriptors. If the reads go out of order
we may have data that doesn't match the TCP/IP header. Since we use
hardware checksumming this bad data is never verified and it makes it
all the way to the application.

This bug was found during stress testing and adding this barrier has
been shown to fix it.  The bug can manifest as a data integrity issue
(bad payload data) or as a BUG in skb_pull().

This was a nasty bug to hunt down, if people agree with the fix I think
it's a candidate for stable.

Previously Submitted to e1000-devel only for ixgbe

http://marc.info/?l=e1000-devel&m=126593062701537&w=3

We've now seen this problem hit with other device drivers (e1000e mostly)
So I'm resubmitting with fixes for other Intel Device Drivers with
similar issues.

CC: Milton Miller 
CC: Anton Blanchard 
CC: Sonny Rao 
CC: stable 
Signed-off-by: Jeff Kirsher 
Signed-off-by: David S. Miller

igb: Program MDICNFG register prior to PHY init

2010-08-03T23:40:53+00:00

This patch addresses an issue seen on 82580 in which the MDICNFG
register will be reset during a single function reset and as a
result we will be unable to communicate with the PHY.  To correct
the issue, added a call to reset_mdicnfg just prior to the first
access of the MDICNFG register in sgnii_uses_mdio.

Signed-off-by: Alexander Duyck 
Tested-by: Jeff Pieper 
Signed-off-by: Jeff Kirsher 
Signed-off-by: David S. Miller

igb: Use irq_synchronize per vector when using MSI-X

2010-08-03T04:20:22+00:00

Synchronize all IRQs when using MSI-X. Similar to ixgbe.
Issue was reported on e1000e, but the patch is also valid for igb.

CC: Jean Delvare 
Signed-off-by: Emil Tantilov 
Tested-by: Jeff Pieper 
Signed-off-by: Jeff Kirsher 
Signed-off-by: David S. Miller

Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

2010-07-28T04:01:35+00:00

Conflicts:
	drivers/net/bnx2x_main.c

Merge bnx2x bug fixes in by hand... :-/

Signed-off-by: David S. Miller

igb: restore EEPROM values of MDICNFG on reset with 82580

2010-07-27T01:42:53+00:00

On a reset the MDICNFG.Destination and MDICNFG.COM_MDIO
register fields are not restored to the EEPROM default.
This patch modifies the reset code to read the EEPROM
and restore the default values.

Signed-off-by: Nicholas Nunley 
Tested-by: Jeff Pieper 
Signed-off-by: Jeff Kirsher 
Signed-off-by: David S. Miller

igb: add support for SGMII-based MDIO PHYs

2010-07-27T01:42:53+00:00

This patch adds support for external MDIO PHYs, in addition to
the standard SFP support for SGMII PHYs over the I2C interface.

Signed-off-by: Nicholas Nunley 
Tested-by: Jeff Pieper 
Signed-off-by: Jeff Kirsher 
Signed-off-by: David S. Miller

ixgbe/igb: catch invalid VF settings

2010-07-21T20:48:55+00:00

Some ixgbe cards put an invalid VF device ID in the PCIe SR-IOV
capability.  The ixgbe driver is only valid for PFs or non SR-IOV
hardware.  It seems that the same problem could occur on igb hardware as
well, so if we discover we are trying to initialize a VF in ixbge_probe
or igb_probe, print an error and exit.

Based on a patch for ixgbe from Chris Wright .

Signed-off-by: Andy Gospodarek 
Cc: Chris Wright 
Acked-by: Chris Wright 
Acked-by: Greg Rose 
Signed-off-by: David S. Miller

igb: drop support for UDP hashing w/ RSS

2010-07-06T01:50:54+00:00

This change removes UDP from the supported protocols for RSS hashing.  The
reason for removing this protocol is because IP fragmentation was causing a
network flow to be broken into two streams, one for fragmented, and one for
non-fragmented and this in turn was causing out-of-order issues.

Signed-off-by: Alexander Duyck 
Signed-off-by: Jeff Kirsher 
Signed-off-by: David S. Miller

igb: Add comment

2010-07-02T05:45:57+00:00

Add explanatory comment to avoid confusion when a pointer is set
to the second word of an array instead of the customary cast of a
pointer to the beginning of the array.

Signed-off-by: Greg Rose 
Signed-off-by: Jeff Kirsher 
Signed-off-by: David S. Miller

igb: correct link test not being run when link is down