linux-toradex.git/drivers/net/benet, branch tegra

be2net: request native mode each time the card is reset

2011-07-22T04:32:54+00:00

Currently be3-native mode is requested only in probe(). It must be requested, each time the card is reset either after an EEH error or after
sleep/hibernation.
Also, the be_cmd_check_native_mode() is better named be_cmd_req_native_mode()

Signed-off-by: Sathya Perla 
Signed-off-by: David S. Miller

be2net: move to new vlan model

2011-07-13T05:10:01+00:00

Signed-off-by: Ajit Khaparde 
Signed-off-by: David S. Miller

be2net: account for skb allocation failures

2011-07-13T05:09:18+00:00

If we cannot allocate new skbs in RX completion handler, we should
increase netdevice rx_dropped counter, not spam console messages.

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

benet: Add missing comma between constant string array

2011-07-09T09:56:56+00:00

Multiple quoted strings are concatenated without comma separators.

Make the arrays const while there.

Signed-off-by: Joe Perches 
Signed-off-by: David S. Miller

be2net: clear intr bit in be_probe()

2011-07-01T05:32:50+00:00

It may be set in the card while the driver is probed by kdump kernel after a
crash.

Signed-off-by: Sathya Perla 
Signed-off-by: David S. Miller

be2net: create/destroy rx-queues on interface open/close

2011-07-01T05:32:50+00:00

On some skews, the BE card sends pause frames (and not drop pkts) if there are
no more posted buffers available for packet reception.  This behaviour has a
side effect: When an interface is disabled, buffers are no longer posted on the
corresponding RX rings. All broadcast and multicast traffic being received on
the port will quickly fill up the PMEM and cause pause push back. As the PMEM
is shared by both the ports, all traffic being received on the other (enabled)
port also gets stalled.
The fix is to destroy RX rings when the interface is disabled. If there is no
RX ring match in the RXF lookup, the packets are discarded and so don't hog the
PMEM.
The RXQ creation cmd must now use MCC instead of MBOX as they are are called
post MCC queue creation.

Signed-off-by: Sathya Perla 
Signed-off-by: David S. Miller

be2net: fix certain cmd failure logging

2011-07-01T05:32:50+00:00

Some (older)versions of cards/fw may not recognize certain cmds and
return illegal/unsupported errors. As long as the driver can handle
this gracefully there is no need to log an error msg.
Also finetuned 2 existing error log messages.

Signed-off-by: Sathya Perla 
Signed-off-by: David S. Miller

be2net: fix initialization of vlan_prio_bmap

2011-06-27T07:09:31+00:00

Initialization of this field to "all priorities" must be done before MCC queue
creation. As soon as the MCC queue is created, an event modifying this value
may be received.

Signed-off-by: Sathya Perla 
Signed-off-by: David S. Miller

be2net: get rid of multi_rxq module param

2011-06-27T07:09:31+00:00

Signed-off-by: Sathya Perla 
Signed-off-by: David S. Miller

be2net: fix netdev_stats_update

2011-06-27T07:09:31+00:00

Problem initially reproted and fixed by Eric Dumazet 

netdev_stats_update() resets netdev->stats and then accumulates stats from
various rings. This is wrong as stats readers can sometimes catch zero values.
Use temporary variables instead for accumulating per-ring values.

Signed-off-by: Sathya Perla 
Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller