summaryrefslogtreecommitdiff
path: root/MAINTAINERS
diff options
context:
space:
mode:
authorVeaceslav Falico <vfalico@redhat.com>2012-10-22 04:43:25 +0000
committerDavid S. Miller <davem@davemloft.net>2012-10-23 02:31:15 -0400
commita35279f002c5843c2b2faaa4538963c8eb18446c (patch)
tree3b5c10e54ffcc850363f1018075668b455bc82e9 /MAINTAINERS
parent9c0314e111a540620441b27aeedb55f572f812f5 (diff)
pch_gbe: don't reset MAC_RX on FIFO overflow
Currently, when FIFO_ERR happens, we stop the dma, wait for it to become idle and then reset the whole MAC_RX logic (and after that we must re-set multicast addresses and also re-enable MAC_RX when we're finally ready to accept new packets). This leads to CRC errors on high number of incoming packets and is not needed according to the datasheet. This patch fixes it by the following steps: 1) remove this reset in pch_gbe_stop_receive(), which causes some functions to not be used anywhere 2) remove already unused functions pch_gbe_wait_clr_bit_irq() and pch_gbe_mac_reset_rx() to correctly build 3) move pch_gbe_enable_mac_rx() out of pch_gbe_start_receive() to pch_gbe_up() where it's only needed after we've removed the MAC_RX reset 4) rename pch_gbe_start/stop_receive() to pch_gbe_enable/disable_dma_rx() to more precisely reflect what the functions are now doing. After these changes we already don't see the CRC errors and gain some increase in RX processing speed. Signed-off-by: Veaceslav Falico <vfalico@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'MAINTAINERS')
0 files changed, 0 insertions, 0 deletions