We need more information on the test you run to get this hang. We have
not seen a hang similar to the one you describe. We have a p-series
machine in our lab and all we need is details on the test to run.
>From: Andrew Morton [mailto:akpm@xxxxxxxx]
>Sent: Thursday, May 26, 2005 12:38 AM
>To: Jian Jun He; Ronciak, John; Venkatesan, Ganesh; Brandeburg, Jesse
>Cc: ganesh.venkatesan@xxxxxxxxx; anton@xxxxxxxxx;
>herbert@xxxxxxxxxxxxxxxxxxx; jgarzik@xxxxxxxxx; linuxppc64-
>dev@xxxxxxxxxxxxxxxxxxxxxxxxxx; netdev@xxxxxxxxxxx; rende@xxxxxxxxxx;
>Subject: Re: Fw: [Bugme-new] [Bug 4628] New: Test server hang while
>rhr (network) test on RHEL4 with kernel 2.6.12-rc1-mm4
>Jian Jun He <hejianj@xxxxxxxxxx> wrote:
>> I download e100-3.4.8 and installed in the test machine (both client
>> server). But the server still hang while running rhr (network) test.
>e100 is one of those drivers which we'd rather like to have working
>Can we please confirm that a) this bug is not fixed in 2.6.12-rc5 and
>nobody has seen a patch which fixes it?
>Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> wrote:
>> Andrew Morton <akpm@xxxxxxxx> wrote:
>> > Might be a bug in the e100 driver, might not be.
>> > I assume this is the
>> > BUG_ON(skb->list != NULL);
>> It certainly is a bug in e100.
>> e100_tx_timeout -> e100_down -> e100_rx_clean_list
>> is racing against
>> e100_poll -> e100_rx_clean -> e100_rx_indicate
>> e100_rx_clean/e100_rx_indicate takes an skb off the RX ring and
>> while it's being processed e100_rx_clean_list comes along and
>> frees it.
>> >From a quick check similar problems may exist in other drivers that
>> have lockless ->poll() functions with RX rings.