hw ip4csum-tx bug on ex(4)? (Re: RTL8169 hw IP4CSUM_Tx workaround)

[Pavel Cahyna]

But there is a report that the follwoing 3C905C-TX on alpha
---
ex0 at pci0 dev 5 function 0: 3Com 3c905C-TX 10/100 Ethernet with mngmt (rev. 0x74)
---

Sorry, this report was wrong. I do actually see the problem with the above
configuration.

Pavel

--
Posted automagically by a mail2news gateway at muc.de e.V.
Please direct questions, flames, donations, etc. to news-***@muc.de

[der Mouse]

(I'm not sure if there is any protocol other than ICMP which could
generate 21 or 22 byte IP fragment packets)

A UDP packet ever so slightly larger than your MTU can do it, surely?

/~\ The ASCII der Mouse
\ / Ribbon Campaign
X Against HTML ***@rodents.montreal.qc.ca
/ \ Email! 7D C8 61 52 5D E7 2D 39 4E F1 31 3E E8 B3 27 4B

--
Posted automagically by a mail2news gateway at muc.de e.V.
Please direct questions, flames, donations, etc. to news-***@muc.de

[Izumi Tsutsui]

Hmm, is there any actual protocal which could create "slightly (i.e.
1 or 2) larger than our MTU"?

An NFS(-over-UDP) read of a suitably sized file can do it - as,
presumably, can an NFS write of a suitably sized chunk of data.

With a quick grance, NFS UDP packets seem rounded to multiples
of 4 bytes, but certain UDP protocols actually have odd bytes.

I'll commit the workaround for the ex(4) ip4csum-tx bug
if there is no objection in a few days.
---
Izumi Tsutsui

--
Posted automagically by a mail2news gateway at muc.de e.V.
Please direct questions, flames, donations, etc. to news-***@muc.de

[Aymeric Vincent]

Post by Izumi Tsutsui
With a quick grance, NFS UDP packets seem rounded to multiples
of 4 bytes, but certain UDP protocols actually have odd bytes.

Any RPC-based protocol should have packets whose size is a multiple
of 4 because they are XDR-encoded, and XDR specifies that every piece
of data is padded to 4 bytes.

Regards,
Aymeric

--
Posted automagically by a mail2news gateway at muc.de e.V.
Please direct questions, flames, donations, etc. to news-***@muc.de