Oh, like the kernel mis-sequencing a packet. I know it's doing it, but I
haven't had time to collect enough data to really prove it beyond the
hardware (Intel has been known to report data incorrectly, but ...)
I have data to indicate the kernel getting or assembling the headers and
data segments exactly TWO frames out of sequence. That has explained every
csum (TCP csum) failure I have captured. I suspect it may be a wild race
condition -- an interrupt at an odd time (those are kinda hard to localize.)
--Ricky