I don't see the advantages of considering two dparent pointers
distant less than 32bytes as the same randomizing value. IMHO this
will only decrease the effect of the randomization we get from the
parent address.
SLAB will L1_CACHE_ALIGN all dentry structures. Did you trace the
code in question to see what the input values to the hash actually
look like?
Later,
David S. Miller
davem@redhat.com
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/