I was looking at mm/memory.c (2.4), and I've noticed that we don't call
pte_mkyoung() on newly created pte's for most of the fault paths.
break_cow(), for example:
establish_pte(vma, address, page_table, pte_mkwrite(pte_mkdirty(mk_pte(new_page, v ma->vm_page_prot))));
Is there any reason why we don't set the young bit on such places ?
I don't think that the window between the pte creation and the actual
access of the pte by the process is always big enough to avoid kswapd (or
other task trying to free memory) from ripping a created pte.
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to firstname.lastname@example.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/