Messages in this thread | | | Date | Mon, 24 May 2004 21:59:36 -0700 (PDT) | From | Linus Torvalds <> | Subject | Re: [PATCH] ppc64: Fix possible race with set_pte on a present PTE |
| |
On Tue, 25 May 2004, Andrea Arcangeli wrote: > > no, that's not what I remeber from alpha, alpha always sets the young > bit as soon as it sets the pte from non-null to something.
Yes.
However, whtn the page is _aged_ later, the young bits will be cleared.
And _that_ is when you will now start getting infinite page faults, because with your patch the young bits will never be set again on a normal read.
See what I'm saying?
Your patch literally leaves the page table alone on pure reads. Which is not acceptable, since the page being marked old was what caused the read-fault in the first place.
But yes, pages will be young by default, so you won't ever actually _see_ this behaviour until you start having memory pressure and VM reclaim starts trying to age the things.
Linus - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |