From owner-freebsd-hackers Fri Jun 2 14: 4:56 2000 Delivered-To: freebsd-hackers@freebsd.org Received: from apollo.backplane.com (apollo.backplane.com [216.240.41.2]) by hub.freebsd.org (Postfix) with ESMTP id 5512137B76B for ; Fri, 2 Jun 2000 14:04:54 -0700 (PDT) (envelope-from dillon@apollo.backplane.com) Received: (from dillon@localhost) by apollo.backplane.com (8.9.3/8.9.1) id OAA49067; Fri, 2 Jun 2000 14:04:46 -0700 (PDT) (envelope-from dillon) Date: Fri, 2 Jun 2000 14:04:46 -0700 (PDT) From: Matthew Dillon Message-Id: <200006022104.OAA49067@apollo.backplane.com> To: Joy Ganguly Cc: freebsd-hackers Subject: Re: Freeing PQ_CACHE pages at interrupt time?? References: <3938141E.E2F1620F@falcon.niksun.com> Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG :hi all, : :Why cant pages in the PQ_CACHE queue be freed at interrupt time. as far :as i could see these pages are clean, though they are still associated :with the object. So what prevents us from dissociating them from the :object . we dont have to do any io and hence not block. : :well maybe i am missing something here. will somebody please explain it :to me?? : :thanx in advance : :joy The VM routines that manage pages associated with objects are not protected against interrupts, so interrupts aren't allowed to change page-object associations. Otherwise an interrupt at just the wrong time could corrupt the mainline kernel VM code. -Matt Matthew Dillon To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message