Date: Tue, 15 Dec 1998 10:29:36 -0500 (EST) From: "Ron G. Minnich" <rminnich@Sarnoff.COM> To: zhihuizhang <bf20761@binghamton.edu> Cc: hackers <freebsd-hackers@FreeBSD.ORG> Subject: Re: Page fault on a read-only apge Message-ID: <Pine.SUN.3.91.981215095959.22446B-100000@terra> In-Reply-To: <Pine.SOL.L3.93.981214214439.3658A-100000@bingsun1>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, 14 Dec 1998, zhihuizhang wrote: > Hi, I read in the mailing list archive something like "Also the VM tends > to not consult the underlying object for a number of cases, the worst > one being that if a write fault occurs on a read-only page, the VM will > tend to add write access without asking the VFS if that is ok". That sounds like something I might have written. It's certainly a problem I've had. A quick scan of current sources for 3.0 indicates it is still broken. The problem: you read-fault on a page and it is brought in by the vfs. But, the vfs wishes to know if you ever write fault on a page so it can support cache coherency (a la MNFS). On SunOS and Solaris, the vfs is called when a write-fault happens on a read-only page. On FreeBSD and Linux and AIX and Irix and ... it doesn't happen correctly. I'm not quite sure about NetBSD. ron To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.SUN.3.91.981215095959.22446B-100000>