From owner-freebsd-hackers Mon Jan 29 15:45:30 2001 Delivered-To: freebsd-hackers@freebsd.org Received: from earth.backplane.com (earth-nat-cw.backplane.com [208.161.114.67]) by hub.freebsd.org (Postfix) with ESMTP id 8C83137B698 for ; Mon, 29 Jan 2001 15:45:13 -0800 (PST) Received: (from dillon@localhost) by earth.backplane.com (8.11.1/8.9.3) id f0TNj6A79322; Mon, 29 Jan 2001 15:45:06 -0800 (PST) (envelope-from dillon) Date: Mon, 29 Jan 2001 15:45:06 -0800 (PST) From: Matt Dillon Message-Id: <200101292345.f0TNj6A79322@earth.backplane.com> To: Drew Eckhardt Cc: freebsd-hackers@FreeBSD.ORG Subject: Re: Suboptimal mmap of devices on i86 References: <200101292327.f0TNRbh22423@chopper.Poohsticks.ORG> Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG I like it, with some minor tweaks. I recommend: * name the new function vm_map_findspace2() (or something similarly short. * change all callers of vm_map_findspace() to instead call vm_map_findspace2() directly. * depreciate the original vm_map_findspace() entirely (get rid of it rather then supplying a compatibility function). The name change is to ensure that out of date loadable modules don't try to use the new function with the wrong arguments. Better to get a kld error then to crash. -Matt :On i86 boxes with 4M page capabilities, we want contiguous chunks :of physical address space for mmaped devices to use those larger pages :when possible. : :In practice, this doesn't happen in applications linked with shared :libraries when mmap() is used in the usual way with 0 as the address :argument and no MAP_FIXED flag. :... To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message