archive mirror
 help / color / mirror / Atom feed
From: Hugh Dickins <>
To: Roland Dreier <>
	Andrea Arcangeli <>,,
Subject: Re: [PATCH/RFC G-U-P experts] IB/umem: Modernize our get_user_pages() parameters
Date: Wed, 8 Feb 2012 15:10:17 -0800 (PST)	[thread overview]
Message-ID: <alpine.LSU.2.00.1202081446110.1320@eggly.anvils> (raw)
In-Reply-To: <alpine.LSU.2.00.1202071225250.2024@eggly.anvils>

On Tue, 7 Feb 2012, Hugh Dickins wrote:
> On Mon, 6 Feb 2012, Roland Dreier wrote:
> > Which I think explains why the code is the way it is.  But clearly
> > we could do better if we had a better way of telling GUP our real
> > intentions -- ie the FOLL_READONLY_COW flag.
> You've persuaded me.  Yes, you have been using force because that was
> the only tool available at the time, to get close to the sensible
> behaviour you are now asking for.
> > 
> > > Can you, for example, enforce the permissions set up by the user?
> > > I mean, if they do the ibv_reg_mr() on a private readonly area,
> > > so __get_user_pages with the FOLL_APPROPRIATELY flag will fault
> > > in ZERO_PAGEs, can you enforce that RDMA will never spray data
> > > into those pages?
> > 
> > Yes, the access flags passed into ibv_reg_mr() are enforced by
> > the RDMA hardware, so if no write access is request, no write
> > access is possible.
> Okay, if you enforce the agreed permissions in hardware, that's fine.

A doubt assaulted me overnight: sorry, I'm back to not understanding.

What are these access flags passed into ibv_reg_mr() that are enforced?
What relation do they bear to what you will pass to __get_user_pages()?

You are asking for a FOLL_FOLLOW ("follow permissions of the vma") flag,
which automatically works for read-write access to a VM_READ|VM_WRITE vma,
but read-only access to a VM_READ-only vma, without you having to know
which permission applies to which range of memory in the area specified.

But you don't need that new flag to set up read-only access, and if you
use that new flag to set up read-write access to an area which happens to
contain VM_READ-only ranges, you have set it up to write into ZERO_PAGEs.


  reply	other threads:[~2012-02-08 23:10 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-01-26  5:59 [PATCH/RFC G-U-P experts] IB/umem: Modernize our get_user_pages() parameters Roland Dreier
2012-01-26 20:01 ` Hugh Dickins
2012-01-26 22:45   ` Roland Dreier
2012-01-27 17:28     ` Roland Dreier
2012-01-28  2:31       ` Hugh Dickins
2012-01-28 19:25         ` Jason Gunthorpe
2012-01-30 19:19           ` Roland Dreier
2012-01-28  2:19     ` Hugh Dickins
2012-01-30 19:16       ` Roland Dreier
2012-01-30 20:20         ` Andrea Arcangeli
2012-02-06 17:46           ` Roland Dreier
2012-01-30 20:34         ` Hugh Dickins
2012-02-06 17:39           ` Roland Dreier
2012-02-07 20:39             ` Hugh Dickins
2012-02-08 23:10               ` Hugh Dickins [this message]
2012-02-09 17:50                 ` Roland Dreier
2012-02-09 22:57                   ` Hugh Dickins

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=alpine.LSU.2.00.1202081446110.1320@eggly.anvils \ \ \ \ \ \ \

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).