All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrea Arcangeli <andrea@qumranet.com>
To: Christoph Lameter <clameter@sgi.com>
Cc: Izik Eidus <izike@qumranet.com>, Robin Holt <holt@sgi.com>,
	Avi Kivity <avi@qumranet.com>, Nick Piggin <npiggin@suse.de>,
	kvm-devel@lists.sourceforge.net,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	steiner@sgi.com, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, daniel.blueman@quadrics.com,
	Hugh Dickins <hugh@veritas.com>
Subject: Re: [patch 0/4] [RFC] MMU Notifiers V1
Date: Mon, 28 Jan 2008 20:40:05 +0100	[thread overview]
Message-ID: <20080128194005.GE7233@v2.random> (raw)
In-Reply-To: <Pine.LNX.4.64.0801281103030.14003@schroedinger.engr.sgi.com>

On Mon, Jan 28, 2008 at 11:04:43AM -0800, Christoph Lameter wrote:
> On Mon, 28 Jan 2008, Andrea Arcangeli wrote:
> 
> > So I'd like to know what can we do to help to merge the 4 patches from
> > Christoph in mainline, I'd appreciate comments on them so we can help
> > to address any outstanding issue!
> 
> There are still some pending issues (RCU troubles). I will post V2 today.

With regard to the synchronize_rcu troubles they also be left to the
notifier-user to solve. Certainly having the synchronize_rcu like in
your last incremental patches in _release, will require less
complications (kvm pins the mm so I suppose we could batch the
call_rcu externally too). But _release is not a fast-path for KVM
usage so your V2 is sure ok (and simpler to deal with) too.

For registration synchronize_rcu is the only way, if the notifiers
have to fire synchronously before mmu_notifier_register returns but
that also can be left up to the caller if required (for example KVM
doesn't need that). Otherwise there could be two mmu_notifier_register
and mmu_notifier_register_rcu where the latter calls synchronize_rcu
before returning.

WARNING: multiple messages have this Message-ID (diff)
From: Andrea Arcangeli <andrea-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
To: Christoph Lameter <clameter-sJ/iWh9BUns@public.gmane.org>
Cc: Nick Piggin <npiggin-l3A5Bk7waGM@public.gmane.org>,
	Peter Zijlstra
	<a.p.zijlstra-/NLkJaSkS4VmR6Xm/wNWPw@public.gmane.org>,
	linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org,
	Benjamin Herrenschmidt
	<benh-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>,
	steiner-sJ/iWh9BUns@public.gmane.org,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>,
	kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org,
	daniel.blueman-xqY44rlHlBpWk0Htik3J/w@public.gmane.org,
	Robin Holt <holt-sJ/iWh9BUns@public.gmane.org>,
	Hugh Dickins <hugh-DTz5qymZ9yRBDgjK7y7TUQ@public.gmane.org>
Subject: Re: [patch 0/4] [RFC] MMU Notifiers V1
Date: Mon, 28 Jan 2008 20:40:05 +0100	[thread overview]
Message-ID: <20080128194005.GE7233@v2.random> (raw)
In-Reply-To: <Pine.LNX.4.64.0801281103030.14003-RYO/mD75kfhx2SFC9UQUAuF7EQX82lMiAL8bYrjMMd8@public.gmane.org>

On Mon, Jan 28, 2008 at 11:04:43AM -0800, Christoph Lameter wrote:
> On Mon, 28 Jan 2008, Andrea Arcangeli wrote:
> 
> > So I'd like to know what can we do to help to merge the 4 patches from
> > Christoph in mainline, I'd appreciate comments on them so we can help
> > to address any outstanding issue!
> 
> There are still some pending issues (RCU troubles). I will post V2 today.

With regard to the synchronize_rcu troubles they also be left to the
notifier-user to solve. Certainly having the synchronize_rcu like in
your last incremental patches in _release, will require less
complications (kvm pins the mm so I suppose we could batch the
call_rcu externally too). But _release is not a fast-path for KVM
usage so your V2 is sure ok (and simpler to deal with) too.

For registration synchronize_rcu is the only way, if the notifiers
have to fire synchronously before mmu_notifier_register returns but
that also can be left up to the caller if required (for example KVM
doesn't need that). Otherwise there could be two mmu_notifier_register
and mmu_notifier_register_rcu where the latter calls synchronize_rcu
before returning.

-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2008.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/

WARNING: multiple messages have this Message-ID (diff)
From: Andrea Arcangeli <andrea@qumranet.com>
To: Christoph Lameter <clameter@sgi.com>
Cc: Izik Eidus <izike@qumranet.com>, Robin Holt <holt@sgi.com>,
	Avi Kivity <avi@qumranet.com>, Nick Piggin <npiggin@suse.de>,
	kvm-devel@lists.sourceforge.net,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	steiner@sgi.com, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, daniel.blueman@quadrics.com,
	Hugh Dickins <hugh@veritas.com>
Subject: Re: [patch 0/4] [RFC] MMU Notifiers V1
Date: Mon, 28 Jan 2008 20:40:05 +0100	[thread overview]
Message-ID: <20080128194005.GE7233@v2.random> (raw)
In-Reply-To: <Pine.LNX.4.64.0801281103030.14003@schroedinger.engr.sgi.com>

On Mon, Jan 28, 2008 at 11:04:43AM -0800, Christoph Lameter wrote:
> On Mon, 28 Jan 2008, Andrea Arcangeli wrote:
> 
> > So I'd like to know what can we do to help to merge the 4 patches from
> > Christoph in mainline, I'd appreciate comments on them so we can help
> > to address any outstanding issue!
> 
> There are still some pending issues (RCU troubles). I will post V2 today.

With regard to the synchronize_rcu troubles they also be left to the
notifier-user to solve. Certainly having the synchronize_rcu like in
your last incremental patches in _release, will require less
complications (kvm pins the mm so I suppose we could batch the
call_rcu externally too). But _release is not a fast-path for KVM
usage so your V2 is sure ok (and simpler to deal with) too.

For registration synchronize_rcu is the only way, if the notifiers
have to fire synchronously before mmu_notifier_register returns but
that also can be left up to the caller if required (for example KVM
doesn't need that). Otherwise there could be two mmu_notifier_register
and mmu_notifier_register_rcu where the latter calls synchronize_rcu
before returning.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2008-01-28 19:40 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-01-25  5:56 [patch 0/4] [RFC] MMU Notifiers V1 Christoph Lameter
2008-01-25  5:56 ` Christoph Lameter
2008-01-25  5:56 ` [patch 1/4] mmu_notifier: Core code Christoph Lameter
2008-01-25  5:56   ` Christoph Lameter
2008-01-25 18:39   ` Robin Holt
2008-01-25 18:39     ` Robin Holt
2008-01-25 18:39     ` Robin Holt
2008-01-25 18:47     ` Christoph Lameter
2008-01-25 18:47       ` Christoph Lameter
2008-01-25 18:47       ` Christoph Lameter
2008-01-25 18:56       ` Robin Holt
2008-01-25 18:56         ` Robin Holt
2008-01-25 19:03         ` Christoph Lameter
2008-01-25 19:03           ` Christoph Lameter
2008-01-25 19:03           ` Christoph Lameter
2008-01-25 19:35           ` Robin Holt
2008-01-25 19:35             ` Robin Holt
2008-01-25 19:35             ` Robin Holt
2008-01-25 20:10             ` Christoph Lameter
2008-01-25 20:10               ` Christoph Lameter
2008-01-25 20:10               ` Christoph Lameter
2008-01-26 11:56               ` Robin Holt
2008-01-26 11:56                 ` Robin Holt
2008-01-26 11:56                 ` Robin Holt
2008-01-28 18:51                 ` Christoph Lameter
2008-01-28 18:51                   ` Christoph Lameter
2008-01-25 21:18             ` Christoph Lameter
2008-01-25 21:18               ` Christoph Lameter
2008-01-25 21:18               ` Christoph Lameter
2008-01-26 12:01               ` Robin Holt
2008-01-26 12:01                 ` Robin Holt
2008-01-26 12:01                 ` Robin Holt
2008-01-28 18:44                 ` Christoph Lameter
2008-01-28 18:44                   ` Christoph Lameter
2008-01-28 18:44                   ` Christoph Lameter
2008-01-25  5:56 ` [patch 2/4] mmu_notifier: Callbacks to invalidate address ranges Christoph Lameter
2008-01-25  5:56   ` Christoph Lameter
2008-01-25  5:56 ` [patch 3/4] mmu_notifier: invalidate_page callbacks for subsystems with rmap Christoph Lameter
2008-01-25  5:56   ` Christoph Lameter
2008-01-25  5:56 ` [patch 4/4] MMU notifier: invalidate_page callbacks using Linux rmaps Christoph Lameter
2008-01-25  5:56   ` Christoph Lameter
2008-01-25 11:42 ` [patch 0/4] [RFC] MMU Notifiers V1 Andrea Arcangeli
2008-01-25 11:42   ` Andrea Arcangeli
2008-01-25 12:43   ` Robin Holt
2008-01-25 12:43     ` Robin Holt
2008-01-25 12:43     ` Robin Holt
2008-01-25 18:31   ` Christoph Lameter
2008-01-25 18:31     ` Christoph Lameter
2008-01-25 18:31     ` Christoph Lameter
2008-01-25 21:18   ` Benjamin Herrenschmidt
2008-01-25 21:18     ` Benjamin Herrenschmidt
2008-01-25 21:18     ` Benjamin Herrenschmidt
2008-01-25 21:25     ` Christoph Lameter
2008-01-25 21:25       ` Christoph Lameter
2008-01-25 21:25       ` Christoph Lameter
2008-01-28 16:10   ` Izik Eidus
2008-01-28 16:10     ` Izik Eidus
2008-01-28 16:10     ` Izik Eidus
2008-01-28 17:25     ` Andrea Arcangeli
2008-01-28 17:25       ` Andrea Arcangeli
2008-01-28 19:04       ` Christoph Lameter
2008-01-28 19:04         ` Christoph Lameter
2008-01-28 19:40         ` Andrea Arcangeli [this message]
2008-01-28 19:40           ` Andrea Arcangeli
2008-01-28 19:40           ` Andrea Arcangeli
2008-01-28 20:16           ` Christoph Lameter
2008-01-28 20:16             ` Christoph Lameter
2008-01-28 20:16             ` Christoph Lameter

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:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

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

  git send-email \
    --in-reply-to=20080128194005.GE7233@v2.random \
    --to=andrea@qumranet.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=avi@qumranet.com \
    --cc=benh@kernel.crashing.org \
    --cc=clameter@sgi.com \
    --cc=daniel.blueman@quadrics.com \
    --cc=holt@sgi.com \
    --cc=hugh@veritas.com \
    --cc=izike@qumranet.com \
    --cc=kvm-devel@lists.sourceforge.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=npiggin@suse.de \
    --cc=steiner@sgi.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* 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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.