From: David Gibson <david@gibson.dropbear.id.au>
To: Paul Mackerras <paulus@ozlabs.org>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>,
linuxppc-dev@lists.ozlabs.org,
Alex Williamson <alex.williamson@redhat.com>,
kvm-ppc@vger.kernel.org, kvm@vger.kernel.org
Subject: Re: [PATCH kernel 3/9] KVM: PPC: Use preregistered memory API to access TCE list
Date: Thu, 10 Mar 2016 23:42:06 +0000 [thread overview]
Message-ID: <20160310234206.GC22546@voom.fritz.box> (raw)
In-Reply-To: <20160310083305.GB1230@fergus.ozlabs.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 1689 bytes --]
On Thu, Mar 10, 2016 at 07:33:05PM +1100, Paul Mackerras wrote:
> On Mon, Mar 07, 2016 at 05:00:14PM +1100, David Gibson wrote:
> > On Mon, Mar 07, 2016 at 02:41:11PM +1100, Alexey Kardashevskiy wrote:
> > > VFIO on sPAPR already implements guest memory pre-registration
> > > when the entire guest RAM gets pinned. This can be used to translate
> > > the physical address of a guest page containing the TCE list
> > > from H_PUT_TCE_INDIRECT.
> > >
> > > This makes use of the pre-registrered memory API to access TCE list
> > > pages in order to avoid unnecessary locking on the KVM memory
> > > reverse map.
> > >
> > > Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> >
> > Ok.. so, what's the benefit of not having to lock the rmap?
>
> It's not primarily about locking or not locking the rmap. The point
> is that when memory is pre-registered, we know that all of guest
> memory is pinned and we have a flat array mapping GPA to HPA. It's
> simpler and quicker to index into that array (even with looking up the
> kernel page tables in vmalloc_to_phys) than it is to find the memslot,
> lock the rmap entry, look up the user page tables, and unlock the rmap
> entry. We were only locking the rmap entry to stop the page being
> unmapped and reallocated to something else, but if memory is
> pre-registered, it's all pinned, so it can't be reallocated.
Ok, that makes sense.
Alexey, can you fold some of that rationale into the commit message?
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
WARNING: multiple messages have this Message-ID (diff)
From: David Gibson <david@gibson.dropbear.id.au>
To: Paul Mackerras <paulus@ozlabs.org>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>,
linuxppc-dev@lists.ozlabs.org,
Alex Williamson <alex.williamson@redhat.com>,
kvm-ppc@vger.kernel.org, kvm@vger.kernel.org
Subject: Re: [PATCH kernel 3/9] KVM: PPC: Use preregistered memory API to access TCE list
Date: Fri, 11 Mar 2016 10:42:06 +1100 [thread overview]
Message-ID: <20160310234206.GC22546@voom.fritz.box> (raw)
In-Reply-To: <20160310083305.GB1230@fergus.ozlabs.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 1689 bytes --]
On Thu, Mar 10, 2016 at 07:33:05PM +1100, Paul Mackerras wrote:
> On Mon, Mar 07, 2016 at 05:00:14PM +1100, David Gibson wrote:
> > On Mon, Mar 07, 2016 at 02:41:11PM +1100, Alexey Kardashevskiy wrote:
> > > VFIO on sPAPR already implements guest memory pre-registration
> > > when the entire guest RAM gets pinned. This can be used to translate
> > > the physical address of a guest page containing the TCE list
> > > from H_PUT_TCE_INDIRECT.
> > >
> > > This makes use of the pre-registrered memory API to access TCE list
> > > pages in order to avoid unnecessary locking on the KVM memory
> > > reverse map.
> > >
> > > Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> >
> > Ok.. so, what's the benefit of not having to lock the rmap?
>
> It's not primarily about locking or not locking the rmap. The point
> is that when memory is pre-registered, we know that all of guest
> memory is pinned and we have a flat array mapping GPA to HPA. It's
> simpler and quicker to index into that array (even with looking up the
> kernel page tables in vmalloc_to_phys) than it is to find the memslot,
> lock the rmap entry, look up the user page tables, and unlock the rmap
> entry. We were only locking the rmap entry to stop the page being
> unmapped and reallocated to something else, but if memory is
> pre-registered, it's all pinned, so it can't be reallocated.
Ok, that makes sense.
Alexey, can you fold some of that rationale into the commit message?
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
next prev parent reply other threads:[~2016-03-10 23:42 UTC|newest]
Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-03-07 3:41 [PATCH kernel 0/9] KVM, PPC, VFIO: Enable in-kernel acceleration Alexey Kardashevskiy
2016-03-07 3:41 ` Alexey Kardashevskiy
2016-03-07 3:41 ` [PATCH kernel 1/9] KVM: PPC: Reserve KVM_CAP_SPAPR_TCE_VFIO capability number Alexey Kardashevskiy
2016-03-07 3:41 ` Alexey Kardashevskiy
2016-03-07 4:58 ` David Gibson
2016-03-07 4:58 ` David Gibson
2016-03-07 3:41 ` [PATCH kernel 2/9] powerpc/mmu: Add real mode support for IOMMU preregistered memory Alexey Kardashevskiy
2016-03-07 3:41 ` Alexey Kardashevskiy
2016-03-07 5:30 ` David Gibson
2016-03-07 5:30 ` David Gibson
2016-03-07 3:41 ` [PATCH kernel 3/9] KVM: PPC: Use preregistered memory API to access TCE list Alexey Kardashevskiy
2016-03-07 3:41 ` Alexey Kardashevskiy
2016-03-07 6:00 ` David Gibson
2016-03-07 6:00 ` David Gibson
2016-03-08 5:47 ` Alexey Kardashevskiy
2016-03-08 5:47 ` Alexey Kardashevskiy
2016-03-08 6:30 ` David Gibson
2016-03-08 6:30 ` David Gibson
2016-03-09 8:55 ` Alexey Kardashevskiy
2016-03-09 8:55 ` Alexey Kardashevskiy
2016-03-09 23:46 ` David Gibson
2016-03-09 23:46 ` David Gibson
2016-03-10 8:33 ` Paul Mackerras
2016-03-10 8:33 ` Paul Mackerras
2016-03-10 23:42 ` David Gibson [this message]
2016-03-10 23:42 ` David Gibson
2016-03-07 3:41 ` [PATCH kernel 4/9] powerpc/powernv/iommu: Add real mode version of xchg() Alexey Kardashevskiy
2016-03-07 3:41 ` Alexey Kardashevskiy
2016-03-07 6:05 ` David Gibson
2016-03-07 6:05 ` David Gibson
2016-03-07 7:32 ` Alexey Kardashevskiy
2016-03-07 7:32 ` Alexey Kardashevskiy
2016-03-08 4:50 ` David Gibson
2016-03-08 4:50 ` David Gibson
2016-03-10 8:43 ` Paul Mackerras
2016-03-10 8:43 ` Paul Mackerras
2016-03-10 8:46 ` Paul Mackerras
2016-03-10 8:46 ` Paul Mackerras
2016-03-07 3:41 ` [PATCH kernel 5/9] KVM: PPC: Enable IOMMU_API for KVM_BOOK3S_64 permanently Alexey Kardashevskiy
2016-03-07 3:41 ` Alexey Kardashevskiy
2016-03-07 3:41 ` [PATCH kernel 6/9] KVM: PPC: Associate IOMMU group with guest view of TCE table Alexey Kardashevskiy
2016-03-07 3:41 ` Alexey Kardashevskiy
2016-03-07 6:25 ` David Gibson
2016-03-07 6:25 ` David Gibson
2016-03-07 9:38 ` Alexey Kardashevskiy
2016-03-07 9:38 ` Alexey Kardashevskiy
2016-03-08 4:55 ` David Gibson
2016-03-08 4:55 ` David Gibson
2016-03-07 3:41 ` [PATCH kernel 7/9] KVM: PPC: Create a virtual-mode only TCE table handlers Alexey Kardashevskiy
2016-03-07 3:41 ` Alexey Kardashevskiy
2016-03-08 6:32 ` David Gibson
2016-03-08 6:32 ` David Gibson
2016-03-07 3:41 ` [PATCH kernel 8/9] KVM: PPC: Add in-kernel handling for VFIO Alexey Kardashevskiy
2016-03-07 3:41 ` Alexey Kardashevskiy
2016-03-08 11:08 ` David Gibson
2016-03-08 11:08 ` David Gibson
2016-03-09 8:46 ` Alexey Kardashevskiy
2016-03-09 8:46 ` Alexey Kardashevskiy
2016-03-10 5:18 ` David Gibson
2016-03-10 5:18 ` David Gibson
2016-03-11 2:15 ` Alexey Kardashevskiy
2016-03-11 2:15 ` Alexey Kardashevskiy
2016-03-15 6:00 ` David Gibson
2016-03-15 6:00 ` David Gibson
2016-03-07 3:41 ` [PATCH kernel 9/9] KVM: PPC: VFIO device: support SPAPR TCE Alexey Kardashevskiy
2016-03-07 3:41 ` Alexey Kardashevskiy
2016-03-09 5:45 ` David Gibson
2016-03-09 5:45 ` David Gibson
2016-03-09 9:20 ` Alexey Kardashevskiy
2016-03-09 9:20 ` Alexey Kardashevskiy
2016-03-10 5:21 ` David Gibson
2016-03-10 5:21 ` David Gibson
2016-03-10 23:09 ` Alexey Kardashevskiy
2016-03-10 23:09 ` Alexey Kardashevskiy
2016-03-15 6:04 ` David Gibson
2016-03-15 6:04 ` David Gibson
[not found] ` <15389a41428.27cb.1ca38dd7e845b990cd13d431eb58563d@ozlabs.ru>
[not found] ` <20160321051932.GJ23586@voom.redhat.com>
2016-03-22 0:34 ` Alexey Kardashevskiy
2016-03-22 0:34 ` Alexey Kardashevskiy
2016-03-23 3:03 ` David Gibson
2016-03-23 3:03 ` David Gibson
2016-06-09 6:47 ` Alexey Kardashevskiy
2016-06-09 6:47 ` Alexey Kardashevskiy
2016-06-10 6:50 ` David Gibson
2016-06-10 6:50 ` David Gibson
2016-06-14 3:30 ` Alexey Kardashevskiy
2016-06-14 3:30 ` Alexey Kardashevskiy
2016-06-15 4:43 ` David Gibson
2016-06-15 4:43 ` David Gibson
2016-04-08 9:13 ` Alexey Kardashevskiy
2016-04-08 9:13 ` Alexey Kardashevskiy
2016-04-11 3:36 ` David Gibson
2016-04-11 3:36 ` David Gibson
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=20160310234206.GC22546@voom.fritz.box \
--to=david@gibson.dropbear.id.au \
--cc=aik@ozlabs.ru \
--cc=alex.williamson@redhat.com \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=paulus@ozlabs.org \
/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.