From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Alexander Graf <agraf@suse.de>
Cc: linuxppc-dev@ozlabs.org, Paul Mackerras <paulus@samba.org>,
kvm@vger.kernel.org
Subject: Re: [PATCH 12/13] kvm/powerpc: Accelerate H_PUT_TCE by implementing it in real mode
Date: Tue, 17 May 2011 19:35:45 +1000 [thread overview]
Message-ID: <1305624945.2781.21.camel@pasglop> (raw)
In-Reply-To: <E483EC5C-5F4A-4783-88D2-1728BD902037@suse.de>
On Tue, 2011-05-17 at 11:31 +0200, Alexander Graf wrote:
> On 17.05.2011, at 11:11, Benjamin Herrenschmidt wrote:
>
> > On Tue, 2011-05-17 at 10:01 +0200, Alexander Graf wrote:
> >> I'm not sure I fully understand how this is supposed to work. If the
> >> tables are kept inside the kernel, how does userspace get to know
> >> where to DMA to?
> >
> > The guest gets a dma range from the device-tree which is the range of
> > device-side dma addresses it can use that correspond to the table.
> >
> > The guest kernel uses the normal linux iommu space allocator to allocate
> > space in that region and uses H_PUT_TCE to populate the corresponding
> > table entries.
> >
> > This is the same interface that is used for "real" iommu's with PCI
> > devices btw.
>
> I'm still slightly puzzled here :). IIUC the main point of an IOMMU is for the kernel
> to change where device accesses actually go to. So device DMAs address A, goes through
> the IOMMU, in reality accesses address B.
Right :-)
> Now, how do we tell the devices implemented in qemu that they're supposed to DMA to
> address B instead of A if the mapping table is kept in-kernel?
Oh, bcs qemu mmaps the table :-)
Cheers,
Ben.
WARNING: multiple messages have this Message-ID (diff)
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Alexander Graf <agraf@suse.de>
Cc: Paul Mackerras <paulus@samba.org>,
linuxppc-dev@ozlabs.org, kvm@vger.kernel.org
Subject: Re: [PATCH 12/13] kvm/powerpc: Accelerate H_PUT_TCE by implementing it in real mode
Date: Tue, 17 May 2011 19:35:45 +1000 [thread overview]
Message-ID: <1305624945.2781.21.camel@pasglop> (raw)
In-Reply-To: <E483EC5C-5F4A-4783-88D2-1728BD902037@suse.de>
On Tue, 2011-05-17 at 11:31 +0200, Alexander Graf wrote:
> On 17.05.2011, at 11:11, Benjamin Herrenschmidt wrote:
>
> > On Tue, 2011-05-17 at 10:01 +0200, Alexander Graf wrote:
> >> I'm not sure I fully understand how this is supposed to work. If the
> >> tables are kept inside the kernel, how does userspace get to know
> >> where to DMA to?
> >
> > The guest gets a dma range from the device-tree which is the range of
> > device-side dma addresses it can use that correspond to the table.
> >
> > The guest kernel uses the normal linux iommu space allocator to allocate
> > space in that region and uses H_PUT_TCE to populate the corresponding
> > table entries.
> >
> > This is the same interface that is used for "real" iommu's with PCI
> > devices btw.
>
> I'm still slightly puzzled here :). IIUC the main point of an IOMMU is for the kernel
> to change where device accesses actually go to. So device DMAs address A, goes through
> the IOMMU, in reality accesses address B.
Right :-)
> Now, how do we tell the devices implemented in qemu that they're supposed to DMA to
> address B instead of A if the mapping table is kept in-kernel?
Oh, bcs qemu mmaps the table :-)
Cheers,
Ben.
next prev parent reply other threads:[~2011-05-17 9:35 UTC|newest]
Thread overview: 103+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-05-11 10:34 [PATCH 0/13] Hypervisor-mode KVM on POWER7 Paul Mackerras
2011-05-11 10:36 ` [PATCH 01/13] kvm/powerpc: Move fields between struct kvm_vcpu_arch and kvmppc_vcpu_book3s Paul Mackerras
2011-05-11 10:38 ` [PATCH 02/13] kvm/powerpc: Fix kvmppc_core_pending_dec Paul Mackerras
2011-05-11 10:39 ` [PATCH 03/13] kvm/powerpc: Fix the build for 32-bit Book 3S (classic) processors Paul Mackerras
2011-05-12 9:33 ` Alexander Graf
2011-05-12 9:33 ` Alexander Graf
2011-05-12 11:15 ` Paul Mackerras
2011-05-12 11:15 ` Paul Mackerras
2011-05-12 11:16 ` Benjamin Herrenschmidt
2011-05-12 11:16 ` Benjamin Herrenschmidt
2011-05-12 11:57 ` Alexander Graf
2011-05-12 11:57 ` Alexander Graf
2011-05-11 10:40 ` [PATCH 04/13] kvm/powerpc: Split out code from book3s.c into book3s_pr.c Paul Mackerras
2011-05-11 10:41 ` [PATCH 05/13] powerpc, kvm: Rework KVM checks in first-level interrupt handlers Paul Mackerras
2011-05-11 10:42 ` [PATCH 06/13] kvm/powerpc: Deliver program interrupts right away instead of queueing them Paul Mackerras
2011-05-11 10:42 ` [PATCH 07/13] kvm/powerpc: Pass init/destroy vm and prepare/commit memory region ops down Paul Mackerras
2011-05-11 10:43 ` [PATCH 08/13] kvm/powerpc: Move guest enter/exit down into subarch-specific code Paul Mackerras
2011-05-17 18:05 ` Marcelo Tosatti
2011-05-17 18:05 ` Marcelo Tosatti
2011-05-17 18:10 ` Marcelo Tosatti
2011-05-17 18:10 ` Marcelo Tosatti
2011-05-11 10:44 ` [PATCH 09/13] powerpc: Set up LPCR for running guest partitions Paul Mackerras
2011-05-11 10:44 ` [PATCH 10/13] kvm/powerpc: Add support for Book3S processors in hypervisor mode Paul Mackerras
2011-05-12 9:07 ` Avi Kivity
2011-05-12 9:07 ` Avi Kivity
2011-05-16 1:07 ` Paul Mackerras
2011-05-16 1:07 ` Paul Mackerras
2011-05-15 21:58 ` Alexander Graf
2011-05-15 21:58 ` Alexander Graf
2011-05-15 21:58 ` Alexander Graf
2011-05-16 5:58 ` [PATCH 10/13] kvm/powerpc: Add support for Book3S processors in Paul Mackerras
2011-05-16 5:58 ` [PATCH 10/13] kvm/powerpc: Add support for Book3S processors in hypervisor mode Paul Mackerras
2011-05-16 5:58 ` Paul Mackerras
2011-05-17 10:17 ` Alexander Graf
2011-05-17 10:17 ` Alexander Graf
2011-05-17 10:17 ` Alexander Graf
2011-05-27 10:33 ` [PATCH 10/13] kvm/powerpc: Add support for Book3S processors in Paul Mackerras
2011-05-27 10:33 ` [PATCH 10/13] kvm/powerpc: Add support for Book3S processors in hypervisor mode Paul Mackerras
2011-05-27 10:33 ` Paul Mackerras
2011-05-27 10:43 ` Alexander Graf
2011-05-27 10:43 ` Alexander Graf
2011-05-27 10:43 ` Alexander Graf
2011-05-27 20:59 ` Segher Boessenkool
2011-05-27 20:59 ` Segher Boessenkool
2011-05-27 20:59 ` Segher Boessenkool
2011-05-27 23:19 ` Alexander Graf
2011-05-27 23:19 ` Alexander Graf
2011-05-27 23:19 ` Alexander Graf
2011-05-28 1:07 ` Segher Boessenkool
2011-05-28 1:07 ` Segher Boessenkool
2011-05-28 1:07 ` Segher Boessenkool
2011-05-31 20:26 ` Jimi Xenidis
2011-05-31 20:26 ` Jimi Xenidis
2011-05-31 20:26 ` Jimi Xenidis
2011-05-31 22:34 ` Segher Boessenkool
2011-05-31 22:34 ` Segher Boessenkool
2011-05-31 22:34 ` Segher Boessenkool
2011-06-01 5:11 ` [PATCH 10/13] kvm/powerpc: Add support for Book3S processors in Paul Mackerras
2011-06-01 5:11 ` [PATCH 10/13] kvm/powerpc: Add support for Book3S processors in hypervisor mode Paul Mackerras
2011-06-01 5:11 ` Paul Mackerras
2011-05-11 10:45 ` [PATCH 11/13] kvm/powerpc: Handle some PAPR hcalls in the kernel Paul Mackerras
2011-05-17 7:54 ` Alexander Graf
2011-05-17 7:54 ` Alexander Graf
2011-05-17 10:28 ` Paul Mackerras
2011-05-11 10:46 ` [PATCH 12/13] kvm/powerpc: Accelerate H_PUT_TCE by implementing it in real mode Paul Mackerras
2011-05-17 8:01 ` Alexander Graf
2011-05-17 8:01 ` Alexander Graf
2011-05-17 9:11 ` Benjamin Herrenschmidt
2011-05-17 9:11 ` Benjamin Herrenschmidt
2011-05-17 9:31 ` Alexander Graf
2011-05-17 9:31 ` Alexander Graf
2011-05-17 9:35 ` Benjamin Herrenschmidt [this message]
2011-05-17 9:35 ` Benjamin Herrenschmidt
2011-05-17 9:39 ` Alexander Graf
2011-05-17 9:39 ` Alexander Graf
2011-05-11 10:46 ` [PATCH 13/13] kvm/powerpc: Allow book3s_hv guests to use SMT processor modes Paul Mackerras
2011-05-11 13:44 ` Christoph Hellwig
2011-05-11 21:17 ` Paul Mackerras
2011-05-11 21:17 ` Paul Mackerras
2011-05-17 8:21 ` Alexander Graf
2011-05-17 8:21 ` Alexander Graf
2011-05-17 10:44 ` Paul Mackerras
2011-05-17 11:36 ` Alexander Graf
2011-05-17 11:36 ` Alexander Graf
2011-05-19 6:06 ` Paul Mackerras
2011-05-17 9:46 ` [PATCH 0/13] Hypervisor-mode KVM on POWER7 Alexander Graf
2011-05-17 9:46 ` Alexander Graf
2011-05-17 11:15 ` Paul Mackerras
2011-05-17 11:38 ` Alexander Graf
2011-05-17 11:38 ` Alexander Graf
2011-05-17 11:42 ` Avi Kivity
2011-05-17 11:42 ` Avi Kivity
2011-05-19 5:22 ` Paul Mackerras
2011-05-19 5:22 ` Paul Mackerras
2011-05-19 6:01 ` Alexander Graf
2011-05-19 6:01 ` Alexander Graf
2011-05-19 6:01 ` Alexander Graf
2011-05-21 16:41 ` Alexander Graf
2011-05-21 16:41 ` Alexander Graf
2011-05-21 17:00 ` Alexander Graf
2011-05-21 17:00 ` Alexander Graf
2011-05-21 18:15 ` Alexander Graf
2011-05-21 18:15 ` Alexander Graf
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=1305624945.2781.21.camel@pasglop \
--to=benh@kernel.crashing.org \
--cc=agraf@suse.de \
--cc=kvm@vger.kernel.org \
--cc=linuxppc-dev@ozlabs.org \
--cc=paulus@samba.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.