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.
next prev parent reply other threads:[~2011-05-17 9:35 UTC|newest]
Thread overview: 55+ 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 11:15 ` Paul Mackerras
2011-05-12 11:16 ` Benjamin Herrenschmidt
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 18:10 ` 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
2011-05-16 1:07 ` Paul Mackerras
2011-05-15 21:58 ` Alexander Graf
2011-05-16 5:58 ` Paul Mackerras
2011-05-17 10:17 ` Alexander Graf
2011-05-27 10:33 ` Paul Mackerras
2011-05-27 10:43 ` Alexander Graf
2011-05-27 20:59 ` Segher Boessenkool
2011-05-27 23:19 ` Alexander Graf
2011-05-28 1:07 ` Segher Boessenkool
2011-05-31 20:26 ` Jimi Xenidis
2011-05-31 22:34 ` Segher Boessenkool
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 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 9:11 ` Benjamin Herrenschmidt
2011-05-17 9:31 ` Alexander Graf
2011-05-17 9:35 ` Benjamin Herrenschmidt [this message]
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
2011-05-17 8:21 ` Alexander Graf
2011-05-17 10:44 ` Paul Mackerras
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 11:15 ` Paul Mackerras
2011-05-17 11:38 ` Alexander Graf
2011-05-17 11:42 ` Avi Kivity
2011-05-19 5:22 ` Paul Mackerras
2011-05-19 6:01 ` Alexander Graf
2011-05-21 16:41 ` Alexander Graf
2011-05-21 17:00 ` 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 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).