From: David Gibson <david@gibson.dropbear.id.au>
To: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: Michael Roth <mdroth@linux.vnet.ibm.com>,
Alex Williamson <alex.williamson@redhat.com>,
qemu-ppc@nongnu.org, qemu-devel@nongnu.org,
Gavin Shan <gwshan@linux.vnet.ibm.com>
Subject: Re: [Qemu-devel] [PATCH qemu v10 00/14] spapr: vfio: Enable Dynamic DMA windows (DDW)
Date: Mon, 6 Jul 2015 21:13:43 +1000 [thread overview]
Message-ID: <20150706111343.GG17857@voom.redhat.com> (raw)
In-Reply-To: <1436148670-6592-1-git-send-email-aik@ozlabs.ru>
[-- Attachment #1: Type: text/plain, Size: 2520 bytes --]
On Mon, Jul 06, 2015 at 12:10:56PM +1000, Alexey Kardashevskiy wrote:
>
> (cut-n-paste from kernel patchset)
>
> Each Partitionable Endpoint (IOMMU group) has an address range on a PCI bus
> where devices are allowed to do DMA. These ranges are called DMA windows.
> By default, there is a single DMA window, 1 or 2GB big, mapped at zero
> on a PCI bus.
>
> PAPR defines a DDW RTAS API which allows pseries guests
> querying the hypervisor about DDW support and capabilities (page size mask
> for now). A pseries guest may request an additional (to the default)
> DMA windows using this RTAS API.
> The existing pseries Linux guests request an additional window as big as
> the guest RAM and map the entire guest window which effectively creates
> direct mapping of the guest memory to a PCI bus.
>
> This patchset reworks PPC64 IOMMU code and adds necessary structures
> to support big windows.
>
> Once a Linux guest discovers the presence of DDW, it does:
> 1. query hypervisor about number of available windows and page size masks;
> 2. create a window with the biggest possible page size (today 4K/64K/16M);
> 3. map the entire guest RAM via H_PUT_TCE* hypercalls;
> 4. switche dma_ops to direct_dma_ops on the selected PE.
>
> Once this is done, H_PUT_TCE is not called anymore for 64bit devices and
> the guest does not waste time on DMA map/unmap operations.
>
> Note that 32bit devices won't use DDW and will keep using the default
> DMA window so KVM optimizations will be required (to be posted later).
>
> This patchset adds DDW support for pseries. The host kernel changes are
> required, available in the current upstream.
>
> This patchset is based on git://github.com/dgibson/qemu.git spapr-next branch.
>
> Please comment. Thanks!
I've applied this to my "spapr-dev" branch. Here's what needs to
happen before I move it into spapr-next (which is what I'll be pushing
to Alex Graf).
* For you and Gavin to test it to see that DDW and EEH work properly
together
* Some word from Alex W on how he wants to go about merging 12-13/14
* Some indication about who should be merging 2/14
* Review from at least one more person - I've looked at so many
versions of the ddw patches I no longer trust that I've got it all
straight in my head
--
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: Type: application/pgp-signature, Size: 819 bytes --]
next prev parent reply other threads:[~2015-07-06 11:16 UTC|newest]
Thread overview: 71+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-06 2:10 [Qemu-devel] [PATCH qemu v10 00/14] spapr: vfio: Enable Dynamic DMA windows (DDW) Alexey Kardashevskiy
2015-07-06 2:10 ` [Qemu-devel] [PATCH qemu v10 01/14] linux-headers: Update to 4.2-rc1 Alexey Kardashevskiy
2015-07-06 11:18 ` Paolo Bonzini
2015-07-06 2:10 ` [Qemu-devel] [PATCH qemu v10 02/14] vmstate: Define VARRAY with VMS_ALLOC Alexey Kardashevskiy
2015-07-06 14:21 ` Thomas Huth
2015-07-06 2:10 ` [Qemu-devel] [PATCH qemu v10 03/14] spapr_pci: Convert finish_realize() to dma_capabilities_update()+dma_init_window() Alexey Kardashevskiy
2015-07-06 16:41 ` Laurent Vivier
2015-07-07 0:28 ` Alexey Kardashevskiy
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 04/14] spapr_iommu: Move table allocation to helpers Alexey Kardashevskiy
2015-07-06 15:14 ` Thomas Huth
2015-07-06 15:43 ` Alexey Kardashevskiy
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 05/14] spapr_iommu: Introduce "enabled" state for TCE table Alexey Kardashevskiy
2015-07-06 10:07 ` David Gibson
2015-07-06 17:04 ` Thomas Huth
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 06/14] spapr_iommu: Remove vfio_accel flag from sPAPRTCETable Alexey Kardashevskiy
2015-07-06 16:45 ` Laurent Vivier
2015-07-06 17:11 ` Thomas Huth
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 07/14] spapr_iommu: Add root memory region Alexey Kardashevskiy
2015-07-06 19:15 ` Thomas Huth
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 08/14] spapr_pci: Do complete reset of DMA config when resetting PHB Alexey Kardashevskiy
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 09/14] spapr_vfio_pci: Remove redundant spapr-pci-vfio-host-bridge Alexey Kardashevskiy
2015-07-06 21:13 ` Thomas Huth
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 10/14] spapr_pci: Enable vfio-pci hotplug Alexey Kardashevskiy
2015-07-06 10:27 ` David Gibson
2015-07-06 21:31 ` Thomas Huth
2015-07-07 9:28 ` Alexey Kardashevskiy
2015-07-10 21:33 ` Michael Roth
2015-07-12 4:59 ` Alexey Kardashevskiy
2015-07-12 14:41 ` Michael Roth
2015-07-13 1:10 ` David Gibson
2015-07-13 7:06 ` Alexey Kardashevskiy
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 11/14] spapr_pci_vfio: Enable multiple groups per container Alexey Kardashevskiy
2015-07-07 7:02 ` Thomas Huth
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 12/14] vfio: Unregister IOMMU notifiers when container is destroyed Alexey Kardashevskiy
2015-07-06 10:33 ` David Gibson
2015-07-06 12:49 ` Alex Williamson
2015-07-06 12:59 ` Alexey Kardashevskiy
2015-07-06 13:45 ` Alex Williamson
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 13/14] vfio: spapr: Add SPAPR IOMMU v2 support (DMA memory preregistering) Alexey Kardashevskiy
2015-07-06 13:42 ` Alex Williamson
2015-07-06 15:34 ` Alexey Kardashevskiy
2015-07-06 16:13 ` Alex Williamson
2015-07-07 0:29 ` David Gibson
2015-07-07 0:36 ` Alexey Kardashevskiy
2015-07-07 12:11 ` Alexey Kardashevskiy
2015-07-07 16:24 ` Alex Williamson
2015-07-08 6:26 ` Alexey Kardashevskiy
2015-07-08 14:51 ` Alex Williamson
2015-07-07 7:23 ` Thomas Huth
2015-07-07 10:05 ` Alexey Kardashevskiy
2015-07-07 10:21 ` Thomas Huth
2015-07-07 11:05 ` Alexey Kardashevskiy
2015-07-08 4:30 ` David Gibson
2015-07-08 6:24 ` Thomas Huth
2015-07-08 6:50 ` David Gibson
2015-07-08 7:07 ` Alexey Kardashevskiy
2015-07-08 14:47 ` Alex Williamson
2015-07-06 2:11 ` [Qemu-devel] [PATCH qemu v10 14/14] spapr_pci/spapr_pci_vfio: Support Dynamic DMA Windows (DDW) Alexey Kardashevskiy
2015-07-06 11:06 ` David Gibson
2015-07-06 11:27 ` Alexey Kardashevskiy
2015-07-07 9:46 ` Alexey Kardashevskiy
2015-07-07 4:58 ` David Gibson
2015-07-07 9:33 ` Thomas Huth
2015-07-07 10:43 ` Alexey Kardashevskiy
2015-07-07 11:35 ` Thomas Huth
2015-07-07 11:53 ` Alexey Kardashevskiy
2015-07-06 11:13 ` David Gibson [this message]
2015-07-06 15:54 ` [Qemu-devel] [PATCH qemu v10 00/14] spapr: vfio: Enable Dynamic DMA windows (DDW) Thomas Huth
2015-07-06 16:07 ` Alexey Kardashevskiy
2015-07-06 16:13 ` Thomas Huth
2015-07-08 4:34 ` 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=20150706111343.GG17857@voom.redhat.com \
--to=david@gibson.dropbear.id.au \
--cc=aik@ozlabs.ru \
--cc=alex.williamson@redhat.com \
--cc=gwshan@linux.vnet.ibm.com \
--cc=mdroth@linux.vnet.ibm.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@nongnu.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).