qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
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 10/14] spapr_pci: Enable vfio-pci hotplug
Date: Mon, 6 Jul 2015 20:27:19 +1000	[thread overview]
Message-ID: <20150706102719.GD17857@voom.redhat.com> (raw)
In-Reply-To: <1436148670-6592-11-git-send-email-aik@ozlabs.ru>

[-- Attachment #1: Type: text/plain, Size: 1981 bytes --]

On Mon, Jul 06, 2015 at 12:11:06PM +1000, Alexey Kardashevskiy wrote:
> sPAPR IOMMU is managing two copies of an TCE table:
> 1) a guest view of the table - this is what emulated devices use and
> this is where H_GET_TCE reads from;
> 2) a hardware TCE table - only present if there is at least one vfio-pci
> device on a PHB; it is updated via a memory listener on a PHB address
> space which forwards map/unmap requests to vfio-pci IOMMU host driver.
> 
> At the moment presence of vfio-pci devices on a bus affect the way
> the guest view table is allocated. If there is no vfio-pci on a PHB
> and the host kernel supports KVM acceleration of H_PUT_TCE, a table
> is allocated in KVM. However, if there is vfio-pci and we do yet not
> support KVM acceleration for these, the table has to be allocated
> by the userspace.
> 
> When vfio-pci device is hotplugged and there were no vfio-pci devices
> already, the guest view table could have been allocated by KVM which
> means that H_PUT_TCE is handled by the host kernel and since we
> do not support vfio-pci in KVM, the hardware table will not be updated.
> 
> This reallocates the guest view table in QEMU if the first vfio-pci
> device has just been plugged. spapr_tce_realloc_userspace() handles this.
> 
> This replays all the mappings to make sure that the tables are in sync.
> This will not have a visible effect though as for a new device
> the guest kernel will allocate-and-map new addresses and therefore
> existing mappings from emulated devices will not be used by vfio-pci
> devices.
> 
> This adds calls to spapr_phb_dma_capabilities_update() in PCI hotplug
> hooks.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

-- 
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 --]

  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 [this message]
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 ` [Qemu-devel] [PATCH qemu v10 00/14] spapr: vfio: Enable Dynamic DMA windows (DDW) David Gibson
2015-07-06 15:54 ` 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=20150706102719.GD17857@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).