From: Alexey Kardashevskiy <aik@ozlabs.ru>
To: qemu-devel@nongnu.org
Cc: Alex Williamson <alex.williamson@redhat.com>,
qemu-ppc@nongnu.org, Alexander Graf <agraf@suse.de>,
Gavin Shan <gwshan@linux.vnet.ibm.com>
Subject: Re: [Qemu-devel] [PATCH v7 1/4] spapr_iommu: Make in-kernel TCE table optional
Date: Thu, 05 Jun 2014 16:43:41 +1000 [thread overview]
Message-ID: <5390119D.8040201@ozlabs.ru> (raw)
In-Reply-To: <1401947401-21329-2-git-send-email-aik@ozlabs.ru>
On 06/05/2014 03:49 PM, Alexey Kardashevskiy wrote:
> POWER KVM supports an KVM_CAP_SPAPR_TCE capability which allows allocating
> TCE tables in the host kernel memory and handle H_PUT_TCE requests
> targeted to specific LIOBN (logical bus number) right in the host without
> switching to QEMU. At the moment this is used for emulated devices only
> and the handler only puts TCE to the table. If the in-kernel H_PUT_TCE
> handler finds a LIOBN and corresponding table, it will put a TCE to
> the table and complete hypercall execution. The user space will not be
> notified.
>
> Upcoming VFIO support is going to use the same sPAPRTCETable device class
> so KVM_CAP_SPAPR_TCE is going to be used as well. That means that TCE
> tables for VFIO are going to be allocated in the host as well.
> However VFIO operates with real IOMMU tables and simple copying of
> a TCE to the real hardware TCE table will not work as guest physical
> to host physical address translation is requited.
>
> So until the host kernel gets VFIO support for H_PUT_TCE, we better not
> to register VFIO's TCE in the host.
>
> This adds a bool @kvm_accel flag to the sPAPRTCETable device telling
> that sPAPRTCETable should not try allocating TCE table in the host kernel.
> Instead, the table will be created in QEMU.
>
> This adds an kvm_accel parameter to spapr_tce_new_table() to let users
> choose whether to use acceleration or not. At the moment it is enabled
> for VIO and emulated PCI. Upcoming VFIO support will set it to false.
>
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
>
> This is a workaround but it lets me have one IOMMU device for VIO, emulated
> PCI and VFIO which is a good thing.
>
> The other way around would be a new KVM_CAP_SPAPR_TCE_VFIO capability but
> this needs kernel update.
Never mind, I'll make it a capability. I'll post capability reservation
patch separately.
> ---
> hw/ppc/spapr_iommu.c | 6 ++++--
> hw/ppc/spapr_pci.c | 2 +-
> hw/ppc/spapr_vio.c | 2 +-
> include/hw/ppc/spapr.h | 4 +++-
> 4 files changed, 9 insertions(+), 5 deletions(-)
>
> diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
> index 3b6e373..bfd3701 100644
> --- a/hw/ppc/spapr_iommu.c
> +++ b/hw/ppc/spapr_iommu.c
> @@ -115,7 +115,7 @@ static int spapr_tce_table_realize(DeviceState *dev)
> {
> sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev);
>
> - if (kvm_enabled()) {
> + if (tcet->kvm_accel && kvm_enabled()) {
> tcet->table = kvmppc_create_spapr_tce(tcet->liobn,
> tcet->nb_table <<
> tcet->page_shift,
> @@ -143,7 +143,8 @@ static int spapr_tce_table_realize(DeviceState *dev)
> sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn,
> uint64_t bus_offset,
> uint32_t page_shift,
> - uint32_t nb_table)
> + uint32_t nb_table,
> + bool kvm_accel)
> {
> sPAPRTCETable *tcet;
>
> @@ -162,6 +163,7 @@ sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn,
> tcet->bus_offset = bus_offset;
> tcet->page_shift = page_shift;
> tcet->nb_table = nb_table;
> + tcet->kvm_accel = kvm_accel;
>
> object_property_add_child(OBJECT(owner), "tce-table", OBJECT(tcet), NULL);
>
> diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c
> index ddfd8bb..6021f35 100644
> --- a/hw/ppc/spapr_pci.c
> +++ b/hw/ppc/spapr_pci.c
> @@ -658,7 +658,7 @@ static void spapr_phb_finish_realize(sPAPRPHBState *sphb, Error **errp)
> tcet = spapr_tce_new_table(DEVICE(sphb), sphb->dma_liobn,
> 0,
> SPAPR_TCE_PAGE_SHIFT,
> - 0x40000000 >> SPAPR_TCE_PAGE_SHIFT);
> + 0x40000000 >> SPAPR_TCE_PAGE_SHIFT, true);
> if (!tcet) {
> error_setg(errp, "Unable to create TCE table for %s",
> sphb->dtbusname);
> diff --git a/hw/ppc/spapr_vio.c b/hw/ppc/spapr_vio.c
> index 48b0125..16385e4 100644
> --- a/hw/ppc/spapr_vio.c
> +++ b/hw/ppc/spapr_vio.c
> @@ -460,7 +460,7 @@ static int spapr_vio_busdev_init(DeviceState *qdev)
> 0,
> SPAPR_TCE_PAGE_SHIFT,
> pc->rtce_window_size >>
> - SPAPR_TCE_PAGE_SHIFT);
> + SPAPR_TCE_PAGE_SHIFT, true);
> address_space_init(&dev->as, spapr_tce_get_iommu(dev->tcet), qdev->id);
> }
>
> diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
> index 4ffb903..7db34ff 100644
> --- a/include/hw/ppc/spapr.h
> +++ b/include/hw/ppc/spapr.h
> @@ -402,6 +402,7 @@ struct sPAPRTCETable {
> uint32_t page_shift;
> uint64_t *table;
> bool bypass;
> + bool kvm_accel;
> int fd;
> MemoryRegion iommu;
> QLIST_ENTRY(sPAPRTCETable) list;
> @@ -413,7 +414,8 @@ int spapr_h_cas_compose_response(target_ulong addr, target_ulong size);
> sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn,
> uint64_t bus_offset,
> uint32_t page_shift,
> - uint32_t nb_table);
> + uint32_t nb_table,
> + bool kvm_accel);
> MemoryRegion *spapr_tce_get_iommu(sPAPRTCETable *tcet);
> void spapr_tce_set_bypass(sPAPRTCETable *tcet, bool bypass);
> int spapr_dma_dt(void *fdt, int node_off, const char *propname,
>
--
Alexey
next prev parent reply other threads:[~2014-06-05 6:44 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-05 5:49 [Qemu-devel] [PATCH v7 0/4] vfio on spapr-ppc64 Alexey Kardashevskiy
2014-06-05 5:49 ` [Qemu-devel] [PATCH v7 1/4] spapr_iommu: Make in-kernel TCE table optional Alexey Kardashevskiy
2014-06-05 6:43 ` Alexey Kardashevskiy [this message]
2014-06-05 13:06 ` Alexander Graf
2014-06-05 13:10 ` Alexey Kardashevskiy
2014-06-05 13:15 ` Alexander Graf
2014-06-05 13:33 ` Alexey Kardashevskiy
2014-06-05 13:36 ` Alexander Graf
2014-06-05 14:33 ` Alexey Kardashevskiy
2014-06-05 16:51 ` Alexander Graf
2014-06-05 23:17 ` Alexey Kardashevskiy
2014-06-05 23:36 ` Alexander Graf
2014-06-05 23:48 ` Alexey Kardashevskiy
2014-06-06 3:38 ` Benjamin Herrenschmidt
2014-06-05 5:49 ` [Qemu-devel] [PATCH v7 2/4] vfio: Add vfio_container_spapr_get_info() Alexey Kardashevskiy
2014-06-05 19:27 ` Alex Williamson
2014-06-05 23:40 ` Alexey Kardashevskiy
2014-06-06 1:32 ` Gavin Shan
2014-06-05 5:50 ` [Qemu-devel] [PATCH v7 3/4] spapr_pci_vfio: Add spapr-pci-vfio-host-bridge to support vfio Alexey Kardashevskiy
2014-06-05 13:34 ` Alexander Graf
2014-06-05 14:37 ` Alexey Kardashevskiy
2014-06-05 5:50 ` [Qemu-devel] [PATCH v7 4/4] vfio: Enable for spapr Alexey Kardashevskiy
2014-06-05 19:31 ` Alex Williamson
2014-06-05 23:39 ` Alexey Kardashevskiy
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=5390119D.8040201@ozlabs.ru \
--to=aik@ozlabs.ru \
--cc=agraf@suse.de \
--cc=alex.williamson@redhat.com \
--cc=gwshan@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).