Re: [PATCH] arm/arm64: KVM: Fix set_clear_sgi_pend_reg offset

Hi Christoffer, On 2014/9/26 21:44, Christoffer Dall wrote: > On Fri, Sep 26, 2014 at 12:16:35PM +0200, Christoffer Dall wrote: >> On Fri, Sep 26, 2014 at 05:26:00PM +0800, Shannon Zhao wrote: >>> >>> >>> On 2014/9/26 16:44, Christoffer Dall wrote: Hi Shannon, On Fri, Sep 26, 2014 a

Re: [RESEND PATCH v3 2/2] vfio/pci: Restore MSIx message prior to enabling

On Sat, 2014-09-27 at 15:43 +1000, Gavin Shan wrote: > The MSIx vector table lives in device memory, which may be cleared as > part of a backdoor device reset. This is the case on the IBM IPR HBA > when the BIST is run on the device. When assigned to a QEMU guest, > the guest driver does a pci_save

Re: [PATCH] drivers/vfio: Export vfio_spapr_iommu_eeh_ioctl() with GPL

On Sat, 2014-09-27 at 16:04 +1000, Gavin Shan wrote: > The function should have been exported with EXPORT_SYMBOL_GPL() > as part of commit 92d18a68 ("drivers/vfio: Fix EEH build error"). > > Suggested-by: Alexey Kardashevskiy > Signed-off-by: Gavin Shan > --- > drivers/vfio/vfio_spapr_eeh.c | 2

[PATCH] vfio-pci: Fix remove path locking

Locking both the remove() and release() path results in a deadlock that should have been obvious. To fix this we can get and hold the vfio_device reference as we evaluate whether to do a bus/slot reset. This will automatically block any remove() calls, allowing us to remove the explict lock. Fixe

Re: [PATCH v11 6/6] arm: KVM: ARMv7 dirty page logging 2nd stage page fault

On 09/29/2014 06:35 AM, Christoffer Dall wrote: > On Mon, Sep 22, 2014 at 05:54:50PM -0700, Mario Smarduch wrote: >> This patch adds support for handling 2nd stage page faults during migration, >> it disables faulting in huge pages, and dissolves huge pages to page tables. >> In case migration is c

Re: FreeBSD Guest Freezes during boot up on Linux KVM, RHEL 6.4 or RHEL 6.5

On Fri, Sep 26, 2014 at 07:31:17AM +, Venkateswara Rao Nandigam wrote: > Hi Paolo, > > As suggested by You, the following is the issue info. Is this something to be > fixed in host kernel? > > Description: > FreeBSD 64bit(10.0) Guest freezes at "booting" on Linux KVM, host running > RH

[PATCH kvm-unit-tests] x86: Test physical x2apic broadcast ICR

Previously KVM did not deliver x2apic broadcast IPI (dest-id==0x) with physical delivery mode. This test checks the fix. Signed-off-by: Nadav Amit --- x86/apic.c | 19 +++ 1 file changed, 19 insertions(+) diff --git a/x86/apic.c b/x86/apic.c index 2619d85..373f6e0 100644

[PATCH] KVM: x86: x2apic broadcast with physical mode does not work

KVM does not deliver x2APIC broadcast messages with physical mode. Intel SDM (10.12.9 ICR Operation in x2APIC Mode) states: "A destination ID value of _H is used for broadcast of interrupts in both logical destination and physical destination modes." The fix tries to combine broadcast in

Re: [PATCH v11 2/6] KVM: Add generic implementation of kvm_vm_ioctl_get_dirty_log

On 09/29/2014 10:18 AM, Cornelia Huck wrote: > On Mon, 22 Sep 2014 17:54:46 -0700 > Mario Smarduch wrote: > >> Add support for generic implementation of dirty log read function. For now >> x86_64 and ARMv7 share generic dirty log read. Other architectures call >> their architecture specific funct

Re: [PATCH v11 2/6] KVM: Add generic implementation of kvm_vm_ioctl_get_dirty_log

On Mon, 22 Sep 2014 17:54:46 -0700 Mario Smarduch wrote: > Add support for generic implementation of dirty log read function. For now > x86_64 and ARMv7 share generic dirty log read. Other architectures call > their architecture specific functions. > > Signed-off-by: Mario Smarduch This (and t

Re: [PATCH v4 2/4] kvmtool: ARM64: Add target type potenza for aarch64

On 19/09/14 00:57, Anup Patel wrote: > The VCPU target type KVM_ARM_TARGET_XGENE_POTENZA is available > in latest Linux-3.16-rcX or higher hence register aarch64 target > type for it. > > This patch enables us to run KVMTOOL on X-Gene Potenza host. I still don't like the addition of another CPU,

Re: [PATCH v11 2/6] KVM: Add generic implementation of kvm_vm_ioctl_get_dirty_log

On Mon, Sep 22, 2014 at 05:54:46PM -0700, Mario Smarduch wrote: > Add support for generic implementation of dirty log read function. For now > x86_64 and ARMv7 share generic dirty log read. Other architectures call > their architecture specific functions. > > Signed-off-by: Mario Smarduch > ---

Re: [PATCH v11 6/6] arm: KVM: ARMv7 dirty page logging 2nd stage page fault

On Mon, Sep 22, 2014 at 05:54:50PM -0700, Mario Smarduch wrote: > This patch adds support for handling 2nd stage page faults during migration, > it disables faulting in huge pages, and dissolves huge pages to page tables. > In case migration is canceled huge pages may be used again. > > > Signed-

Re: [PATCH] KVM: PPC: BOOK3S: HV: CMA: Reserve cma region only in hypervisor mode

Il 29/09/2014 13:57, Alexander Graf ha scritto: > > > On 29.09.14 13:48, Paolo Bonzini wrote: >> Il 29/09/2014 10:28, Alexander Graf ha scritto: >>> >>> >>> On 29.09.14 10:02, Aneesh Kumar K.V wrote: We use cma reserved area for creating guest hash page table. Don't do the reservation i

Re: [Qemu-devel] KVM call for agenda for 2014-09-30

On 28/09/2014 18:33, Juan Quintela wrote: Hi Please, send any topic that you are interested in covering. Call details: 15:00 CEST 13:00 UTC 09:00 EDT Every two weeks By popular demand, a google calendar public entry with it https://www.google.com/calendar/embed?src=dG9iMXRqcXAz

Re: [PATCH] KVM: PPC: BOOK3S: HV: CMA: Reserve cma region only in hypervisor mode

On 29.09.14 13:48, Paolo Bonzini wrote: > Il 29/09/2014 10:28, Alexander Graf ha scritto: >> >> >> On 29.09.14 10:02, Aneesh Kumar K.V wrote: >>> We use cma reserved area for creating guest hash page table. >>> Don't do the reservation in non-hypervisor mode. This avoids unnecessary >>> CMA reser

Re: [PATCH] KVM: PPC: BOOK3S: HV: CMA: Reserve cma region only in hypervisor mode

Il 29/09/2014 10:28, Alexander Graf ha scritto: > > > On 29.09.14 10:02, Aneesh Kumar K.V wrote: >> We use cma reserved area for creating guest hash page table. >> Don't do the reservation in non-hypervisor mode. This avoids unnecessary >> CMA reservation when booting with limited memory configs

Re: [PATCHv7 06/26] vfio/iommu_type1: implement the VFIO_DMA_MAP_FLAG_NOEXEC flag

On Fri, Sep 26, 2014 at 10:27 PM, Alex Williamson wrote: > On Fri, 2014-09-26 at 17:39 +0200, Antonios Motakis wrote: >> On Wed, Sep 24, 2014 at 12:40 AM, Alex Williamson >> wrote: >> > On Tue, 2014-09-23 at 16:46 +0200, Antonios Motakis wrote: >> >> Some IOMMU drivers, such as the ARM SMMU drive

Re: [PATCHv7 10/26] vfio: platform: probe to devices on the platform bus

On Fri, Sep 26, 2014 at 10:18 PM, Alex Williamson wrote: > On Fri, 2014-09-26 at 17:30 +0200, Antonios Motakis wrote: >> On Wed, Sep 24, 2014 at 1:01 AM, Alex Williamson >> wrote: >> > >> > On Tue, 2014-09-23 at 16:46 +0200, Antonios Motakis wrote: >> > > Driver to bind to Linux platform devices,

Re: [PATCHv7 07/26] driver core: amba: add device binding path 'driver_override'

On Fri, Sep 26, 2014 at 5:37 PM, Russell King - ARM Linux wrote: > On Tue, Sep 23, 2014 at 04:46:06PM +0200, Antonios Motakis wrote: >> As already demonstrated with PCI [1] and the platform bus [2], a >> driver_override property in sysfs can be used to bypass the id matching >> of a device to a AM

[no subject]

subscribe kvm -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html

Re: reduce networking latency

On Wed, Sep 24, 2014 at 02:40:53PM -0400, David Xu wrote: > Hi Michael, > > I found this interesting project from KVM TODO website: > > allow handling short packets from softirq or VCPU context > Plan: >We are going through the scheduler 3 times >(could be up to 5 if softirqd is involved

Re: [PATCH] KVM: PPC: BOOK3S: HV: CMA: Reserve cma region only in hypervisor mode

On 29.09.14 10:02, Aneesh Kumar K.V wrote: > We use cma reserved area for creating guest hash page table. > Don't do the reservation in non-hypervisor mode. This avoids unnecessary > CMA reservation when booting with limited memory configs like > fadump and kdump. > > Signed-off-by: Aneesh Kumar

[PATCH] KVM: PPC: BOOK3S: HV: CMA: Reserve cma region only in hypervisor mode

We use cma reserved area for creating guest hash page table. Don't do the reservation in non-hypervisor mode. This avoids unnecessary CMA reservation when booting with limited memory configs like fadump and kdump. Signed-off-by: Aneesh Kumar K.V --- arch/powerpc/kvm/book3s_hv_builtin.c | 6 +