On Tue, Sep 08, 2020 at 10:57:30PM +0200, Alexander Graf wrote:
> We currently pass through the number of PMU counters that we have available
> in hardware to guests. So if my host supports 10 concurrently active PMU
> counters, my guest will be able to spawn 10 counters as well.
>
> This is undes
On 8/24/2020 11:35 AM, Florian Fainelli wrote:
Changes in v2:
- included missing preliminary patch to define the SB barrier instruction
Will Deacon (2):
arm64: Add support for SB barrier and patch in over DSB; ISB sequences
arm64: entry: Place an SB sequence following an ERET instructi
Hi Will,
Minor nitpick below.
On 9/7/20 4:23 PM, Will Deacon wrote:
> Add support for relaxing the permissions of a stage-2 mapping (i.e.
> adding additional permissions) to the generic page-table code.
>
> Cc: Marc Zyngier
> Cc: Quentin Perret
> Reviewed-by: Gavin Shan
> Signed-off-by: Will D
Hi Will,
On 9/7/20 4:23 PM, Will Deacon wrote:
> Convert the page-aging functions and access fault handler to use the
> generic page-table code instead of walking the page-table directly.
>
> Cc: Marc Zyngier
> Cc: Quentin Perret
> Reviewed-by: Gavin Shan
> Signed-off-by: Will Deacon
> ---
>
Hi Will,
The patch looks good to me, I have a question below.
On 9/7/20 4:23 PM, Will Deacon wrote:
> Add stage-2 mkyoung(), mkold() and is_young() operations to the generic
> page-table code.
>
> Cc: Marc Zyngier
> Cc: Quentin Perret
> Reviewed-by: Gavin Shan
> Signed-off-by: Will Deacon
> -
On Mon, Sep 07, 2020 at 03:20:07PM +0100, Marc Zyngier wrote:
> On Thu, 03 Sep 2020 14:53:05 +0100,
> Andrew Scull wrote:
> >
> > Rather than passing arbitrary function pointers to run at hyp, define
> > and equivalent set of SMCCC functions.
> >
> > Since the SMCCC functions are strongly tied t
On Mon, Sep 07, 2020 at 02:33:17PM +0100, Marc Zyngier wrote:
> On Thu, 03 Sep 2020 14:53:03 +0100,
> Andrew Scull wrote:
> >
> > To avoid warning about implicit casting, make the casting explicit. This
> > allows, for example, pointers to be used as arguments as are used in the
> > KVM hyp inter
On Mon, Sep 07, 2020 at 02:29:11PM +0100, Marc Zyngier wrote:
> On Thu, 03 Sep 2020 14:52:57 +0100,
> Andrew Scull wrote:
> >
> > During __guest_enter, save and restore from a new hyp context rather
> > than the host context. This is preparation for separation of the hyp and
> > host context in n
On Mon, Sep 07, 2020 at 02:02:54PM +0100, Marc Zyngier wrote:
> Hi Andrew,
>
> On Thu, 03 Sep 2020 14:53:01 +0100,
> Andrew Scull wrote:
> >
> > Save and restore the host context when switching to and from hyp. This
> > gives hyp its own context that the host will not see as a step towards a
> >
On Mon, Sep 07, 2020 at 12:38:46PM +0100, Marc Zyngier wrote:
> Hi Andrew,
>
> On Thu, 03 Sep 2020 14:52:55 +0100,
> Andrew Scull wrote:
> >
> > The host is treated differently from the guests when an exception is
> > taken so introduce a separate vector that is specialized for the host.
> > Thi
On Mon, Sep 07, 2020 at 11:38:38AM +0100, Marc Zyngier wrote:
> Hi Andrew,
>
> On Thu, 03 Sep 2020 14:52:53 +0100,
> Andrew Scull wrote:
> >
> > nVHE symbols are prefixed but this is sometimes hidden from the host by
> > aliasing the non-prefixed symbol to the prefixed version with a macro.
> >
Hi Will,
On 9/3/20 6:57 PM, Will Deacon wrote:
> On Wed, Sep 02, 2020 at 05:23:08PM +0100, Alexandru Elisei wrote:
>> On 8/25/20 10:39 AM, Will Deacon wrote:
>>> Convert unmap_stage2_range() to use kvm_pgtable_stage2_unmap() instead
>>> of walking the page-table directly.
>>>
>>> Cc: Marc Zyngier
On 2020-09-08 13:23, Alexandru Elisei wrote:
Hi Marc,
On 9/4/20 10:58 AM, Marc Zyngier wrote:
Hi Alex,
On Tue, 01 Sep 2020 14:33:57 +0100,
Alexandru Elisei wrote:
When userspace uses hugetlbfs for the VM memory, user_mem_abort()
tries to
use the same block size to map the faulting IPA in sta
Hi Marc,
On 9/4/20 10:58 AM, Marc Zyngier wrote:
> Hi Alex,
>
> On Tue, 01 Sep 2020 14:33:57 +0100,
> Alexandru Elisei wrote:
>> When userspace uses hugetlbfs for the VM memory, user_mem_abort() tries to
>> use the same block size to map the faulting IPA in stage 2. If stage 2
>> cannot use the s
Hi Will,
On 2020-09-07 16:23, Will Deacon wrote:
Now that KVM is using the generic page-table code to manage the guest
stage-2 page-tables, we can remove a bunch of unused macros, #defines
and static inline functions from the old implementation.
Cc: Marc Zyngier
Cc: Quentin Perret
Reviewed-by
On Tue, Sep 08, 2020 at 08:58:30AM +0100, Marc Zyngier wrote:
> Add a small blurb describing how the event filtering API gets used.
>
> Signed-off-by: Marc Zyngier
> ---
> Documentation/virt/kvm/devices/vcpu.rst | 46 +
> 1 file changed, 46 insertions(+)
>
> diff --git a
On Tue, Sep 08, 2020 at 08:58:28AM +0100, Marc Zyngier wrote:
> It can be desirable to expose a PMU to a guest, and yet not want the
> guest to be able to count some of the implemented events (because this
> would give information on shared resources, for example.
>
> For this, let's extend the PM
Hi Andrew,
On 2020-09-08 10:53, Andrew Jones wrote:
Hi Marc,
On Tue, Sep 08, 2020 at 08:58:26AM +0100, Marc Zyngier wrote:
The PMU emulation error handling is pretty messy when dealing with
attributes. Let's refactor it so that we have less duplication,
and that it is easy to extend later on.
On Tue, Sep 08, 2020 at 08:58:27AM +0100, Marc Zyngier wrote:
> The PMU code suffers from a small defect where we assume that the event
> number provided by the guest is always 16 bit wide, even if the CPU only
> implements the ARMv8.0 architecture. This isn't really problematic in
> the sense that
Hi Marc,
On Tue, Sep 08, 2020 at 08:58:26AM +0100, Marc Zyngier wrote:
> The PMU emulation error handling is pretty messy when dealing with
> attributes. Let's refactor it so that we have less duplication,
> and that it is easy to extend later on.
>
> A functional change is that kvm_arm_pmu_v3_in
The PMU emulation error handling is pretty messy when dealing with
attributes. Let's refactor it so that we have less duplication,
and that it is easy to extend later on.
A functional change is that kvm_arm_pmu_v3_init() used to return
-ENXIO when the PMU feature wasn't set. The error is now repor
It is at times necessary to prevent a guest from being able to sample
certain events if multiple CPUs share resources such as a cache level. In
this case, it would be interesting if the VMM could simply prevent certain
events from being counted instead of hiding the PMU.
Given that most events are
It can be desirable to expose a PMU to a guest, and yet not want the
guest to be able to count some of the implemented events (because this
would give information on shared resources, for example.
For this, let's extend the PMUv3 device API, and offer a way to setup a
bitmap of the allowed events
Add a small blurb describing how the event filtering API gets used.
Signed-off-by: Marc Zyngier
---
Documentation/virt/kvm/devices/vcpu.rst | 46 +
1 file changed, 46 insertions(+)
diff --git a/Documentation/virt/kvm/devices/vcpu.rst
b/Documentation/virt/kvm/devices/vcp
As we can now hide events from the guest, let's also adjust its view of
PCMEID{0,1}_EL1 so that it can figure out why some common events are not
counting as they should.
The astute user can still look into the TRM for their CPU and find out
they've been cheated, though. Nobody's perfect.
Signed-o
The PMU code suffers from a small defect where we assume that the event
number provided by the guest is always 16 bit wide, even if the CPU only
implements the ARMv8.0 architecture. This isn't really problematic in
the sense that the event number ends up in a system register, cropping
it to the rig
26 matches
Mail list logo