KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Will Deacon <will@kernel.org>
To: Andrew Murray <andrew.murray@arm.com>
Cc: Catalin Marinas <Catalin.Marinas@arm.com>,
	kvm@vger.kernel.org, Marc Zyngier <maz@kernel.org>,
	linux-kernel@vger.kernel.org, Sudeep Holla <Sudeep.Holla@arm.com>,
	kvmarm <kvmarm@lists.cs.columbia.edu>,
	linux-arm-kernel <linux-arm-kernel@lists.infradead.org>
Subject: Re: [PATCH v2 09/18] arm64: KVM: enable conditional save/restore full SPE profiling buffer controls
Date: Thu, 9 Jan 2020 12:01:39 +0000
Message-ID: <20200109120139.GA7512@willie-the-truck> (raw)
In-Reply-To: <20200109112504.GZ42593@e119886-lin.cambridge.arm.com>

On Thu, Jan 09, 2020 at 11:25:04AM +0000, Andrew Murray wrote:
> On Thu, Jan 09, 2020 at 11:23:37AM +0000, Andrew Murray wrote:
> > On Wed, Jan 08, 2020 at 01:10:21PM +0000, Will Deacon wrote:
> > > On Wed, Jan 08, 2020 at 12:36:11PM +0000, Marc Zyngier wrote:
> > > > On 2020-01-08 11:58, Will Deacon wrote:
> > > > > On Wed, Jan 08, 2020 at 11:17:16AM +0000, Marc Zyngier wrote:
> > > > > > On 2020-01-07 15:13, Andrew Murray wrote:
> > > > > > > Looking at the vcpu_load and related code, I don't see a way of saying
> > > > > > > 'don't schedule this VCPU on this CPU' or bailing in any way.
> > > > > > 
> > > > > > That would actually be pretty easy to implement. In vcpu_load(), check
> > > > > > that that the CPU physical has SPE. If not, raise a request for that
> > > > > > vcpu.
> > > > > > In the run loop, check for that request and abort if raised, returning
> > > > > > to userspace.
> > 
> > I hadn't really noticed the kvm_make_request mechanism - however it's now
> > clear how this could be implemented.
> > 
> > This approach gives responsibility for which CPUs should be used to userspace
> > and if userspace gets it wrong then the KVM_RUN ioctl won't do very much.
> > 
> > 
> > > > > > 
> > > > > > Userspace can always check /sys/devices/arm_spe_0/cpumask and work out
> > > > > > where to run that particular vcpu.
> > > > > 
> > > > > It's also worth considering systems where there are multiple
> > > > > implementations
> > > > > of SPE in play. Assuming we don't want to expose this to a guest, then
> > > > > the
> > > > > right interface here is probably for userspace to pick one SPE
> > > > > implementation and expose that to the guest.
> > 
> > If I understand correctly then this implies the following:
> > 
> >  - If the host userspace indicates it wants support for SPE in the guest (via 
> >    KVM_SET_DEVICE_ATTR at start of day) - then we should check in vcpu_load that
> >    the minimum version of SPE is present on the current CPU. 'minimum' because
> >    we don't know why userspace has selected the given cpumask.
> > 
> >  - Userspace can get it wrong, i.e. it can create a CPU mask with CPUs that
> >    have SPE with differing versions. If it does, and all CPUs have some form of
> >    SPE then errors may occur in the guest. Perhaps this is OK and userspace
> >    shouldn't get it wrong?
> 
> Actually this could be guarded against by emulating the ID_AA64DFR0_EL1 such to
> cap the version to the minimum SPE version - if absolutely required.

The problem is, it's not as simple as checking a version field. Instead,
you'd have to look at all of the ID registers for SPE so that you don't end
up with funny differences such as minimum sampling interval, or hardware RNG
support. Ultimately though, *much* of the trace is going to be describing
IMP DEF stuff because it's so micro-architectural, and there's very little
you can do to hide that.

Will

  reply index

Thread overview: 78+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-20 14:30 [PATCH v2 00/18] arm64: KVM: add SPE profiling support Andrew Murray
2019-12-20 14:30 ` [PATCH v2 01/18] dt-bindings: ARM SPE: highlight the need for PPI partitions on heterogeneous systems Andrew Murray
2019-12-20 14:30 ` [PATCH v2 02/18] arm64: KVM: reset E2PB correctly in MDCR_EL2 when exiting the guest(VHE) Andrew Murray
2019-12-21 13:12   ` Marc Zyngier
2019-12-24 10:29     ` Andrew Murray
2020-01-02 16:21       ` Andrew Murray
2019-12-20 14:30 ` [PATCH v2 03/18] arm64: KVM: define SPE data structure for each vcpu Andrew Murray
2019-12-21 13:19   ` Marc Zyngier
2019-12-24 12:01     ` Andrew Murray
2019-12-20 14:30 ` [PATCH v2 04/18] arm64: KVM: add SPE system registers to sys_reg_descs Andrew Murray
2019-12-20 14:30 ` [PATCH v2 05/18] arm64: KVM/VHE: enable the use PMSCR_EL12 on VHE systems Andrew Murray
2019-12-20 14:30 ` [PATCH v2 06/18] arm64: KVM: split debug save restore across vm/traps activation Andrew Murray
2019-12-20 14:30 ` [PATCH v2 07/18] arm64: KVM/debug: drop pmscr_el1 and use sys_regs[PMSCR_EL1] in kvm_cpu_context Andrew Murray
2019-12-20 14:30 ` [PATCH v2 08/18] arm64: KVM: add support to save/restore SPE profiling buffer controls Andrew Murray
2019-12-21 13:57   ` Marc Zyngier
2019-12-24 10:49     ` Andrew Murray
2019-12-24 15:17       ` Andrew Murray
2019-12-24 15:48         ` Marc Zyngier
2019-12-20 14:30 ` [PATCH v2 09/18] arm64: KVM: enable conditional save/restore full " Andrew Murray
2019-12-20 18:06   ` Mark Rutland
2019-12-24 12:15     ` Andrew Murray
2019-12-21 14:13   ` Marc Zyngier
2020-01-07 15:13     ` Andrew Murray
2020-01-08 11:17       ` Marc Zyngier
2020-01-08 11:58         ` Will Deacon
2020-01-08 12:36           ` Marc Zyngier
2020-01-08 13:10             ` Will Deacon
2020-01-09 11:23               ` Andrew Murray
2020-01-09 11:25                 ` Andrew Murray
2020-01-09 12:01                   ` Will Deacon [this message]
2020-01-10 10:54     ` Andrew Murray
2020-01-10 11:04       ` Andrew Murray
2020-01-10 11:51         ` Marc Zyngier
2020-01-10 12:12           ` Andrew Murray
2020-01-10 11:18       ` Marc Zyngier
2020-01-10 12:12         ` Andrew Murray
2020-01-10 13:34           ` Marc Zyngier
2019-12-20 14:30 ` [PATCH v2 10/18] arm64: KVM/debug: use EL1&0 stage 1 translation regime Andrew Murray
2019-12-22 10:34   ` Marc Zyngier
2019-12-24 11:11     ` Andrew Murray
2020-01-13 16:31     ` Andrew Murray
2020-01-15 14:03       ` Marc Zyngier
2019-12-20 14:30 ` [PATCH v2 11/18] KVM: arm64: don't trap Statistical Profiling controls to EL2 Andrew Murray
2019-12-20 18:08   ` Mark Rutland
2019-12-22 10:42   ` Marc Zyngier
2019-12-23 11:56     ` Andrew Murray
2019-12-23 12:05       ` Marc Zyngier
2019-12-23 12:10         ` Andrew Murray
2020-01-09 17:25           ` Andrew Murray
2020-01-09 17:42             ` Mark Rutland
2020-01-09 17:46               ` Andrew Murray
2019-12-20 14:30 ` [PATCH v2 12/18] KVM: arm64: add a new vcpu device control group for SPEv1 Andrew Murray
2019-12-22 11:03   ` Marc Zyngier
2019-12-24 12:30     ` Andrew Murray
2019-12-20 14:30 ` [PATCH v2 13/18] perf: arm_spe: Add KVM structure for obtaining IRQ info Andrew Murray
2019-12-22 11:24   ` Marc Zyngier
2019-12-24 12:35     ` Andrew Murray
2019-12-20 14:30 ` [PATCH v2 14/18] KVM: arm64: spe: Provide guest virtual interrupts for SPE Andrew Murray
2019-12-22 12:07   ` Marc Zyngier
2019-12-24 11:50     ` Andrew Murray
2019-12-24 12:42       ` Marc Zyngier
2019-12-24 13:08         ` Andrew Murray
2019-12-24 13:22           ` Marc Zyngier
2019-12-24 13:36             ` Andrew Murray
2019-12-24 13:46               ` Marc Zyngier
2019-12-20 14:30 ` [PATCH v2 15/18] perf: arm_spe: Handle guest/host exclusion flags Andrew Murray
2019-12-20 18:10   ` Mark Rutland
2019-12-22 12:10   ` Marc Zyngier
2019-12-23 12:10     ` Andrew Murray
2019-12-23 12:18       ` Marc Zyngier
2019-12-20 14:30 ` [PATCH v2 16/18] KVM: arm64: enable SPE support Andrew Murray
2019-12-20 14:30 ` [PATCH v2 17/18, KVMTOOL] update_headers: Sync kvm UAPI headers with linux v5.5-rc2 Andrew Murray
2019-12-20 14:30 ` [PATCH v2 18/18, KVMTOOL] kvm: add a vcpu feature for SPEv1 support Andrew Murray
2019-12-20 17:55 ` [PATCH v2 00/18] arm64: KVM: add SPE profiling support Mark Rutland
2019-12-24 12:54   ` Andrew Murray
2019-12-21 10:48 ` Marc Zyngier
2019-12-22 12:22   ` Marc Zyngier
2019-12-24 12:56     ` Andrew Murray

Reply instructions:

You may reply publically 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=20200109120139.GA7512@willie-the-truck \
    --to=will@kernel.org \
    --cc=Catalin.Marinas@arm.com \
    --cc=Sudeep.Holla@arm.com \
    --cc=andrew.murray@arm.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maz@kernel.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

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git