From: Paolo Bonzini <pbonzini@redhat.com>
To: Oliver Upton <oupton@google.com>,
kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu
Cc: Sean Christopherson <seanjc@google.com>,
Marc Zyngier <maz@kernel.org>, Peter Shier <pshier@google.com>,
Jim Mattson <jmattson@google.com>,
David Matlack <dmatlack@google.com>,
Ricardo Koller <ricarkol@google.com>,
Jing Zhang <jingzhangos@google.com>,
Raghavendra Rao Anata <rananta@google.com>,
James Morse <james.morse@arm.com>,
Alexandru Elisei <alexandru.elisei@arm.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
linux-arm-kernel@lists.infradead.org,
Andrew Jones <drjones@redhat.com>, Will Deacon <will@kernel.org>,
Catalin Marinas <catalin.marinas@arm.com>
Subject: Re: [PATCH v8 5/7] kvm: x86: protect masterclock with a seqcount
Date: Fri, 24 Sep 2021 18:42:26 +0200 [thread overview]
Message-ID: <e6af1bc9-6018-6fd7-fcc1-098b8af0ecdc@redhat.com> (raw)
In-Reply-To: <20210916181538.968978-6-oupton@google.com>
On 16/09/21 20:15, Oliver Upton wrote:
> From: Paolo Bonzini<pbonzini@redhat.com>
>
> Protect the reference point for kvmclock with a seqcount, so that
> kvmclock updates for all vCPUs can proceed in parallel. Xen runstate
> updates will also run in parallel and not bounce the kvmclock cacheline.
>
> nr_vcpus_matched_tsc is updated outside pvclock_update_vm_gtod_copy
> though, so a spinlock must be kept for that one.
>
> Signed-off-by: Paolo Bonzini<pbonzini@redhat.com>
> [Oliver - drop unused locals, don't double acquire tsc_write_lock]
> Signed-off-by: Oliver Upton<oupton@google.com>
> ---
This needs a small adjustment:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 07d00e711043..b0c21d42f453 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11289,6 +11289,7 @@ void kvm_arch_free_vm(struct kvm *kvm)
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
int ret;
+ unsigned long flags;
if (type)
return -EINVAL;
@@ -11314,7 +11315,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
mutex_init(&kvm->arch.apic_map_lock);
seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock);
kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
+
+ raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
+ raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
kvm->arch.guest_can_read_msr_platform_info = true;
WARNING: multiple messages have this Message-ID (diff)
From: Paolo Bonzini <pbonzini@redhat.com>
To: Oliver Upton <oupton@google.com>,
kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu
Cc: Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>, Peter Shier <pshier@google.com>,
Marc Zyngier <maz@kernel.org>,
David Matlack <dmatlack@google.com>,
linux-arm-kernel@lists.infradead.org,
Jim Mattson <jmattson@google.com>
Subject: Re: [PATCH v8 5/7] kvm: x86: protect masterclock with a seqcount
Date: Fri, 24 Sep 2021 18:42:26 +0200 [thread overview]
Message-ID: <e6af1bc9-6018-6fd7-fcc1-098b8af0ecdc@redhat.com> (raw)
In-Reply-To: <20210916181538.968978-6-oupton@google.com>
On 16/09/21 20:15, Oliver Upton wrote:
> From: Paolo Bonzini<pbonzini@redhat.com>
>
> Protect the reference point for kvmclock with a seqcount, so that
> kvmclock updates for all vCPUs can proceed in parallel. Xen runstate
> updates will also run in parallel and not bounce the kvmclock cacheline.
>
> nr_vcpus_matched_tsc is updated outside pvclock_update_vm_gtod_copy
> though, so a spinlock must be kept for that one.
>
> Signed-off-by: Paolo Bonzini<pbonzini@redhat.com>
> [Oliver - drop unused locals, don't double acquire tsc_write_lock]
> Signed-off-by: Oliver Upton<oupton@google.com>
> ---
This needs a small adjustment:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 07d00e711043..b0c21d42f453 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11289,6 +11289,7 @@ void kvm_arch_free_vm(struct kvm *kvm)
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
int ret;
+ unsigned long flags;
if (type)
return -EINVAL;
@@ -11314,7 +11315,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
mutex_init(&kvm->arch.apic_map_lock);
seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock);
kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
+
+ raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
+ raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
kvm->arch.guest_can_read_msr_platform_info = true;
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
WARNING: multiple messages have this Message-ID (diff)
From: Paolo Bonzini <pbonzini@redhat.com>
To: Oliver Upton <oupton@google.com>,
kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu
Cc: Sean Christopherson <seanjc@google.com>,
Marc Zyngier <maz@kernel.org>, Peter Shier <pshier@google.com>,
Jim Mattson <jmattson@google.com>,
David Matlack <dmatlack@google.com>,
Ricardo Koller <ricarkol@google.com>,
Jing Zhang <jingzhangos@google.com>,
Raghavendra Rao Anata <rananta@google.com>,
James Morse <james.morse@arm.com>,
Alexandru Elisei <alexandru.elisei@arm.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
linux-arm-kernel@lists.infradead.org,
Andrew Jones <drjones@redhat.com>, Will Deacon <will@kernel.org>,
Catalin Marinas <catalin.marinas@arm.com>
Subject: Re: [PATCH v8 5/7] kvm: x86: protect masterclock with a seqcount
Date: Fri, 24 Sep 2021 18:42:26 +0200 [thread overview]
Message-ID: <e6af1bc9-6018-6fd7-fcc1-098b8af0ecdc@redhat.com> (raw)
In-Reply-To: <20210916181538.968978-6-oupton@google.com>
On 16/09/21 20:15, Oliver Upton wrote:
> From: Paolo Bonzini<pbonzini@redhat.com>
>
> Protect the reference point for kvmclock with a seqcount, so that
> kvmclock updates for all vCPUs can proceed in parallel. Xen runstate
> updates will also run in parallel and not bounce the kvmclock cacheline.
>
> nr_vcpus_matched_tsc is updated outside pvclock_update_vm_gtod_copy
> though, so a spinlock must be kept for that one.
>
> Signed-off-by: Paolo Bonzini<pbonzini@redhat.com>
> [Oliver - drop unused locals, don't double acquire tsc_write_lock]
> Signed-off-by: Oliver Upton<oupton@google.com>
> ---
This needs a small adjustment:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 07d00e711043..b0c21d42f453 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11289,6 +11289,7 @@ void kvm_arch_free_vm(struct kvm *kvm)
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
int ret;
+ unsigned long flags;
if (type)
return -EINVAL;
@@ -11314,7 +11315,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
mutex_init(&kvm->arch.apic_map_lock);
seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock);
kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
+
+ raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
+ raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
kvm->arch.guest_can_read_msr_platform_info = true;
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2021-09-24 16:42 UTC|newest]
Thread overview: 113+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-16 18:15 [PATCH v8 0/7] KVM: x86: Add idempotent controls for migrating system counter state Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` [PATCH v8 1/7] kvm: x86: abstract locking around pvclock_update_vm_gtod_copy Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` [PATCH v8 2/7] KVM: x86: extract KVM_GET_CLOCK/KVM_SET_CLOCK to separate functions Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` [PATCH v8 3/7] KVM: x86: Fix potential race in KVM_GET_CLOCK Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-29 13:33 ` Marcelo Tosatti
2021-09-29 13:33 ` Marcelo Tosatti
2021-09-29 13:33 ` Marcelo Tosatti
2021-09-16 18:15 ` [PATCH v8 4/7] KVM: x86: Report host tsc and realtime values " Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-28 18:53 ` Marcelo Tosatti
2021-09-28 18:53 ` Marcelo Tosatti
2021-09-28 18:53 ` Marcelo Tosatti
2021-09-29 11:20 ` Paolo Bonzini
2021-09-29 11:20 ` Paolo Bonzini
2021-09-29 11:20 ` Paolo Bonzini
2021-09-29 18:56 ` Marcelo Tosatti
2021-09-29 18:56 ` Marcelo Tosatti
2021-09-29 18:56 ` Marcelo Tosatti
2021-09-30 19:21 ` Marcelo Tosatti
2021-09-30 19:21 ` Marcelo Tosatti
2021-09-30 19:21 ` Marcelo Tosatti
2021-09-30 23:02 ` Thomas Gleixner
2021-09-30 23:02 ` Thomas Gleixner
2021-09-30 23:02 ` Thomas Gleixner
2021-10-01 12:05 ` Marcelo Tosatti
2021-10-01 12:05 ` Marcelo Tosatti
2021-10-01 12:05 ` Marcelo Tosatti
2021-10-01 12:10 ` Marcelo Tosatti
2021-10-01 12:10 ` Marcelo Tosatti
2021-10-01 12:10 ` Marcelo Tosatti
2021-10-01 19:59 ` Thomas Gleixner
2021-10-01 19:59 ` Thomas Gleixner
2021-10-01 19:59 ` Thomas Gleixner
2021-10-01 21:03 ` Oliver Upton
2021-10-01 21:03 ` Oliver Upton
2021-10-01 21:03 ` Oliver Upton
2021-10-01 14:17 ` Paolo Bonzini
2021-10-01 14:17 ` Paolo Bonzini
2021-10-01 14:17 ` Paolo Bonzini
2021-10-01 14:39 ` Paolo Bonzini
2021-10-01 14:39 ` Paolo Bonzini
2021-10-01 14:39 ` Paolo Bonzini
2021-10-01 14:41 ` Paolo Bonzini
2021-10-01 14:41 ` Paolo Bonzini
2021-10-01 14:41 ` Paolo Bonzini
2021-10-01 15:39 ` Oliver Upton
2021-10-01 15:39 ` Oliver Upton
2021-10-01 15:39 ` Oliver Upton
2021-10-01 16:42 ` Paolo Bonzini
2021-10-01 16:42 ` Paolo Bonzini
2021-10-01 16:42 ` Paolo Bonzini
2024-01-17 14:28 ` David Woodhouse
2024-01-17 14:28 ` David Woodhouse
2021-09-16 18:15 ` [PATCH v8 5/7] kvm: x86: protect masterclock with a seqcount Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-24 16:42 ` Paolo Bonzini [this message]
2021-09-24 16:42 ` Paolo Bonzini
2021-09-24 16:42 ` Paolo Bonzini
2021-09-30 17:51 ` Marcelo Tosatti
2021-09-30 17:51 ` Marcelo Tosatti
2021-09-30 17:51 ` Marcelo Tosatti
2021-10-01 16:48 ` Paolo Bonzini
2021-10-01 16:48 ` Paolo Bonzini
2021-10-01 16:48 ` Paolo Bonzini
2021-09-16 18:15 ` [PATCH v8 6/7] KVM: x86: Refactor tsc synchronization code Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` [PATCH v8 7/7] KVM: x86: Expose TSC offset controls to userspace Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-16 18:15 ` Oliver Upton
2021-09-30 19:14 ` Marcelo Tosatti
2021-09-30 19:14 ` Marcelo Tosatti
2021-09-30 19:14 ` Marcelo Tosatti
2021-10-01 9:17 ` Paolo Bonzini
2021-10-01 9:17 ` Paolo Bonzini
2021-10-01 9:17 ` Paolo Bonzini
2021-10-01 10:32 ` Marcelo Tosatti
2021-10-01 10:32 ` Marcelo Tosatti
2021-10-01 10:32 ` Marcelo Tosatti
2021-10-01 15:12 ` Paolo Bonzini
2021-10-01 15:12 ` Paolo Bonzini
2021-10-01 15:12 ` Paolo Bonzini
2021-10-01 19:11 ` Marcelo Tosatti
2021-10-01 19:11 ` Marcelo Tosatti
2021-10-01 19:11 ` Marcelo Tosatti
2021-10-01 19:33 ` Oliver Upton
2021-10-01 19:33 ` Oliver Upton
2021-10-01 19:33 ` Oliver Upton
2021-10-04 14:30 ` Marcelo Tosatti
2021-10-04 14:30 ` Marcelo Tosatti
2021-10-04 14:30 ` Marcelo Tosatti
2021-10-04 11:44 ` Paolo Bonzini
2021-10-04 11:44 ` Paolo Bonzini
2021-10-04 11:44 ` Paolo Bonzini
2021-10-05 15:22 ` Sean Christopherson
2021-10-05 15:22 ` Sean Christopherson
2021-10-05 15:22 ` Sean Christopherson
2022-02-23 10:02 ` David Woodhouse
2022-02-23 10:02 ` David Woodhouse
2022-02-23 10:02 ` David Woodhouse
2021-09-24 16:43 ` [PATCH v8 0/7] KVM: x86: Add idempotent controls for migrating system counter state Paolo Bonzini
2021-09-24 16:43 ` Paolo Bonzini
2021-09-24 16:43 ` Paolo Bonzini
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=e6af1bc9-6018-6fd7-fcc1-098b8af0ecdc@redhat.com \
--to=pbonzini@redhat.com \
--cc=alexandru.elisei@arm.com \
--cc=catalin.marinas@arm.com \
--cc=dmatlack@google.com \
--cc=drjones@redhat.com \
--cc=james.morse@arm.com \
--cc=jingzhangos@google.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=maz@kernel.org \
--cc=oupton@google.com \
--cc=pshier@google.com \
--cc=rananta@google.com \
--cc=ricarkol@google.com \
--cc=seanjc@google.com \
--cc=suzuki.poulose@arm.com \
--cc=will@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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.