public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Vitaly Kuznetsov <vkuznets@redhat.com>
To: kvm@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>,
	Marcelo Tosatti <mtosatti@redhat.com>
Subject: [PATCH v2 2/4] KVM: x86: hyper-v: Prevent using not-yet-updated TSC page by secondary CPUs
Date: Tue, 16 Mar 2021 15:37:34 +0100	[thread overview]
Message-ID: <20210316143736.964151-3-vkuznets@redhat.com> (raw)
In-Reply-To: <20210316143736.964151-1-vkuznets@redhat.com>

When KVM_REQ_MASTERCLOCK_UPDATE request is issued (e.g. after migration)
we need to make sure no vCPU sees stale values in PV clock structures and
thus all vCPUs are kicked with KVM_REQ_CLOCK_UPDATE. Hyper-V TSC page
clocksource is global and kvm_guest_time_update() only updates in on vCPU0
but this is not entirely correct: nothing blocks some other vCPU from
entering the guest before we finish the update on CPU0 and it can read
stale values from the page.

Invalidate TSC page in kvm_gen_update_masterclock() to switch all vCPUs
to using MSR based clocksource (HV_X64_MSR_TIME_REF_COUNT).

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
 arch/x86/kvm/hyperv.c | 23 +++++++++++++++++++++++
 arch/x86/kvm/hyperv.h |  1 +
 arch/x86/kvm/x86.c    |  2 ++
 3 files changed, 26 insertions(+)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index eefb85b86fe8..a0e3c49233d4 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1137,6 +1137,29 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	mutex_unlock(&hv->hv_lock);
 }
 
+void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
+{
+	struct kvm_hv *hv = to_kvm_hv(kvm);
+	u64 gfn;
+
+	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+		return;
+
+	mutex_lock(&hv->hv_lock);
+
+	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+		goto out_unlock;
+
+	gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
+
+	hv->tsc_ref.tsc_sequence = 0;
+	kvm_write_guest(kvm, gfn_to_gpa(gfn),
+			&hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence));
+
+out_unlock:
+	mutex_unlock(&hv->hv_lock);
+}
+
 static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 			     bool host)
 {
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index e951af1fcb2c..60547d5cb6d7 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -133,6 +133,7 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu);
 
 void kvm_hv_setup_tsc_page(struct kvm *kvm,
 			   struct pvclock_vcpu_time_info *hv_clock);
+void kvm_hv_invalidate_tsc_page(struct kvm *kvm);
 
 void kvm_hv_init_vm(struct kvm *kvm);
 void kvm_hv_destroy_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 47e021bdcc94..a5c5b38735e1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2551,6 +2551,8 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	struct kvm_arch *ka = &kvm->arch;
 
+	kvm_hv_invalidate_tsc_page(kvm);
+
 	spin_lock(&ka->pvclock_gtod_sync_lock);
 	kvm_make_mclock_inprogress_request(kvm);
 	/* no guest entries from this point */
-- 
2.30.2


  parent reply	other threads:[~2021-03-16 14:38 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-16 14:37 [PATCH v2 0/4] KVM: x86: hyper-v: TSC page fixes Vitaly Kuznetsov
2021-03-16 14:37 ` [PATCH v2 1/4] KVM: x86: hyper-v: Limit guest to writing zero to HV_X64_MSR_TSC_EMULATION_STATUS Vitaly Kuznetsov
2021-03-16 14:37 ` Vitaly Kuznetsov [this message]
2021-03-18 17:02   ` [PATCH v2 2/4] KVM: x86: hyper-v: Prevent using not-yet-updated TSC page by secondary CPUs Marcelo Tosatti
2021-03-18 18:04     ` Marcelo Tosatti
2021-03-18 18:05       ` Paolo Bonzini
2021-03-18 18:30         ` Marcelo Tosatti
2021-03-19  9:29           ` Vitaly Kuznetsov
2021-03-16 14:37 ` [PATCH v2 3/4] KVM: x86: hyper-v: Track Hyper-V TSC page status Vitaly Kuznetsov
2021-03-17  8:07   ` Paolo Bonzini
2021-03-17 11:19     ` [PATCH v2 5/4] KVM: x86: hyper-v: Briefly document enum hv_tsc_page_status Vitaly Kuznetsov
2021-03-16 14:37 ` [PATCH v2 4/4] KVM: x86: hyper-v: Don't touch TSC page values when guest opted for re-enlightenment Vitaly Kuznetsov
2021-03-18 14:09 ` [PATCH v2 6/4] selftests: kvm: Add basic Hyper-V clocksources tests Vitaly Kuznetsov
2021-03-18 14:26   ` Paolo Bonzini
2021-03-18 14:52     ` Vitaly Kuznetsov
2021-03-18 15:01       ` Paolo Bonzini
2021-03-18 15:23         ` Vitaly Kuznetsov
2021-03-18 15:27   ` Paolo Bonzini
2021-03-18 16:57   ` Marcelo Tosatti
2021-03-18 17:50     ` Paolo Bonzini
2021-03-18 17:55       ` Marcelo Tosatti
2021-03-19  9:35         ` Vitaly Kuznetsov

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=20210316143736.964151-3-vkuznets@redhat.com \
    --to=vkuznets@redhat.com \
    --cc=jmattson@google.com \
    --cc=kvm@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=seanjc@google.com \
    --cc=wanpengli@tencent.com \
    /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