From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=90.155.50.34 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1794187280; b=1TLF5MGHP9wLe0iKxWwymF3cbtl15QWyCDT8nycwgTO+q5W5LK1qRhwXUI6Ase9Rm6wX YjUM/FGlI4kn0dpE5xy3+/OVS8/Q08RgEVkRhjSXk7Gf1oNm5wIF1an73Qz2A5VkwW4gg UFMppvUI6c3hE9aK7EapxOT06ftn9eivqLh8W6bb5iW+4oHeW6a4W9fwFTJMEpuIRIt0u 9x5hgKLP7CItA+98wBasCbIc/GUSnajtDIBkS1qs5N2g9ixc6ArTgUZF404PiKzTfOa77 flK3kV//SryFRiAPo+QaWrs9JQpp86jz6LOYN1+ISjTM0KgVf8XBqznEc9FQK52X9sg== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1794187280; h=DMARC-Filter:DKIM-Signature:Received:Received:From:To:Cc:Subject: Date:Message-ID:X-Mailer:In-Reply-To:References:MIME-Version: Content-Type:Content-Transfer-Encoding:Sender:X-SRS-Rewrite; bh=o4iYp1mgiuHJ22mIDE1+YNcbZQqDTtCDvucolqruxaE=; b=ln3GbimlRiZX4I5ga8y6vjP5uKKEYMr5TZ8ngpvmx1cfc4LrIWnprFCTpCrczN/RDQ1a 3XT92+kpeWroP10DysPtCYZHhQZWIEtDmM1lU7gBONXa0UWQ6kfehQ5rSFtBuEGdYjIsO sA1vsXwAxVa0nt8UMkYGo063lG5G146/XbQ4XO0tzwEpAStbgZPqy+DrOOIakH6LYXlGI yhv/nrXb35IWN0Re/mOKp+I7l2xfv1F7WaGrz8oonYyUGMxFUwpN1/SA8R9DjluPk9Loo j7oXdgquftqkH9S5M2HFUkqRdRmBr+d+G4SXtqRGce18RMZcIIrzKzrbPzwA0Msi3Qw== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=infradead.org; spf=none smtp.mailfrom=casper.srs.infradead.org; dkim=pass header.d=infradead.org header.i=@infradead.org header.a=rsa-sha256 header.s=casper.20170209 header.b=Z8CMFoCM; arc=none smtp.remote-ip=90.155.50.34 Received: from casper.infradead.org (casper.infradead.org [90.155.50.34]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 713B2606A322; Mon, 9 Nov 2026 01:21:17 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 713B2606A322 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=infradead.org Authentication-Results: smtp.subspace.kernel.org; spf=none smtp.mailfrom=casper.srs.infradead.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=infradead.org header.i=@infradead.org header.a=rsa-sha256 header.s=casper.20170209 header.b=Z8CMFoCM DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=casper.20170209; h=Sender:Content-Transfer-Encoding: Content-Type:MIME-Version:References:In-Reply-To:Message-ID:Date:Subject:Cc: To:From:Reply-To:Content-ID:Content-Description; bh=o4iYp1mgiuHJ22mIDE1+YNcbZQqDTtCDvucolqruxaE=; b=Z8CMFoCMwHNkaDy4xwo7g9Tmfd tEwNb6kGCLWxN0HFFV7k4VHAgrkwh4xZ10twvER4YDsWRNU7lDrIrWJVB9GEAvPSoMKwxbphrCVg1 1JGCz0nSNZquQsoMn1Kt4Cv8ecpUsrPCB7TTO1LOr9YJ1YRS8QKOLbf5EnkpN3sNLCXajNGREffp+ VrUkl4ivaMoP1RzkF36Ret4vhIuuveiRg7A6jj8iPWsrIT/wmWo4+tloIbP98O6aIuEAxrzwI7+Mu E7iwDwmUAL3iXuSad6DonGqnkgDshF30+l/0tqo6hRb5JC9/SY6VMj5PAvsgEDP1FI4v9G83nxEPi X0Yzfb4g==; Received: from [2001:8b0:10b:1::425] (helo=i7.infradead.org) by casper.infradead.org with esmtpsa (Exim 4.100.1 #2 (Red Hat Linux)) id 1xQE4P-00000007Pvy-05vk; Mon, 09 Nov 2026 01:21:13 +0000 Received: from dwoodhou by i7.infradead.org with local (Exim 4.99.5 #2 (Red Hat Linux)) id 1xQE4O-0000000EKUd-3UqI; Mon, 09 Nov 2026 01:21:12 +0000 From: David Woodhouse To: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org, linux-doc@vger.kernel.org, xen-devel@lists.xenproject.org, x86@kernel.org, Paolo Bonzini , Sean Christopherson , Paul Durrant , Vitaly Kuznetsov , Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "H . Peter Anvin" , Jonathan Corbet , Shuah Khan , Juergen Gross , Boris Ostrovsky , Jonathan Cameron , Sascha Bischoff , Marc Zyngier , Joey Gouly , Jack Allister , Dongli Zhang , joe.jin@oracle.com, David Woodhouse Subject: [PATCH v12 09/24] KVM: x86: Cache host vclock_mode for masterclock eligibility checks Date: Sun, 8 Nov 2026 17:20:55 -0800 Message-ID: <20261109012112.3415328-10-dwmw2@infradead.org> X-Mailer: git-send-email 2.55.0 In-Reply-To: <20261109012112.3415328-1-dwmw2@infradead.org> References: <20261109012112.3415328-1-dwmw2@infradead.org> X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: David Woodhouse X-SRS-Rewrite: SMTP reverse-path rewritten from by casper.infradead.org. See http://www.infradead.org/rpr.html From: David Woodhouse The remaining users of pvclock_gtod_data only need to know whether the host clocksource is TSC-based. Cache the vclock_mode value in a simple kvm_host_vclock_mode variable, updated by the pvclock_gtod_notify callback, and use gtod_is_based_on_tsc() for eligibility checks. This is inherently racy (as it always was — kvm_track_tsc_matching never held the gtod seqcount), relying on eventual consistency: the notifier fires on every timekeeping update and will correct any transient inconsistency within one tick. Signed-off-by: David Woodhouse --- arch/x86/kvm/x86.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b47c36265c2f..0ed3d2549ac3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1187,6 +1187,8 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) } #ifdef CONFIG_X86_64 +static int kvm_host_vclock_mode; + static inline bool gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; @@ -1216,7 +1218,6 @@ static bool kvm_use_master_clock(struct kvm *kvm) static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool update_mclock) { struct kvm_arch *ka = &vcpu->kvm->arch; - struct pvclock_gtod_data *gtod = &pvclock_gtod_data; bool prev_matched_tsc = ka->all_vcpus_matched_tsc; bool prev_matched_freq = ka->all_vcpus_matched_freq; @@ -1269,8 +1270,9 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool update_mclock) * are fine — each vCPU's pvclock has its own tsc_timestamp that * accounts for its offset. */ + int host_vclock_mode = READ_ONCE(kvm_host_vclock_mode); bool use_master_clock = kvm_use_master_clock(vcpu->kvm) && - gtod_is_based_on_tsc(gtod->clock.vclock_mode); + gtod_is_based_on_tsc(host_vclock_mode); /* * Request a masterclock update if needed: toggling master clock, @@ -1283,7 +1285,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool update_mclock) trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, atomic_read(&vcpu->kvm->online_vcpus), - ka->use_master_clock, gtod->clock.vclock_mode); + ka->use_master_clock, host_vclock_mode); } #else static inline void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, @@ -1454,7 +1456,7 @@ static inline bool kvm_check_tsc_unstable(void) * TSC is marked unstable when we're running on Hyper-V, * 'TSC page' clocksource is good. */ - if (pvclock_gtod_data.clock.vclock_mode == VDSO_CLOCKMODE_HVCLOCK) + if (READ_ONCE(kvm_host_vclock_mode) == VDSO_CLOCKMODE_HVCLOCK) return false; #endif return check_tsc_unstable(); @@ -1788,7 +1790,6 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) { #ifdef CONFIG_X86_64 struct kvm_arch *ka = &kvm->arch; - int vclock_mode; bool host_tsc_clocksource; lockdep_assert_held(&kvm->arch.tsc_write_lock); @@ -1828,9 +1829,9 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) ka->use_master_clock = false; } - vclock_mode = pvclock_gtod_data.clock.vclock_mode; - trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode, - ka->all_vcpus_matched_freq); + trace_kvm_update_master_clock(ka->use_master_clock, + READ_ONCE(kvm_host_vclock_mode), + ka->all_vcpus_matched_freq); #endif } @@ -7210,17 +7211,23 @@ static DEFINE_IRQ_WORK(pvclock_irq_work, pvclock_irq_work_fn); static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, void *priv) { - struct pvclock_gtod_data *gtod = &pvclock_gtod_data; struct timekeeper *tk = priv; update_pvclock_gtod(tk); + /* + * Pairs with the READ_ONCE() in the lockless readers; the race is + * benign by design, relying on eventual consistency (the notifier + * fires on every timekeeping update). + */ + WRITE_ONCE(kvm_host_vclock_mode, tk->tkr_mono.clock->vdso_clock_mode); + /* * Disable master clock if host does not trust, or does not use, * TSC based clocksource. Delegate queue_work() to irq_work as * this is invoked with tk_core.seq write held. */ - if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) && + if (!gtod_is_based_on_tsc(kvm_host_vclock_mode) && atomic_read(&kvm_guest_has_master_clock) != 0) irq_work_queue(&pvclock_irq_work); return 0; -- 2.43.0