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=1793893809; b=4UrnIUbkR6TElT627Rj3ddp3NGmwpMY+iSEEfOMJpKBhzG7HW1/I5XDGgq5AveaFqxhe R49ztG8nSk784jJPnaHa5zjlCRXLqCc5i4YhBx5zH9U90q6gjSsU0EMuKPk9RoftyNUPU oL3yvDt1O15oPh2I67PD9hHWu5v73SjQU4c7/m35kjGUrti2D1YEO1mLIY3eYqotOUMnZ sxKEZY/WlDjJWpE3TgOwNfPpOX30/5mypAdAAvAcNKwx7HFmayfLoUCnluNtX7m6fr4Wb aNtV2bjFKWKAR4dn4paw59d+mzM6WiQYld26HOZe3h5S3ArVNVoy9bLdF33CG1rV5SA== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1793893809; 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=SBqwWuzZUe9tKH8X7ZE6UU3BvbQWCNJQkaJJqsbprJg=; b=YrOkSLhrsdHO7trgk7J5m4EreIdJkUvCYipmvkaOAHsTVzL/nYEVhHAEfJmiuThs5ylM ZgraSkC6MRF7kX8q7c/n9MQZ0AQKSSVs3pVb2s4rKUqqXAj23PtIxswE812laqj7CvNm5 X2wgOaHHAeUC1BO4uXzRNczzS2x0nKWr3GTXPf70sEXgvz74Nqi1Cl1/8StaiWHk7RTaN hEJAhM/dxopujREmP63LHlKmLH/NKe8bhe04llDqCLYj4gJFmAcMh9PszfeG0JQ1JMIev KWkZ37OVAGM74Mh836tTGpmn0fIBS0FFXkjAbDA6zv8WxaLrbaVDlnnYPxU3ohBHbEA== 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=FodKgNUh; 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 B213E60A6F7E; Thu, 5 Nov 2026 15:50:05 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org B213E60A6F7E 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, unprotected) header.d=infradead.org header.i=@infradead.org header.a=rsa-sha256 header.s=casper.20170209 header.b=FodKgNUh 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=SBqwWuzZUe9tKH8X7ZE6UU3BvbQWCNJQkaJJqsbprJg=; b=FodKgNUhaEcN6KVT7o+1tHJEEr wKhNLefbLxXuApYmEFzXlgF2ixoRX3JQFxnhrIMM3BtnHxxCq4DdbGnwD5qBiYMOZ5EhtouAZ4IM8 NEJbu820jzVuJPEaVRfm5DSeqHhKMfLoiAn7GBdLpVJ+d61VpXZNBRjNhd9oz7Q+cVLm+hJQT/nh3 G0Thelxcek6QXJkrZKwvEEdOyh1IhRf8U9g0raHyubWC1Zs9SBkKvqUSE912AJBmH2ek5gUoZAyCb RtPhXNGgFdKQ/BiXsjDCQyb0f9HNeT8esej0h2z0F07pPXkfwlhfdRIpfvcyfVo1kLTwGBTuNhnMk mIEwOwxQ==; 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 1xOziu-00000009aoo-0MW8; Thu, 05 Nov 2026 15:49:56 +0000 Received: from dwoodhou by i7.infradead.org with local (Exim 4.99.5 #2 (Red Hat Linux)) id 1xOzit-0000000AazI-3n30; Thu, 05 Nov 2026 15:49:55 +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 v11 09/23] KVM: x86: Cache host vclock_mode for masterclock eligibility checks Date: Thu, 5 Nov 2026 07:49:40 -0800 Message-ID: <20261105154955.2525419-10-dwmw2@infradead.org> X-Mailer: git-send-email 2.55.0 In-Reply-To: <20261105154955.2525419-1-dwmw2@infradead.org> References: <20261105154955.2525419-1-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 f551056d7274..e81e527e7b99 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1136,6 +1136,8 @@ 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; @@ -1165,7 +1167,6 @@ 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; /* @@ -1209,8 +1210,9 @@ 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, @@ -1223,7 +1225,7 @@ 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, @@ -1394,7 +1396,7 @@ 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(); @@ -1689,7 +1691,6 @@ 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); @@ -1729,9 +1730,9 @@ 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 } @@ -7089,17 +7090,23 @@ 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