From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=90.155.92.199 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1794420579; b=EWA9rnKJLFLgV8xgTJ8onJvV41Ewz87trV9e87VGWtQYjTiWsLpbbe/hmrvM5qlybO3B jcs3IkV6POxIu3CGoA7gTDIaY4INeDrdf2Jk85ZWvZ4mKe90QlB+BRVCdBY+QT3xoCmqM 0LSGTNzz6zzGvDiM/ELIRx0M/xVQsdeW1CbISebGGxNGxgm8epI+AEgoiLNxiXO4gCW8m 4GzQ3Ms49LRC57pHaacbafcw8WLr3TvpesP4SIKaUiGWIhmd6uOWUncjLDkgoGnlSvyn5 5O2OOARA3uEwwu4A6Bv3Dq0FZ0tCAgLjLZWWZNRB/0OA8Hf4dtI+GoKFaoKPJ7SR3/Q== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1794420579; 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=hG5BZ0GH5lCV4VFdff4Rs7YNoTlgAIqSVWn/Ib3MefQ=; b=iQ70Mf5NefazcI0Zz5DLds+CbEGfqOexyTEoV/R/hQhkQWz84nc7P17clbFx6e0HPujU fMNHzeMAGnu142YvhfiaGNraJ8MMTL12tZWd3g7Oay/UN2WbN0IxnYp6oI2FWII2daXUf Z7Ppwd/BmIbK5QCerJFDI6B9zsbnhA8npfQ1HtmZY/ZVQLcIKjESsCTzqBztfcb8/+uzZ wlEl9M6suW1LlFe6UWPGtzHpXV6DZjz9TXOztJg0aMwJJbBsdsOKuv2u37Rd240aYVx/W Tc79e3mGAY3bvmK0cAS7J8/tFLQTo89Tk+rOPYF4MI4zbtgafJ+w6cPkN4MJgkmyzkg== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=infradead.org; spf=none smtp.mailfrom=desiato.srs.infradead.org; dkim=pass header.d=infradead.org header.i=@infradead.org header.a=rsa-sha256 header.s=desiato.20200630 header.b="pRsnq65/"; arc=none smtp.remote-ip=90.155.92.199 Received: from desiato.infradead.org (desiato.infradead.org [90.155.92.199]) (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 189FE606C14D; Wed, 11 Nov 2026 18:09:38 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 189FE606C14D 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=desiato.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=desiato.20200630 header.b=pRsnq65/ DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=desiato.20200630; 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=hG5BZ0GH5lCV4VFdff4Rs7YNoTlgAIqSVWn/Ib3MefQ=; b=pRsnq65/l31Fvq0M3F515Ivmye 7B0IxhPzrQQtPyuijoD+5M3Q6pE/cLuHz2hllAyF+agQjSeT1wDJ8IuYYGN2IUV65R+GX+bsfuG93 JeuV7/MRYvElaaE03jdNpr6RhCDzdJllckcuEMQCqPmch4EG+NxRnh0m93XikBJgHuLr6i97TwuDm osXLbtdpBqVwanq2mJHfx1gHaZFzCmH1FwZSahqt3vP2MDcYv2vON3rOCi+52r+e8lzwHNfBsg3b3 Iqo5FSqVR605u9tXoIZDiz4amrq/hWDHqrRM9LSrMKubSTM16fp7EV2jVRUl7pfTMXdxEhGMff1vL zEhEYhlQ==; Received: from [2001:8b0:10b:1::425] (helo=i7.infradead.org) by desiato.infradead.org with esmtpsa (Exim 4.100.1 #2 (Red Hat Linux)) id 1xRClB-00000009PvO-3EGv; Wed, 11 Nov 2026 18:09:31 +0000 Received: from dwoodhou by i7.infradead.org with local (Exim 4.99.5 #2 (Red Hat Linux)) id 1xRCl9-0000000HWsi-0xEB; Wed, 11 Nov 2026 18:09:23 +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 v13 11/26] KVM: x86: Cache host vclock_mode for masterclock eligibility checks Date: Wed, 11 Nov 2026 10:09:07 -0800 Message-ID: <20261111180922.4177927-12-dwmw2@infradead.org> X-Mailer: git-send-email 2.55.0 In-Reply-To: <20261111180922.4177927-1-dwmw2@infradead.org> References: <20261111180922.4177927-1-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 desiato.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 cf35363366f1..f7dd4129dc51 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1224,6 +1224,8 @@ 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; @@ -1253,7 +1255,6 @@ 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; @@ -1306,8 +1307,9 @@ 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, @@ -1320,7 +1322,7 @@ 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, @@ -1491,7 +1493,7 @@ 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(); @@ -1935,7 +1937,6 @@ 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); @@ -1975,9 +1976,9 @@ 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 } @@ -7452,17 +7453,23 @@ 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