Linux-HyperV List
 help / color / mirror / Atom feed
From: Sean Christopherson <seanjc@google.com>
To: Kiryl Shutsemau <kas@kernel.org>,
	Paolo Bonzini <pbonzini@redhat.com>,
	 Sean Christopherson <seanjc@google.com>,
	"K. Y. Srinivasan" <kys@microsoft.com>,
	 Haiyang Zhang <haiyangz@microsoft.com>,
	Wei Liu <wei.liu@kernel.org>,  Dexuan Cui <decui@microsoft.com>,
	Long Li <longli@microsoft.com>,
	 Ajay Kaher <ajay.kaher@broadcom.com>,
	Alexey Makhalov <alexey.makhalov@broadcom.com>,
	 Jan Kiszka <jan.kiszka@siemens.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	 Andy Lutomirski <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Juergen Gross <jgross@suse.com>,
	 Daniel Lezcano <daniel.lezcano@kernel.org>,
	Thomas Gleixner <tglx@kernel.org>,
	 John Stultz <jstultz@google.com>
Cc: Rick Edgecombe <rick.p.edgecombe@intel.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	 Broadcom internal kernel review list
	<bcm-kernel-feedback-list@broadcom.com>,
	 Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Stephen Boyd <sboyd@kernel.org>,
	x86@kernel.org,  linux-coco@lists.linux.dev, kvm@vger.kernel.org,
	linux-hyperv@vger.kernel.org,  virtualization@lists.linux.dev,
	linux-kernel@vger.kernel.org,  xen-devel@lists.xenproject.org,
	Michael Kelley <mhklinux@outlook.com>,
	 Tom Lendacky <thomas.lendacky@amd.com>,
	Nikunj A Dadhania <nikunj@amd.com>,
	 Thomas Gleixner <tglx@linutronix.de>,
	David Woodhouse <dwmw@amazon.co.uk>
Subject: [PATCH v3 27/41] x86/kvmclock: Enable kvmclock on APs during onlining if kvmclock isn't sched_clock
Date: Fri, 15 May 2026 12:19:28 -0700	[thread overview]
Message-ID: <20260515191942.1892718-28-seanjc@google.com> (raw)
In-Reply-To: <20260515191942.1892718-1-seanjc@google.com>

In anticipation of making x86_cpuinit.early_percpu_clock_init(), i.e.
kvm_setup_secondary_clock(), a dedicated sched_clock hook that will be
invoked if and only if kvmclock is set as sched_clock, ensure APs enable
their kvmclock during CPU online.  While a redundant write to the MSR is
technically ok, skip the registration when kvmclock is sched_clock so that
it's somewhat obvious that kvmclock *needs* to be enabled during early
bringup when it's being used as sched_clock.

Plumb in the BSP's resume path purely for documentation purposes.  Both
KVM (as-a-guest) and timekeeping/clocksource hook syscore_ops, and it's
not super obvious that using KVM's hooks would be flawed.  E.g. it would
work today, because KVM's hooks happen to run after/before timekeeping's
hooks during suspend/resume, but that's sheer dumb luck as the order in
which syscore_ops are invoked depends entirely on when a subsystem is
initialized and thus registers its hooks.

Opportunsitically make the registration messages more precise to help
debug issues where kvmclock is enabled too late.

Opportunstically WARN in kvmclock_{suspend,resume}() to harden against
future bugs.

Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_para.h |  2 ++
 arch/x86/kernel/kvm.c           | 24 +++++++++++-------
 arch/x86/kernel/kvmclock.c      | 44 +++++++++++++++++++++++++++------
 3 files changed, 53 insertions(+), 17 deletions(-)

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 2adba2aff539..17053d2bf270 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -120,6 +120,8 @@ static inline long kvm_sev_hypercall3(unsigned int nr, unsigned long p1,
 #ifdef CONFIG_KVM_GUEST
 enum kvm_guest_cpu_action {
 	KVM_GUEST_BSP_SUSPEND,
+	KVM_GUEST_BSP_RESUME,
+	KVM_GUEST_AP_ONLINE,
 	KVM_GUEST_AP_OFFLINE,
 	KVM_GUEST_SHUTDOWN,
 };
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 0131bc1cb459..65c787b1ea03 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -471,18 +471,24 @@ static void kvm_guest_cpu_offline(enum kvm_guest_cpu_action action)
 	kvmclock_cpu_action(action);
 }
 
+static int __kvm_cpu_online(unsigned int cpu, enum kvm_guest_cpu_action action)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	kvmclock_cpu_action(action);
+	kvm_guest_cpu_init();
+	local_irq_restore(flags);
+	return 0;
+}
+
+#ifdef CONFIG_SMP
+
 static int kvm_cpu_online(unsigned int cpu)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	kvm_guest_cpu_init();
-	local_irq_restore(flags);
-	return 0;
+	return __kvm_cpu_online(cpu, KVM_GUEST_AP_ONLINE);
 }
 
-#ifdef CONFIG_SMP
-
 static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
 
 static bool pv_tlb_flush_supported(void)
@@ -747,7 +753,7 @@ static int kvm_suspend(void *data)
 
 static void kvm_resume(void *data)
 {
-	kvm_cpu_online(raw_smp_processor_id());
+	__kvm_cpu_online(raw_smp_processor_id(), KVM_GUEST_BSP_RESUME);
 
 #ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
 	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index e7250d21c672..d3bb281c0805 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -53,6 +53,7 @@ static struct pvclock_vsyscall_time_info *hvclock_mem;
 DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
 EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu);
 
+static bool kvmclock_is_sched_clock;
 static bool kvmclock_suspended;
 
 /*
@@ -129,7 +130,7 @@ static void kvm_save_sched_clock_state(void)
 #ifdef CONFIG_SMP
 static void kvm_setup_secondary_clock(void)
 {
-	kvm_register_clock("secondary cpu clock");
+	kvm_register_clock("secondary cpu, sched_clock setup");
 }
 #endif
 
@@ -141,25 +142,51 @@ static void kvm_restore_sched_clock_state(void)
 
 static void kvmclock_suspend(struct clocksource *cs)
 {
+	if (WARN_ON_ONCE(kvmclock_is_sched_clock))
+		return;
+
 	kvmclock_suspended = true;
 	kvmclock_disable();
 }
 
 static void kvmclock_resume(struct clocksource *cs)
 {
+	if (WARN_ON_ONCE(kvmclock_is_sched_clock))
+		return;
+
 	kvmclock_suspended = false;
 	kvm_register_clock("primary cpu, clocksource resume");
 }
 
 void kvmclock_cpu_action(enum kvm_guest_cpu_action action)
 {
-	/*
-	 * Don't disable kvmclock on the BSP during suspend.  If kvmclock is
-	 * being used for sched_clock, then it needs to be kept alive until the
-	 * last minute, and restored as quickly as possible after resume.
-	 */
-	if (action != KVM_GUEST_BSP_SUSPEND)
+	switch (action) {
+		/*
+		 * The BSP's clock is managed via clocksource suspend/resume,
+		 * to ensure it's enabled/disabled when timekeeping needs it
+		 * to be, e.g. before reading wallclock (which uses kvmclock).
+		 */
+	case KVM_GUEST_BSP_SUSPEND:
+	case KVM_GUEST_BSP_RESUME:
+		break;
+	case KVM_GUEST_AP_ONLINE:
+		/*
+		 * Secondary CPUs use dedicated sched_clock hooks to enable
+		 * kvmclock early during bringup, there's nothing to be done
+		 * when during CPU online.
+		 */
+		if (kvmclock_is_sched_clock)
+			break;
+		kvm_register_clock("secondary cpu, online");
+		break;
+	case KVM_GUEST_AP_OFFLINE:
+	case KVM_GUEST_SHUTDOWN:
 		kvmclock_disable();
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
 }
 
 /*
@@ -315,6 +342,7 @@ static __init void kvm_sched_clock_init(bool stable)
 	__paravirt_set_sched_clock(kvm_sched_clock_read, stable,
 				   kvm_save_sched_clock_state,
 				   kvm_restore_sched_clock_state);
+	kvmclock_is_sched_clock = true;
 
 	/*
 	 * The BSP's clock is managed via dedicated sched_clock save/restore
@@ -358,7 +386,7 @@ void __init kvmclock_init(void)
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
 	this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]);
-	kvm_register_clock("primary cpu clock");
+	kvm_register_clock("primary cpu, online");
 	pvclock_set_pvti_cpu0_va(hv_clock_boot);
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) {
-- 
2.54.0.563.g4f69b47b94-goog


  parent reply	other threads:[~2026-05-15 19:21 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-15 19:19 [PATCH v3 00/41] x86: Try to wrangle PV clocks vs. TSC Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 01/41] x86/tsc: Add a standalone helpers for getting TSC info from CPUID.0x15 Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 02/41] x86/tsc: Add helper to register CPU and TSC freq calibration routines Sean Christopherson
2026-05-15 20:06   ` sashiko-bot
2026-05-15 19:19 ` [PATCH v3 03/41] x86/sev: Mark TSC as reliable when configuring Secure TSC Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 04/41] x86/sev: Move check for SNP Secure TSC support to tsc_early_init() Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 05/41] x86/tdx: Override PV calibration routines with CPUID-based calibration Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 06/41] x86/acrn: Mark TSC frequency as known when using ACRN for calibration Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 07/41] clocksource: hyper-v: Register sched_clock save/restore iff it's necessary Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 08/41] clocksource: hyper-v: Drop wrappers to sched_clock save/restore helpers Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 09/41] clocksource: hyper-v: Don't save/restore TSC offset when using HV sched_clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 10/41] x86/kvmclock: Setup kvmclock for secondary CPUs iff CONFIG_SMP=y Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 11/41] x86/kvm: Don't disable kvmclock on BSP in syscore_suspend() Sean Christopherson
2026-05-15 20:34   ` sashiko-bot
2026-05-15 22:29     ` Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 12/41] x86/paravirt: Remove unnecessary PARAVIRT=n stub for paravirt_set_sched_clock() Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 13/41] x86/paravirt: Move handling of unstable PV clocks into paravirt_set_sched_clock() Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 14/41] x86/kvmclock: Move sched_clock save/restore helpers up in kvmclock.c Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 15/41] x86/xen/time: Nullify x86_platform's sched_clock save/restore hooks Sean Christopherson
2026-05-15 19:48   ` sashiko-bot
2026-05-15 22:43     ` Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 16/41] x86/vmware: Nullify save/restore hooks when using VMware's sched_clock Sean Christopherson
2026-05-15 19:42   ` sashiko-bot
2026-05-15 19:19 ` [PATCH v3 17/41] x86/tsc: WARN if TSC sched_clock save/restore used with PV sched_clock Sean Christopherson
2026-05-15 19:55   ` sashiko-bot
2026-05-15 19:19 ` [PATCH v3 18/41] x86/paravirt: Pass sched_clock save/restore helpers during registration Sean Christopherson
2026-05-15 19:56   ` sashiko-bot
2026-05-15 19:19 ` [PATCH v3 19/41] x86/kvmclock: Move kvm_sched_clock_init() down in kvmclock.c Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 20/41] x86/xen/time: Mark xen_setup_vsyscall_time_info() as __init Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 21/41] x86/pvclock: Mark setup helpers and related various as __init/__ro_after_init Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 22/41] x86/pvclock: WARN if pvclock's valid_flags are overwritten Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 23/41] x86/kvmclock: Refactor handling of PVCLOCK_TSC_STABLE_BIT during kvmclock_init() Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 24/41] timekeeping: Resume clocksources before reading persistent clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 25/41] x86/kvmclock: Hook clocksource.suspend/resume when kvmclock isn't sched_clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 26/41] x86/kvmclock: WARN if wall clock is read while kvmclock is suspended Sean Christopherson
2026-05-15 19:19 ` Sean Christopherson [this message]
2026-05-15 19:47   ` [PATCH v3 27/41] x86/kvmclock: Enable kvmclock on APs during onlining if kvmclock isn't sched_clock sashiko-bot
2026-05-15 19:19 ` [PATCH v3 28/41] x86/paravirt: Mark __paravirt_set_sched_clock() as __init Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 29/41] x86/paravirt: Plumb a return code into __paravirt_set_sched_clock() Sean Christopherson
2026-05-15 19:48   ` sashiko-bot
2026-05-15 19:19 ` [PATCH v3 30/41] x86/paravirt: Don't use a PV sched_clock in CoCo guests with trusted TSC Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 31/41] x86/tsc: Pass KNOWN_FREQ and RELIABLE as params to registration Sean Christopherson
2026-05-15 19:45   ` sashiko-bot
2026-05-15 19:19 ` [PATCH v3 32/41] x86/tsc: Rejects attempts to override TSC calibration with lesser routine Sean Christopherson
2026-05-15 20:16   ` sashiko-bot
2026-05-15 19:19 ` [PATCH v3 33/41] x86/kvmclock: Mark TSC as reliable when it's constant and nonstop Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 34/41] KVM: x86: Officially define CPUID 0x40000010 as PV Timing Info (TSC and Bus) Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 35/41] x86/kvmclock: Obtain TSC frequency from CPUID if present Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 36/41] x86/kvmclock: Get local APIC bus frequency from PV CPUID Timing Info Sean Christopherson
2026-05-15 19:55   ` sashiko-bot
2026-05-15 19:19 ` [PATCH v3 37/41] x86/kvmclock: Use TSC for sched_clock if it's constant and non-stop Sean Christopherson
2026-05-15 20:09   ` sashiko-bot
2026-05-15 19:19 ` [PATCH v3 38/41] x86/paravirt: kvmclock: Setup kvmclock early iff it's sched_clock Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 39/41] x86/paravirt: Move using_native_sched_clock() stub into timer.h Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 40/41] x86/tsc: Add standalone helper for getting CPU frequency from CPUID Sean Christopherson
2026-05-15 19:51   ` sashiko-bot
2026-05-15 23:04     ` Sean Christopherson
2026-05-15 19:19 ` [PATCH v3 41/41] x86/kvmclock: Get CPU base frequency from CPUID when it's available Sean Christopherson
2026-05-15 19:59   ` sashiko-bot

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=20260515191942.1892718-28-seanjc@google.com \
    --to=seanjc@google.com \
    --cc=ajay.kaher@broadcom.com \
    --cc=alexey.makhalov@broadcom.com \
    --cc=bcm-kernel-feedback-list@broadcom.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=daniel.lezcano@kernel.org \
    --cc=dave.hansen@linux.intel.com \
    --cc=decui@microsoft.com \
    --cc=dwmw@amazon.co.uk \
    --cc=haiyangz@microsoft.com \
    --cc=jan.kiszka@siemens.com \
    --cc=jgross@suse.com \
    --cc=jstultz@google.com \
    --cc=kas@kernel.org \
    --cc=kvm@vger.kernel.org \
    --cc=kys@microsoft.com \
    --cc=linux-coco@lists.linux.dev \
    --cc=linux-hyperv@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=longli@microsoft.com \
    --cc=luto@kernel.org \
    --cc=mhklinux@outlook.com \
    --cc=nikunj@amd.com \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rick.p.edgecombe@intel.com \
    --cc=sboyd@kernel.org \
    --cc=tglx@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=virtualization@lists.linux.dev \
    --cc=vkuznets@redhat.com \
    --cc=wei.liu@kernel.org \
    --cc=x86@kernel.org \
    --cc=xen-devel@lists.xenproject.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox