Re: [PATCH v7 11/36] KVM: x86: Restructure kvm_guest_time_update() for TSC upscaling

On Tue, Jul 28, 2026, David Woodhouse wrote:
> From: David Woodhouse <[email protected]>
> 
> Restructure kvm_guest_time_update() so that kernel_ns/host_tsc are
> always "now" when doing TSC catchup, then swap in the master clock
> reference values afterward for the hv_clock.
> 
> This makes the TSC upscaling code considerably simpler: the catchup
> adjustment is computed as the delta between what the guest TSC *should*
> be at "now" and what it actually is, rather than mixing "now" and
> "master clock reference" timestamps.
> 
> The seqcount loop now also contains the kvm_get_time_and_clockread()
> call (matching get_kvmclock's pattern).
> 
> Based on a suggestion by Sean Christopherson.

Looking at this with fresh eyes, it wasn't a very good suggestion.  In addition
to the goof Sashiko reported, propagating master_host_tsc/master_kernel_ns to
host_tsc/kernel_ns is completely unnecessary and convoluted, it's much easier to
simply use master_{host_tsc,kernel_ns} when stuffing hv_clock.

> Signed-off-by: David Woodhouse <[email protected]>
> ---
>  arch/x86/kvm/x86.c | 78 ++++++++++++++++++++++++++++++++--------------
>  1 file changed, 54 insertions(+), 24 deletions(-)
> 
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 52c9268007f8..12c3d7d503ca 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -1793,45 +1793,60 @@ static void kvm_setup_guest_pvclock(struct pvclock_vcpu_time_info *ref_hv_clock,
>  int kvm_guest_time_update(struct kvm_vcpu *v)
>  {
>  	struct pvclock_vcpu_time_info hv_clock = {};
> -	unsigned long flags;
>  	u64 tgt_tsc_hz;
>  	unsigned seq;
>  	struct kvm_vcpu_arch *vcpu = &v->arch;
>  	struct kvm_arch *ka = &v->kvm->arch;
>  	s64 kernel_ns;
>  	u64 tsc_timestamp, host_tsc;
> +	u64 master_host_tsc = 0;
> +	s64 master_kernel_ns = 0;
> +	s64 kvmclock_offset = 0;
>  	bool use_master_clock;
>  
> -	kernel_ns = 0;
> -	host_tsc = 0;
> -
>  	/*
>  	 * If the host uses TSC clock, then passthrough TSC as stable
>  	 * to the guest.
>  	 */
>  	do {
>  		seq = read_seqcount_begin(&ka->pvclock_sc);
> +
>  		use_master_clock = ka->use_master_clock;
> +
> +		/*
> +		 * The TSC read and the call to get_cpu_tsc_khz() must happen
> +		 * on the same CPU.
> +		 */
> +		get_cpu();
> +
> +		tgt_tsc_hz = (u64)get_cpu_tsc_khz() * HZ_PER_KHZ;
> +
> +#ifdef CONFIG_X86_64
> +		if (use_master_clock &&
> +		    !kvm_get_time_and_clockread(&kernel_ns, &host_tsc) &&
> +		    !read_seqcount_retry(&ka->pvclock_sc, seq))
> +			use_master_clock = false;
> +#endif

Actually, the entire use_master_clock code can be thrown under CONFIG_X86_64=y
(in a separate prep patch).

> @@ -1841,17 +1856,32 @@ int kvm_guest_time_update(struct kvm_vcpu *v)
>  	 *      entry to avoid unknown leaps of TSC even when running
>  	 *      again on the same CPU.  This may cause apparent elapsed
>  	 *      time to disappear, and the guest to stand still or run
> -	 *	very slowly.
> +	 *      very slowly.
>  	 */
>  	if (vcpu->tsc_catchup) {
> -		u64 tsc = compute_guest_tsc(v, kernel_ns);
> -		if (tsc > tsc_timestamp) {
> -			adjust_tsc_offset_guest(v, tsc - tsc_timestamp);
> -			tsc_timestamp = tsc;
> -		}
> +		s64 adjustment;
> +
> +		/*
> +		 * Calculate the delta between what the guest TSC *should* be
> +		 * and what it actually is according to kvm_read_l1_tsc().
> +		 */
> +		adjustment = compute_guest_tsc(v, kernel_ns) -
> +			     kvm_read_l1_tsc(v, host_tsc);
> +		if (adjustment > 0)
> +			adjust_tsc_offset_guest(v, adjustment);
>  	}
>  
> -	local_irq_restore(flags);
> +	/*
> +	 * Now that TSC upscaling is out of the way, the remaining calculations
> +	 * are all relative to the reference time that's placed in hv_clock.
> +	 * If the master clock is NOT in use, the reference time is "now".  If
> +	 * master clock is in use, the reference time comes from there.
> +	 */
> +	if (use_master_clock) {
> +		host_tsc = master_host_tsc;
> +		kernel_ns = master_kernel_ns;
> +	}
> +	tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);

And the big reason my suggestion was bad: this is wrong for vcpu->last_guest_tsc,
because vcpu->last_guest_tsc needs to be updated to "now" (it's the same TSC
that's shoved into TSC_OFFSET in the tsc_catchup path).

This is what I have locally for the change this patch really cares about.  This,
and several prep cleanup patches, pass your selftests with the rest of the series
piled on top.

Assuming my other testing doesn't explode, I'll get a sub-series through
"KVM: x86: Remove implicit rdtsc() from kvm_compute_l1_tsc_offset()" posted
tomorrow, with the plan of landing all of that in 7.3.  That'd leave about half
the patches for 7.4, which certainly isn't ideal, but it's not too shabby either.

---
 arch/x86/kvm/x86.c | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 793340292d39..e826d1f8cabe 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1796,12 +1796,11 @@ static void kvm_setup_guest_pvclock(struct pvclock_vcpu_time_info *ref_hv_clock,
 
 int kvm_guest_time_update(struct kvm_vcpu *v)
 {
+	u64 tgt_tsc_hz, tsc_timestamp, host_tsc, master_tsc, master_ns;
 	struct kvm_arch *ka __maybe_unused = &v->kvm->arch;
 	struct pvclock_vcpu_time_info hv_clock = {};
-	u64 tgt_tsc_hz;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	s64 kernel_ns;
-	u64 tsc_timestamp, host_tsc;
 
 	/*
 	 * If the host uses TSC clock, then passthrough TSC as stable
@@ -1814,10 +1813,16 @@ int kvm_guest_time_update(struct kvm_vcpu *v)
 	do {
 		seq = read_seqcount_begin(&ka->pvclock_sc);
 		use_master_clock = ka->use_master_clock;
-		if (use_master_clock) {
-			host_tsc = ka->master_cycle_now;
-			kernel_ns = ka->master_kernel_ns;
+		if (!use_master_clock)
+			continue;
+
+		if (!kvm_get_time_and_clockread(&kernel_ns, &host_tsc)) {
+			use_master_clock = false;
+			continue;
 		}
+
+		master_tsc = ka->master_cycle_now;
+		master_ns = ka->master_kernel_ns;
 	} while (read_seqcount_retry(&ka->pvclock_sc, seq));
 #else
 	const bool use_master_clock = false;
@@ -1883,8 +1888,18 @@ int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	hv_clock.tsc_shift = vcpu->pvclock_tsc_shift;
 	hv_clock.tsc_to_system_mul = vcpu->pvclock_tsc_mul;
-	hv_clock.tsc_timestamp = tsc_timestamp;
-	hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
+	/*
+	 * If the master clock is NOT in use, the reference time placed in the
+	 * hv_clock is "now".  If master clock is in use, the reference time is
+	 * the master clock's snapshot from some time in the past, not "now".
+	 */
+	if (use_master_clock) {
+		hv_clock.tsc_timestamp = kvm_read_l1_tsc(v, master_tsc);
+		hv_clock.system_time = master_ns + v->kvm->arch.kvmclock_offset;
+	} else {
+		hv_clock.tsc_timestamp = tsc_timestamp;
+		hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
+	}
 
 	/* If the host uses TSC clocksource, then it is stable */
 	hv_clock.flags = 0;
--