From 796b73bba57728f8a67744916459afbed75f629a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 26 Aug 2026 14:32:47 -0700 Subject: KVM: x86: Drop unnecessary CPU pinning when computing/getting kvmclock When computing the current kvmclock value, don't pin the task to the current CPU for the entire duration of the master clock path, as the CPU pinning was never about ensuring rdtsc() and cpu_tsc_khz would agree. As pointed out by David, ka->use_master_clock can only be true when the host clocksource is TSC based, which in turn requires a stable, constant and synchronised TSC across all CPUs. The CPU pinning was added in commit e2c2206a1899 ("KVM: x86: Fix potential preemption when get the current kvmclock timestamp") purely in response to a CONFIG_DEBUG_PREEMPT=y bug due to accessing a per-CPU variable with preemption enabled. Despite what the comment would suggest, including rdtsc() in the {get,put}_cpu() section was opportunistic. In fact, Paolo even said exactly that when suggesting that KVM guarantee the rdtsc() would execute on the same CPU[*]: : Also, rdtsc() should really be on the same CPU as __this_cpu_read. We : know it's not really really necessary because the master clock is : active, but since we need a get_cpu/put_cpu pair, better be clean. Nothing has changed in the last ~9 years, i.e. the rdtsc() still *should* be on the same CPU, but super strictly speaking, all will be fine if the task is migrated between grabbing the frequency and doing rdtsc(). Dropping the CPU pinning will allow dropping the rdtsc() entirely without having to resort to a large "rewrite get_kvmclock()" patch. Opportunistically add a comment to explain why KVM needs to snapshot the frequency, because that _is_ a hard requirement to avoid reintroducing the bug fixed by commit e70b57a6ce4e ("KVM: X86: Fix softlockup when get the current kvmclock") Link: https://lore.kernel.org/all/ae8de642-8f14-a70a-1fab-57e2c4093cd5@redhat.com [*] Suggested-by: David Woodhouse Link: https://patch.msgid.link/20260826213303.914988-8-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 113c9c564ad3..b26699cf302d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1657,13 +1657,18 @@ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; + u64 tsc_hz; - /* both __this_cpu_read() and rdtsc() should be on the same cpu */ + /* + * Snapshot and validate the TSC frequency as kvmclock_cpu_down_prep() + * zeros the per-CPU value when a CPU is going offline. + */ get_cpu(); + tsc_hz = (u64)get_cpu_tsc_khz() * HZ_PER_KHZ; + put_cpu(); data->flags = 0; - if (ka->use_master_clock && - (cpu_feature_enabled(X86_FEATURE_CONSTANT_TSC) || __this_cpu_read(cpu_tsc_khz))) { + if (ka->use_master_clock && tsc_hz) { #ifdef CONFIG_X86_64 struct timespec64 ts; @@ -1677,15 +1682,13 @@ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) data->flags |= KVM_CLOCK_TSC_STABLE; hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; - kvm_get_time_scale(NSEC_PER_SEC, get_cpu_tsc_khz() * 1000LL, + kvm_get_time_scale(NSEC_PER_SEC, tsc_hz, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc); } else { data->clock = get_kvmclock_base_ns() + ka->kvmclock_offset; } - - put_cpu(); } static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) -- cgit v1.2.3