[X][PATCH 2/2] kvmclock: fix TSC calibration for nested guests

[Heitor R. Alves de Siqueira]

From: Peng Hao <peng.hao2 at zte.com.cn>

BugLink: https://bugs.launchpad.net/bugs/1822821

Inside a nested guest, access to hardware can be slow enough that
tsc_read_refs always return ULLONG_MAX, causing tsc_refine_calibration_work
to be called periodically and the nested guest to spend a lot of time
reading the ACPI timer.

However, if the TSC frequency is available from the pvclock page,
we can just set X86_FEATURE_TSC_KNOWN_FREQ and avoid the recalibration.
'refine' operation.

Suggested-by: Peter Zijlstra <peterz at infradead.org>
Signed-off-by: Peng Hao <peng.hao2 at zte.com.cn>
[Commit message rewritten. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini at redhat.com>
(cherry picked from commit e10f7805032365cc11c739a97f226ebb48aee042)
Signed-off-by: Heitor R. Alves de Siqueira <halves at canonical.com>
---
 arch/x86/kernel/kvmclock.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index ec1b06dc82d2..dd77acfee614 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -140,6 +140,7 @@ static unsigned long kvm_get_tsc_khz(void)
 	src = &hv_clock[cpu].pvti;
 	tsc_khz = pvclock_tsc_khz(src);
 	put_cpu();
+	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
 	return tsc_khz;
 }
 
-- 
2.21.0