[PATCH 16/16] x86/kvmclock: Use TSC for sched_clock if it's constant and non-stop

[Sean Christopherson <seanjc@google.com>]

Prefer the TSC over kvmclock for sched_clock if the TSC is constant,
nonstop, and not marked unstable via command line.  I.e. use the same
criteria as tweaking the clocksource rating so that TSC is preferred over
kvmclock.  Per the below comment from native_sched_clock(), sched_clock
is more tolerant of slop than clocksource; using TSC for clocksource but
not sched_clock makes little to no sense, especially now that KVM CoCo
guests with a trusted TSC use TSC, not kvmclock.

        /*
         * Fall back to jiffies if there's no TSC available:
         * ( But note that we still use it if the TSC is marked
         *   unstable. We do this because unlike Time Of Day,
         *   the scheduler clock tolerates small errors and it's
         *   very important for it to be as fast as the platform
         *   can achieve it. )
         */

The only advantage of using kvmclock is that doing so allows for early
and common detection of PVCLOCK_GUEST_STOPPED, but that code has been
broken for nearly two years with nary a complaint, i.e. it can't be
_that_ valuable.  And as above, certain types of KVM guests are losing
the functionality regardless, i.e. acknowledging PVCLOCK_GUEST_STOPPED
needs to be decoupled from sched_clock() no matter what.

Link: https://lore.kernel.org/all/Z4hDK27OV7wK572A@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kernel/kvmclock.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 9d05d070fe25..fb8cd8313d18 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -344,23 +344,23 @@ void __init kvmclock_init(void)
 		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 
 	/*
-	 * X86_FEATURE_NONSTOP_TSC is TSC runs at constant rate
-	 * with P/T states and does not stop in deep C-states.
-	 *
-	 * Invariant TSC exposed by host means kvmclock is not necessary:
-	 * can use TSC as clocksource.
-	 *
+	 * If the TSC counts at a constant frequency across P/T states, counts
+	 * in deep C-states, and the TSC hasn't been marked unstable, prefer
+	 * the TSC over kvmclock for sched_clock and drop kvmclock's rating so
+	 * that TSC is chosen as the clocksource.  Note, the TSC unstable check
+	 * exists purely to honor the TSC being marked unstable via command
+	 * line, any runtime detection of an unstable will happen after this.
 	 */
 	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
 	    boot_cpu_has(X86_FEATURE_NONSTOP_TSC) &&
 	    !check_tsc_unstable()) {
 		kvm_clock.rating = 299;
 		tsc_properties = TSC_FREQ_KNOWN_AND_RELIABLE;
+	} else {
+		flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
+		kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
 	}
 
-	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
-	kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
-
 	tsc_register_calibration_routines(kvm_get_tsc_khz, kvm_get_cpu_khz,
 					  tsc_properties);
 
@@ -369,6 +369,11 @@ void __init kvmclock_init(void)
 #ifdef CONFIG_X86_LOCAL_APIC
 	x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock;
 #endif
+	/*
+	 * Save/restore "sched" clock state even if kvmclock isn't being used
+	 * for sched_clock, as kvmclock is still used for wallclock and relies
+	 * on these hooks to re-enable kvmclock after suspend+resume.
+	 */
 	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
 	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
 	kvm_get_preset_lpj();
-- 
2.48.1.362.g079036d154-goog