Merge tag 'for-linus-6.3-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - help deprecate the /proc/xen files by making the related information
   available via sysfs

 - mark the Xen variants of play_dead "noreturn"

 - support a shared Xen platform interrupt

 - several small cleanups and fixes

* tag 'for-linus-6.3-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: sysfs: make kobj_type structure constant
  x86/Xen: drop leftover VM-assist uses
  xen: Replace one-element array with flexible-array member
  xen/grant-dma-iommu: Implement a dummy probe_device() callback
  xen/pvcalls-back: fix permanently masked event channel
  xen: Allow platform PCI interrupt to be shared
  x86/xen/time: prefer tsc as clocksource when it is invariant
  x86/xen: mark xen_pv_play_dead() as __noreturn
  x86/xen: don't let xen_pv_play_dead() return
  drivers/xen/hypervisor: Expose Xen SIF flags to userspace

1 files changed, 37 insertions, 1 deletions

diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 6b8836deb738..1d597364b49d 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -482,15 +482,51 @@ static void xen_setup_vsyscall_time_info(void)
 	xen_clocksource.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
 }
 
+/*
+ * Check if it is possible to safely use the tsc as a clocksource.  This is
+ * only true if the hypervisor notifies the guest that its tsc is invariant,
+ * the tsc is stable, and the tsc instruction will never be emulated.
+ */
+static int __init xen_tsc_safe_clocksource(void)
+{
+	u32 eax, ebx, ecx, edx;
+
+	if (!(boot_cpu_has(X86_FEATURE_CONSTANT_TSC)))
+		return 0;
+
+	if (!(boot_cpu_has(X86_FEATURE_NONSTOP_TSC)))
+		return 0;
+
+	if (check_tsc_unstable())
+		return 0;
+
+	/* Leaf 4, sub-leaf 0 (0x40000x03) */
+	cpuid_count(xen_cpuid_base() + 3, 0, &eax, &ebx, &ecx, &edx);
+
+	/* tsc_mode = no_emulate (2) */
+	if (ebx != 2)
+		return 0;
+
+	return 1;
+}
+
 static void __init xen_time_init(void)
 {
 	struct pvclock_vcpu_time_info *pvti;
 	int cpu = smp_processor_id();
 	struct timespec64 tp;
 
-	/* As Dom0 is never moved, no penalty on using TSC there */
+	/*
+	 * As Dom0 is never moved, no penalty on using TSC there.
+	 *
+	 * If it is possible for the guest to determine that the tsc is a safe
+	 * clocksource, then set xen_clocksource rating below that of the tsc
+	 * so that the system prefers tsc instead.
+	 */
 	if (xen_initial_domain())
 		xen_clocksource.rating = 275;
+	else if (xen_tsc_safe_clocksource())
+		xen_clocksource.rating = 299;
 
 	clocksource_register_hz(&xen_clocksource, NSEC_PER_SEC);