Merge tag 'x86-timers-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 timer updates from Thomas Gleixner:

 - Use the topology information of number of packages for making the
   decision about TSC trust instead of using the number of online nodes
   which is not reflecting the real topology.

 - Stop the PIT timer 0 when its not in use as to stop pointless
   emulation in the VMM.

 - Fix the PIT timer stop sequence for timer 0 so it truly stops both
   real hardware and buggy VMM emulations.

* tag 'x86-timers-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/tsc: Check for sockets instead of CPUs to make code match comment
  clockevents/drivers/i8253: Fix stop sequence for timer 0
  x86/i8253: Disable PIT timer 0 when not in use
  x86/tsc: Use topology_max_packages() to get package number

1 files changed, 34 insertions, 15 deletions

diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
index d4350bb10b83..39f7c2d736d1 100644
--- a/drivers/clocksource/i8253.c
+++ b/drivers/clocksource/i8253.c
@@ -20,13 +20,6 @@
 DEFINE_RAW_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
-/*
- * Handle PIT quirk in pit_shutdown() where zeroing the counter register
- * restarts the PIT, negating the shutdown. On platforms with the quirk,
- * platform specific code can set this to false.
- */
-bool i8253_clear_counter_on_shutdown __ro_after_init = true;
-
 #ifdef CONFIG_CLKSRC_I8253
 /*
  * Since the PIT overflows every tick, its not very useful
@@ -108,21 +101,47 @@ int __init clocksource_i8253_init(void)
 #endif
 
 #ifdef CONFIG_CLKEVT_I8253
-static int pit_shutdown(struct clock_event_device *evt)
+void clockevent_i8253_disable(void)
 {
-	if (!clockevent_state_oneshot(evt) && !clockevent_state_periodic(evt))
-		return 0;
-
 	raw_spin_lock(&i8253_lock);
 
+	/*
+	 * Writing the MODE register should stop the counter, according to
+	 * the datasheet. This appears to work on real hardware (well, on
+	 * modern Intel and AMD boxes; I didn't dig the Pegasos out of the
+	 * shed).
+	 *
+	 * However, some virtual implementations differ, and the MODE change
+	 * doesn't have any effect until either the counter is written (KVM
+	 * in-kernel PIT) or the next interrupt (QEMU). And in those cases,
+	 * it may not stop the *count*, only the interrupts. Although in
+	 * the virt case, that probably doesn't matter, as the value of the
+	 * counter will only be calculated on demand if the guest reads it;
+	 * it's the interrupts which cause steal time.
+	 *
+	 * Hyper-V apparently has a bug where even in mode 0, the IRQ keeps
+	 * firing repeatedly if the counter is running. But it *does* do the
+	 * right thing when the MODE register is written.
+	 *
+	 * So: write the MODE and then load the counter, which ensures that
+	 * the IRQ is stopped on those buggy virt implementations. And then
+	 * write the MODE again, which is the right way to stop it.
+	 */
 	outb_p(0x30, PIT_MODE);
+	outb_p(0, PIT_CH0);
+	outb_p(0, PIT_CH0);
 
-	if (i8253_clear_counter_on_shutdown) {
-		outb_p(0, PIT_CH0);
-		outb_p(0, PIT_CH0);
-	}
+	outb_p(0x30, PIT_MODE);
 
 	raw_spin_unlock(&i8253_lock);
+}
+
+static int pit_shutdown(struct clock_event_device *evt)
+{
+	if (!clockevent_state_oneshot(evt) && !clockevent_state_periodic(evt))
+		return 0;
+
+	clockevent_i8253_disable();
 	return 0;
 }