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

5 files changed, 48 insertions, 35 deletions

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index ead967479fa6..d18078834ded 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kexec.h>
-#include <linux/i8253.h>
 #include <linux/random.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
@@ -537,16 +536,6 @@ static void __init ms_hyperv_init_platform(void)
 	if (efi_enabled(EFI_BOOT))
 		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 
-	/*
-	 * Hyper-V VMs have a PIT emulation quirk such that zeroing the
-	 * counter register during PIT shutdown restarts the PIT. So it
-	 * continues to interrupt @18.2 HZ. Setting i8253_clear_counter
-	 * to false tells pit_shutdown() not to zero the counter so that
-	 * the PIT really is shutdown. Generation 2 VMs don't have a PIT,
-	 * and setting this value has no effect.
-	 */
-	i8253_clear_counter_on_shutdown = false;
-
 #if IS_ENABLED(CONFIG_HYPERV)
 	if ((hv_get_isolation_type() == HV_ISOLATION_TYPE_VBS) ||
 	    ms_hyperv.paravisor_present)
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 2b7999a1a50a..80e262bb627f 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -8,6 +8,7 @@
 #include <linux/timex.h>
 #include <linux/i8253.h>
 
+#include <asm/hypervisor.h>
 #include <asm/apic.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
@@ -39,9 +40,15 @@ static bool __init use_pit(void)
 
 bool __init pit_timer_init(void)
 {
-	if (!use_pit())
+	if (!use_pit()) {
+		/*
+		 * Don't just ignore the PIT. Ensure it's stopped, because
+		 * VMMs otherwise steal CPU time just to pointlessly waggle
+		 * the (masked) IRQ.
+		 */
+		clockevent_i8253_disable();
 		return false;
-
+	}
 	clockevent_i8253_init(true);
 	global_clock_event = &i8253_clockevent;
 	return true;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index d4462fb26299..dfe6847fd99e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -28,6 +28,7 @@
 #include <asm/apic.h>
 #include <asm/cpu_device_id.h>
 #include <asm/i8259.h>
+#include <asm/topology.h>
 #include <asm/uv/uv.h>
 
 unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
@@ -1253,15 +1254,12 @@ static void __init check_system_tsc_reliable(void)
 	 *  - TSC which does not stop in C-States
 	 *  - the TSC_ADJUST register which allows to detect even minimal
 	 *    modifications
-	 *  - not more than two sockets. As the number of sockets cannot be
-	 *    evaluated at the early boot stage where this has to be
-	 *    invoked, check the number of online memory nodes as a
-	 *    fallback solution which is an reasonable estimate.
+	 *  - not more than four packages
 	 */
 	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
 	    boot_cpu_has(X86_FEATURE_NONSTOP_TSC) &&
 	    boot_cpu_has(X86_FEATURE_TSC_ADJUST) &&
-	    nr_online_nodes <= 4)
+	    topology_max_packages() <= 4)
 		tsc_disable_clocksource_watchdog();
 }
 
@@ -1290,7 +1288,7 @@ int unsynchronized_tsc(void)
 	 */
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
 		/* assume multi socket systems are not synchronized: */
-		if (num_possible_cpus() > 1)
+		if (topology_max_packages() > 1)
 			return 1;
 	}
 
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;
 }
 
diff --git a/include/linux/i8253.h b/include/linux/i8253.h
index 8336b2f6f834..56c280eb2d4f 100644
--- a/include/linux/i8253.h
+++ b/include/linux/i8253.h
@@ -21,9 +21,9 @@
 #define PIT_LATCH	((PIT_TICK_RATE + HZ/2) / HZ)
 
 extern raw_spinlock_t i8253_lock;
-extern bool i8253_clear_counter_on_shutdown;
 extern struct clock_event_device i8253_clockevent;
 extern void clockevent_i8253_init(bool oneshot);
+extern void clockevent_i8253_disable(void);
 
 extern void setup_pit_timer(void);