Merge branch 'pm-cpuidle'

Merge cpuidle updates for 6.16-rc2:

 - Update data types of variables passed as arguments to
   mwait_idle_with_hints() to match the function definition
   after recent changes (Uros Bizjak).

 - Eliminate mwait_play_dead_cpuid_hint() again after reverting its
   elimination during the merge window due to a problem with handling
   "dead" SMT siblings, but this time prevent leaving them in C1 after
   initialization by taking them online and back offline when a proper
   cpuidle driver for the platform has been registered (Rafael Wysocki).

* pm-cpuidle:
  intel_idle: Update arguments of mwait_idle_with_hints()
  Reapply "x86/smp: Eliminate mwait_play_dead_cpuid_hint()"
  ACPI: processor: Rescan "dead" SMT siblings during initialization
  intel_idle: Rescan "dead" SMT siblings during initialization
  x86/smp: PM/hibernate: Split arch_resume_nosmt()
  intel_idle: Use subsys_initcall_sync() for initialization

Author: rafaeljw

arch/x86/kernel/smp.c

@@ -299,3 +299,27 @@ struct smp_ops smp_ops = {
 	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
+
+int arch_cpu_rescan_dead_smt_siblings(void)
+{
+	enum cpuhp_smt_control old = cpu_smt_control;
+	int ret;
+
+	/*
+	 * If SMT has been disabled and SMT siblings are in HLT, bring them back
+	 * online and offline them again so that they end up in MWAIT proper.
+	 *
+	 * Called with hotplug enabled.
+	 */
+	if (old != CPU_SMT_DISABLED && old != CPU_SMT_FORCE_DISABLED)
+		return 0;
+
+	ret = cpuhp_smt_enable();
+	if (ret)
+		return ret;
+
+	ret = cpuhp_smt_disable(old);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(arch_cpu_rescan_dead_smt_siblings);

arch/x86/kernel/smpboot.c

@@ -1244,6 +1244,10 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
 void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
@@ -1289,50 +1293,6 @@ void __noreturn mwait_play_dead(unsigned int eax_hint)
 	}
 }
 
-/*
- * We need to flush the caches before going to sleep, lest we have
- * dirty data in our caches when we come back up.
- */
-static inline void mwait_play_dead_cpuid_hint(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		return;
-	if (!this_cpu_has(X86_FEATURE_MWAIT))
-		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
-		return;
-
-	eax = CPUID_LEAF_MWAIT;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	/*
-	 * eax will be 0 if EDX enumeration is not valid.
-	 * Initialized below to cstate, sub_cstate value when EDX is valid.
-	 */
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
-		eax = 0;
-	} else {
-		edx >>= MWAIT_SUBSTATE_SIZE;
-		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-			if (edx & MWAIT_SUBSTATE_MASK) {
-				highest_cstate = i;
-				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-			}
-		}
-		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-			(highest_subcstate - 1);
-	}
-
-	mwait_play_dead(eax);
-}
-
 /*
  * Kick all "offline" CPUs out of mwait on kexec(). See comment in
  * mwait_play_dead().
@@ -1383,9 +1343,9 @@ void native_play_dead(void)
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead_cpuid_hint();
-	if (cpuidle_play_dead())
-		hlt_play_dead();
+	/* Below returns only on error. */
+	cpuidle_play_dead();
+	hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */

arch/x86/power/hibernate.c

@@ -192,7 +192,8 @@ int relocate_restore_code(void)
 
 int arch_resume_nosmt(void)
 {
-	int ret = 0;
+	int ret;
+
 	/*
 	 * We reached this while coming out of hibernation. This means
 	 * that SMT siblings are sleeping in hlt, as mwait is not safe
@@ -206,18 +207,10 @@ int arch_resume_nosmt(void)
 	 * Called with hotplug disabled.
 	 */
 	cpu_hotplug_enable();
-	if (cpu_smt_control == CPU_SMT_DISABLED ||
-			cpu_smt_control == CPU_SMT_FORCE_DISABLED) {
-		enum cpuhp_smt_control old = cpu_smt_control;
-
-		ret = cpuhp_smt_enable();
-		if (ret)
-			goto out;
-		ret = cpuhp_smt_disable(old);
-		if (ret)
-			goto out;
-	}
-out:
+
+	ret = arch_cpu_rescan_dead_smt_siblings();
+
 	cpu_hotplug_disable();
+
 	return ret;
 }

drivers/acpi/internal.h

@@ -175,6 +175,12 @@ bool processor_physically_present(acpi_handle handle);
 static inline void acpi_early_processor_control_setup(void) {}
 #endif
 
+#ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+void acpi_idle_rescan_dead_smt_siblings(void);
+#else
+static inline void acpi_idle_rescan_dead_smt_siblings(void) {}
+#endif
+
 /* --------------------------------------------------------------------------
                                   Embedded Controller
    -------------------------------------------------------------------------- */

drivers/acpi/processor_driver.c

@@ -279,6 +279,9 @@ static int __init acpi_processor_driver_init(void)
 	 * after acpi_cppc_processor_probe() has been called for all online CPUs
 	 */
 	acpi_processor_init_invariance_cppc();
+
+	acpi_idle_rescan_dead_smt_siblings();
+
 	return 0;
 err:
 	driver_unregister(&acpi_processor_driver);

drivers/acpi/processor_idle.c

@@ -24,6 +24,8 @@
 #include <acpi/processor.h>
 #include <linux/context_tracking.h>
 
+#include "internal.h"
+
 /*
  * Include the apic definitions for x86 to have the APIC timer related defines
  * available also for UP (on SMP it gets magically included via linux/smp.h).
@@ -55,6 +57,12 @@ struct cpuidle_driver acpi_idle_driver = {
 };
 
 #ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+void acpi_idle_rescan_dead_smt_siblings(void)
+{
+	if (cpuidle_get_driver() == &acpi_idle_driver)
+		arch_cpu_rescan_dead_smt_siblings();
+}
+
 static
 DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], acpi_cstate);
 

drivers/idle/intel_idle.c

@@ -152,8 +152,8 @@ static __always_inline int __intel_idle(struct cpuidle_device *dev,
 					int index, bool irqoff)
 {
 	struct cpuidle_state *state = &drv->states[index];
-	unsigned long eax = flg2MWAIT(state->flags);
-	unsigned long ecx = 1*irqoff; /* break on interrupt flag */
+	unsigned int eax = flg2MWAIT(state->flags);
+	unsigned int ecx = 1*irqoff; /* break on interrupt flag */
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -226,9 +226,9 @@ static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
 static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
-	unsigned long ecx = 1; /* break on interrupt flag */
 	struct cpuidle_state *state = &drv->states[index];
-	unsigned long eax = flg2MWAIT(state->flags);
+	unsigned int eax = flg2MWAIT(state->flags);
+	unsigned int ecx = 1; /* break on interrupt flag */
 
 	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
 		fpu_idle_fpregs();
@@ -2507,6 +2507,8 @@ static int __init intel_idle_init(void)
 	pr_debug("Local APIC timer is reliable in %s\n",
 		 boot_cpu_has(X86_FEATURE_ARAT) ? "all C-states" : "C1");
 
+	arch_cpu_rescan_dead_smt_siblings();
+
 	return 0;
 
 hp_setup_fail:
@@ -2518,7 +2520,7 @@ static int __init intel_idle_init(void)
 	return retval;
 
 }
-device_initcall(intel_idle_init);
+subsys_initcall_sync(intel_idle_init);
 
 /*
  * We are not really modular, but we used to support that.  Meaning we also

include/linux/cpu.h

@@ -120,6 +120,7 @@ extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 int bringup_hibernate_cpu(unsigned int sleep_cpu);
 void bringup_nonboot_cpus(unsigned int max_cpus);
+int arch_cpu_rescan_dead_smt_siblings(void);
 
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
@@ -134,6 +135,8 @@ static inline void cpu_maps_update_done(void)
 
 static inline int add_cpu(unsigned int cpu) { return 0;}
 
+static inline int arch_cpu_rescan_dead_smt_siblings(void) { return 0; }
+
 #endif /* CONFIG_SMP */
 extern const struct bus_type cpu_subsys;