Merge: Update intel_idle to upstream v6.15

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6660

JIRA: https://issues.redhat.com/browse/RHEL-85522
JIRA: https://issues.redhat.com/browse/RHEL-45063

Signed-off-by: David Arcari <darcari@redhat.com>

Approved-by: Tony Camuso <tcamuso@redhat.com>
Approved-by: Lenny Szubowicz <lszubowi@redhat.com>
Approved-by: Steve Best <sbest@redhat.com>
Approved-by: Mark Langsdorf <mlangsdo@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Augusto Caringi <acaringi@redhat.com>

Author: caringi

Documentation/admin-guide/pm/intel_idle.rst

@@ -192,11 +192,19 @@ even if they have been enumerated (see :ref:`cpu-pm-qos` in
 Documentation/admin-guide/pm/cpuidle.rst).
 Setting ``max_cstate`` to 0 causes the ``intel_idle`` initialization to fail.
 
-The ``no_acpi`` and ``use_acpi`` module parameters (recognized by ``intel_idle``
-if the kernel has been configured with ACPI support) can be set to make the
-driver ignore the system's ACPI tables entirely or use them for all of the
-recognized processor models, respectively (they both are unset by default and
-``use_acpi`` has no effect if ``no_acpi`` is set).
+The ``no_acpi``, ``use_acpi`` and ``no_native`` module parameters are
+recognized by ``intel_idle`` if the kernel has been configured with ACPI
+support.  In the case that ACPI is not configured these flags have no impact
+on functionality.
+
+``no_acpi`` - Do not use ACPI at all.  Only native mode is available, no
+ACPI mode.
+
+``use_acpi`` - No-op in ACPI mode, the driver will consult ACPI tables for
+C-states on/off status in native mode.
+
+``no_native`` - Work only in ACPI mode, no native mode available (ignore
+all custom tables).
 
 The value of the ``states_off`` module parameter (0 by default) represents a
 list of idle states to be disabled by default in the form of a bitmask.

arch/x86/include/asm/smp.h

@@ -119,6 +119,7 @@ void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
 
 void smp_kick_mwait_play_dead(void);
+void __noreturn mwait_play_dead(unsigned int eax_hint);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
@@ -169,6 +170,8 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return (struct cpumask *)cpumask_of(0);
 }
+
+static inline void __noreturn mwait_play_dead(unsigned int eax_hint) { BUG(); }
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_DEBUG_NMI_SELFTEST

arch/x86/kernel/acpi/cstate.c

@@ -15,6 +15,7 @@
 #include <acpi/processor.h>
 #include <asm/mwait.h>
 #include <asm/special_insns.h>
+#include <asm/smp.h>
 
 /*
  * Initialize bm_flags based on the CPU cache properties
@@ -204,6 +205,16 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
 
+void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+{
+	unsigned int cpu = smp_processor_id();
+	struct cstate_entry *percpu_entry;
+
+	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+	mwait_play_dead(percpu_entry->states[cx->index].eax);
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_play_dead);
+
 void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
 {
 	unsigned int cpu = smp_processor_id();

arch/x86/kernel/hpet.c

@@ -927,9 +927,6 @@ static bool __init mwait_pc10_supported(void)
 	if (!cpu_feature_enabled(X86_FEATURE_MWAIT))
 		return false;
 
-	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
-		return false;
-
 	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates);
 
 	return (ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) &&

arch/x86/kernel/smpboot.c

@@ -1282,49 +1282,9 @@ 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.
- */
-static inline void mwait_play_dead(void)
+void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
-	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;
-	if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
-		return;
-
-	eax = CPUID_MWAIT_LEAF;
-	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);
-	}
 
 	/* Set up state for the kexec() hack below */
 	md->status = CPUDEAD_MWAIT_WAIT;
@@ -1345,7 +1305,7 @@ static inline void mwait_play_dead(void)
 		mb();
 		__monitor(md, 0, 0);
 		mb();
-		__mwait(eax, 0);
+		__mwait(eax_hint, 0);
 
 		if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) {
 			/*
@@ -1368,6 +1328,50 @@ static inline void mwait_play_dead(void)
 	}
 }
 
+/*
+ * 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_MWAIT_LEAF;
+	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().
@@ -1418,7 +1422,7 @@ void native_play_dead(void)
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead();
+	mwait_play_dead_cpuid_hint();
 	if (cpuidle_play_dead())
 		hlt_play_dead();
 }

drivers/acpi/acpi_pad.c

@@ -42,8 +42,6 @@ static void power_saving_mwait_init(void)
 
 	if (!boot_cpu_has(X86_FEATURE_MWAIT))
 		return;
-	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
-		return;
 
 	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
 

drivers/acpi/processor_idle.c

@@ -578,7 +578,7 @@ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
  * @dev: the target CPU
  * @index: the index of suggested state
  */
-static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
+static void acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 {
 	struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);
 
@@ -590,12 +590,11 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 			raw_safe_halt();
 		else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
 			io_idle(cx->address);
+		} else if (cx->entry_method == ACPI_CSTATE_FFH) {
+			acpi_processor_ffh_play_dead(cx);
 		} else
-			return -ENODEV;
+			return;
 	}
-
-	/* Never reached */
-	return 0;
 }
 
 static __always_inline bool acpi_idle_fallback_to_c1(struct acpi_processor *pr)

drivers/cpuidle/cpuidle.c

@@ -69,11 +69,15 @@ int cpuidle_play_dead(void)
 	if (!drv)
 		return -ENODEV;
 
-	/* Find lowest-power state that supports long-term idle */
-	for (i = drv->state_count - 1; i >= 0; i--)
+	for (i = drv->state_count - 1; i >= 0; i--) {
 		if (drv->states[i].enter_dead)
-			return drv->states[i].enter_dead(dev, i);
+			drv->states[i].enter_dead(dev, i);
+	}
 
+	/*
+	 * If :enter_dead() is successful, it will never return, so reaching
+	 * here means that all of them failed above or were not present.
+	 */
 	return -ENODEV;
 }