From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>

Revert commit 96040f7273e2 ("x86/smp: Eliminate mwait_play_dead_cpuid_hint()")
because it introduced a significant power regression on systems that start
with "nosmt" in the kernel command line.

Namely, on such systems, SMT siblings permanently go offline early,
when cpuidle has not been initialized yet, so after the above commit,
hlt_play_dead() is called for them.  Later on, when the processor
attempts to enter a deep package C-state, including PC10 which is
requisite for reaching minimum power in suspend-to-idle, it is not
able to do that because of the SMT siblings staying in C1 (which
they have been put into by HLT).

Fixes: 96040f7273e2 ("x86/smp: Eliminate mwait_play_dead_cpuid_hint()")
Reported-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Tested-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Cc: 6.15+ <stable@vger.kernel.org> # 6.15+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/kernel/smpboot.c |   54 ++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 47 insertions(+), 7 deletions(-)

--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1238,10 +1238,6 @@
 	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);
@@ -1288,6 +1284,50 @@
 }
 
 /*
+ * 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().
  */
@@ -1337,9 +1377,9 @@
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	/* Below returns only on error. */
-	cpuidle_play_dead();
-	hlt_play_dead();
+	mwait_play_dead_cpuid_hint();
+	if (cpuidle_play_dead())
+		hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */