diff mbox series

[v1,5/5] Reapply "x86/smp: Eliminate mwait_play_dead_cpuid_hint()"

Message ID 7813065.EvYhyI6sBW@rjwysocki.net
State New
Headers show
Series [v1,1/5] intel_idle: Use subsys_initcall_sync() for initialization | expand

Commit Message

Rafael J. Wysocki June 5, 2025, 3:09 p.m. UTC 
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>

Revert commit 70523f335734 ("Revert "x86/smp: Eliminate
mwait_play_dead_cpuid_hint()"") to reapply the changes from commit
96040f7273e2 ("x86/smp: Eliminate mwait_play_dead_cpuid_hint()")
reverted by it.

Previously, these changes caused idle power to rise on systems booting
with "nosmt" in the kernel command line because they effectively caused
"dead" SMT siblings to remain in idle state C1 after executing the HLT
instruction, which prevented the processor from reaching package idle
states deeper than PC2 going forward.

Now, the "dead" SMT siblings are rescanned after initializing a proper
cpuidle driver for the processor (either intel_idle or ACPI idle), at
which point they are able to enter a sufficiently deep idle state
in native_play_dead() via cpuidle, so the code changes in question can
be reapplied.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/kernel/smpboot.c |   54 +++++-----------------------------------------
 1 file changed, 7 insertions(+), 47 deletions(-)
diff mbox series

Patch

--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1238,6 +1238,10 @@ 
 	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);
@@ -1284,50 +1288,6 @@ 
 }
 
 /*
- * 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().
  */
@@ -1377,9 +1337,9 @@ 
 	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 */