From: "Rafael J. Wysocki" <rjw@rjwysocki.net>
To: x86 Maintainers <x86@kernel.org>, Linux PM <linux-pm@vger.kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>, Len Brown <lenb@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Thomas Gleixner <tglx@linutronix.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
Artem Bityutskiy <artem.bityutskiy@linux.intel.com>,
"Gautham R. Shenoy" <gautham.shenoy@amd.com>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
Linux ACPI <linux-acpi@vger.kernel.org>
Subject: [PATCH v1 5/5] Reapply "x86/smp: Eliminate mwait_play_dead_cpuid_hint()"
Date: Thu, 05 Jun 2025 17:09:35 +0200 [thread overview]
Message-ID: <7813065.EvYhyI6sBW@rjwysocki.net> (raw)
In-Reply-To: <2226957.irdbgypaU6@rjwysocki.net>
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(-)
--- 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 */
next prev parent reply other threads:[~2025-06-05 15:09 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-05 15:03 [PATCH v1 0/5] x86/smp: Restore the elimination of mwait_play_dead_cpuid_hint() Rafael J. Wysocki
2025-06-05 15:04 ` [PATCH v1 1/5] intel_idle: Use subsys_initcall_sync() for initialization Rafael J. Wysocki
2025-06-05 15:05 ` [PATCH v1 2/5] x86/smp: PM/hibernate: Split arch_resume_nosmt() Rafael J. Wysocki
2025-06-05 15:06 ` [PATCH v1 3/5] intel_idle: Rescan "dead" SMT siblings during initialization Rafael J. Wysocki
2025-06-05 15:07 ` [PATCH v1 4/5] ACPI: processor: " Rafael J. Wysocki
2025-06-05 16:14 ` Dave Hansen
2025-06-05 18:20 ` Rafael J. Wysocki
2025-06-05 15:09 ` Rafael J. Wysocki [this message]
2025-06-06 10:51 ` [PATCH v1 0/5] x86/smp: Restore the elimination of mwait_play_dead_cpuid_hint() Artem Bityutskiy
2025-06-06 10:53 ` Rafael J. Wysocki
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=7813065.EvYhyI6sBW@rjwysocki.net \
--to=rjw@rjwysocki.net \
--cc=artem.bityutskiy@linux.intel.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=gautham.shenoy@amd.com \
--cc=lenb@kernel.org \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox