linux-kernel - Re: 50 Watt idle power regression bisected to Linux-3.10

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1386764955.12005.60.camel@marge.simpson.net>
Date:	Wed, 11 Dec 2013 13:29:15 +0100
From:	Mike Galbraith <bitbucket@...ine.de>
To:	Peter Zijlstra <peterz@...radead.org>
Cc:	Borislav Petkov <bp@...en8.de>,
	Thomas Gleixner <tglx@...utronix.de>,
	Len Brown <lenb@...nel.org>,
	Linux PM list <linux-pm@...r.kernel.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	Jeremy Eder <jeder@...hat.com>, x86@...nel.org
Subject: Re: 50 Watt idle power regression bisected to Linux-3.10

On Wed, 2013-12-11 at 12:52 +0100, Peter Zijlstra wrote: 
> On Wed, Dec 11, 2013 at 12:38:39PM +0100, Borislav Petkov wrote:
> > Right, if it turns out that this is really the case and that this
> > erratum hasn't been fixed for models later than 29 - we'd need the
> > additional model numbers to set X86_FEATURE_CLFLUSH_MONITOR correctly.
> 
> You also need: https://lkml.org/lkml/2013/11/19/143
> 
> Because obviously not all mwait idle loops check that cpu bit.

I had tried that patch, to see if it would magically make the thing
start working, nope.  I had also tried...

---
 drivers/idle/intel_idle.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

Index: linux-2.6/drivers/idle/intel_idle.c
===================================================================
--- linux-2.6.orig/drivers/idle/intel_idle.c
+++ linux-2.6/drivers/idle/intel_idle.c
@@ -376,11 +376,14 @@ static int intel_idle(struct cpuidle_dev
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 
 	if (!current_set_polling_and_test()) {
-
+		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
+			clflush((void *)&current_thread_info()->flags);
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
 		if (!need_resched())
 			__mwait(eax, ecx);
+		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
+			clflush((void *)&current_thread_info()->flags);
 	}
 
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))

..a cflush before _and_ after, among other (shazam!.. darn) guesses, but
nogo.  Turning that into the tglx one liner indeed did fix the thing, as
did adding this to your patch.

---
 arch/x86/include/asm/mwait.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Index: linux-2.6/arch/x86/include/asm/mwait.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/mwait.h
+++ linux-2.6/arch/x86/include/asm/mwait.h
@@ -43,7 +43,7 @@ static inline void __mwait(unsigned long
 static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 {
 	if (!current_set_polling_and_test()) {
-		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
+//		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);



Grrr.

flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe
syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx est tm2
ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt lahf_lm dtherm
tpr_shadow vnmi flexpriority ept vpid

-Mike

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/