linux-kernel - Re: [PATCH V2 2/2] platform/x86/intel/pmc: Disable C1 auto-demotion during suspend

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: <462d0bd9eb9c461e01ef27a8da9cd02f92ce8f9f.camel@linux.intel.com>
Date: Fri, 11 Oct 2024 09:36:52 -0700
From: srinivas pandruvada <srinivas.pandruvada@...ux.intel.com>
To: david.e.box@...ux.intel.com, hdegoede@...hat.com, 
	ilpo.jarvinen@...ux.intel.com, rjw@...ysocki.net, 
	platform-driver-x86@...r.kernel.org, linux-kernel@...r.kernel.org, 
	linux-pm@...r.kernel.org
Subject: Re: [PATCH V2 2/2] platform/x86/intel/pmc: Disable C1 auto-demotion
 during suspend

On Thu, 2024-10-10 at 20:50 -0700, David E. Box wrote:
> On Thu, 2024-10-10 at 19:09 -0700, srinivas pandruvada wrote:
> > On Thu, 2024-10-10 at 17:36 -0700, David E. Box wrote:
> > > On some platforms, aggressive C1 auto-demotion may lead to
> > > failure to
> > > enter
> > > the deepest C-state during suspend-to-idle, causing high power
> > > consumption.
> > > To prevent this, disable C1 auto-demotion during suspend and re-
> > > enable on
> > > resume.
> > > 
> > > Signed-off-by: David E. Box <david.e.box@...ux.intel.com>
> > > ---
> > > 
> > > V2 - Remove #define DEBUG
> > >    - Move refactor of cnl_resume() to separate patch
> > >    - Use smp_call_function() to disable and restore
> > > C1_AUTO_DEMOTE
> > >    - Add comment that the MSR is per core, not per package.
> > >    - Add comment that the online cpu mask remains unchanged
> > > during
> > >      suspend due to frozen userspace.
> > > 
> > >  drivers/platform/x86/intel/pmc/cnp.c | 53
> > > ++++++++++++++++++++++++++++
> > >  1 file changed, 53 insertions(+)
> > > 
> > > diff --git a/drivers/platform/x86/intel/pmc/cnp.c
> > > b/drivers/platform/x86/intel/pmc/cnp.c
> > > index 513c02670c5a..f12d4f0f9e93 100644
> > > --- a/drivers/platform/x86/intel/pmc/cnp.c
> > > +++ b/drivers/platform/x86/intel/pmc/cnp.c
> > > @@ -8,6 +8,8 @@
> > >   *
> > >   */
> > >  
> > > +#include <linux/smp.h>
> > > +#include <linux/suspend.h>
> > >  #include "core.h"
> > >  
> > >  /* Cannon Lake: PGD PFET Enable Ack Status Register(s) bitmap */
> > > @@ -206,8 +208,52 @@ const struct pmc_reg_map cnp_reg_map = {
> > >  	.etr3_offset = ETR3_OFFSET,
> > >  };
> > >  
> > > +
> > > +/*
> > > + * Disable C1 auto-demotion
> > > + *
> > > + * Aggressive C1 auto-demotion may lead to failure to enter the
> > > deepest C-state
> > > + * during suspend-to-idle, causing high power consumption. To
> > > prevent this, we
> > > + * disable C1 auto-demotion during suspend and re-enable on
> > > resume.
> > > + *
> > > + * Note that, although MSR_PKG_CST_CONFIG_CONTROL has 'package'
> > > in
> > > its name, it
> > > + * is actually a per-core MSR on client platforms, affecting
> > > only a
> > > single CPU.
> > > + * Therefore, it must be configured on all online CPUs. The
> > > online
> > > cpu mask is
> > > + * unchanged during the phase of suspend/resume as user space is
> > > frozen.
> > > + */
> > > +
> > > +static DEFINE_PER_CPU(u64, pkg_cst_config);
> > > +
> > > +static void disable_c1_auto_demote(void *unused)
> > > +{
> > > +	int cpunum = smp_processor_id();
> > > +	u64 val;
> > > +
> > > +	rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, val);
> > > +	per_cpu(pkg_cst_config, cpunum) = val;
> > > +	val &= ~NHM_C1_AUTO_DEMOTE;
> > > +	wrmsrl(MSR_PKG_CST_CONFIG_CONTROL, val);
> > > +	pr_debug("%s: cpu:%d cst %llx\n", __func__, cpunum,
> > > val);
> > Do you want to leave pr_debug?
> 
> Thought it could be useful but it can be removed.
> 
> > 
> > > +}
> > > +
> > > +static void restore_c1_auto_demote(void *unused)
> > > +{
> > > +	int cpunum = smp_processor_id();
> > > +
> > > +	pr_debug("%s: cpu:%d cst %llx\n", __func__, cpunum,
> > > +		 per_cpu(pkg_cst_config, cpunum));
> > > +	wrmsrl(MSR_PKG_CST_CONFIG_CONTROL,
> > > per_cpu(pkg_cst_config,
> > > cpunum));
> > > +}
> > > +
> > >  void cnl_suspend(struct pmc_dev *pmcdev)
> > >  {
> > > +	if (!pm_suspend_via_firmware()) {
> > > +		preempt_disable();
> > Why do you need this?
> 
> To ensure that the cpu doesn't change between the next two calls.

Correct. You need for smp_processor_id()

Generally for this avoiding issue with smp_processor_id(), you can use
get_cpu(), which gives current cpu as return value and also disable
preemption.

Something like this

                this_cpu = get_cpu();
                disable_c1_auto_demote(&this_cpu);
smp_call_function_many(cpu_online_mask, disable_c1_auto_demote, NULL,
0);
                put_cpu();


But fine, this makes your code more complex as you have to pass now a
param and use for local_cpu and use smp_procesor_id() for remote call
via smp_call..


Thanks,
Srinivas

> 
> David
> 
> > 
> > 
> > Thanks,
> > Srinivas
> > 
> > > +		disable_c1_auto_demote(NULL);
> > > +		smp_call_function(disable_c1_auto_demote, NULL,
> > > 0);
> > > +		preempt_enable();
> > > +	}
> > > +
> > >  	/*
> > >  	 * Due to a hardware limitation, the GBE LTR blocks PC10
> > >  	 * when a cable is attached. To unblock PC10 during
> > > suspend,
> > > @@ -218,6 +264,13 @@ void cnl_suspend(struct pmc_dev *pmcdev)
> > >  
> > >  int cnl_resume(struct pmc_dev *pmcdev)
> > >  {
> > > +	if (!pm_suspend_via_firmware()) {
> > > +		preempt_disable();
> > > +		restore_c1_auto_demote(NULL);
> > > +		smp_call_function(restore_c1_auto_demote, NULL,
> > > 0);
> > > +		preempt_enable();
> > > +	}
> > > +
> > >  	pmc_core_send_ltr_ignore(pmcdev, 3, 0);
> > >  
> > >  	return pmc_core_resume_common(pmcdev);
> > 
> 
>