linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Pandruvada, Srinivas" <srinivas.pandruvada@intel.com>
To: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"prarit@redhat.com" <prarit@redhat.com>,
	"linux-pm@vger.kernel.org" <linux-pm@vger.kernel.org>
Cc: "Jovanovic, Radivoje" <radivoje.jovanovic@intel.com>,
	"s.ikarashi@jp.fujitsu.com" <s.ikarashi@jp.fujitsu.com>,
	"David Rajamanickam,
	Ajay Thomas"  <ajay.thomas.david.rajamanickam@intel.com>,
	"Wysocki, Rafael J" <rafael.j.wysocki@intel.com>,
	"minipli@googlemail.com" <minipli@googlemail.com>
Subject: Re: [PATCH 1/3 v4] powercap, intel_rapl, implement get_max_time_window
Date: Thu, 31 Mar 2016 18:28:59 +0000	[thread overview]
Message-ID: <1459448760.4569.87.camel@intel.com> (raw)
In-Reply-To: <1458563236-19269-2-git-send-email-prarit@redhat.com>

On Mon, 2016-03-21 at 08:27 -0400, Prarit Bhargava wrote:
> The MSR_PKG_POWER_INFO register (Intel ASDM, section 14.9.3
> "Package RAPL Domain") provides a maximum time window which the
> system can support.  This window is read-only and is currently
> not examined when setting the time windows for the package.
> 
Usually this field has lot of junk. It is not supported uniformly.
The system provides this value from another ACPI element called PPCC.
If supported this will be in 

$ /sys/bus/pci/devices/0000:00:04.0/power_limits
$ grep . *
power_limit_0_max_uw:15000000
power_limit_0_min_uw:125000
power_limit_0_step_uw:1000000
power_limit_0_tmax_us:32000000
power_limit_0_tmin_us:28000000
power_limit_1_max_uw:25000000
power_limit_1_min_uw:25000000
power_limit_1_step_uw:1000000
power_limit_1_tmax_us:0
power_limit_1_tmin_us:0

Thanks,
Srinivas
> This patch implements get_max_time_window_us() and checks the window
> when
> a user attempts to set power capping for the package.
> 
> Before the patch it was possible to set the window to, for example,
> 10000
> micro seconds:
> 
> [root@intel-chiefriver-03 rhel7]# echo 10000 >
> /sys/devices/virtual/powercap/intel-rapl/intel-
> rapl\:0/constraint_0_time_window_us;
> egrep ^ /sys/devices/virtual/powercap/intel-rapl/intel-
> rapl\:0/constraint_0_time_window_us
> 
> /sys/devices/virtual/powercap/intel-rapl/intel-
> rapl:0/constraint_0_time_window_us:1:9765
> 
> but from 'turbostat -d', the package is limited to 976us:
> 
> cpu0: MSR_PKG_POWER_INFO: 0x01200168 (45 W TDP, RAPL 36 - 0 W,
> 0.000977 sec.)
> 
> (Note, there appears to be a rounding issue in turbostat which needs
> to
> also be fixed.  Looking at the values in the register it is clear the
> value is 1/1024 = 976us.)
> 
> After the patch we are limited by the maximum time window:
> 
> [root@intel-chiefriver-03 rhel7]# echo 10000 >
> /sys/devices/virtual/powercap/intel-rapl/intel-
> rapl\:0/constraint_0_time_window_us;
> egrep ^ /sys/devices/virtual/powercap/intel-rapl/intel-
> rapl\:0/constraint_0_time_window_us
> 
> -bash: echo: write error: Invalid argument
> /sys/devices/virtual/powercap/intel-rapl/intel-
> rapl:0/constraint_0_time_window_us:1:976
> 
> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
> Cc: Prarit Bhargava <prarit@redhat.com>
> Cc: Radivoje Jovanovic <radivoje.jovanovic@intel.com>
> Cc: Seiichi Ikarashi <s.ikarashi@jp.fujitsu.com>
> Cc: Mathias Krause <minipli@googlemail.com>
> Cc: Ajay Thomas <ajay.thomas.david.rajamanickam@intel.com>
> Signed-off-by: Prarit Bhargava <prarit@redhat.com>
> ---
>  drivers/powercap/intel_rapl.c   |   31
> +++++++++++++++++++++++++++++++
>  drivers/powercap/powercap_sys.c |    6 ++++--
>  2 files changed, 35 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/powercap/intel_rapl.c
> b/drivers/powercap/intel_rapl.c
> index 6c592dc..feb063d 100644
> --- a/drivers/powercap/intel_rapl.c
> +++ b/drivers/powercap/intel_rapl.c
> @@ -493,13 +493,42 @@ static int get_current_power_limit(struct
> powercap_zone *power_zone, int id,
>  	return ret;
>  }
>  
> +static int get_max_time_window(struct powercap_zone *power_zone, int
> id,
> +			       u64 *data)
> +{
> +	struct rapl_domain *rd;
> +	int ret = 0;
> +	u64 val;
> +
> +	get_online_cpus();
> +	rd = power_zone_to_rapl_domain(power_zone);
> +
> +	if (rapl_read_data_raw(rd, MAX_TIME_WINDOW, true, &val))
> +		ret = -EIO;
> +	else
> +		*data = val;
> +
> +	put_online_cpus();
> +	return ret;
> +}
> +
>  static int set_time_window(struct powercap_zone *power_zone, int id,
>  								u64
> window)
>  {
>  	struct rapl_domain *rd;
>  	int ret = 0;
> +	u64 max_window;
>  
>  	get_online_cpus();
> +	ret = get_max_time_window(power_zone, id, &max_window);
> +	if (ret < 0)
> +		goto out;
> +
> +	if (window > max_window) {
> +		ret = -EINVAL;
> +		goto out;
> +	}
> +
>  	rd = power_zone_to_rapl_domain(power_zone);
>  	switch (rd->rpl[id].prim_id) {
>  	case PL1_ENABLE:
> @@ -511,6 +540,7 @@ static int set_time_window(struct powercap_zone
> *power_zone, int id,
>  	default:
>  		ret = -EINVAL;
>  	}
> +out:
>  	put_online_cpus();
>  	return ret;
>  }
> @@ -590,6 +620,7 @@ static const struct powercap_zone_constraint_ops
> constraint_ops = {
>  	.set_time_window_us = set_time_window,
>  	.get_time_window_us = get_time_window,
>  	.get_max_power_uw = get_max_power,
> +	.get_max_time_window_us = get_max_time_window,
>  	.get_name = get_constraint_name,
>  };
>  
> diff --git a/drivers/powercap/powercap_sys.c
> b/drivers/powercap/powercap_sys.c
> index 14bde0d..53fad0f 100644
> --- a/drivers/powercap/powercap_sys.c
> +++ b/drivers/powercap/powercap_sys.c
> @@ -101,7 +101,7 @@ static ssize_t store_constraint_##_attr(struct
> device *dev,\
>  	int err; \
>  	u64 value; \
>  	struct powercap_zone *power_zone = to_powercap_zone(dev); \
> -	int id; \
> +	int id, ret; \
>  	struct powercap_zone_constraint *pconst;\
>  	\
>  	if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id)) \
> @@ -113,8 +113,10 @@ static ssize_t store_constraint_##_attr(struct
> device *dev,\
>  	if (err) \
>  		return -EINVAL; \
>  	if (pconst && pconst->ops && pconst->ops->set_##_attr) { \
> -		if (!pconst->ops->set_##_attr(power_zone, id,
> value)) \
> +		ret = pconst->ops->set_##_attr(power_zone, id,
> value); \
> +		if (!ret) \
>  			return count; \
> +		return ret; \
>  	} \
>  	\
>  	return -ENODATA; \

  reply	other threads:[~2016-03-31 18:29 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-21 12:27 [RESEND PATCH 0/3 v4] powercap, intel_rapl, implement time window checks Prarit Bhargava
2016-03-21 12:27 ` [PATCH 1/3 v4] powercap, intel_rapl, implement get_max_time_window Prarit Bhargava
2016-03-31 18:28   ` Pandruvada, Srinivas [this message]
2016-04-05 13:14     ` Prarit Bhargava
2016-04-11 11:33     ` Prarit Bhargava
2016-04-11 14:11       ` Pandruvada, Srinivas
2016-03-21 12:27 ` [PATCH 2/3 v4] powercap, intel_rapl, implement check for minimum time window Prarit Bhargava
2016-03-21 12:27 ` [PATCH 3/3 v3] powercap, intel_rapl, Add ignore_max_time_window_check module parameter for broken BIOSes Prarit Bhargava
2016-03-28 18:07 ` [RESEND PATCH 0/3 v4] powercap, intel_rapl, implement time window checks Pandruvada, Srinivas
  -- strict thread matches above, loose matches on Subject: below --
2016-03-16 12:00 [PATCH " Prarit Bhargava
2016-03-16 12:00 ` [PATCH 1/3 v4] powercap, intel_rapl, implement get_max_time_window Prarit Bhargava
2016-03-19  2:18   ` 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=1459448760.4569.87.camel@intel.com \
    --to=srinivas.pandruvada@intel.com \
    --cc=ajay.thomas.david.rajamanickam@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=minipli@googlemail.com \
    --cc=prarit@redhat.com \
    --cc=radivoje.jovanovic@intel.com \
    --cc=rafael.j.wysocki@intel.com \
    --cc=s.ikarashi@jp.fujitsu.com \
    /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;
as well as URLs for NNTP newsgroup(s).