From: "Rafael J. Wysocki" <rjw@rjwysocki.net>
To: Linux PM <linux-pm@vger.kernel.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>,
Viresh Kumar <viresh.kumar@linaro.org>,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
Zhang Rui <rui.zhang@intel.com>,
LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH 2/2] cpufreq: intel_pstate: Take target_min and target_max into account
Date: Thu, 05 Nov 2020 19:25:10 +0100 [thread overview]
Message-ID: <3200924.ySlC381xRO@kreacher> (raw)
In-Reply-To: <7417968.Ghue05m4RV@kreacher>
From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Make the intel_pstate driver take the new target_min and target_max
cpufreq policy parameters into accout when it operates in the passive
mode with HWP enabled, so as to fix the "powersave" governor behavior
in that case (currently, HWP is allowed to scale the performance all
the way up to the policy max limit when the "powersave" governor is
used, but it should be contrained to the policy min limit then).
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/cpufreq/intel_pstate.c | 32 ++++++++++++++++++++++----------
1 file changed, 22 insertions(+), 10 deletions(-)
Index: linux-pm/drivers/cpufreq/intel_pstate.c
===================================================================
--- linux-pm.orig/drivers/cpufreq/intel_pstate.c
+++ linux-pm/drivers/cpufreq/intel_pstate.c
@@ -2527,7 +2527,7 @@ static void intel_cpufreq_trace(struct c
}
static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate,
- bool fast_switch)
+ u32 target_max, bool fast_switch)
{
u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev;
@@ -2539,7 +2539,7 @@ static void intel_cpufreq_adjust_hwp(str
* field in it, so opportunistically update the max too if needed.
*/
value &= ~HWP_MAX_PERF(~0L);
- value |= HWP_MAX_PERF(cpu->max_perf_ratio);
+ value |= HWP_MAX_PERF(target_max);
if (value == prev)
return;
@@ -2562,19 +2562,31 @@ static void intel_cpufreq_adjust_perf_ct
pstate_funcs.get_val(cpu, target_pstate));
}
-static int intel_cpufreq_update_pstate(struct cpudata *cpu, int target_pstate,
- bool fast_switch)
+static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy,
+ int target_pstate, bool fast_switch)
{
+ struct cpudata *cpu = all_cpu_data[policy->cpu];
int old_pstate = cpu->pstate.current_pstate;
- target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
if (hwp_active) {
- intel_cpufreq_adjust_hwp(cpu, target_pstate, fast_switch);
- cpu->pstate.current_pstate = target_pstate;
+ int min_pstate = max(cpu->pstate.min_pstate, cpu->min_perf_ratio);
+ int max_pstate = max(min_pstate, cpu->max_perf_ratio);
+ int target_min = DIV_ROUND_UP(policy->target_min,
+ cpu->pstate.scaling);
+ int target_max = policy->target_max / cpu->pstate.scaling;
+
+ target_min = clamp_t(int, target_min, min_pstate, max_pstate);
+ target_max = clamp_t(int, target_max, min_pstate, max_pstate);
+
+ target_pstate = clamp_t(int, target_pstate, target_min, target_max);
+
+ intel_cpufreq_adjust_hwp(cpu, target_pstate, target_max, fast_switch);
} else if (target_pstate != old_pstate) {
+ target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+
intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch);
- cpu->pstate.current_pstate = target_pstate;
}
+ cpu->pstate.current_pstate = target_pstate;
intel_cpufreq_trace(cpu, fast_switch ? INTEL_PSTATE_TRACE_FAST_SWITCH :
INTEL_PSTATE_TRACE_TARGET, old_pstate);
@@ -2609,7 +2621,7 @@ static int intel_cpufreq_target(struct c
break;
}
- target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, false);
+ target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false);
freqs.new = target_pstate * cpu->pstate.scaling;
@@ -2628,7 +2640,7 @@ static unsigned int intel_cpufreq_fast_s
target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
- target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, true);
+ target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true);
return target_pstate * cpu->pstate.scaling;
}
prev parent reply other threads:[~2020-11-05 18:25 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-05 18:17 [PATCH 0/2] cpufreq: intel_pstate: Handle powersave governor correctly in the passive mode with HWP Rafael J. Wysocki
2020-11-05 18:23 ` [PATCH 1/2] cpufreq: Introduce target min and max frequency hints Rafael J. Wysocki
2020-11-06 1:49 ` Doug Smythies
2020-11-06 10:07 ` Viresh Kumar
2020-11-06 17:02 ` Rafael J. Wysocki
2020-11-09 4:39 ` Viresh Kumar
2020-11-09 12:27 ` Rafael J. Wysocki
2020-11-05 18:25 ` Rafael J. Wysocki [this message]
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=3200924.ySlC381xRO@kreacher \
--to=rjw@rjwysocki.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=rafael@kernel.org \
--cc=rui.zhang@intel.com \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=viresh.kumar@linaro.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;
as well as URLs for NNTP newsgroup(s).