From: "Rafael J. Wysocki" <rjw@rjwysocki.net>
To: Linux PM list <linux-pm@vger.kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
Viresh Kumar <viresh.kumar@linaro.org>,
Juri Lelli <juri.lelli@arm.com>,
Steve Muckle <steve.muckle@linaro.org>,
Thomas Gleixner <tglx@linutronix.de>
Subject: [PATCH v6 2/3] cpufreq: intel_pstate: Replace timers with utilization update callbacks
Date: Wed, 10 Feb 2016 16:25:36 +0100 [thread overview]
Message-ID: <1810149.UMGIdihhTe@vostro.rjw.lan> (raw)
In-Reply-To: <2111826.yKEUOzphHC@vostro.rjw.lan>
From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Instead of using a per-CPU deferrable timer for utilization sampling
and P-states adjustments, register a utilization update callback that
will be invoked from the scheduler on utilization changes.
The sampling rate is still the same as what was used for the deferrable
timers, so the functional impact of this patch should not be significant.
Based on an earlier patch from Srinivas Pandruvada.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
No changes from the previous version.
---
drivers/cpufreq/intel_pstate.c | 103 +++++++++++++++--------------------------
1 file changed, 39 insertions(+), 64 deletions(-)
Index: linux-pm/drivers/cpufreq/intel_pstate.c
===================================================================
--- linux-pm.orig/drivers/cpufreq/intel_pstate.c
+++ linux-pm/drivers/cpufreq/intel_pstate.c
@@ -71,7 +71,7 @@ struct sample {
u64 mperf;
u64 tsc;
int freq;
- ktime_t time;
+ u64 time;
};
struct pstate_data {
@@ -103,13 +103,13 @@ struct _pid {
struct cpudata {
int cpu;
- struct timer_list timer;
+ struct update_util_data update_util;
struct pstate_data pstate;
struct vid_data vid;
struct _pid pid;
- ktime_t last_sample_time;
+ u64 last_sample_time;
u64 prev_aperf;
u64 prev_mperf;
u64 prev_tsc;
@@ -120,6 +120,7 @@ struct cpudata {
static struct cpudata **all_cpu_data;
struct pstate_adjust_policy {
int sample_rate_ms;
+ s64 sample_rate_ns;
int deadband;
int setpoint;
int p_gain_pct;
@@ -712,7 +713,7 @@ static void core_set_pstate(struct cpuda
if (limits->no_turbo && !limits->turbo_disabled)
val |= (u64)1 << 32;
- wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
+ wrmsrl(MSR_IA32_PERF_CTL, val);
}
static int knl_get_turbo_pstate(void)
@@ -883,7 +884,7 @@ static inline void intel_pstate_calc_bus
sample->core_pct_busy = (int32_t)core_pct;
}
-static inline void intel_pstate_sample(struct cpudata *cpu)
+static inline void intel_pstate_sample(struct cpudata *cpu, u64 time)
{
u64 aperf, mperf;
unsigned long flags;
@@ -900,7 +901,7 @@ static inline void intel_pstate_sample(s
local_irq_restore(flags);
cpu->last_sample_time = cpu->sample.time;
- cpu->sample.time = ktime_get();
+ cpu->sample.time = time;
cpu->sample.aperf = aperf;
cpu->sample.mperf = mperf;
cpu->sample.tsc = tsc;
@@ -915,22 +916,6 @@ static inline void intel_pstate_sample(s
cpu->prev_tsc = tsc;
}
-static inline void intel_hwp_set_sample_time(struct cpudata *cpu)
-{
- int delay;
-
- delay = msecs_to_jiffies(50);
- mod_timer_pinned(&cpu->timer, jiffies + delay);
-}
-
-static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
-{
- int delay;
-
- delay = msecs_to_jiffies(pid_params.sample_rate_ms);
- mod_timer_pinned(&cpu->timer, jiffies + delay);
-}
-
static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
{
struct sample *sample = &cpu->sample;
@@ -970,8 +955,7 @@ static inline int32_t get_target_pstate_
static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
{
int32_t core_busy, max_pstate, current_pstate, sample_ratio;
- s64 duration_us;
- u32 sample_time;
+ u64 duration_ns;
/*
* core_busy is the ratio of actual performance to max
@@ -990,18 +974,16 @@ static inline int32_t get_target_pstate_
core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
/*
- * Since we have a deferred timer, it will not fire unless
- * we are in C0. So, determine if the actual elapsed time
- * is significantly greater (3x) than our sample interval. If it
- * is, then we were idle for a long enough period of time
- * to adjust our busyness.
+ * Since our utilization update callback will not run unless we are
+ * in C0, check if the actual elapsed time is significantly greater (3x)
+ * than our sample interval. If it is, then we were idle for a long
+ * enough period of time to adjust our busyness.
*/
- sample_time = pid_params.sample_rate_ms * USEC_PER_MSEC;
- duration_us = ktime_us_delta(cpu->sample.time,
- cpu->last_sample_time);
- if (duration_us > sample_time * 3) {
- sample_ratio = div_fp(int_tofp(sample_time),
- int_tofp(duration_us));
+ duration_ns = cpu->sample.time - cpu->last_sample_time;
+ if ((s64)duration_ns > pid_params.sample_rate_ns * 3
+ && cpu->last_sample_time > 0) {
+ sample_ratio = div_fp(int_tofp(pid_params.sample_rate_ns),
+ int_tofp(duration_ns));
core_busy = mul_fp(core_busy, sample_ratio);
}
@@ -1031,23 +1013,17 @@ static inline void intel_pstate_adjust_b
sample->freq);
}
-static void intel_hwp_timer_func(unsigned long __data)
-{
- struct cpudata *cpu = (struct cpudata *) __data;
-
- intel_pstate_sample(cpu);
- intel_hwp_set_sample_time(cpu);
-}
-
-static void intel_pstate_timer_func(unsigned long __data)
+static void intel_pstate_update_util(struct update_util_data *data, u64 time,
+ unsigned long util, unsigned long max)
{
- struct cpudata *cpu = (struct cpudata *) __data;
-
- intel_pstate_sample(cpu);
+ struct cpudata *cpu = container_of(data, struct cpudata, update_util);
+ u64 delta_ns = time - cpu->sample.time;
- intel_pstate_adjust_busy_pstate(cpu);
-
- intel_pstate_set_sample_time(cpu);
+ if ((s64)delta_ns >= pid_params.sample_rate_ns) {
+ intel_pstate_sample(cpu, time);
+ if (!hwp_active)
+ intel_pstate_adjust_busy_pstate(cpu);
+ }
}
#define ICPU(model, policy) \
@@ -1095,24 +1071,19 @@ static int intel_pstate_init_cpu(unsigne
cpu->cpu = cpunum;
- if (hwp_active)
+ if (hwp_active) {
intel_pstate_hwp_enable(cpu);
+ pid_params.sample_rate_ms = 50;
+ pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC;
+ }
intel_pstate_get_cpu_pstates(cpu);
- init_timer_deferrable(&cpu->timer);
- cpu->timer.data = (unsigned long)cpu;
- cpu->timer.expires = jiffies + HZ/100;
-
- if (!hwp_active)
- cpu->timer.function = intel_pstate_timer_func;
- else
- cpu->timer.function = intel_hwp_timer_func;
-
intel_pstate_busy_pid_reset(cpu);
- intel_pstate_sample(cpu);
+ intel_pstate_sample(cpu, 0);
- add_timer_on(&cpu->timer, cpunum);
+ cpu->update_util.func = intel_pstate_update_util;
+ cpufreq_set_update_util_data(cpunum, &cpu->update_util);
pr_debug("intel_pstate: controlling: cpu %d\n", cpunum);
@@ -1196,7 +1167,9 @@ static void intel_pstate_stop_cpu(struct
pr_debug("intel_pstate: CPU %d exiting\n", cpu_num);
- del_timer_sync(&all_cpu_data[cpu_num]->timer);
+ cpufreq_set_update_util_data(cpu_num, NULL);
+ synchronize_rcu();
+
if (hwp_active)
return;
@@ -1260,6 +1233,7 @@ static int intel_pstate_msrs_not_valid(v
static void copy_pid_params(struct pstate_adjust_policy *policy)
{
pid_params.sample_rate_ms = policy->sample_rate_ms;
+ pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
pid_params.p_gain_pct = policy->p_gain_pct;
pid_params.i_gain_pct = policy->i_gain_pct;
pid_params.d_gain_pct = policy->d_gain_pct;
@@ -1451,7 +1425,8 @@ out:
get_online_cpus();
for_each_online_cpu(cpu) {
if (all_cpu_data[cpu]) {
- del_timer_sync(&all_cpu_data[cpu]->timer);
+ cpufreq_set_update_util_data(cpu, NULL);
+ synchronize_rcu();
kfree(all_cpu_data[cpu]);
}
}
next prev parent reply other threads:[~2016-02-10 15:36 UTC|newest]
Thread overview: 134+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-01-29 22:52 [PATCH 0/3] cpufreq: Replace timers with utilization update callbacks Rafael J. Wysocki
2016-01-29 22:53 ` [PATCH 1/3] cpufreq: Add a mechanism for registering " Rafael J. Wysocki
2016-02-04 3:31 ` Viresh Kumar
2016-01-29 22:56 ` [PATCH 2/3] cpufreq: intel_pstate: Replace timers with " Rafael J. Wysocki
2016-01-29 22:59 ` [PATCH 3/3] cpufreq: governor: " Rafael J. Wysocki
2016-02-03 1:16 ` [Update][PATCH " Rafael J. Wysocki
2016-02-04 4:49 ` Viresh Kumar
2016-02-04 10:54 ` Rafael J. Wysocki
2016-02-05 1:28 ` [PATCH 3/3 v3] " Rafael J. Wysocki
2016-02-05 6:50 ` Viresh Kumar
2016-02-05 13:36 ` Rafael J. Wysocki
2016-02-05 14:47 ` Viresh Kumar
2016-02-05 23:10 ` Rafael J. Wysocki
2016-02-07 9:10 ` Viresh Kumar
2016-02-07 14:43 ` Rafael J. Wysocki
2016-02-08 2:08 ` Rafael J. Wysocki
2016-02-08 11:52 ` Viresh Kumar
2016-02-08 12:52 ` Rafael J. Wysocki
2016-02-08 13:40 ` Rafael J. Wysocki
2016-02-05 23:01 ` Rafael J. Wysocki
2016-02-06 3:40 ` [PATCH 3/3 v4] " Rafael J. Wysocki
2016-02-07 9:20 ` Viresh Kumar
2016-02-07 14:36 ` Rafael J. Wysocki
2016-02-07 14:50 ` [PATCH 3/3 v5] " Rafael J. Wysocki
2016-02-07 15:36 ` Viresh Kumar
2016-02-09 10:01 ` Gautham R Shenoy
2016-02-09 18:49 ` Rafael J. Wysocki
2016-02-03 22:20 ` [PATCH 0/3] cpufreq: " Rafael J. Wysocki
2016-02-04 0:08 ` Srinivas Pandruvada
2016-02-04 17:16 ` Rafael J. Wysocki
2016-02-04 10:51 ` Juri Lelli
2016-02-04 17:19 ` Rafael J. Wysocki
2016-02-08 23:06 ` Rafael J. Wysocki
2016-02-09 0:39 ` Steve Muckle
2016-02-09 1:01 ` Rafael J. Wysocki
2016-02-09 20:05 ` Rafael J. Wysocki
2016-02-10 1:02 ` Steve Muckle
2016-02-10 1:57 ` Rafael J. Wysocki
2016-02-10 3:09 ` Rafael J. Wysocki
2016-02-10 19:47 ` Steve Muckle
2016-02-10 21:49 ` Rafael J. Wysocki
2016-02-10 22:07 ` Steve Muckle
2016-02-10 22:12 ` Rafael J. Wysocki
2016-02-11 11:59 ` Peter Zijlstra
2016-02-11 12:24 ` Juri Lelli
2016-02-11 15:26 ` Peter Zijlstra
2016-02-11 18:23 ` Vincent Guittot
2016-02-12 14:04 ` Peter Zijlstra
2016-02-12 14:48 ` Vincent Guittot
2016-03-01 13:58 ` Peter Zijlstra
2016-03-01 14:17 ` Juri Lelli
2016-03-01 14:24 ` Peter Zijlstra
2016-03-01 14:26 ` Peter Zijlstra
2016-03-01 14:42 ` Juri Lelli
2016-03-01 15:04 ` Peter Zijlstra
2016-03-01 19:49 ` Rafael J. Wysocki
2016-03-01 14:58 ` Vincent Guittot
2016-02-11 17:06 ` Steve Muckle
2016-02-11 17:30 ` Peter Zijlstra
2016-02-11 17:34 ` Rafael J. Wysocki
2016-02-11 17:38 ` Peter Zijlstra
2016-02-11 18:52 ` Steve Muckle
2016-02-11 19:04 ` Rafael J. Wysocki
2016-02-12 13:43 ` Rafael J. Wysocki
2016-02-12 14:10 ` Peter Zijlstra
2016-02-12 16:01 ` Rafael J. Wysocki
2016-02-12 16:15 ` Rafael J. Wysocki
2016-02-12 16:53 ` Ashwin Chaugule
2016-02-12 23:14 ` Rafael J. Wysocki
2016-02-12 17:02 ` Doug Smythies
2016-02-12 23:17 ` Rafael J. Wysocki
2016-02-10 12:33 ` Juri Lelli
2016-02-10 13:23 ` Rafael J. Wysocki
2016-02-10 14:03 ` Juri Lelli
2016-02-10 14:26 ` Rafael J. Wysocki
2016-02-10 14:46 ` Juri Lelli
2016-02-10 15:46 ` Rafael J. Wysocki
2016-02-10 16:05 ` Juri Lelli
2016-02-11 11:51 ` Peter Zijlstra
2016-02-11 12:08 ` Rafael J. Wysocki
2016-02-11 15:29 ` Peter Zijlstra
2016-02-11 15:58 ` Rafael J. Wysocki
2016-02-11 20:47 ` Rafael J. Wysocki
2016-02-10 15:17 ` [PATCH v6 " Rafael J. Wysocki
2016-02-10 15:21 ` [PATCH v6 1/3] cpufreq: Add mechanism for registering " Rafael J. Wysocki
2016-02-10 23:01 ` [PATCH v7 " Rafael J. Wysocki
2016-02-11 17:30 ` [PATCH v8 " Rafael J. Wysocki
2016-02-12 13:16 ` [PATCH v9 " Rafael J. Wysocki
2016-02-15 21:47 ` [PATCH v10 " Rafael J. Wysocki
2016-02-18 20:22 ` Rafael J. Wysocki
2016-02-19 8:09 ` Juri Lelli
2016-02-19 16:42 ` Srinivas Pandruvada
2016-02-19 17:26 ` Juri Lelli
2016-02-19 22:26 ` Rafael J. Wysocki
2016-02-22 9:42 ` Juri Lelli
2016-02-22 21:41 ` Rafael J. Wysocki
2016-02-23 11:10 ` Juri Lelli
2016-02-24 1:52 ` Rafael J. Wysocki
2016-02-22 10:45 ` Viresh Kumar
2016-02-19 17:28 ` Steve Muckle
2016-02-19 22:35 ` Rafael J. Wysocki
2016-02-23 3:58 ` Steve Muckle
2016-02-22 10:52 ` Peter Zijlstra
2016-02-22 14:33 ` Vincent Guittot
2016-02-22 15:31 ` Peter Zijlstra
2016-02-22 14:40 ` Juri Lelli
2016-02-22 15:42 ` Peter Zijlstra
2016-02-22 21:46 ` Rafael J. Wysocki
2016-02-19 22:14 ` Rafael J. Wysocki
2016-02-22 9:32 ` Juri Lelli
2016-02-22 21:26 ` Rafael J. Wysocki
2016-02-23 11:01 ` Juri Lelli
2016-02-24 2:01 ` Rafael J. Wysocki
2016-03-08 19:24 ` Michael Turquette
2016-03-08 20:40 ` Rafael J. Wysocki
[not found] ` <20160308220632.4103.13377@quark.deferred.io>
2016-03-08 22:43 ` Rafael J. Wysocki
2016-03-09 12:35 ` Peter Zijlstra
2016-03-09 13:22 ` Rafael J. Wysocki
2016-03-09 13:32 ` Ingo Molnar
2016-03-09 13:39 ` Rafael J. Wysocki
2016-03-10 2:12 ` Vincent Guittot
2016-02-10 15:25 ` Rafael J. Wysocki [this message]
2016-02-10 15:36 ` [PATCH v6 3/3] cpufreq: governor: Replace timers with " Rafael J. Wysocki
2016-02-10 23:11 ` [PATCH v6 0/3] cpufreq: " Doug Smythies
2016-02-10 23:17 ` Rafael J. Wysocki
2016-02-11 22:50 ` Doug Smythies
2016-02-11 23:28 ` Rafael J. Wysocki
2016-02-12 1:02 ` Doug Smythies
2016-02-12 1:20 ` Rafael J. Wysocki
2016-02-12 7:25 ` Doug Smythies
2016-02-12 13:39 ` Rafael J. Wysocki
2016-02-12 17:33 ` Doug Smythies
2016-02-12 23:21 ` Rafael J. Wysocki
2016-02-11 6:02 ` Srinivas Pandruvada
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=1810149.UMGIdihhTe@vostro.rjw.lan \
--to=rjw@rjwysocki.net \
--cc=juri.lelli@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=steve.muckle@linaro.org \
--cc=tglx@linutronix.de \
--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 read-only IMAP folder(s) and NNTP newsgroup(s).