public inbox for [email protected]
 help / color / mirror / Atom feed
From: Christian Loehle <[email protected]>
To: [email protected], [email protected],
	[email protected], [email protected]
Cc: [email protected], [email protected],
	[email protected], [email protected],
	[email protected], [email protected],
	[email protected], [email protected],
	[email protected], [email protected], [email protected],
	[email protected], [email protected],
	[email protected], [email protected], [email protected]
Subject: [RFC PATCH] TEST: cpufreq: intel_pstate: sysfs iowait_boost_cap
Date: Thu, 12 Sep 2024 12:22:21 +0100	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

For non-HWP systems, rework iowait boost to be linear and add
the sysfs knob iowait_boost_cap to limit the maximum boost in
8 steps.

I don't see a good way to translate this to HWP, as the
boost applied isn't as static as it is for non-HWP, but there
is already the dynamic_hwp_boost sysfs to enable/disable
completely.

Signed-off-by: Christian Loehle <[email protected]>
---
 drivers/cpufreq/intel_pstate.c | 39 ++++++++++++++++++++++++++++++++--
 1 file changed, 37 insertions(+), 2 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index c0278d023cfc..6882d8c74e61 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -183,6 +183,7 @@ struct global_params {
 	bool turbo_disabled;
 	int max_perf_pct;
 	int min_perf_pct;
+	unsigned int iowait_boost_cap;
 };
 
 /**
@@ -1444,6 +1445,30 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b,
 	return count;
 }
 
+static ssize_t store_iowait_boost_cap(struct kobject *a, struct kobj_attribute *b,
+				  const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+
+	ret = sscanf(buf, "%u", &input);
+	if (ret != 1)
+		return -EINVAL;
+
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!intel_pstate_driver) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
+	global.iowait_boost_cap = clamp_t(int, input, 0, 8);
+
+	mutex_unlock(&intel_pstate_driver_lock);
+
+	return count;
+}
+
 static ssize_t show_hwp_dynamic_boost(struct kobject *kobj,
 				struct kobj_attribute *attr, char *buf)
 {
@@ -1497,6 +1522,7 @@ static ssize_t store_energy_efficiency(struct kobject *a, struct kobj_attribute
 
 show_one(max_perf_pct, max_perf_pct);
 show_one(min_perf_pct, min_perf_pct);
+show_one(iowait_boost_cap, iowait_boost_cap);
 
 define_one_global_rw(status);
 define_one_global_rw(no_turbo);
@@ -1506,6 +1532,7 @@ define_one_global_ro(turbo_pct);
 define_one_global_ro(num_pstates);
 define_one_global_rw(hwp_dynamic_boost);
 define_one_global_rw(energy_efficiency);
+define_one_global_rw(iowait_boost_cap);
 
 static struct attribute *intel_pstate_attributes[] = {
 	&status.attr,
@@ -1562,6 +1589,9 @@ static void __init intel_pstate_sysfs_expose_params(void)
 		rc = sysfs_create_file(intel_pstate_kobject, &energy_efficiency.attr);
 		WARN_ON(rc);
 	}
+
+	rc = sysfs_create_file(intel_pstate_kobject, &iowait_boost_cap.attr);
+	WARN_ON(rc);
 }
 
 static void __init intel_pstate_sysfs_remove(void)
@@ -2322,18 +2352,23 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time,
 		if (delta_ns > TICK_NSEC) {
 			cpu->iowait_boost = ONE_EIGHTH_FP;
 		} else if (cpu->iowait_boost >= ONE_EIGHTH_FP) {
-			cpu->iowait_boost <<= 1;
+			cpu->iowait_boost += ONE_EIGHTH_FP;
 			if (cpu->iowait_boost > int_tofp(1))
 				cpu->iowait_boost = int_tofp(1);
 		} else {
 			cpu->iowait_boost = ONE_EIGHTH_FP;
 		}
+		if (cpu->iowait_boost > global.iowait_boost_cap * ONE_EIGHTH_FP)
+			cpu->iowait_boost = global.iowait_boost_cap * ONE_EIGHTH_FP;
 	} else if (cpu->iowait_boost) {
 		/* Clear iowait_boost if the CPU may have been idle. */
 		if (delta_ns > TICK_NSEC)
 			cpu->iowait_boost = 0;
-		else
+		else {
 			cpu->iowait_boost >>= 1;
+			if (cpu->iowait_boost < ONE_EIGHTH_FP)
+				cpu->iowait_boost = 0;
+		}
 	}
 	cpu->last_update = time;
 	delta_ns = time - cpu->sample.time;
-- 
2.25.1

  reply	other threads:[~2024-09-12 11:22 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-09-05  9:26 [RFT RFC PATCH 0/8] cpufreq: cpuidle: Remove iowait behaviour Christian Loehle
2024-09-05  9:26 ` [RFC PATCH 1/8] cpuidle: menu: Remove iowait influence Christian Loehle
2024-09-05  9:26 ` [RFC PATCH 2/8] cpuidle: Prefer teo over menu governor Christian Loehle
2024-09-05  9:26 ` [RFC PATCH 3/8] TEST: cpufreq/schedutil: Linear iowait boost step Christian Loehle
2024-09-05  9:26 ` [RFC PATCH 4/8] TEST: cpufreq/schedutil: iowait boost cap sysfs Christian Loehle
2024-09-05  9:26 ` [RFC PATCH 5/8] cpufreq/schedutil: Remove iowait boost Christian Loehle
2024-09-05  9:26 ` [RFC PATCH 6/8] cpufreq: intel_pstate: " Christian Loehle
2024-09-12 11:22   ` Christian Loehle [this message]
2024-09-05  9:26 ` [RFC PATCH 7/8] cpufreq: Remove SCHED_CPUFREQ_IOWAIT update Christian Loehle
2024-09-05  9:26 ` [RFC PATCH 8/8] io_uring: Do not set iowait before sleeping Christian Loehle
2024-09-05 12:31 ` [RFT RFC PATCH 0/8] cpufreq: cpuidle: Remove iowait behaviour Christian Loehle

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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