From: Beata Michalska <beata.michalska@arm.com>
To: linux-kernel@vger.kernel.org,
linux-arm-kernel@lists.infradead.org, ionela.voinescu@arm.com,
vanshikonda@os.amperecomputing.com
Cc: sudeep.holla@arm.com, will@kernel.org, catalin.marinas@arm.com,
vincent.guittot@linaro.org, sumitg@nvidia.com,
yang@os.amperecomputing.com, lihuisong@huawei.com,
viresh.kumar@linaro.org
Subject: [PATCH v5 3/5] arm64: Provide an AMU-based version of arch_freq_get_on_cpu
Date: Wed, 17 Apr 2024 10:38:46 +0100 [thread overview]
Message-ID: <20240417093848.1555462-4-beata.michalska@arm.com> (raw)
In-Reply-To: <20240417093848.1555462-1-beata.michalska@arm.com>
With the Frequency Invariance Engine (FIE) being already wired up with
sched tick and making use of relevant (core counter and constant
counter) AMU counters, getting the current frequency for a given CPU,
can be achieved by utilizing the frequency scale factor which reflects
an average CPU frequency for the last tick period length.
The solution is partially based on APERF/MPERF implementation of
arch_freq_get_on_cpu.
Suggested-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Beata Michalska <beata.michalska@arm.com>
---
arch/arm64/kernel/topology.c | 110 +++++++++++++++++++++++++++++++----
1 file changed, 100 insertions(+), 10 deletions(-)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 3c814a278534..475fdbf3032a 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -17,6 +17,7 @@
#include <linux/cpufreq.h>
#include <linux/init.h>
#include <linux/percpu.h>
+#include <linux/sched/isolation.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
@@ -88,18 +89,28 @@ int __init parse_acpi_topology(void)
* initialized.
*/
static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) = 1UL << (2 * SCHED_CAPACITY_SHIFT);
-static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
-static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
static cpumask_var_t amu_fie_cpus;
+struct amu_cntr_sample {
+ u64 arch_const_cycles_prev;
+ u64 arch_core_cycles_prev;
+ unsigned long last_update;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct amu_cntr_sample, cpu_amu_samples);
+
void update_freq_counters_refs(void)
{
- this_cpu_write(arch_core_cycles_prev, read_corecnt());
- this_cpu_write(arch_const_cycles_prev, read_constcnt());
+ struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
+
+ amu_sample->arch_core_cycles_prev = read_corecnt();
+ amu_sample->arch_const_cycles_prev = read_constcnt();
}
static inline bool freq_counters_valid(int cpu)
{
+ struct amu_cntr_sample *amu_sample = per_cpu_ptr(&cpu_amu_samples, cpu);
+
if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
return false;
@@ -108,8 +119,8 @@ static inline bool freq_counters_valid(int cpu)
return false;
}
- if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) ||
- !per_cpu(arch_core_cycles_prev, cpu))) {
+ if (unlikely(!amu_sample->arch_const_cycles_prev ||
+ !amu_sample->arch_core_cycles_prev)) {
pr_debug("CPU%d: cycle counters are not enabled.\n", cpu);
return false;
}
@@ -152,17 +163,22 @@ void freq_inv_set_max_ratio(int cpu, u64 max_rate)
static void amu_scale_freq_tick(void)
{
+ struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
u64 prev_core_cnt, prev_const_cnt;
u64 core_cnt, const_cnt, scale;
- prev_const_cnt = this_cpu_read(arch_const_cycles_prev);
- prev_core_cnt = this_cpu_read(arch_core_cycles_prev);
+ prev_const_cnt = amu_sample->arch_const_cycles_prev;
+ prev_core_cnt = amu_sample->arch_core_cycles_prev;
update_freq_counters_refs();
- const_cnt = this_cpu_read(arch_const_cycles_prev);
- core_cnt = this_cpu_read(arch_core_cycles_prev);
+ const_cnt = amu_sample->arch_const_cycles_prev;
+ core_cnt = amu_sample->arch_core_cycles_prev;
+ /*
+ * This should not happen unless the AMUs have been reset and the
+ * counter values have not been restored - unlikely
+ */
if (unlikely(core_cnt <= prev_core_cnt ||
const_cnt <= prev_const_cnt))
return;
@@ -182,6 +198,8 @@ static void amu_scale_freq_tick(void)
scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
this_cpu_write(arch_freq_scale, (unsigned long)scale);
+
+ amu_sample->last_update = jiffies;
}
static struct scale_freq_data amu_sfd = {
@@ -189,6 +207,78 @@ static struct scale_freq_data amu_sfd = {
.set_freq_scale = amu_scale_freq_tick,
};
+static __always_inline bool amu_fie_cpu_supported(unsigned int cpu)
+{
+ return cpumask_available(amu_fie_cpus) &&
+ cpumask_test_cpu(cpu, amu_fie_cpus);
+}
+
+#define AMU_SAMPLE_EXP_MS 20
+
+unsigned int arch_freq_get_on_cpu(int cpu)
+{
+ struct amu_cntr_sample *amu_sample;
+ unsigned int start_cpu = cpu;
+ unsigned long last_update;
+ unsigned int freq = 0;
+ u64 scale;
+
+ if (!amu_fie_cpu_supported(cpu) || !arch_scale_freq_ref(cpu))
+ return 0;
+
+retry:
+ amu_sample = per_cpu_ptr(&cpu_amu_samples, cpu);
+
+ last_update = amu_sample->last_update;
+
+ /*
+ * For those CPUs that are in full dynticks mode,
+ * and those that have not seen tick for a while
+ * try an alternative source for the counters (and thus freq scale),
+ * if available, for given policy:
+ * this boils down to identifying an active cpu within the same freq
+ * domain, if any.
+ */
+ if (!housekeeping_cpu(cpu, HK_TYPE_TICK) ||
+ time_is_before_jiffies(last_update + msecs_to_jiffies(AMU_SAMPLE_EXP_MS))) {
+ struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+ int ref_cpu = cpu;
+
+ if (!policy)
+ goto leave;
+
+ if (!policy_is_shared(policy)) {
+ cpufreq_cpu_put(policy);
+ goto leave;
+ }
+
+ do {
+ ref_cpu = cpumask_next_wrap(ref_cpu, policy->cpus,
+ start_cpu, false);
+
+ } while (ref_cpu < nr_cpu_ids && idle_cpu(ref_cpu));
+
+ cpufreq_cpu_put(policy);
+
+ if (ref_cpu >= nr_cpu_ids)
+ /* No alternative to pull info from */
+ goto leave;
+
+ cpu = ref_cpu;
+ goto retry;
+ }
+ /*
+ * Reversed computation to the one used to determine
+ * the arch_freq_scale value
+ * (see amu_scale_freq_tick for details)
+ */
+ scale = arch_scale_freq_capacity(cpu);
+ freq = scale * arch_scale_freq_ref(cpu);
+ freq >>= SCHED_CAPACITY_SHIFT;
+leave:
+ return freq;
+}
+
static void amu_fie_setup(const struct cpumask *cpus)
{
int cpu;
--
2.25.1
next prev parent reply other threads:[~2024-04-17 9:39 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-17 9:38 [PATCH v5 0/5] Add support for AArch64 AMUv1-based arch_freq_get_on_cpu Beata Michalska
2024-04-17 9:38 ` [PATCH v5 1/5] arch_topology: init capacity_freq_ref to 0 Beata Michalska
2024-04-18 10:50 ` Sudeep Holla
2024-04-17 9:38 ` [PATCH v5 2/5] arm64: amu: Rule out potential use after free Beata Michalska
2024-04-18 10:50 ` Sudeep Holla
2024-04-18 15:55 ` Beata Michalska
2024-04-24 10:25 ` Sudeep Holla
2024-04-25 14:27 ` Beata Michalska
2024-05-07 7:24 ` Ionela Voinescu
2024-04-17 9:38 ` Beata Michalska [this message]
2024-04-18 1:39 ` [PATCH v5 3/5] arm64: Provide an AMU-based version of arch_freq_get_on_cpu Vanshidhar Konda
2024-04-26 10:50 ` Beata Michalska
2024-04-17 9:38 ` [PATCH v5 4/5] arm64: Update AMU-based frequency scale factor on entering idle Beata Michalska
2024-04-17 9:38 ` [PATCH v5 5/5] cpufreq: Use arch specific feedback for cpuinfo_cur_freq Beata Michalska
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=20240417093848.1555462-4-beata.michalska@arm.com \
--to=beata.michalska@arm.com \
--cc=catalin.marinas@arm.com \
--cc=ionela.voinescu@arm.com \
--cc=lihuisong@huawei.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=sudeep.holla@arm.com \
--cc=sumitg@nvidia.com \
--cc=vanshikonda@os.amperecomputing.com \
--cc=vincent.guittot@linaro.org \
--cc=viresh.kumar@linaro.org \
--cc=will@kernel.org \
--cc=yang@os.amperecomputing.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 read-only IMAP folder(s) and NNTP newsgroup(s).