From: David Dai <davidai@google.com>
To: "Rafael J. Wysocki" <rafael@kernel.org>,
Viresh Kumar <viresh.kumar@linaro.org>,
Rob Herring <robh+dt@kernel.org>,
Krzysztof Kozlowski <krzysztof.kozlowski+dt@linaro.org>,
Conor Dooley <conor+dt@kernel.org>,
Sudeep Holla <sudeep.holla@arm.com>,
David Dai <davidai@google.com>,
Saravana Kannan <saravanak@google.com>
Cc: Quentin Perret <qperret@google.com>,
Masami Hiramatsu <mhiramat@google.com>,
Will Deacon <will@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Vincent Guittot <vincent.guittot@linaro.org>,
Marc Zyngier <maz@kernel.org>,
Oliver Upton <oliver.upton@linux.dev>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Pavan Kondeti <quic_pkondeti@quicinc.com>,
Gupta Pankaj <pankaj.gupta@amd.com>,
Mel Gorman <mgorman@suse.de>,
kernel-team@android.com, linux-pm@vger.kernel.org,
devicetree@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v5 2/2] cpufreq: add virtual-cpufreq driver
Date: Fri, 26 Jan 2024 16:43:16 -0800 [thread overview]
Message-ID: <20240127004321.1902477-3-davidai@google.com> (raw)
In-Reply-To: <20240127004321.1902477-1-davidai@google.com>
Introduce a virtualized cpufreq driver for guest kernels to improve
performance and power of workloads within VMs.
This driver does two main things:
1. Sends the frequency of vCPUs as a hint to the host. The host uses the
hint to schedule the vCPU threads and decide physical CPU frequency.
2. If a VM does not support a virtualized FIE(like AMUs), it queries the
host CPU frequency by reading a MMIO region of a virtual cpufreq device
to update the guest's frequency scaling factor periodically. This enables
accurate Per-Entity Load Tracking for tasks running in the guest.
Co-developed-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: David Dai <davidai@google.com>
---
drivers/cpufreq/Kconfig | 15 +++
drivers/cpufreq/Makefile | 1 +
drivers/cpufreq/virtual-cpufreq.c | 209 ++++++++++++++++++++++++++++++
include/linux/arch_topology.h | 1 +
4 files changed, 226 insertions(+)
create mode 100644 drivers/cpufreq/virtual-cpufreq.c
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 35efb53d5492..f2d37075aa10 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -217,6 +217,21 @@ config CPUFREQ_DT
If in doubt, say N.
+config CPUFREQ_VIRT
+ tristate "Virtual cpufreq driver"
+ depends on OF
+ select PM_OPP
+ help
+ This adds a virtualized cpufreq driver for guest kernels that
+ read/writes to a MMIO region for a virtualized cpufreq device to
+ communicate with the host. It sends frequency updates to the host
+ which gets used as a hint to schedule vCPU threads and select CPU
+ frequency. If a VM does not support a virtualized FIE such as AMUs,
+ it updates the frequency scaling factor by polling host CPU frequency
+ to enable accurate Per-Entity Load Tracking for tasks running in the guest.
+
+ If in doubt, say N.
+
config CPUFREQ_DT_PLATDEV
tristate "Generic DT based cpufreq platdev driver"
depends on OF
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 8d141c71b016..eb72ecdc24db 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_CPU_FREQ_GOV_ATTR_SET) += cpufreq_governor_attr_set.o
obj-$(CONFIG_CPUFREQ_DT) += cpufreq-dt.o
obj-$(CONFIG_CPUFREQ_DT_PLATDEV) += cpufreq-dt-platdev.o
+obj-$(CONFIG_CPUFREQ_VIRT) += virtual-cpufreq.o
# Traces
CFLAGS_amd-pstate-trace.o := -I$(src)
diff --git a/drivers/cpufreq/virtual-cpufreq.c b/drivers/cpufreq/virtual-cpufreq.c
new file mode 100644
index 000000000000..0132f430a13e
--- /dev/null
+++ b/drivers/cpufreq/virtual-cpufreq.c
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 Google LLC
+ */
+
+#include <linux/arch_topology.h>
+#include <linux/cpufreq.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+
+#define REG_CUR_FREQ_KHZ_OFFSET 0x0
+#define REG_SET_FREQ_KHZ_OFFSET 0x4
+#define PER_CPU_OFFSET 0x8
+
+static void __iomem *base;
+
+static void virt_scale_freq_tick(void)
+{
+ int cpu = smp_processor_id();
+ u32 max_freq = (u32)cpufreq_get_hw_max_freq(cpu);
+ u64 cur_freq;
+ unsigned long scale;
+
+ cur_freq = (u64)readl_relaxed(base + cpu * PER_CPU_OFFSET
+ + REG_CUR_FREQ_KHZ_OFFSET);
+
+ cur_freq <<= SCHED_CAPACITY_SHIFT;
+ scale = (unsigned long)div_u64(cur_freq, max_freq);
+ scale = min(scale, SCHED_CAPACITY_SCALE);
+
+ this_cpu_write(arch_freq_scale, scale);
+}
+
+static struct scale_freq_data virt_sfd = {
+ .source = SCALE_FREQ_SOURCE_VIRT,
+ .set_freq_scale = virt_scale_freq_tick,
+};
+
+static unsigned int virt_cpufreq_set_perf(struct cpufreq_policy *policy,
+ unsigned int target_freq)
+{
+ writel_relaxed(target_freq,
+ base + policy->cpu * PER_CPU_OFFSET + REG_SET_FREQ_KHZ_OFFSET);
+ return 0;
+}
+
+static unsigned int virt_cpufreq_fast_switch(struct cpufreq_policy *policy,
+ unsigned int target_freq)
+{
+ virt_cpufreq_set_perf(policy, target_freq);
+ return target_freq;
+}
+
+static int virt_cpufreq_target_index(struct cpufreq_policy *policy,
+ unsigned int index)
+{
+ return virt_cpufreq_set_perf(policy,
+ policy->freq_table[index].frequency);
+}
+
+static int virt_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+ struct cpufreq_frequency_table *table;
+ struct device *cpu_dev;
+ int ret;
+
+ cpu_dev = get_cpu_device(policy->cpu);
+ if (!cpu_dev)
+ return -ENODEV;
+
+ ret = dev_pm_opp_of_add_table(cpu_dev);
+ if (ret)
+ return ret;
+
+ ret = dev_pm_opp_get_opp_count(cpu_dev);
+ if (ret <= 0) {
+ dev_err(cpu_dev, "OPP table can't be empty\n");
+ return -ENODEV;
+ }
+
+ ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &table);
+ if (ret) {
+ dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
+ return ret;
+ }
+
+ policy->freq_table = table;
+
+ /*
+ * To simplify and improve latency of handling frequency requests on
+ * the host side, this ensures that the vCPU thread triggering the MMIO
+ * abort is the same thread whose performance constraints (Ex. uclamp
+ * settings) need to be updated. This simplifies the VMM (Virtual
+ * Machine Manager) having to find the correct vCPU thread and/or
+ * facing permission issues when configuring other threads.
+ */
+ policy->dvfs_possible_from_any_cpu = false;
+ policy->fast_switch_possible = true;
+
+ /*
+ * Using the default SCALE_FREQ_SOURCE_CPUFREQ is insufficient since
+ * the actual physical CPU frequency may not match requested frequency
+ * from the vCPU thread due to frequency update latencies or other
+ * inputs to the physical CPU frequency selection. This additional FIE
+ * source allows for more accurate freq_scale updates and only takes
+ * effect if another FIE source such as AMUs have not been registered.
+ */
+ topology_set_scale_freq_source(&virt_sfd, policy->cpus);
+
+ return 0;
+}
+
+static int virt_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+ struct device *cpu_dev;
+
+ cpu_dev = get_cpu_device(policy->cpu);
+ if (!cpu_dev)
+ return -ENODEV;
+
+ topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_VIRT, policy->related_cpus);
+ dev_pm_opp_free_cpufreq_table(cpu_dev, &policy->freq_table);
+ return 0;
+}
+
+static int virt_cpufreq_online(struct cpufreq_policy *policy)
+{
+ /* Nothing to restore. */
+ return 0;
+}
+
+static int virt_cpufreq_offline(struct cpufreq_policy *policy)
+{
+ /* Dummy offline() to avoid exit() being called and freeing resources. */
+ return 0;
+}
+
+static struct cpufreq_driver cpufreq_virt_driver = {
+ .name = "virt-cpufreq",
+ .init = virt_cpufreq_cpu_init,
+ .exit = virt_cpufreq_cpu_exit,
+ .online = virt_cpufreq_online,
+ .offline = virt_cpufreq_offline,
+ .verify = cpufreq_generic_frequency_table_verify,
+ .target_index = virt_cpufreq_target_index,
+ .fast_switch = virt_cpufreq_fast_switch,
+ .attr = cpufreq_generic_attr,
+};
+
+static int virt_cpufreq_driver_probe(struct platform_device *pdev)
+{
+ int ret;
+
+ base = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ ret = cpufreq_register_driver(&cpufreq_virt_driver);
+ if (ret) {
+ dev_err(&pdev->dev, "Virtual CPUFreq driver failed to register: %d\n", ret);
+ return ret;
+ }
+
+ dev_dbg(&pdev->dev, "Virtual CPUFreq driver initialized\n");
+ return 0;
+}
+
+static int virt_cpufreq_driver_remove(struct platform_device *pdev)
+{
+ cpufreq_unregister_driver(&cpufreq_virt_driver);
+ return 0;
+}
+
+static const struct of_device_id virt_cpufreq_match[] = {
+ { .compatible = "qemu,virtual-cpufreq", .data = NULL},
+ {}
+};
+MODULE_DEVICE_TABLE(of, virt_cpufreq_match);
+
+static struct platform_driver virt_cpufreq_driver = {
+ .probe = virt_cpufreq_driver_probe,
+ .remove = virt_cpufreq_driver_remove,
+ .driver = {
+ .name = "virt-cpufreq",
+ .of_match_table = virt_cpufreq_match,
+ },
+};
+
+static int __init virt_cpufreq_init(void)
+{
+ return platform_driver_register(&virt_cpufreq_driver);
+}
+postcore_initcall(virt_cpufreq_init);
+
+static void __exit virt_cpufreq_exit(void)
+{
+ platform_driver_unregister(&virt_cpufreq_driver);
+}
+module_exit(virt_cpufreq_exit);
+
+MODULE_DESCRIPTION("Virtual cpufreq driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index a63d61ca55af..fb272b4bf7b1 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -49,6 +49,7 @@ enum scale_freq_source {
SCALE_FREQ_SOURCE_CPUFREQ = 0,
SCALE_FREQ_SOURCE_ARCH,
SCALE_FREQ_SOURCE_CPPC,
+ SCALE_FREQ_SOURCE_VIRT,
};
struct scale_freq_data {
--
2.43.0.429.g432eaa2c6b-goog
next prev parent reply other threads:[~2024-01-27 0:43 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-27 0:43 [PATCH v5 0/2] Improve VM CPUfreq and task placement behavior David Dai
2024-01-27 0:43 ` [PATCH v5 1/2] dt-bindings: cpufreq: add virtual cpufreq device David Dai
2024-01-31 17:06 ` Rob Herring
2024-01-31 18:23 ` Saravana Kannan
2024-02-02 15:53 ` Rob Herring
2024-02-04 10:23 ` Marc Zyngier
2024-03-11 11:40 ` Quentin Perret
2024-02-05 8:38 ` Viresh Kumar
2024-02-05 16:39 ` Rob Herring
2024-02-15 11:26 ` Sudeep Holla
2024-05-02 20:17 ` David Dai
2024-05-07 10:21 ` Sudeep Holla
2024-05-17 20:59 ` David Dai
2024-01-27 0:43 ` David Dai [this message]
2024-01-31 1:13 ` [PATCH v5 2/2] cpufreq: add virtual-cpufreq driver kernel test robot
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=20240127004321.1902477-3-davidai@google.com \
--to=davidai@google.com \
--cc=conor+dt@kernel.org \
--cc=devicetree@vger.kernel.org \
--cc=dietmar.eggemann@arm.com \
--cc=kernel-team@android.com \
--cc=krzysztof.kozlowski+dt@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=maz@kernel.org \
--cc=mgorman@suse.de \
--cc=mhiramat@google.com \
--cc=oliver.upton@linux.dev \
--cc=pankaj.gupta@amd.com \
--cc=peterz@infradead.org \
--cc=qperret@google.com \
--cc=quic_pkondeti@quicinc.com \
--cc=rafael@kernel.org \
--cc=robh+dt@kernel.org \
--cc=saravanak@google.com \
--cc=sudeep.holla@arm.com \
--cc=vincent.guittot@linaro.org \
--cc=viresh.kumar@linaro.org \
--cc=will@kernel.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).