Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Mon, 24 Sep 2018 09:44:55 -0700
From:   Matthias Kaehlcke <mka@chromium.org>
To:     Taniya Das <tdas@codeaurora.org>
Cc:     "Rafael J. Wysocki" <rjw@rjwysocki.net>,
        Viresh Kumar <viresh.kumar@linaro.org>,
        linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
        Stephen Boyd <sboyd@kernel.org>,
        Rajendra Nayak <rnayak@codeaurora.org>,
        Amit Nischal <anischal@codeaurora.org>,
        devicetree@vger.kernel.org, robh@kernel.org,
        skannan@codeaurora.org, amit.kucheria@linaro.org,
        evgreen@google.com
Subject: Re: [PATCH v7 2/2] cpufreq: qcom-hw: Add support for QCOM cpufreq HW
 driver
Message-ID: <20180924164455.GY22824@google.com>
References: <1532428970-18122-1-git-send-email-tdas@codeaurora.org>
 <1532428970-18122-3-git-send-email-tdas@codeaurora.org>
 <20180910193016.GG22824@google.com>
 <97b9cde0-b33e-503e-ad29-e3c85adc26c4@codeaurora.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <97b9cde0-b33e-503e-ad29-e3c85adc26c4@codeaurora.org>
User-Agent: Mutt/1.9.2 (2017-12-15)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Sun, Sep 23, 2018 at 03:18:20PM +0530, Taniya Das wrote:
> 
> 
> On 9/11/2018 1:00 AM, Matthias Kaehlcke wrote:
> > On Tue, Jul 24, 2018 at 04:12:50PM +0530, Taniya Das wrote:
> > > The CPUfreq HW present in some QCOM chipsets offloads the steps necessary
> > > for changing the frequency of CPUs. The driver implements the cpufreq
> > > driver interface for this hardware engine.
> > > 
> > > Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
> > > Signed-off-by: Taniya Das <tdas@codeaurora.org>
> > > ---
> > >   drivers/cpufreq/Kconfig.arm       |  11 ++
> > >   drivers/cpufreq/Makefile          |   1 +
> > >   drivers/cpufreq/qcom-cpufreq-hw.c | 348 ++++++++++++++++++++++++++++++++++++++
> > >   3 files changed, 360 insertions(+)
> > >   create mode 100644 drivers/cpufreq/qcom-cpufreq-hw.c
> > > 
> > > diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
> > > index 0cd8eb7..93a9d72 100644
> > > --- a/drivers/cpufreq/Kconfig.arm
> > > +++ b/drivers/cpufreq/Kconfig.arm
> > > @@ -298,3 +298,14 @@ config ARM_PXA2xx_CPUFREQ
> > >   	  This add the CPUFreq driver support for Intel PXA2xx SOCs.
> > > 
> > >   	  If in doubt, say N.
> > > +
> > > +config ARM_QCOM_CPUFREQ_HW
> > > +	bool "QCOM CPUFreq HW driver"
> > > +	depends on ARCH_QCOM
> > > +	help
> > > +	 Support for the CPUFreq HW driver.
> > > +	 Some QCOM chipsets have a HW engine to offload the steps
> > > +	 necessary for changing the frequency of the CPUs. Firmware loaded
> > > +	 in this engine exposes a programming interface to the OS.
> > > +	 The driver implements the cpufreq interface for this HW engine.
> > > +	 Say Y if you want to support CPUFreq HW.
> > > diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
> > > index c1ffeab..ca48a1d 100644
> > > --- a/drivers/cpufreq/Makefile
> > > +++ b/drivers/cpufreq/Makefile
> > > @@ -85,6 +85,7 @@ obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
> > >   obj-$(CONFIG_ARM_TEGRA186_CPUFREQ)	+= tegra186-cpufreq.o
> > >   obj-$(CONFIG_ARM_TI_CPUFREQ)		+= ti-cpufreq.o
> > >   obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ)	+= vexpress-spc-cpufreq.o
> > > +obj-$(CONFIG_ARM_QCOM_CPUFREQ_HW)	+= qcom-cpufreq-hw.o
> > > 
> > > 
> > >   ##################################################################################
> > > diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
> > > new file mode 100644
> > > index 0000000..ea8f7d1
> > > --- /dev/null
> > > +++ b/drivers/cpufreq/qcom-cpufreq-hw.c
> > > @@ -0,0 +1,348 @@
> > > +// SPDX-License-Identifier: GPL-2.0
> > > +/*
> > > + * Copyright (c) 2018, The Linux Foundation. All rights reserved.
> > > + */
> > > +
> > > +#include <linux/cpufreq.h>
> > > +#include <linux/init.h>
> > > +#include <linux/kernel.h>
> > > +#include <linux/module.h>
> > > +#include <linux/of_address.h>
> > > +#include <linux/of_platform.h>
> > > +
> > > +#define INIT_RATE			300000000UL
> > > +#define LUT_MAX_ENTRIES			40U
> > > +#define CORE_COUNT_VAL(val)		(((val) & (GENMASK(18, 16))) >> 16)
> > > +#define LUT_ROW_SIZE			32
> > > +
> > > +enum {
> > > +	REG_ENABLE,
> > > +	REG_LUT_TABLE,
> > > +	REG_PERF_STATE,
> > > +
> > > +	REG_ARRAY_SIZE,
> > > +};
> > > +
> > > +struct cpufreq_qcom {
> > > +	struct cpufreq_frequency_table *table;
> > > +	struct device *dev;
> > > +	void __iomem *reg_bases[REG_ARRAY_SIZE];
> > > +	cpumask_t related_cpus;
> > > +	unsigned int max_cores;
> > > +	unsigned long xo_rate;
> > > +};
> > > +
> > > +static const u16 cpufreq_qcom_std_offsets[REG_ARRAY_SIZE] = {
> > > +	[REG_ENABLE]		= 0x0,
> > > +	[REG_LUT_TABLE]		= 0x110,
> > > +	[REG_PERF_STATE]	= 0x920,
> > > +};
> > > +
> > > +static struct cpufreq_qcom *qcom_freq_domain_map[NR_CPUS];
> > > +
> > > +static int
> > > +qcom_cpufreq_hw_target_index(struct cpufreq_policy *policy,
> > > +			     unsigned int index)
> > > +{
> > > +	struct cpufreq_qcom *c = policy->driver_data;
> > > +
> > > +	writel_relaxed(index, c->reg_bases[REG_PERF_STATE]);
> > > +
> > > +	return 0;
> > > +}
> > > +
> > > +static unsigned int qcom_cpufreq_hw_get(unsigned int cpu)
> > > +{
> > > +	struct cpufreq_qcom *c;
> > > +	struct cpufreq_policy *policy;
> > > +	unsigned int index;
> > > +
> > > +	policy = cpufreq_cpu_get_raw(cpu);
> > > +	if (!policy)
> > > +		return 0;
> > > +
> > > +	c = policy->driver_data;
> > > +
> > > +	index = readl_relaxed(c->reg_bases[REG_PERF_STATE]);
> > > +	index = min(index, LUT_MAX_ENTRIES - 1);
> > > +
> > > +	return policy->freq_table[index].frequency;
> > > +}
> > > +
> > > +static unsigned int
> > > +qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
> > > +			    unsigned int target_freq)
> > > +{
> > > +	struct cpufreq_qcom *c = policy->driver_data;
> > > +	int index;
> > > +
> > > +	index = policy->cached_resolved_idx;
> > > +	if (index < 0)
> > > +		return 0;
> > > +
> > > +	writel_relaxed(index, c->reg_bases[REG_PERF_STATE]);
> > > +
> > > +	return policy->freq_table[index].frequency;
> > > +}
> > > +
> > > +static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
> > > +{
> > > +	struct cpufreq_qcom *c;
> > > +
> > > +	c = qcom_freq_domain_map[policy->cpu];
> > > +	if (!c) {
> > > +		pr_err("No scaling support for CPU%d\n", policy->cpu);
> > > +		return -ENODEV;
> > > +	}
> > > +
> > > +	cpumask_copy(policy->cpus, &c->related_cpus);
> > > +
> > > +	policy->fast_switch_possible = true;
> > > +	policy->freq_table = c->table;
> > > +	policy->driver_data = c;
> > > +
> > > +	return 0;
> > > +}
> > > +
> > > +static struct freq_attr *qcom_cpufreq_hw_attr[] = {
> > > +	&cpufreq_freq_attr_scaling_available_freqs,
> > > +	&cpufreq_freq_attr_scaling_boost_freqs,
> > > +	NULL
> > > +};
> > > +
> > > +static struct cpufreq_driver cpufreq_qcom_hw_driver = {
> > > +	.flags		= CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK |
> > > +			  CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
> > > +	.verify		= cpufreq_generic_frequency_table_verify,
> > > +	.target_index	= qcom_cpufreq_hw_target_index,
> > > +	.get		= qcom_cpufreq_hw_get,
> > > +	.init		= qcom_cpufreq_hw_cpu_init,
> > > +	.fast_switch    = qcom_cpufreq_hw_fast_switch,
> > > +	.name		= "qcom-cpufreq-hw",
> > > +	.attr		= qcom_cpufreq_hw_attr,
> > > +	.boost_enabled	= true,
> > > +};
> > > +
> > > +static int qcom_cpufreq_hw_read_lut(struct platform_device *pdev,
> > > +				    struct cpufreq_qcom *c)
> > > +{
> > > +	struct device *dev = &pdev->dev;
> > > +	void __iomem *base;
> > > +	u32 data, src, lval, i, core_count, prev_cc, prev_freq, cur_freq;
> > > +
> > > +	c->table = devm_kcalloc(dev, LUT_MAX_ENTRIES + 1,
> > > +				sizeof(*c->table), GFP_KERNEL);
> > > +	if (!c->table)
> > > +		return -ENOMEM;
> > > +
> > > +	base = c->reg_bases[REG_LUT_TABLE];
> > > +
> > > +	for (i = 0; i < LUT_MAX_ENTRIES; i++) {
> > > +		data = readl_relaxed(base + i * LUT_ROW_SIZE);
> > > +		src = (data & GENMASK(31, 30)) >> 30;
> > > +		lval = data & GENMASK(7, 0);
> > > +		core_count = CORE_COUNT_VAL(data);
> > > +
> > > +		if (src)
> > > +			c->table[i].frequency = c->xo_rate * lval / 1000;
> > > +		else
> > > +			c->table[i].frequency = INIT_RATE / 1000;
> > > +
> > > +		cur_freq = c->table[i].frequency;
> > > +
> > > +		dev_dbg(dev, "index=%d freq=%d, core_count %d\n",
> > > +			i, c->table[i].frequency, core_count);
> > > +
> > > +		if (core_count != c->max_cores)
> > > +			cur_freq = CPUFREQ_ENTRY_INVALID;
> > > +
> > 
> > I noticed that the 'power_allocator' thermal governor currently can't
> > be used with this driver since there is no OPP table with frequency and
> > voltage information. Does the LUT contain information about the
> > voltage or is there another mechanism to retrieve it?
> > 
> 
> No, currently there is no way of reading the voltage information.

That leaves the 'power_allocator' out of question :(

Which thermal governor is/should typically be used on these systems?
Step wise and user space should work out of the box, however the
response of step wise could be slow (step by step) and user space
requires a thermal daemon (and could suffer from latencies). Fair
share could be an option if the thermal cooling devices are registered
with a 'weight', which could come from the device tree.