Hi,
On Thu, Jul 12, 2018 at 11:35:45PM +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 <skan...@codeaurora.org>
> Signed-off-by: Taniya Das <t...@codeaurora.org>
> ---
> drivers/cpufreq/Kconfig.arm | 10 ++
> drivers/cpufreq/Makefile | 1 +
> drivers/cpufreq/qcom-cpufreq-hw.c | 344
> ++++++++++++++++++++++++++++++++++++++
> 3 files changed, 355 insertions(+)
> create mode 100644 drivers/cpufreq/qcom-cpufreq-hw.c
>
> diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
> index 52f5f1a..141ec3e 100644
> --- a/drivers/cpufreq/Kconfig.arm
> +++ b/drivers/cpufreq/Kconfig.arm
> @@ -312,3 +312,13 @@ 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"
> + 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 interafce to the High-level OS.
> + The driver implements the cpufreq driver 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 fb4a2ec..1226a3e 100644
> --- a/drivers/cpufreq/Makefile
> +++ b/drivers/cpufreq/Makefile
> @@ -86,6 +86,7 @@ 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..fa25a95
> --- /dev/null
> +++ b/drivers/cpufreq/qcom-cpufreq-hw.c
> @@ -0,0 +1,344 @@
> +// 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 XO_RATE 19200000UL
> +#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;
> + const u16 *reg_offset;
> + void __iomem *base;
> + cpumask_t related_cpus;
> + unsigned int max_cores;
Same comment as on v4:
Why *max*_cores? This seems to be the number of CPUs in a cluster and
qcom_read_lut() expects the core count read from the LUT to match
exactly. Maybe it's the name from the datasheet? Should it still be
'num_cores' or similer?
> +static struct cpufreq_qcom *qcom_freq_domain_map[NR_CPUS];
It would be an option to limit this to the number of CPU clusters and
allocate it dynamically when the driver is initialized (key = first
core in the cluster). Probably not worth the hassle with the limited
number of cores though.
> +static int qcom_read_lut(struct platform_device *pdev,
> + struct cpufreq_qcom *c)
> +{
> + struct device *dev = &pdev->dev;
> + unsigned int offset;
> + 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;
> +
> + offset = c->reg_offset[REG_LUT_TABLE];
> +
> + for (i = 0; i < LUT_MAX_ENTRIES; i++) {
> + data = readl_relaxed(c->base + offset + i * LUT_ROW_SIZE);
> + src = ((data & GENMASK(31, 30)) >> 30);
> + lval = (data & GENMASK(7, 0));
> + core_count = CORE_COUNT_VAL(data);
> +
> + if (src == 0)
> + c->table[i].frequency = INIT_RATE / 1000;
> + else
> + c->table[i].frequency = XO_RATE * lval / 1000;
You changed the condition from '!src' to 'src == 0'. My suggestion on
v4 was in part about a negative condition, but also about the
order. If it doesn't obstruct the code otherwise I think for an if-else
branch it is good practice to handle the more common case first and
then the 'exception'. I would expect most entries to have an actual
rate. Just a nit in any case, feel free to ignore if you prefer as is.
> +static int qcom_cpu_resources_init(struct platform_device *pdev,
> + struct device_node *np, unsigned int cpu)
> +{
> + struct cpufreq_qcom *c;
> + struct resource res;
> + struct device *dev = &pdev->dev;
> + unsigned int offset, cpu_r;
> + int ret;
> +
> + c = devm_kzalloc(dev, sizeof(*c), GFP_KERNEL);
> + if (!c)
> + return -ENOMEM;
> +
> + c->reg_offset = of_device_get_match_data(&pdev->dev);
> + if (!c->reg_offset)
> + return -EINVAL;
> +
> + if (of_address_to_resource(np, 0, &res))
> + return -ENOMEM;
> +
> + c->base = devm_ioremap(dev, res.start, resource_size(&res));
> + if (!c->base) {
> + dev_err(dev, "Unable to map %s base\n", np->name);
> + return -ENOMEM;
> + }
> +
> + offset = c->reg_offset[REG_ENABLE];
> +
> + /* HW should be in enabled state to proceed */
> + if (!(readl_relaxed(c->base + offset) & 0x1)) {
> + dev_err(dev, "%s cpufreq hardware not enabled\n", np->name);
> + return -ENODEV;
> + }
> +
> + ret = qcom_get_related_cpus(np, &c->related_cpus);
> + if (ret) {
> + dev_err(dev, "%s failed to get related CPUs\n", np->name);
> + return ret;
> + }
> +
> + c->max_cores = cpumask_weight(&c->related_cpus);
> + if (!c->max_cores)
> + return -ENOENT;
> +
> + ret = qcom_read_lut(pdev, c);
> + if (ret) {
> + dev_err(dev, "%s failed to read LUT\n", np->name);
> + return ret;
> + }
> +
> + qcom_freq_domain_map[cpu] = c;
If the general code structure remains as is (see my comment below)
the assignment could be done in a 'if (cpu == cpu_r)' branch instead
of first assigning and then overwriting it for 'cpu != cpu_r'.
> +
> + /* Related CPUs to keep a single copy */
> + cpu_r = cpumask_first(&c->related_cpus);
> + if (cpu != cpu_r) {
> + qcom_freq_domain_map[cpu] = qcom_freq_domain_map[cpu_r];
> + devm_kfree(dev, c);
> + }
Couldn't we do this at the beginning of the function instead of going
through allocation, ioremap, read_lut for every core only to throw the
information away later for the 'related' CPUs?
qcom_cpu_resources_init() is called with increasing 'cpu' values, hence the
'first' CPU of the cluster is already initialized when the 'related'
ones are processed.
> + return 0;
> +}
> +
> +static int qcom_resources_init(struct platform_device *pdev)
> +{
> + struct device_node *np, *cpu_np;
> + unsigned int cpu;
> + int ret;
> +
> + for_each_possible_cpu(cpu) {
> + cpu_np = of_cpu_device_node_get(cpu);
> + if (!cpu_np) {
> + dev_err(&pdev->dev, "Failed to get cpu %d device\n",
> + cpu);
> + continue;
> + }
> +
> + np = of_parse_phandle(cpu_np, "qcom,freq-domain", 0);
> + if (!np) {
> + dev_err(&pdev->dev, "Failed to get freq-domain
> device\n");
of_node_put(cpu_np);
> + return -EINVAL;
> + }
> +
> + of_node_put(cpu_np);
> +
> + ret = qcom_cpu_resources_init(pdev, np, cpu);
> + if (ret)
> + return ret;
> + }
> +
> + return 0;
> +}
Thanks
Matthias
