On Thu, Oct 5, 2017 at 1:43 AM, Srinivas Pandruvada <srinivas.pandruvada@xxxxxxxxxxxxxxx> wrote: > Added functionality to read LPIT table, which provides: > > - Sysfs interface to read residency counters via > /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us > /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us > > Here the count "low_power_idle_cpu_residency_us" shows the time spent > by CPU package in low power state. This is read via MSR interface, which > points to MSR for PKG C10. > > Here the count "low_power_idle_system_residency_us" show the count the > system was in low power state. This is read via MMIO interface. This > is mapped to SLP_S0 residency on modern Intel systems. This residency > is achieved only when CPU is in PKG C10 and all functional blocks are > in low power state. > > It is possible that none of the above counters present or anyone of the > counter present or all counters present. > > For example: On my Kabylake system both of the above counters present. > After suspend to idle these counts updated and prints: > 6916179 > 6998564 > > This counter can be read by tools like turbostat to display. Or it can > be used to debug, if modern systems are reaching desired low power state. > > - Provides an interface to read residency counter memory address > This address can be used to get the base address of PMC memory mapped IO. > This is utilized by intel_pmc_core driver to print more debug information. > > Link: http://www.uefi.org/sites/default/files/resources/Intel_ACPI_Low_Power_S0_Idle.pdf > Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@xxxxxxxxxxxxxxx> > --- > Documentation/acpi/lpit.txt | 26 ++++++++ > drivers/acpi/Kconfig | 5 ++ > drivers/acpi/Makefile | 1 + > drivers/acpi/acpi_lpit.c | 157 ++++++++++++++++++++++++++++++++++++++++++++ > drivers/acpi/scan.c | 3 + > include/acpi/acpi_lpit.h | 34 ++++++++++ > 6 files changed, 226 insertions(+) > create mode 100644 Documentation/acpi/lpit.txt > create mode 100644 drivers/acpi/acpi_lpit.c > create mode 100644 include/acpi/acpi_lpit.h > > diff --git a/Documentation/acpi/lpit.txt b/Documentation/acpi/lpit.txt > new file mode 100644 > index 0000000..6be68c0 > --- /dev/null > +++ b/Documentation/acpi/lpit.txt > @@ -0,0 +1,26 @@ > +To enumerate platform Low Power Idle states, Intel platforms are using > +“Low Power Idle Table” (LPIT). More details about this table can be > +downloaded from: > +http://www.uefi.org/sites/default/files/resources/Intel_ACPI_Low_Power_S0_Idle.pdf > + > +Residencies for each low power state can be read via FFH > +(Function fixed hardware) or a memory mapped interface. > + > +On platforms supporting S0ix sleep states, there can be two types of > +residencies: > +- CPU PKG C10 (Read via FFH interface) > +- Platform Controller Hub (PCH) SLP_S0 (Read via memory mapped interface) > + > +The following attributes are added dynamically to the cpuidle > +sysfs attribute group: > + /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us > + /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us > + > +The "low_power_idle_cpu_residency_us" attribute shows time spent > +by the CPU package in PKG C10 > + > +The "low_power_idle_system_residency_us" attribute shows SLP_S0 > +residency, or system time spent with the SLP_S0# signal asserted. > +This is the lowest possible system power state, achieved only when CPU is in > +PKG C10 and all functional blocks in PCH are in a low power state. > + > diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig > index 1ce52f8..4bfef0f 100644 > --- a/drivers/acpi/Kconfig > +++ b/drivers/acpi/Kconfig > @@ -80,6 +80,11 @@ endif > config ACPI_SPCR_TABLE > bool > > +config ACPI_LPIT > + bool > + depends on X86_64 > + default y > + > config ACPI_SLEEP > bool > depends on SUSPEND || HIBERNATION > diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile > index 90265ab..6a19bd7 100644 > --- a/drivers/acpi/Makefile > +++ b/drivers/acpi/Makefile > @@ -56,6 +56,7 @@ acpi-$(CONFIG_DEBUG_FS) += debugfs.o > acpi-$(CONFIG_ACPI_NUMA) += numa.o > acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o > acpi-y += acpi_lpat.o > +acpi-$(CONFIG_ACPI_LPIT) += acpi_lpit.o > acpi-$(CONFIG_ACPI_GENERIC_GSI) += irq.o > acpi-$(CONFIG_ACPI_WATCHDOG) += acpi_watchdog.o > > diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c > new file mode 100644 > index 0000000..38d760d > --- /dev/null > +++ b/drivers/acpi/acpi_lpit.c > @@ -0,0 +1,157 @@ > + > +/* > + * acpi_lpit.c - LPIT table processing functions > + * > + * Copyright (C) 2017 Intel Corporation. All rights reserved. > + * > + * This program is free software; you can redistribute it and/or > + * modify it under the terms of the GNU General Public License version > + * 2 as published by the Free Software Foundation. > + * > + * This program is distributed in the hope that it will be useful, > + * but WITHOUT ANY WARRANTY; without even the implied warranty of > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the > + * GNU General Public License for more details. > + */ > + > +#include <linux/cpu.h> > +#include <linux/acpi.h> > +#include <asm/msr.h> > +#include <asm/tsc.h> > + > +struct lpit_residency_info { > + struct acpi_generic_address gaddr; > + u64 frequency; > + void __iomem *iomem_addr; > +}; > + > +/* Storage for an memory mapped and FFH based entries */ > +static struct lpit_residency_info residency_info_mem; > +static struct lpit_residency_info residency_info_ffh; > + > +static int lpit_read_residency_counter_us(u64 *counter, bool io_mem) > +{ > + int err; > + > + if (io_mem) { > + u32 count; > + > + count = readl(residency_info_mem.iomem_addr); > + *counter = div64_u64(count * 1000000ULL, residency_info_mem.frequency); > + return 0; > + } > + > + err = rdmsrl_safe(residency_info_ffh.gaddr.address, counter); > + if (!err) { > + u64 mask = GENMASK_ULL(residency_info_ffh.gaddr.bit_offset + > + residency_info_ffh.gaddr. bit_width - 1, > + residency_info_ffh.gaddr.bit_offset); > + > + *counter &= mask; > + *counter >>= residency_info_ffh.gaddr.bit_offset; > + *counter = div64_u64(*counter * 1000000ULL, residency_info_ffh.frequency); > + return 0; > + } > + > + return -ENODATA; > +} > + > +static ssize_t low_power_idle_system_residency_us_show(struct device *dev, > + struct device_attribute *attr, > + char *buf) > +{ > + u64 counter; > + int ret; > + > + ret = lpit_read_residency_counter_us(&counter, true); > + if (ret) > + return ret; > + > + return sprintf(buf, "%llu\n", counter); > +} > +static DEVICE_ATTR_RO(low_power_idle_system_residency_us); > + > +static ssize_t low_power_idle_cpu_residency_us_show(struct device *dev, > + struct device_attribute *attr, > + char *buf) > +{ > + u64 counter; > + int ret; > + > + ret = lpit_read_residency_counter_us(&counter, false); > + if (ret) > + return ret; > + > + return sprintf(buf, "%llu\n", counter); > +} > +static DEVICE_ATTR_RO(low_power_idle_cpu_residency_us); > + > +int lpit_read_residency_count_address(u64 *address) > +{ > + if (!residency_info_mem.gaddr.address) > + return -EINVAL; > + > + *address = residency_info_mem.gaddr.address; > + > + return 0; > +} I don't see users of this. Are there any? > + > +static void lpit_update_residency(struct lpit_residency_info *info, > + struct acpi_lpit_native *lpit_native) > +{ > + info->frequency = lpit_native->counter_frequency ? > + lpit_native->counter_frequency : tsc_khz * 1000; > + if (!info->frequency) > + info->frequency = 1; > + > + info->gaddr = lpit_native->residency_counter; > + if (info->gaddr.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { > + info->iomem_addr = ioremap_nocache(info->gaddr.address, > + info->gaddr.bit_width / 8); > + if (!info->iomem_addr) > + return; > + > + /* Silently fail, if cpuidle attribute group is not present */ > + sysfs_add_file_to_group(&cpu_subsys.dev_root->kobj, > + &dev_attr_low_power_idle_system_residency_us.attr, > + "cpuidle"); > + } else if (info->gaddr.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) { > + /* Silently fail, if cpuidle attribute group is not present */ > + sysfs_add_file_to_group(&cpu_subsys.dev_root->kobj, > + &dev_attr_low_power_idle_cpu_residency_us.attr, > + "cpuidle"); > + } > +} > + > +static void lpit_process(u64 begin, u64 end) > +{ > + while (begin + sizeof(struct acpi_lpit_native) < end) { > + struct acpi_lpit_native *lpit_native = (struct acpi_lpit_native *)begin; > + > + if (!lpit_native->header.type && !lpit_native->header.flags) { > + if (lpit_native->residency_counter.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY && > + !residency_info_mem.gaddr.address) { > + lpit_update_residency(&residency_info_mem, lpit_native); > + } else if (lpit_native->residency_counter.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE && > + !residency_info_ffh.gaddr.address) { > + lpit_update_residency(&residency_info_ffh, lpit_native); > + } > + } > + begin += lpit_native->header.length; > + } > +} > + > +void acpi_init_lpit(void) > +{ > + acpi_status status; > + u64 lpit_begin; > + struct acpi_table_lpit *lpit; > + > + status = acpi_get_table(ACPI_SIG_LPIT, 0, (struct acpi_table_header **)&lpit); > + > + if (ACPI_FAILURE(status)) > + return; > + > + lpit_begin = (u64)lpit + sizeof(*lpit); > + lpit_process(lpit_begin, lpit_begin + lpit->header.length); > +} > diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c > index 602f8ff..3f05d43 100644 > --- a/drivers/acpi/scan.c > +++ b/drivers/acpi/scan.c > @@ -15,6 +15,8 @@ > #include <linux/dma-mapping.h> > #include <linux/platform_data/x86/apple.h> > > +#include <acpi/acpi_lpit.h> > + > #include <asm/pgtable.h> > > #include "internal.h" > @@ -2122,6 +2124,7 @@ int __init acpi_scan_init(void) > acpi_int340x_thermal_init(); > acpi_amba_init(); > acpi_watchdog_init(); > + acpi_init_lpit(); > > acpi_scan_add_handler(&generic_device_handler); > > diff --git a/include/acpi/acpi_lpit.h b/include/acpi/acpi_lpit.h > new file mode 100644 > index 0000000..5d5285a > --- /dev/null > +++ b/include/acpi/acpi_lpit.h > @@ -0,0 +1,34 @@ > +/* > + * acpi_lpit.h - LPIT table processing functions interface > + * > + * Copyright (C) 2017 Intel Corporation. All rights reserved. > + * > + * This program is free software; you can redistribute it and/or > + * modify it under the terms of the GNU General Public License version > + * 2 as published by the Free Software Foundation. > + * > + * This program is distributed in the hope that it will be useful, > + * but WITHOUT ANY WARRANTY; without even the implied warranty of > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the > + * GNU General Public License for more details. > + */ > + > +#ifndef ACPI_LPIT_H > +#define ACPI_LPIT_H > + > +#ifdef CONFIG_ACPI_LPIT > + > +void acpi_init_lpit(void); > +int lpit_read_residency_count_address(u64 *address); > + > +#else > + > +static inline void acpi_init_lpit(void) { } > + > +static inline int lpit_read_residency_count_address(u64 *address) > +{ > + return -EINVAL; > +} > + > +#endif > +#endif The above can go into internal.h or sleep.h in drivers/acpi/ IMO. There's not need to export it. Thanks, Rafael -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
