new file mode 100644
@@ -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.
+
@@ -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
@@ -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
new file mode 100644
@@ -0,0 +1,162 @@
+
+/*
+ * 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) {
+ u64 count = 0;
+ int error;
+
+ error = acpi_os_read_iomem(residency_info_mem.iomem_addr, &count,
+ residency_info_mem.gaddr.bit_width);
+ if (error)
+ return error;
+
+ *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;
+}
+
+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);
+}
@@ -248,4 +248,10 @@ void acpi_watchdog_init(void);
static inline void acpi_watchdog_init(void) {}
#endif
+#ifdef CONFIG_ACPI_LPIT
+void acpi_init_lpit(void);
+#else
+static inline void acpi_init_lpit(void) { }
+#endif
+
#endif /* _ACPI_INTERNAL_H_ */
@@ -663,6 +663,29 @@ acpi_status acpi_os_write_port(acpi_io_address port, u32 value, u32 width)
EXPORT_SYMBOL(acpi_os_write_port);
+int acpi_os_read_iomem(void __iomem *virt_addr, u64 *value, u32 width)
+{
+
+ switch (width) {
+ case 8:
+ *(u8 *) value = readb(virt_addr);
+ break;
+ case 16:
+ *(u16 *) value = readw(virt_addr);
+ break;
+ case 32:
+ *(u32 *) value = readl(virt_addr);
+ break;
+ case 64:
+ *(u64 *) value = readq(virt_addr);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
acpi_status
acpi_os_read_memory(acpi_physical_address phys_addr, u64 *value, u32 width)
{
@@ -670,6 +693,7 @@ acpi_os_read_memory(acpi_physical_address phys_addr, u64 *value, u32 width)
unsigned int size = width / 8;
bool unmap = false;
u64 dummy;
+ int error;
rcu_read_lock();
virt_addr = acpi_map_vaddr_lookup(phys_addr, size);
@@ -684,22 +708,8 @@ acpi_os_read_memory(acpi_physical_address phys_addr, u64 *value, u32 width)
if (!value)
value = &dummy;
- switch (width) {
- case 8:
- *(u8 *) value = readb(virt_addr);
- break;
- case 16:
- *(u16 *) value = readw(virt_addr);
- break;
- case 32:
- *(u32 *) value = readl(virt_addr);
- break;
- case 64:
- *(u64 *) value = readq(virt_addr);
- break;
- default:
- BUG();
- }
+ error = acpi_os_read_iomem(virt_addr, value, width);
+ BUG_ON(error);
if (unmap)
iounmap(virt_addr);
@@ -2122,6 +2122,7 @@ 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);
@@ -287,6 +287,8 @@ acpi_status acpi_os_write_port(acpi_io_address address, u32 value, u32 width);
/*
* Platform and hardware-independent physical memory interfaces
*/
+int acpi_os_read_iomem(void __iomem *virt_addr, u64 *value, u32 width);
+
#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_read_memory
acpi_status
acpi_os_read_memory(acpi_physical_address address, u64 *value, u32 width);
@@ -1254,4 +1254,13 @@ int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res)
}
#endif
+#ifdef CONFIG_ACPI_LPIT
+int lpit_read_residency_count_address(u64 *address);
+#else
+static inline int lpit_read_residency_count_address(u64 *address)
+{
+ return -EINVAL;
+}
+#endif
+
#endif /*_LINUX_ACPI_H*/
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. In addition, to avoid code duplication to read iomem, removed the read of iomem from acpi_os_read_memory() in osl.c and made a common function acpi_os_read_iomem(). This new function is used for reading iomem in in both osl.c and acpi_lpit.c. Link: http://www.uefi.org/sites/default/files/resources/Intel_ACPI_Low_Power_S0_Idle.pdf Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> --- v3 - Created a common function to read iomem acpi_os_read_iomem() and using that. v2 - Dropped include file acpi_lpit.h - although bit_width currently is 32, but for future proof using different mmio read* calls based on the bit_width. Documentation/acpi/lpit.txt | 26 +++++++ drivers/acpi/Kconfig | 5 ++ drivers/acpi/Makefile | 1 + drivers/acpi/acpi_lpit.c | 162 ++++++++++++++++++++++++++++++++++++++++++++ drivers/acpi/internal.h | 6 ++ drivers/acpi/osl.c | 42 +++++++----- drivers/acpi/scan.c | 1 + include/acpi/acpiosxf.h | 2 + include/linux/acpi.h | 9 +++ 9 files changed, 238 insertions(+), 16 deletions(-) create mode 100644 Documentation/acpi/lpit.txt create mode 100644 drivers/acpi/acpi_lpit.c