OpenCloudOS-Kernel/drivers/acpi/acpi_pad.c

498 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
/*
* acpi_pad.c ACPI Processor Aggregator Driver
*
* Copyright (c) 2009, Intel Corporation.
*/
#include <linux/kernel.h>
#include <linux/cpumask.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/kthread.h>
#include <uapi/linux/sched/types.h>
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
#include <linux/freezer.h>
#include <linux/cpu.h>
#include <linux/tick.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
ACPI: Clean up inclusions of ACPI header files Replace direct inclusions of <acpi/acpi.h>, <acpi/acpi_bus.h> and <acpi/acpi_drivers.h>, which are incorrect, with <linux/acpi.h> inclusions and remove some inclusions of those files that aren't necessary. First of all, <acpi/acpi.h>, <acpi/acpi_bus.h> and <acpi/acpi_drivers.h> should not be included directly from any files that are built for CONFIG_ACPI unset, because that generally leads to build warnings about undefined symbols in !CONFIG_ACPI builds. For CONFIG_ACPI set, <linux/acpi.h> includes those files and for CONFIG_ACPI unset it provides stub ACPI symbols to be used in that case. Second, there are ordering dependencies between those files that always have to be met. Namely, it is required that <acpi/acpi_bus.h> be included prior to <acpi/acpi_drivers.h> so that the acpi_pci_root declarations the latter depends on are always there. And <acpi/acpi.h> which provides basic ACPICA type declarations should always be included prior to any other ACPI headers in CONFIG_ACPI builds. That also is taken care of including <linux/acpi.h> as appropriate. Signed-off-by: Lv Zheng <lv.zheng@intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Tony Luck <tony.luck@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> (drivers/pci stuff) Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> (Xen stuff) Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-12-03 08:49:16 +08:00
#include <linux/acpi.h>
#include <asm/mwait.h>
#include <xen/xen.h>
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
#define ACPI_PROCESSOR_AGGREGATOR_CLASS "acpi_pad"
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
#define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator"
#define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80
static DEFINE_MUTEX(isolated_cpus_lock);
static DEFINE_MUTEX(round_robin_lock);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
static unsigned long power_saving_mwait_eax;
static unsigned char tsc_detected_unstable;
static unsigned char tsc_marked_unstable;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
static void power_saving_mwait_init(void)
{
unsigned int eax, ebx, ecx, edx;
unsigned int highest_cstate = 0;
unsigned int highest_subcstate = 0;
int i;
if (!boot_cpu_has(X86_FEATURE_MWAIT))
return;
if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
return;
cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
!(ecx & CPUID5_ECX_INTERRUPT_BREAK))
return;
edx >>= MWAIT_SUBSTATE_SIZE;
for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
if (edx & MWAIT_SUBSTATE_MASK) {
highest_cstate = i;
highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
}
}
power_saving_mwait_eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
(highest_subcstate - 1);
#if defined(CONFIG_X86)
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_HYGON:
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
case X86_VENDOR_AMD:
case X86_VENDOR_INTEL:
case X86_VENDOR_ZHAOXIN:
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
/*
* AMD Fam10h TSC will tick in all
* C/P/S0/S1 states when this bit is set.
*/
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
tsc_detected_unstable = 1;
break;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
default:
ACPI/PAD: Remove the local APIC nonsense While looking through the (ab)use of the clockevents_notify() function I stumbled over the following gem in the acpi_pad code: if (lapic_detected_unstable && !lapic_marked_unstable) { /* LAPIC could halt in idle, so notify users */ for_each_online_cpu(i) clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &i); lapic_marked_unstable = 1; } This code calls on the cpu which detects the lapic unstable condition first clockevents_notify() to tell the core code that the broadcast should be enabled on all online cpus. Brilliant stuff that as it notifies the core code a num_online_cpus() times that the broadcast should be enabled on the current cpu. This probably has never been noticed because that code got never tested with NOHZ=n and HIGHRES_TIMER=n or it just worked by chance because one of the other mechanisms told the core in the right way that the local apic timer is wreckaged. Sigh, this is: - The 4th incarnation of idle drivers which has their own mechanism to detect and deal with X86_FEATURE_ARAT. - The 2nd incarnation of fake idle mechanisms with a different set of brainmelting bugs. - Has been merged against an explicit NAK of the scheduler maintainer with the promise to improve it over time. - Another example of featuritis driven trainwreck engineering. - Another pointless waste of my time. Fix this nonsense by removing that lapic detection and notification logic and simply call into the clockevents code unconditonally. The ARAT feature is marked in the lapic clockevent already so the core code will just ignore the requests and return. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1887788.RObRuI4tSv@vostro.rjw.lan Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-03 07:46:34 +08:00
/* TSC could halt in idle */
tsc_detected_unstable = 1;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
}
#endif
}
static unsigned long cpu_weight[NR_CPUS];
static int tsk_in_cpu[NR_CPUS] = {[0 ... NR_CPUS-1] = -1};
static DECLARE_BITMAP(pad_busy_cpus_bits, NR_CPUS);
static void round_robin_cpu(unsigned int tsk_index)
{
struct cpumask *pad_busy_cpus = to_cpumask(pad_busy_cpus_bits);
cpumask_var_t tmp;
int cpu;
unsigned long min_weight = -1;
unsigned long preferred_cpu;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
if (!alloc_cpumask_var(&tmp, GFP_KERNEL))
return;
mutex_lock(&round_robin_lock);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
cpumask_clear(tmp);
for_each_cpu(cpu, pad_busy_cpus)
cpumask_or(tmp, tmp, topology_sibling_cpumask(cpu));
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
cpumask_andnot(tmp, cpu_online_mask, tmp);
/* avoid HT sibilings if possible */
if (cpumask_empty(tmp))
cpumask_andnot(tmp, cpu_online_mask, pad_busy_cpus);
if (cpumask_empty(tmp)) {
mutex_unlock(&round_robin_lock);
free_cpumask_var(tmp);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
return;
}
for_each_cpu(cpu, tmp) {
if (cpu_weight[cpu] < min_weight) {
min_weight = cpu_weight[cpu];
preferred_cpu = cpu;
}
}
if (tsk_in_cpu[tsk_index] != -1)
cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
tsk_in_cpu[tsk_index] = preferred_cpu;
cpumask_set_cpu(preferred_cpu, pad_busy_cpus);
cpu_weight[preferred_cpu]++;
mutex_unlock(&round_robin_lock);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
set_cpus_allowed_ptr(current, cpumask_of(preferred_cpu));
free_cpumask_var(tmp);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
}
static void exit_round_robin(unsigned int tsk_index)
{
struct cpumask *pad_busy_cpus = to_cpumask(pad_busy_cpus_bits);
cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus);
tsk_in_cpu[tsk_index] = -1;
}
static unsigned int idle_pct = 5; /* percentage */
static unsigned int round_robin_time = 1; /* second */
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
static int power_saving_thread(void *data)
{
int do_sleep;
unsigned int tsk_index = (unsigned long)data;
u64 last_jiffies = 0;
sched_set_fifo_low(current);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
while (!kthread_should_stop()) {
unsigned long expire_time;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
/* round robin to cpus */
expire_time = last_jiffies + round_robin_time * HZ;
if (time_before(expire_time, jiffies)) {
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
last_jiffies = jiffies;
round_robin_cpu(tsk_index);
}
do_sleep = 0;
expire_time = jiffies + HZ * (100 - idle_pct) / 100;
while (!need_resched()) {
if (tsc_detected_unstable && !tsc_marked_unstable) {
/* TSC could halt in idle, so notify users */
mark_tsc_unstable("TSC halts in idle");
tsc_marked_unstable = 1;
}
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
local_irq_disable();
tick_broadcast_enable();
tick_broadcast_enter();
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
stop_critical_timings();
mwait_idle_with_hints(power_saving_mwait_eax, 1);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
start_critical_timings();
tick_broadcast_exit();
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
local_irq_enable();
if (time_before(expire_time, jiffies)) {
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
do_sleep = 1;
break;
}
}
/*
* current sched_rt has threshold for rt task running time.
* When a rt task uses 95% CPU time, the rt thread will be
* scheduled out for 5% CPU time to not starve other tasks. But
* the mechanism only works when all CPUs have RT task running,
* as if one CPU hasn't RT task, RT task from other CPUs will
* borrow CPU time from this CPU and cause RT task use > 95%
* CPU time. To make 'avoid starvation' work, takes a nap here.
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
*/
ACPI / PAD: call schedule() when need_resched() is true The purpose of the acpi_pad driver is to implement the "processor power aggregator" device as described in the ACPI 4.0 spec section 8.5. It takes requests from the BIOS (via ACPI) to put a specified number of CPUs into idle, in order to save power, until further notice. It does this by creating high-priority threads that try to keep the CPUs in a high C-state (using the monitor/mwait CPU instructions). The mwait() call is in a loop that checks periodically if the thread should end and a few other things. It was discovered through testing that the power_saving threads were causing the system to consume more power than the system was consuming before the threads were created. A counter in the main loop of power_saving_thread() revealed that it was spinning. The mwait() instruction was not keeping the CPU in a high C state very much if at all. Here is a simplification of the loop in function power_saving_thread() in drivers/acpi/acpi_pad.c while (!kthread_should_stop()) { : try_to_freeze() : while (!need_resched()) { : if (!need_resched()) __mwait(power_saving_mwait_eax, 1); : if (jiffies > expire_time) { do_sleep = 1; break; } } } If need_resched() returns true, then mwait() is not called. It was returning true because of things like timer interrupts, as in the following sequence. hrtimer_interrupt->__run_hrtimer->tick_sched_timer-> update_process_times-> rcu_check_callbacks->rcu_pending->__rcu_pending->set_need_resched Kernels 3.5.0-rc2+ do not exhibit this problem, because a patch to try_to_freeze() in include/linux/freezer.h introduces a call to might_sleep(), which ultimately calls schedule() to clear the reschedule flag and allows the the loop to execute the call to mwait(). However, the changes to try_to_freeze are unrelated to acpi_pad, and it does not seem like a good idea to rely on an unrelated patch in a function that could later be changed and reintroduce this bug. Therefore, it seems better to make an explicit call to schedule() in the outer loop when the need_resched flag is set. Reported-and-tested-by: Stuart Hayes <stuart_hayes@dell.com> Signed-off-by: Tony Camuso <tcamuso@redhat.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-04-26 02:19:29 +08:00
if (unlikely(do_sleep))
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
schedule_timeout_killable(HZ * idle_pct / 100);
ACPI / PAD: call schedule() when need_resched() is true The purpose of the acpi_pad driver is to implement the "processor power aggregator" device as described in the ACPI 4.0 spec section 8.5. It takes requests from the BIOS (via ACPI) to put a specified number of CPUs into idle, in order to save power, until further notice. It does this by creating high-priority threads that try to keep the CPUs in a high C-state (using the monitor/mwait CPU instructions). The mwait() call is in a loop that checks periodically if the thread should end and a few other things. It was discovered through testing that the power_saving threads were causing the system to consume more power than the system was consuming before the threads were created. A counter in the main loop of power_saving_thread() revealed that it was spinning. The mwait() instruction was not keeping the CPU in a high C state very much if at all. Here is a simplification of the loop in function power_saving_thread() in drivers/acpi/acpi_pad.c while (!kthread_should_stop()) { : try_to_freeze() : while (!need_resched()) { : if (!need_resched()) __mwait(power_saving_mwait_eax, 1); : if (jiffies > expire_time) { do_sleep = 1; break; } } } If need_resched() returns true, then mwait() is not called. It was returning true because of things like timer interrupts, as in the following sequence. hrtimer_interrupt->__run_hrtimer->tick_sched_timer-> update_process_times-> rcu_check_callbacks->rcu_pending->__rcu_pending->set_need_resched Kernels 3.5.0-rc2+ do not exhibit this problem, because a patch to try_to_freeze() in include/linux/freezer.h introduces a call to might_sleep(), which ultimately calls schedule() to clear the reschedule flag and allows the the loop to execute the call to mwait(). However, the changes to try_to_freeze are unrelated to acpi_pad, and it does not seem like a good idea to rely on an unrelated patch in a function that could later be changed and reintroduce this bug. Therefore, it seems better to make an explicit call to schedule() in the outer loop when the need_resched flag is set. Reported-and-tested-by: Stuart Hayes <stuart_hayes@dell.com> Signed-off-by: Tony Camuso <tcamuso@redhat.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-04-26 02:19:29 +08:00
/* If an external event has set the need_resched flag, then
* we need to deal with it, or this loop will continue to
* spin without calling __mwait().
*/
if (unlikely(need_resched()))
schedule();
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
}
exit_round_robin(tsk_index);
return 0;
}
static struct task_struct *ps_tsks[NR_CPUS];
static unsigned int ps_tsk_num;
static int create_power_saving_task(void)
{
int rc;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
ps_tsks[ps_tsk_num] = kthread_run(power_saving_thread,
(void *)(unsigned long)ps_tsk_num,
"acpi_pad/%d", ps_tsk_num);
if (IS_ERR(ps_tsks[ps_tsk_num])) {
rc = PTR_ERR(ps_tsks[ps_tsk_num]);
ps_tsks[ps_tsk_num] = NULL;
} else {
rc = 0;
ps_tsk_num++;
}
return rc;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
}
static void destroy_power_saving_task(void)
{
if (ps_tsk_num > 0) {
ps_tsk_num--;
kthread_stop(ps_tsks[ps_tsk_num]);
ps_tsks[ps_tsk_num] = NULL;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
}
}
static void set_power_saving_task_num(unsigned int num)
{
if (num > ps_tsk_num) {
while (ps_tsk_num < num) {
if (create_power_saving_task())
return;
}
} else if (num < ps_tsk_num) {
while (ps_tsk_num > num)
destroy_power_saving_task();
}
}
static void acpi_pad_idle_cpus(unsigned int num_cpus)
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
{
get_online_cpus();
num_cpus = min_t(unsigned int, num_cpus, num_online_cpus());
set_power_saving_task_num(num_cpus);
put_online_cpus();
}
static uint32_t acpi_pad_idle_cpus_num(void)
{
return ps_tsk_num;
}
static ssize_t acpi_pad_rrtime_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
unsigned long num;
if (kstrtoul(buf, 0, &num))
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
return -EINVAL;
if (num < 1 || num >= 100)
return -EINVAL;
mutex_lock(&isolated_cpus_lock);
round_robin_time = num;
mutex_unlock(&isolated_cpus_lock);
return count;
}
static ssize_t acpi_pad_rrtime_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
return scnprintf(buf, PAGE_SIZE, "%d\n", round_robin_time);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
}
static DEVICE_ATTR(rrtime, S_IRUGO|S_IWUSR,
acpi_pad_rrtime_show,
acpi_pad_rrtime_store);
static ssize_t acpi_pad_idlepct_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
unsigned long num;
if (kstrtoul(buf, 0, &num))
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
return -EINVAL;
if (num < 1 || num >= 100)
return -EINVAL;
mutex_lock(&isolated_cpus_lock);
idle_pct = num;
mutex_unlock(&isolated_cpus_lock);
return count;
}
static ssize_t acpi_pad_idlepct_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
return scnprintf(buf, PAGE_SIZE, "%d\n", idle_pct);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
}
static DEVICE_ATTR(idlepct, S_IRUGO|S_IWUSR,
acpi_pad_idlepct_show,
acpi_pad_idlepct_store);
static ssize_t acpi_pad_idlecpus_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
unsigned long num;
if (kstrtoul(buf, 0, &num))
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
return -EINVAL;
mutex_lock(&isolated_cpus_lock);
acpi_pad_idle_cpus(num);
mutex_unlock(&isolated_cpus_lock);
return count;
}
static ssize_t acpi_pad_idlecpus_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
return cpumap_print_to_pagebuf(false, buf,
to_cpumask(pad_busy_cpus_bits));
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
}
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
static DEVICE_ATTR(idlecpus, S_IRUGO|S_IWUSR,
acpi_pad_idlecpus_show,
acpi_pad_idlecpus_store);
static int acpi_pad_add_sysfs(struct acpi_device *device)
{
int result;
result = device_create_file(&device->dev, &dev_attr_idlecpus);
if (result)
return -ENODEV;
result = device_create_file(&device->dev, &dev_attr_idlepct);
if (result) {
device_remove_file(&device->dev, &dev_attr_idlecpus);
return -ENODEV;
}
result = device_create_file(&device->dev, &dev_attr_rrtime);
if (result) {
device_remove_file(&device->dev, &dev_attr_idlecpus);
device_remove_file(&device->dev, &dev_attr_idlepct);
return -ENODEV;
}
return 0;
}
static void acpi_pad_remove_sysfs(struct acpi_device *device)
{
device_remove_file(&device->dev, &dev_attr_idlecpus);
device_remove_file(&device->dev, &dev_attr_idlepct);
device_remove_file(&device->dev, &dev_attr_rrtime);
}
/*
* Query firmware how many CPUs should be idle
* return -1 on failure
*/
static int acpi_pad_pur(acpi_handle handle)
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
{
struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
union acpi_object *package;
int num = -1;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
if (ACPI_FAILURE(acpi_evaluate_object(handle, "_PUR", NULL, &buffer)))
return num;
if (!buffer.length || !buffer.pointer)
return num;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
package = buffer.pointer;
if (package->type == ACPI_TYPE_PACKAGE &&
package->package.count == 2 &&
package->package.elements[0].integer.value == 1) /* rev 1 */
num = package->package.elements[1].integer.value;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
kfree(buffer.pointer);
return num;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
}
static void acpi_pad_handle_notify(acpi_handle handle)
{
int num_cpus;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
uint32_t idle_cpus;
struct acpi_buffer param = {
.length = 4,
.pointer = (void *)&idle_cpus,
};
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
mutex_lock(&isolated_cpus_lock);
num_cpus = acpi_pad_pur(handle);
if (num_cpus < 0) {
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
mutex_unlock(&isolated_cpus_lock);
return;
}
acpi_pad_idle_cpus(num_cpus);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
idle_cpus = acpi_pad_idle_cpus_num();
acpi_evaluate_ost(handle, ACPI_PROCESSOR_AGGREGATOR_NOTIFY, 0, &param);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
mutex_unlock(&isolated_cpus_lock);
}
static void acpi_pad_notify(acpi_handle handle, u32 event,
void *data)
{
struct acpi_device *device = data;
switch (event) {
case ACPI_PROCESSOR_AGGREGATOR_NOTIFY:
acpi_pad_handle_notify(handle);
acpi_bus_generate_netlink_event(device->pnp.device_class,
dev_name(&device->dev), event, 0);
break;
default:
pr_warn("Unsupported event [0x%x]\n", event);
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
break;
}
}
static int acpi_pad_add(struct acpi_device *device)
{
acpi_status status;
strcpy(acpi_device_name(device), ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME);
strcpy(acpi_device_class(device), ACPI_PROCESSOR_AGGREGATOR_CLASS);
if (acpi_pad_add_sysfs(device))
return -ENODEV;
status = acpi_install_notify_handler(device->handle,
ACPI_DEVICE_NOTIFY, acpi_pad_notify, device);
if (ACPI_FAILURE(status)) {
acpi_pad_remove_sysfs(device);
return -ENODEV;
}
return 0;
}
static int acpi_pad_remove(struct acpi_device *device)
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
{
mutex_lock(&isolated_cpus_lock);
acpi_pad_idle_cpus(0);
mutex_unlock(&isolated_cpus_lock);
acpi_remove_notify_handler(device->handle,
ACPI_DEVICE_NOTIFY, acpi_pad_notify);
acpi_pad_remove_sysfs(device);
return 0;
}
static const struct acpi_device_id pad_device_ids[] = {
{"ACPI000C", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, pad_device_ids);
static struct acpi_driver acpi_pad_driver = {
.name = "processor_aggregator",
.class = ACPI_PROCESSOR_AGGREGATOR_CLASS,
.ids = pad_device_ids,
.ops = {
.add = acpi_pad_add,
.remove = acpi_pad_remove,
},
};
static int __init acpi_pad_init(void)
{
/* Xen ACPI PAD is used when running as Xen Dom0. */
if (xen_initial_domain())
return -ENODEV;
ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li <shaohua.li@intel.com> NACKed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Len Brown <len.brown@intel.com>
2009-07-28 06:11:02 +08:00
power_saving_mwait_init();
if (power_saving_mwait_eax == 0)
return -EINVAL;
return acpi_bus_register_driver(&acpi_pad_driver);
}
static void __exit acpi_pad_exit(void)
{
acpi_bus_unregister_driver(&acpi_pad_driver);
}
module_init(acpi_pad_init);
module_exit(acpi_pad_exit);
MODULE_AUTHOR("Shaohua Li<shaohua.li@intel.com>");
MODULE_DESCRIPTION("ACPI Processor Aggregator Driver");
MODULE_LICENSE("GPL");