Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 2cdd5cc7 authored by Rafael J. Wysocki's avatar Rafael J. Wysocki
Browse files

Merge branch 'pm-cpuidle' 

* pm-cpuidle:
  cpuidle-haltpoll: Enable kvm guest polling when dedicated physical CPUs are available
  cpuidle-haltpoll: do not set an owner to allow modunload
  cpuidle-haltpoll: return -ENODEV on modinit failure
  cpuidle-haltpoll: set haltpoll as preferred governor
  cpuidle: allow governor switch on cpuidle_register_driver()
  powercap: idle_inject: Use higher resolution for idle injection
  cpuidle: play_idle: Increase the resolution to usec
  cpuidle-haltpoll: vcpu hotplug support
  cpuidle: teo: Get rid of redundant check in teo_update()
  cpuidle: teo: Allow tick to be stopped if PM QoS is used
  cpuidle: menu: Allow tick to be stopped if PM QoS is used
  cpuidle: header file stubs must be "static inline"
  cpuidle-haltpoll: disable host side polling when kvm virtualized
  cpuidle: add haltpoll governor
  governors: unify last_state_idx
  cpuidle: add poll_limit_ns to cpuidle_device structure
  add cpuidle-haltpoll driver
parents d2817063 1328edca

Documentation/virtual/guest-halt-polling.txt

0 → 100644
+78 −0
Original line number Diff line number Diff line 
Guest halt polling

==================



The cpuidle_haltpoll driver, with the haltpoll governor, allows

the guest vcpus to poll for a specified amount of time before

halting.

This provides the following benefits to host side polling:



	1) The POLL flag is set while polling is performed, which allows

	   a remote vCPU to avoid sending an IPI (and the associated

	   cost of handling the IPI) when performing a wakeup.



	2) The VM-exit cost can be avoided.



The downside of guest side polling is that polling is performed

even with other runnable tasks in the host.



The basic logic as follows: A global value, guest_halt_poll_ns,

is configured by the user, indicating the maximum amount of

time polling is allowed. This value is fixed.



Each vcpu has an adjustable guest_halt_poll_ns

("per-cpu guest_halt_poll_ns"), which is adjusted by the algorithm

in response to events (explained below).



Module Parameters

=================



The haltpoll governor has 5 tunable module parameters:



1) guest_halt_poll_ns:

Maximum amount of time, in nanoseconds, that polling is

performed before halting.



Default: 200000



2) guest_halt_poll_shrink:

Division factor used to shrink per-cpu guest_halt_poll_ns when

wakeup event occurs after the global guest_halt_poll_ns.



Default: 2



3) guest_halt_poll_grow:

Multiplication factor used to grow per-cpu guest_halt_poll_ns

when event occurs after per-cpu guest_halt_poll_ns

but before global guest_halt_poll_ns.



Default: 2



4) guest_halt_poll_grow_start:

The per-cpu guest_halt_poll_ns eventually reaches zero

in case of an idle system. This value sets the initial

per-cpu guest_halt_poll_ns when growing. This can

be increased from 10000, to avoid misses during the initial

growth stage:



10k, 20k, 40k, ... (example assumes guest_halt_poll_grow=2).



Default: 50000



5) guest_halt_poll_allow_shrink:



Bool parameter which allows shrinking. Set to N

to avoid it (per-cpu guest_halt_poll_ns will remain

high once achieves global guest_halt_poll_ns value).



Default: Y



The module parameters can be set from the debugfs files in:



	/sys/module/haltpoll/parameters/



Further Notes

=============



- Care should be taken when setting the guest_halt_poll_ns parameter as a

large value has the potential to drive the cpu usage to 100% on a machine which

would be almost entirely idle otherwise.

arch/x86/Kconfig

+7 −0
Original line number Diff line number Diff line
@@ -794,6 +794,7 @@ config KVM_GUEST 
	bool "KVM Guest support (including kvmclock)"

	depends on PARAVIRT

	select PARAVIRT_CLOCK

	select ARCH_CPUIDLE_HALTPOLL

	default y

	---help---

	  This option enables various optimizations for running under the KVM
@@ -802,6 +803,12 @@ config KVM_GUEST 
	  underlying device model, the host provides the guest with

	  timing infrastructure such as time of day, and system time



config ARCH_CPUIDLE_HALTPOLL

        def_bool n

        prompt "Disable host haltpoll when loading haltpoll driver"

        help

	  If virtualized under KVM, disable host haltpoll.



config PVH

	bool "Support for running PVH guests"

	---help---

arch/x86/include/asm/cpuidle_haltpoll.h

0 → 100644
+8 −0
Original line number Diff line number Diff line 
/* SPDX-License-Identifier: GPL-2.0 */

#ifndef _ARCH_HALTPOLL_H

#define _ARCH_HALTPOLL_H



void arch_haltpoll_enable(unsigned int cpu);

void arch_haltpoll_disable(unsigned int cpu);



#endif

arch/x86/kernel/kvm.c

+37 −0
Original line number Diff line number Diff line
@@ -705,6 +705,7 @@ unsigned int kvm_arch_para_hints(void) 
{

	return cpuid_edx(kvm_cpuid_base() | KVM_CPUID_FEATURES);

}

EXPORT_SYMBOL_GPL(kvm_arch_para_hints);



static uint32_t __init kvm_detect(void)

{
@@ -867,3 +868,39 @@ void __init kvm_spinlock_init(void) 
}



#endif	/* CONFIG_PARAVIRT_SPINLOCKS */



#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL



static void kvm_disable_host_haltpoll(void *i)

{

	wrmsrl(MSR_KVM_POLL_CONTROL, 0);

}



static void kvm_enable_host_haltpoll(void *i)

{

	wrmsrl(MSR_KVM_POLL_CONTROL, 1);

}



void arch_haltpoll_enable(unsigned int cpu)

{

	if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) {

		pr_err_once("kvm: host does not support poll control\n");

		pr_err_once("kvm: host upgrade recommended\n");

		return;

	}



	/* Enable guest halt poll disables host halt poll */

	smp_call_function_single(cpu, kvm_disable_host_haltpoll, NULL, 1);

}

EXPORT_SYMBOL_GPL(arch_haltpoll_enable);



void arch_haltpoll_disable(unsigned int cpu)

{

	if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))

		return;



	/* Enable guest halt poll disables host halt poll */

	smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);

}

EXPORT_SYMBOL_GPL(arch_haltpoll_disable);

#endif

arch/x86/kernel/process.c

+1 −1
Original line number Diff line number Diff line
@@ -580,7 +580,7 @@ void __cpuidle default_idle(void) 
	safe_halt();

	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());

}

#ifdef CONFIG_APM_MODULE

#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)

EXPORT_SYMBOL(default_idle);

#endif