maobibo <maobibo@xxxxxxxxxxx> writes:
> On 2024/7/27 上午4:21, Ankur Arora wrote:
>> Add architectural support for cpuidle-haltpoll driver by defining
>> arch_haltpoll_*().
>> Also define ARCH_CPUIDLE_HALTPOLL to allow cpuidle-haltpoll to be
>> selected, and given that we have an optimized polling mechanism
>> in smp_cond_load*(), select ARCH_HAS_OPTIMIZED_POLL.
>> smp_cond_load*() are implemented via LDXR, WFE, with LDXR loading
>> a memory region in exclusive state and the WFE waiting for any
>> stores to it.
>> In the edge case -- no CPU stores to the waited region and there's no
>> interrupt -- the event-stream will provide the terminating condition
>> ensuring we don't wait forever, but because the event-stream runs at
>> a fixed frequency (configured at 10kHz) we might spend more time in
>> the polling stage than specified by cpuidle_poll_time().
>> This would only happen in the last iteration, since overshooting the
>> poll_limit means the governor moves out of the polling stage.
>> Signed-off-by: Ankur Arora <ankur.a.arora@xxxxxxxxxx>
>> ---
>> arch/arm64/Kconfig | 10 ++++++++++
>> arch/arm64/include/asm/cpuidle_haltpoll.h | 9 +++++++++
>> arch/arm64/kernel/cpuidle.c | 23 +++++++++++++++++++++++
>> 3 files changed, 42 insertions(+)
>> create mode 100644 arch/arm64/include/asm/cpuidle_haltpoll.h
>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>> index 5d91259ee7b5..cf1c6681eb0a 100644
>> --- a/arch/arm64/Kconfig
>> +++ b/arch/arm64/Kconfig
>> @@ -35,6 +35,7 @@ config ARM64
>> select ARCH_HAS_MEMBARRIER_SYNC_CORE
>> select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
>> select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
>> + select ARCH_HAS_OPTIMIZED_POLL
>> select ARCH_HAS_PTE_DEVMAP
>> select ARCH_HAS_PTE_SPECIAL
>> select ARCH_HAS_HW_PTE_YOUNG
>> @@ -2376,6 +2377,15 @@ config ARCH_HIBERNATION_HEADER
>> config ARCH_SUSPEND_POSSIBLE
>> def_bool y
>> +config ARCH_CPUIDLE_HALTPOLL
>> + bool "Enable selection of the cpuidle-haltpoll driver"
>> + default n
>> + help
>> + cpuidle-haltpoll allows for adaptive polling based on
>> + current load before entering the idle state.
>> +
>> + Some virtualized workloads benefit from using it.
>> +
>> endmenu # "Power management options"
>> menu "CPU Power Management"
>> diff --git a/arch/arm64/include/asm/cpuidle_haltpoll.h b/arch/arm64/include/asm/cpuidle_haltpoll.h
>> new file mode 100644
>> index 000000000000..65f289407a6c
>> --- /dev/null
>> +++ b/arch/arm64/include/asm/cpuidle_haltpoll.h
>> @@ -0,0 +1,9 @@
>> +/* SPDX-License-Identifier: GPL-2.0 */
>> +#ifndef _ARCH_HALTPOLL_H
>> +#define _ARCH_HALTPOLL_H
>> +
>> +static inline void arch_haltpoll_enable(unsigned int cpu) { }
>> +static inline void arch_haltpoll_disable(unsigned int cpu) { }
> It is better that guest supports halt poll on more architectures, LoongArch
> wants this if result is good.
>
> Do we need disable halt polling on host hypervisor if guest also uses halt
> polling idle method?
Yes. The intent is to work on that separately from this series. As the comment
below states, until that is available we only allow force loading.
>> +
>> +bool arch_haltpoll_want(bool force);
>> +#endif
>> diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
>> index f372295207fb..334df82a0eac 100644
>> --- a/arch/arm64/kernel/cpuidle.c
>> +++ b/arch/arm64/kernel/cpuidle.c
>> @@ -72,3 +72,26 @@ __cpuidle int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
>> lpi->index, state);
>> }
>> #endif
>> +
>> +#if IS_ENABLED(CONFIG_HALTPOLL_CPUIDLE)
>> +
>> +#include <asm/cpuidle_haltpoll.h>
>> +
>> +bool arch_haltpoll_want(bool force)
>> +{
>> + /*
>> + * Enabling haltpoll requires two things:
>> + *
>> + * - Event stream support to provide a terminating condition to the
>> + * WFE in the poll loop.
>> + *
>> + * - KVM support for arch_haltpoll_enable(), arch_haltpoll_enable().
>> + *
>> + * Given that the second is missing, allow haltpoll to only be force
>> + * loaded.
>> + */
>> + return (arch_timer_evtstrm_available() && false) || force;
>> +}
>> +
>> +EXPORT_SYMBOL_GPL(arch_haltpoll_want);
>> +#endif
>>
--
ankur
