diff --git a/Documentation/virtual/guest-halt-polling.txt b/Documentation/virtual/guest-halt-polling.txt new file mode 100644 index 000000000000..b3a2a294532d --- /dev/null +++ b/Documentation/virtual/guest-halt-polling.txt @@ -0,0 +1,78 @@ +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. diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig index cc8efc56be7d..88727b7c0d59 100644 --- a/drivers/cpuidle/Kconfig +++ b/drivers/cpuidle/Kconfig @@ -33,6 +33,17 @@ config CPU_IDLE_GOV_TEO Some workloads benefit from using it and it generally should be safe to use. Say Y here if you are not happy with the alternatives. +config CPU_IDLE_GOV_HALTPOLL + bool "Haltpoll governor (for virtualized systems)" + depends on KVM_GUEST + help + This governor implements haltpoll idle state selection, to be + used in conjunction with the haltpoll cpuidle driver, allowing + for polling for a certain amount of time before entering idle + state. + + Some virtualized workloads benefit from using it. + config DT_IDLE_STATES bool diff --git a/drivers/cpuidle/governors/Makefile b/drivers/cpuidle/governors/Makefile index 42f44cc610dd..63abb5393a4d 100644 --- a/drivers/cpuidle/governors/Makefile +++ b/drivers/cpuidle/governors/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o obj-$(CONFIG_CPU_IDLE_GOV_TEO) += teo.o +obj-$(CONFIG_CPU_IDLE_GOV_HALTPOLL) += haltpoll.o diff --git a/drivers/cpuidle/governors/haltpoll.c b/drivers/cpuidle/governors/haltpoll.c new file mode 100644 index 000000000000..797477bda486 --- /dev/null +++ b/drivers/cpuidle/governors/haltpoll.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * haltpoll.c - haltpoll idle governor + * + * Copyright 2019 Red Hat, Inc. and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Authors: Marcelo Tosatti + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static unsigned int guest_halt_poll_ns __read_mostly = 200000; +module_param(guest_halt_poll_ns, uint, 0644); + +/* division factor to shrink halt_poll_ns */ +static unsigned int guest_halt_poll_shrink __read_mostly = 2; +module_param(guest_halt_poll_shrink, uint, 0644); + +/* multiplication factor to grow per-cpu poll_limit_ns */ +static unsigned int guest_halt_poll_grow __read_mostly = 2; +module_param(guest_halt_poll_grow, uint, 0644); + +/* value in us to start growing per-cpu halt_poll_ns */ +static unsigned int guest_halt_poll_grow_start __read_mostly = 50000; +module_param(guest_halt_poll_grow_start, uint, 0644); + +/* allow shrinking guest halt poll */ +static bool guest_halt_poll_allow_shrink __read_mostly = true; +module_param(guest_halt_poll_allow_shrink, bool, 0644); + +/** + * haltpoll_select - selects the next idle state to enter + * @drv: cpuidle driver containing state data + * @dev: the CPU + * @stop_tick: indication on whether or not to stop the tick + */ +static int haltpoll_select(struct cpuidle_driver *drv, + struct cpuidle_device *dev, + bool *stop_tick) +{ + int latency_req = cpuidle_governor_latency_req(dev->cpu); + + if (!drv->state_count || latency_req == 0) { + *stop_tick = false; + return 0; + } + + if (dev->poll_limit_ns == 0) + return 1; + + /* Last state was poll? */ + if (dev->last_state_idx == 0) { + /* Halt if no event occurred on poll window */ + if (dev->poll_time_limit == true) + return 1; + + *stop_tick = false; + /* Otherwise, poll again */ + return 0; + } + + *stop_tick = false; + /* Last state was halt: poll */ + return 0; +} + +static void adjust_poll_limit(struct cpuidle_device *dev, unsigned int block_us) +{ + unsigned int val; + u64 block_ns = block_us*NSEC_PER_USEC; + + /* Grow cpu_halt_poll_us if + * cpu_halt_poll_us < block_ns < guest_halt_poll_us + */ + if (block_ns > dev->poll_limit_ns && block_ns <= guest_halt_poll_ns) { + val = dev->poll_limit_ns * guest_halt_poll_grow; + + if (val < guest_halt_poll_grow_start) + val = guest_halt_poll_grow_start; + if (val > guest_halt_poll_ns) + val = guest_halt_poll_ns; + + dev->poll_limit_ns = val; + } else if (block_ns > guest_halt_poll_ns && + guest_halt_poll_allow_shrink) { + unsigned int shrink = guest_halt_poll_shrink; + + val = dev->poll_limit_ns; + if (shrink == 0) + val = 0; + else + val /= shrink; + dev->poll_limit_ns = val; + } +} + +/** + * haltpoll_reflect - update variables and update poll time + * @dev: the CPU + * @index: the index of actual entered state + */ +static void haltpoll_reflect(struct cpuidle_device *dev, int index) +{ + dev->last_state_idx = index; + + if (index != 0) + adjust_poll_limit(dev, dev->last_residency); +} + +/** + * haltpoll_enable_device - scans a CPU's states and does setup + * @drv: cpuidle driver + * @dev: the CPU + */ +static int haltpoll_enable_device(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + dev->poll_limit_ns = 0; + + return 0; +} + +static struct cpuidle_governor haltpoll_governor = { + .name = "haltpoll", + .rating = 21, + .enable = haltpoll_enable_device, + .select = haltpoll_select, + .reflect = haltpoll_reflect, +}; + +static int __init init_haltpoll(void) +{ + if (kvm_para_available()) + return cpuidle_register_governor(&haltpoll_governor); + + return 0; +} + +postcore_initcall(init_haltpoll);