linux/kernel/sched/isolation.c

183 lines
4.8 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Housekeeping management. Manage the targets for routine code that can run on
* any CPU: unbound workqueues, timers, kthreads and any offloadable work.
*
* Copyright (C) 2017 Red Hat, Inc., Frederic Weisbecker
* Copyright (C) 2017-2018 SUSE, Frederic Weisbecker
*
*/
2018-02-21 12:17:27 +08:00
#include "sched.h"
DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
EXPORT_SYMBOL_GPL(housekeeping_overridden);
static cpumask_var_t housekeeping_mask;
static unsigned int housekeeping_flags;
KVM: LAPIC: Inject timer interrupt via posted interrupt Dedicated instances are currently disturbed by unnecessary jitter due to the emulated lapic timers firing on the same pCPUs where the vCPUs reside. There is no hardware virtual timer on Intel for guest like ARM, so both programming timer in guest and the emulated timer fires incur vmexits. This patch tries to avoid vmexit when the emulated timer fires, at least in dedicated instance scenario when nohz_full is enabled. In that case, the emulated timers can be offload to the nearest busy housekeeping cpus since APICv has been found for several years in server processors. The guest timer interrupt can then be injected via posted interrupts, which are delivered by the housekeeping cpu once the emulated timer fires. The host should tuned so that vCPUs are placed on isolated physical processors, and with several pCPUs surplus for busy housekeeping. If disabled mwait/hlt/pause vmexits keep the vCPUs in non-root mode, ~3% redis performance benefit can be observed on Skylake server, and the number of external interrupt vmexits drops substantially. Without patch VM-EXIT Samples Samples% Time% Min Time Max Time Avg time EXTERNAL_INTERRUPT 42916 49.43% 39.30% 0.47us 106.09us 0.71us ( +- 1.09% ) While with patch: VM-EXIT Samples Samples% Time% Min Time Max Time Avg time EXTERNAL_INTERRUPT 6871 9.29% 2.96% 0.44us 57.88us 0.72us ( +- 4.02% ) Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Wanpeng Li <wanpengli@tencent.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-06 09:26:51 +08:00
bool housekeeping_enabled(enum hk_flags flags)
{
return !!(housekeeping_flags & flags);
}
EXPORT_SYMBOL_GPL(housekeeping_enabled);
int housekeeping_any_cpu(enum hk_flags flags)
{
int cpu;
if (static_branch_unlikely(&housekeeping_overridden)) {
if (housekeeping_flags & flags) {
cpu = sched_numa_find_closest(housekeeping_mask, smp_processor_id());
if (cpu < nr_cpu_ids)
return cpu;
return cpumask_any_and(housekeeping_mask, cpu_online_mask);
}
}
return smp_processor_id();
}
EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
{
if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
return housekeeping_mask;
return cpu_possible_mask;
}
EXPORT_SYMBOL_GPL(housekeeping_cpumask);
void housekeeping_affine(struct task_struct *t, enum hk_flags flags)
{
if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
set_cpus_allowed_ptr(t, housekeeping_mask);
}
EXPORT_SYMBOL_GPL(housekeeping_affine);
bool housekeeping_test_cpu(int cpu, enum hk_flags flags)
{
if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
return cpumask_test_cpu(cpu, housekeeping_mask);
return true;
}
EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
void __init housekeeping_init(void)
{
if (!housekeeping_flags)
return;
static_branch_enable(&housekeeping_overridden);
2018-02-21 12:17:27 +08:00
if (housekeeping_flags & HK_FLAG_TICK)
sched_tick_offload_init();
/* We need at least one CPU to handle housekeeping work */
WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
}
static int __init housekeeping_setup(char *str, enum hk_flags flags)
{
cpumask_var_t non_housekeeping_mask;
cpumask_var_t tmp;
int err;
alloc_bootmem_cpumask_var(&non_housekeeping_mask);
err = cpulist_parse(str, non_housekeeping_mask);
if (err < 0 || cpumask_last(non_housekeeping_mask) >= nr_cpu_ids) {
pr_warn("Housekeeping: nohz_full= or isolcpus= incorrect CPU range\n");
free_bootmem_cpumask_var(non_housekeeping_mask);
return 0;
}
alloc_bootmem_cpumask_var(&tmp);
if (!housekeeping_flags) {
alloc_bootmem_cpumask_var(&housekeeping_mask);
cpumask_andnot(housekeeping_mask,
cpu_possible_mask, non_housekeeping_mask);
cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
if (cpumask_empty(tmp)) {
pr_warn("Housekeeping: must include one present CPU, "
"using boot CPU:%d\n", smp_processor_id());
__cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
}
} else {
cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
if (cpumask_empty(tmp))
__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask);
if (!cpumask_equal(tmp, housekeeping_mask)) {
pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
free_bootmem_cpumask_var(tmp);
free_bootmem_cpumask_var(non_housekeeping_mask);
return 0;
}
}
free_bootmem_cpumask_var(tmp);
if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
tick_nohz_full_setup(non_housekeeping_mask);
} else {
pr_warn("Housekeeping: nohz unsupported."
" Build with CONFIG_NO_HZ_FULL\n");
free_bootmem_cpumask_var(non_housekeeping_mask);
return 0;
}
}
housekeeping_flags |= flags;
free_bootmem_cpumask_var(non_housekeeping_mask);
return 1;
}
static int __init housekeeping_nohz_full_setup(char *str)
{
unsigned int flags;
flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC;
return housekeeping_setup(str, flags);
}
__setup("nohz_full=", housekeeping_nohz_full_setup);
static int __init housekeeping_isolcpus_setup(char *str)
{
unsigned int flags = 0;
while (isalpha(*str)) {
if (!strncmp(str, "nohz,", 5)) {
str += 5;
flags |= HK_FLAG_TICK;
continue;
}
if (!strncmp(str, "domain,", 7)) {
str += 7;
flags |= HK_FLAG_DOMAIN;
continue;
}
genirq, sched/isolation: Isolate from handling managed interrupts The affinity of managed interrupts is completely handled in the kernel and cannot be changed via the /proc/irq/* interfaces from user space. As the kernel tries to spread out interrupts evenly accross CPUs on x86 to prevent vector exhaustion, it can happen that a managed interrupt whose affinity mask contains both isolated and housekeeping CPUs is routed to an isolated CPU. As a consequence IO submitted on a housekeeping CPU causes interrupts on the isolated CPU. Add a new sub-parameter 'managed_irq' for 'isolcpus' and the corresponding logic in the interrupt affinity selection code. The subparameter indicates to the interrupt affinity selection logic that it should try to avoid the above scenario. This isolation is best effort and only effective if the automatically assigned interrupt mask of a device queue contains isolated and housekeeping CPUs. If housekeeping CPUs are online then such interrupts are directed to the housekeeping CPU so that IO submitted on the housekeeping CPU cannot disturb the isolated CPU. If a queue's affinity mask contains only isolated CPUs then this parameter has no effect on the interrupt routing decision, though interrupts are only happening when tasks running on those isolated CPUs submit IO. IO submitted on housekeeping CPUs has no influence on those queues. If the affinity mask contains both housekeeping and isolated CPUs, but none of the contained housekeeping CPUs is online, then the interrupt is also routed to an isolated CPU. Interrupts are only delivered when one of the isolated CPUs in the affinity mask submits IO. If one of the contained housekeeping CPUs comes online, the CPU hotplug logic migrates the interrupt automatically back to the upcoming housekeeping CPU. Depending on the type of interrupt controller, this can require that at least one interrupt is delivered to the isolated CPU in order to complete the migration. [ tglx: Removed unused parameter, added and edited comments/documentation and rephrased the changelog so it contains more details. ] Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20200120091625.17912-1-ming.lei@redhat.com
2020-01-20 17:16:25 +08:00
if (!strncmp(str, "managed_irq,", 12)) {
str += 12;
flags |= HK_FLAG_MANAGED_IRQ;
continue;
}
pr_warn("isolcpus: Error, unknown flag\n");
return 0;
}
/* Default behaviour for isolcpus without flags */
if (!flags)
flags |= HK_FLAG_DOMAIN;
return housekeeping_setup(str, flags);
}
__setup("isolcpus=", housekeeping_isolcpus_setup);