linux_dsm_epyc7002/include/linux/kernel_stat.h
Frederic Weisbecker 64eea63c19 sched/kcpustat: Introduce vtime-aware kcpustat accessor for CPUTIME_SYSTEM
Kcpustat is not correctly supported on nohz_full CPUs. The tick doesn't
fire and the cputime therefore doesn't move forward. The issue has shown
up after the vanishing of the remaining 1Hz which has made the stall
visible.

We are solving that with checking the task running on a CPU through RCU
and reading its vtime delta that we add to the raw kcpustat values.

We make sure that we fetch a coherent raw-kcpustat/vtime-delta couple
sequence while checking that the CPU referred by the target vtime is the
correct one, under the locked vtime seqcount.

Only CPUTIME_SYSTEM is handled here as a start because it's the trivial
case. User and guest time will require more preparation work to
correctly handle niceness.

Reported-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpengli@tencent.com>
Link: https://lkml.kernel.org/r/20191025020303.19342-1-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-10-29 10:01:17 +01:00

112 lines
2.8 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_KERNEL_STAT_H
#define _LINUX_KERNEL_STAT_H
#include <linux/smp.h>
#include <linux/threads.h>
#include <linux/percpu.h>
#include <linux/cpumask.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/vtime.h>
#include <asm/irq.h>
/*
* 'kernel_stat.h' contains the definitions needed for doing
* some kernel statistics (CPU usage, context switches ...),
* used by rstatd/perfmeter
*/
enum cpu_usage_stat {
CPUTIME_USER,
CPUTIME_NICE,
CPUTIME_SYSTEM,
CPUTIME_SOFTIRQ,
CPUTIME_IRQ,
CPUTIME_IDLE,
CPUTIME_IOWAIT,
CPUTIME_STEAL,
CPUTIME_GUEST,
CPUTIME_GUEST_NICE,
NR_STATS,
};
struct kernel_cpustat {
u64 cpustat[NR_STATS];
};
struct kernel_stat {
unsigned long irqs_sum;
unsigned int softirqs[NR_SOFTIRQS];
};
DECLARE_PER_CPU(struct kernel_stat, kstat);
DECLARE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
/* Must have preemption disabled for this to be meaningful. */
#define kstat_this_cpu this_cpu_ptr(&kstat)
#define kcpustat_this_cpu this_cpu_ptr(&kernel_cpustat)
#define kstat_cpu(cpu) per_cpu(kstat, cpu)
#define kcpustat_cpu(cpu) per_cpu(kernel_cpustat, cpu)
extern unsigned long long nr_context_switches(void);
extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
extern void kstat_incr_irq_this_cpu(unsigned int irq);
static inline void kstat_incr_softirqs_this_cpu(unsigned int irq)
{
__this_cpu_inc(kstat.softirqs[irq]);
}
static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)
{
return kstat_cpu(cpu).softirqs[irq];
}
/*
* Number of interrupts per specific IRQ source, since bootup
*/
extern unsigned int kstat_irqs(unsigned int irq);
extern unsigned int kstat_irqs_usr(unsigned int irq);
/*
* Number of interrupts per cpu, since bootup
*/
static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu)
{
return kstat_cpu(cpu).irqs_sum;
}
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
extern u64 kcpustat_field(struct kernel_cpustat *kcpustat,
enum cpu_usage_stat usage, int cpu);
#else
static inline u64 kcpustat_field(struct kernel_cpustat *kcpustat,
enum cpu_usage_stat usage, int cpu)
{
return kcpustat->cpustat[usage];
}
#endif
extern void account_user_time(struct task_struct *, u64);
extern void account_guest_time(struct task_struct *, u64);
extern void account_system_time(struct task_struct *, int, u64);
extern void account_system_index_time(struct task_struct *, u64,
enum cpu_usage_stat);
extern void account_steal_time(u64);
extern void account_idle_time(u64);
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
static inline void account_process_tick(struct task_struct *tsk, int user)
{
vtime_flush(tsk);
}
#else
extern void account_process_tick(struct task_struct *, int user);
#endif
extern void account_idle_ticks(unsigned long ticks);
#endif /* _LINUX_KERNEL_STAT_H */