mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-05 18:39:59 +00:00
![Frederic Weisbecker](/assets/img/avatar_default.png)
The local nohz kick is currently used by perf which needs it to be
NMI-safe. Recent commit though (7d1311b93e
)
changed its implementation to fire the local kick using the remote kick
API. It was convenient to make the code more generic but the remote kick
isn't NMI-safe.
As a result:
WARNING: CPU: 3 PID: 18062 at kernel/irq_work.c:72 irq_work_queue_on+0x11e/0x140()
CPU: 3 PID: 18062 Comm: trinity-subchil Not tainted 3.16.0+ #34
0000000000000009 00000000903774d1 ffff880244e06c00 ffffffff9a7f1e37
0000000000000000 ffff880244e06c38 ffffffff9a0791dd ffff880244fce180
0000000000000003 ffff880244e06d58 ffff880244e06ef8 0000000000000000
Call Trace:
<NMI> [<ffffffff9a7f1e37>] dump_stack+0x4e/0x7a
[<ffffffff9a0791dd>] warn_slowpath_common+0x7d/0xa0
[<ffffffff9a07930a>] warn_slowpath_null+0x1a/0x20
[<ffffffff9a17ca1e>] irq_work_queue_on+0x11e/0x140
[<ffffffff9a10a2c7>] tick_nohz_full_kick_cpu+0x57/0x90
[<ffffffff9a186cd5>] __perf_event_overflow+0x275/0x350
[<ffffffff9a184f80>] ? perf_event_task_disable+0xa0/0xa0
[<ffffffff9a01a4cf>] ? x86_perf_event_set_period+0xbf/0x150
[<ffffffff9a187934>] perf_event_overflow+0x14/0x20
[<ffffffff9a020386>] intel_pmu_handle_irq+0x206/0x410
[<ffffffff9a0b54d3>] ? arch_vtime_task_switch+0x63/0x130
[<ffffffff9a01937b>] perf_event_nmi_handler+0x2b/0x50
[<ffffffff9a007b72>] nmi_handle+0xd2/0x390
[<ffffffff9a007aa5>] ? nmi_handle+0x5/0x390
[<ffffffff9a0d131b>] ? lock_release+0xab/0x330
[<ffffffff9a008062>] default_do_nmi+0x72/0x1c0
[<ffffffff9a0c925f>] ? cpuacct_account_field+0xcf/0x200
[<ffffffff9a008268>] do_nmi+0xb8/0x100
Lets fix this by restoring the use of local irq work for the nohz local
kick.
Reported-by: Catalin Iacob <iacobcatalin@gmail.com>
Reported-and-tested-by: Dave Jones <davej@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
232 lines
6.7 KiB
C
232 lines
6.7 KiB
C
/* linux/include/linux/tick.h
|
|
*
|
|
* This file contains the structure definitions for tick related functions
|
|
*
|
|
*/
|
|
#ifndef _LINUX_TICK_H
|
|
#define _LINUX_TICK_H
|
|
|
|
#include <linux/clockchips.h>
|
|
#include <linux/irqflags.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/hrtimer.h>
|
|
#include <linux/context_tracking_state.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/sched.h>
|
|
|
|
#ifdef CONFIG_GENERIC_CLOCKEVENTS
|
|
|
|
enum tick_device_mode {
|
|
TICKDEV_MODE_PERIODIC,
|
|
TICKDEV_MODE_ONESHOT,
|
|
};
|
|
|
|
struct tick_device {
|
|
struct clock_event_device *evtdev;
|
|
enum tick_device_mode mode;
|
|
};
|
|
|
|
enum tick_nohz_mode {
|
|
NOHZ_MODE_INACTIVE,
|
|
NOHZ_MODE_LOWRES,
|
|
NOHZ_MODE_HIGHRES,
|
|
};
|
|
|
|
/**
|
|
* struct tick_sched - sched tick emulation and no idle tick control/stats
|
|
* @sched_timer: hrtimer to schedule the periodic tick in high
|
|
* resolution mode
|
|
* @last_tick: Store the last tick expiry time when the tick
|
|
* timer is modified for nohz sleeps. This is necessary
|
|
* to resume the tick timer operation in the timeline
|
|
* when the CPU returns from nohz sleep.
|
|
* @tick_stopped: Indicator that the idle tick has been stopped
|
|
* @idle_jiffies: jiffies at the entry to idle for idle time accounting
|
|
* @idle_calls: Total number of idle calls
|
|
* @idle_sleeps: Number of idle calls, where the sched tick was stopped
|
|
* @idle_entrytime: Time when the idle call was entered
|
|
* @idle_waketime: Time when the idle was interrupted
|
|
* @idle_exittime: Time when the idle state was left
|
|
* @idle_sleeptime: Sum of the time slept in idle with sched tick stopped
|
|
* @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding
|
|
* @sleep_length: Duration of the current idle sleep
|
|
* @do_timer_lst: CPU was the last one doing do_timer before going idle
|
|
*/
|
|
struct tick_sched {
|
|
struct hrtimer sched_timer;
|
|
unsigned long check_clocks;
|
|
enum tick_nohz_mode nohz_mode;
|
|
ktime_t last_tick;
|
|
int inidle;
|
|
int tick_stopped;
|
|
unsigned long idle_jiffies;
|
|
unsigned long idle_calls;
|
|
unsigned long idle_sleeps;
|
|
int idle_active;
|
|
ktime_t idle_entrytime;
|
|
ktime_t idle_waketime;
|
|
ktime_t idle_exittime;
|
|
ktime_t idle_sleeptime;
|
|
ktime_t iowait_sleeptime;
|
|
ktime_t sleep_length;
|
|
unsigned long last_jiffies;
|
|
unsigned long next_jiffies;
|
|
ktime_t idle_expires;
|
|
int do_timer_last;
|
|
};
|
|
|
|
extern void __init tick_init(void);
|
|
extern int tick_is_oneshot_available(void);
|
|
extern struct tick_device *tick_get_device(int cpu);
|
|
|
|
# ifdef CONFIG_HIGH_RES_TIMERS
|
|
extern int tick_init_highres(void);
|
|
extern int tick_program_event(ktime_t expires, int force);
|
|
extern void tick_setup_sched_timer(void);
|
|
# endif
|
|
|
|
# if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
|
|
extern void tick_cancel_sched_timer(int cpu);
|
|
# else
|
|
static inline void tick_cancel_sched_timer(int cpu) { }
|
|
# endif
|
|
|
|
# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
|
|
extern struct tick_device *tick_get_broadcast_device(void);
|
|
extern struct cpumask *tick_get_broadcast_mask(void);
|
|
|
|
# ifdef CONFIG_TICK_ONESHOT
|
|
extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
|
|
# endif
|
|
|
|
# endif /* BROADCAST */
|
|
|
|
# ifdef CONFIG_TICK_ONESHOT
|
|
extern void tick_clock_notify(void);
|
|
extern int tick_check_oneshot_change(int allow_nohz);
|
|
extern struct tick_sched *tick_get_tick_sched(int cpu);
|
|
extern void tick_irq_enter(void);
|
|
extern int tick_oneshot_mode_active(void);
|
|
# ifndef arch_needs_cpu
|
|
# define arch_needs_cpu(cpu) (0)
|
|
# endif
|
|
# else
|
|
static inline void tick_clock_notify(void) { }
|
|
static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
|
|
static inline void tick_irq_enter(void) { }
|
|
static inline int tick_oneshot_mode_active(void) { return 0; }
|
|
# endif
|
|
|
|
#else /* CONFIG_GENERIC_CLOCKEVENTS */
|
|
static inline void tick_init(void) { }
|
|
static inline void tick_cancel_sched_timer(int cpu) { }
|
|
static inline void tick_clock_notify(void) { }
|
|
static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
|
|
static inline void tick_irq_enter(void) { }
|
|
static inline int tick_oneshot_mode_active(void) { return 0; }
|
|
#endif /* !CONFIG_GENERIC_CLOCKEVENTS */
|
|
|
|
# ifdef CONFIG_NO_HZ_COMMON
|
|
DECLARE_PER_CPU(struct tick_sched, tick_cpu_sched);
|
|
|
|
static inline int tick_nohz_tick_stopped(void)
|
|
{
|
|
return __this_cpu_read(tick_cpu_sched.tick_stopped);
|
|
}
|
|
|
|
extern void tick_nohz_idle_enter(void);
|
|
extern void tick_nohz_idle_exit(void);
|
|
extern void tick_nohz_irq_exit(void);
|
|
extern ktime_t tick_nohz_get_sleep_length(void);
|
|
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
|
|
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
|
|
|
|
# else /* !CONFIG_NO_HZ_COMMON */
|
|
static inline int tick_nohz_tick_stopped(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void tick_nohz_idle_enter(void) { }
|
|
static inline void tick_nohz_idle_exit(void) { }
|
|
|
|
static inline ktime_t tick_nohz_get_sleep_length(void)
|
|
{
|
|
ktime_t len = { .tv64 = NSEC_PER_SEC/HZ };
|
|
|
|
return len;
|
|
}
|
|
static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
|
|
static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
|
|
# endif /* !CONFIG_NO_HZ_COMMON */
|
|
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
extern bool tick_nohz_full_running;
|
|
extern cpumask_var_t tick_nohz_full_mask;
|
|
extern cpumask_var_t housekeeping_mask;
|
|
|
|
static inline bool tick_nohz_full_enabled(void)
|
|
{
|
|
if (!context_tracking_is_enabled())
|
|
return false;
|
|
|
|
return tick_nohz_full_running;
|
|
}
|
|
|
|
static inline bool tick_nohz_full_cpu(int cpu)
|
|
{
|
|
if (!tick_nohz_full_enabled())
|
|
return false;
|
|
|
|
return cpumask_test_cpu(cpu, tick_nohz_full_mask);
|
|
}
|
|
|
|
extern void tick_nohz_init(void);
|
|
extern void __tick_nohz_full_check(void);
|
|
extern void tick_nohz_full_kick(void);
|
|
extern void tick_nohz_full_kick_cpu(int cpu);
|
|
extern void tick_nohz_full_kick_all(void);
|
|
extern void __tick_nohz_task_switch(struct task_struct *tsk);
|
|
#else
|
|
static inline void tick_nohz_init(void) { }
|
|
static inline bool tick_nohz_full_enabled(void) { return false; }
|
|
static inline bool tick_nohz_full_cpu(int cpu) { return false; }
|
|
static inline void __tick_nohz_full_check(void) { }
|
|
static inline void tick_nohz_full_kick_cpu(int cpu) { }
|
|
static inline void tick_nohz_full_kick(void) { }
|
|
static inline void tick_nohz_full_kick_all(void) { }
|
|
static inline void __tick_nohz_task_switch(struct task_struct *tsk) { }
|
|
#endif
|
|
|
|
static inline bool is_housekeeping_cpu(int cpu)
|
|
{
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
if (tick_nohz_full_enabled())
|
|
return cpumask_test_cpu(cpu, housekeeping_mask);
|
|
#endif
|
|
return true;
|
|
}
|
|
|
|
static inline void housekeeping_affine(struct task_struct *t)
|
|
{
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
if (tick_nohz_full_enabled())
|
|
set_cpus_allowed_ptr(t, housekeeping_mask);
|
|
|
|
#endif
|
|
}
|
|
|
|
static inline void tick_nohz_full_check(void)
|
|
{
|
|
if (tick_nohz_full_enabled())
|
|
__tick_nohz_full_check();
|
|
}
|
|
|
|
static inline void tick_nohz_task_switch(struct task_struct *tsk)
|
|
{
|
|
if (tick_nohz_full_enabled())
|
|
__tick_nohz_task_switch(tsk);
|
|
}
|
|
|
|
|
|
#endif
|