Peter Zijlstra f27dde8dee sched: Add NEED_RESCHED to the preempt_count
In order to combine the preemption and need_resched test we need to
fold the need_resched information into the preempt_count value.

Since the NEED_RESCHED flag is set across CPUs this needs to be an
atomic operation, however we very much want to avoid making
preempt_count atomic, therefore we keep the existing TIF_NEED_RESCHED
infrastructure in place but at 3 sites test it and fold its value into
preempt_count; namely:

 - resched_task() when setting TIF_NEED_RESCHED on the current task
 - scheduler_ipi() when resched_task() sets TIF_NEED_RESCHED on a
                   remote task it follows it up with a reschedule IPI
                   and we can modify the cpu local preempt_count from
                   there.
 - cpu_idle_loop() for when resched_task() found tsk_is_polling().

We use an inverted bitmask to indicate need_resched so that a 0 means
both need_resched and !atomic.

Also remove the barrier() in preempt_enable() between
preempt_enable_no_resched() and preempt_check_resched() to avoid
having to reload the preemption value and allow the compiler to use
the flags of the previuos decrement. I couldn't come up with any sane
reason for this barrier() to be there as preempt_enable_no_resched()
already has a barrier() before doing the decrement.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-7a7m5qqbn5pmwnd4wko9u6da@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-09-25 14:07:49 +02:00

228 lines
6.0 KiB
C

#ifndef __LINUX_PREEMPT_H
#define __LINUX_PREEMPT_H
/*
* include/linux/preempt.h - macros for accessing and manipulating
* preempt_count (used for kernel preemption, interrupt count, etc.)
*/
#include <linux/thread_info.h>
#include <linux/linkage.h>
#include <linux/list.h>
/*
* We use the MSB mostly because its available; see <linux/preempt_mask.h> for
* the other bits -- can't include that header due to inclusion hell.
*/
#define PREEMPT_NEED_RESCHED 0x80000000
/*
* We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
* that think a non-zero value indicates we cannot preempt.
*/
static __always_inline int preempt_count(void)
{
return current_thread_info()->preempt_count & ~PREEMPT_NEED_RESCHED;
}
static __always_inline int *preempt_count_ptr(void)
{
return &current_thread_info()->preempt_count;
}
/*
* We now loose PREEMPT_NEED_RESCHED and cause an extra reschedule; however the
* alternative is loosing a reschedule. Better schedule too often -- also this
* should be a very rare operation.
*/
static __always_inline void preempt_count_set(int pc)
{
*preempt_count_ptr() = pc;
}
/*
* We fold the NEED_RESCHED bit into the preempt count such that
* preempt_enable() can decrement and test for needing to reschedule with a
* single instruction.
*
* We invert the actual bit, so that when the decrement hits 0 we know we both
* need to resched (the bit is cleared) and can resched (no preempt count).
*/
static __always_inline void set_preempt_need_resched(void)
{
*preempt_count_ptr() &= ~PREEMPT_NEED_RESCHED;
}
static __always_inline void clear_preempt_need_resched(void)
{
*preempt_count_ptr() |= PREEMPT_NEED_RESCHED;
}
static __always_inline bool test_preempt_need_resched(void)
{
return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED);
}
#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
extern void add_preempt_count(int val);
extern void sub_preempt_count(int val);
#else
# define add_preempt_count(val) do { *preempt_count_ptr() += (val); } while (0)
# define sub_preempt_count(val) do { *preempt_count_ptr() -= (val); } while (0)
#endif
#define inc_preempt_count() add_preempt_count(1)
#define dec_preempt_count() sub_preempt_count(1)
#ifdef CONFIG_PREEMPT
asmlinkage void preempt_schedule(void);
#define preempt_check_resched() \
do { \
if (unlikely(!*preempt_count_ptr())) \
preempt_schedule(); \
} while (0)
#ifdef CONFIG_CONTEXT_TRACKING
void preempt_schedule_context(void);
#define preempt_check_resched_context() \
do { \
if (unlikely(!*preempt_count_ptr())) \
preempt_schedule_context(); \
} while (0)
#else
#define preempt_check_resched_context() preempt_check_resched()
#endif /* CONFIG_CONTEXT_TRACKING */
#else /* !CONFIG_PREEMPT */
#define preempt_check_resched() do { } while (0)
#define preempt_check_resched_context() do { } while (0)
#endif /* CONFIG_PREEMPT */
#ifdef CONFIG_PREEMPT_COUNT
#define preempt_disable() \
do { \
inc_preempt_count(); \
barrier(); \
} while (0)
#define sched_preempt_enable_no_resched() \
do { \
barrier(); \
dec_preempt_count(); \
} while (0)
#define preempt_enable_no_resched() sched_preempt_enable_no_resched()
#define preempt_enable() \
do { \
preempt_enable_no_resched(); \
preempt_check_resched(); \
} while (0)
/* For debugging and tracer internals only! */
#define add_preempt_count_notrace(val) \
do { *preempt_count_ptr() += (val); } while (0)
#define sub_preempt_count_notrace(val) \
do { *preempt_count_ptr() -= (val); } while (0)
#define inc_preempt_count_notrace() add_preempt_count_notrace(1)
#define dec_preempt_count_notrace() sub_preempt_count_notrace(1)
#define preempt_disable_notrace() \
do { \
inc_preempt_count_notrace(); \
barrier(); \
} while (0)
#define preempt_enable_no_resched_notrace() \
do { \
barrier(); \
dec_preempt_count_notrace(); \
} while (0)
/* preempt_check_resched is OK to trace */
#define preempt_enable_notrace() \
do { \
preempt_enable_no_resched_notrace(); \
preempt_check_resched_context(); \
} while (0)
#else /* !CONFIG_PREEMPT_COUNT */
/*
* Even if we don't have any preemption, we need preempt disable/enable
* to be barriers, so that we don't have things like get_user/put_user
* that can cause faults and scheduling migrate into our preempt-protected
* region.
*/
#define preempt_disable() barrier()
#define sched_preempt_enable_no_resched() barrier()
#define preempt_enable_no_resched() barrier()
#define preempt_enable() barrier()
#define preempt_disable_notrace() barrier()
#define preempt_enable_no_resched_notrace() barrier()
#define preempt_enable_notrace() barrier()
#endif /* CONFIG_PREEMPT_COUNT */
#ifdef CONFIG_PREEMPT_NOTIFIERS
struct preempt_notifier;
/**
* preempt_ops - notifiers called when a task is preempted and rescheduled
* @sched_in: we're about to be rescheduled:
* notifier: struct preempt_notifier for the task being scheduled
* cpu: cpu we're scheduled on
* @sched_out: we've just been preempted
* notifier: struct preempt_notifier for the task being preempted
* next: the task that's kicking us out
*
* Please note that sched_in and out are called under different
* contexts. sched_out is called with rq lock held and irq disabled
* while sched_in is called without rq lock and irq enabled. This
* difference is intentional and depended upon by its users.
*/
struct preempt_ops {
void (*sched_in)(struct preempt_notifier *notifier, int cpu);
void (*sched_out)(struct preempt_notifier *notifier,
struct task_struct *next);
};
/**
* preempt_notifier - key for installing preemption notifiers
* @link: internal use
* @ops: defines the notifier functions to be called
*
* Usually used in conjunction with container_of().
*/
struct preempt_notifier {
struct hlist_node link;
struct preempt_ops *ops;
};
void preempt_notifier_register(struct preempt_notifier *notifier);
void preempt_notifier_unregister(struct preempt_notifier *notifier);
static inline void preempt_notifier_init(struct preempt_notifier *notifier,
struct preempt_ops *ops)
{
INIT_HLIST_NODE(&notifier->link);
notifier->ops = ops;
}
#endif
#endif /* __LINUX_PREEMPT_H */