mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 01:10:04 +00:00
![Joel Fernandes (Google)](/assets/img/avatar_default.png)
This patch detaches the preemptirq tracepoints from the tracers and keeps it separate. Advantages: * Lockdep and irqsoff event can now run in parallel since they no longer have their own calls. * This unifies the usecase of adding hooks to an irqsoff and irqson event, and a preemptoff and preempton event. 3 users of the events exist: - Lockdep - irqsoff and preemptoff tracers - irqs and preempt trace events The unification cleans up several ifdefs and makes the code in preempt tracer and irqsoff tracers simpler. It gets rid of all the horrific ifdeferry around PROVE_LOCKING and makes configuration of the different users of the tracepoints more easy and understandable. It also gets rid of the time_* function calls from the lockdep hooks used to call into the preemptirq tracer which is not needed anymore. The negative delta in lines of code in this patch is quite large too. In the patch we introduce a new CONFIG option PREEMPTIRQ_TRACEPOINTS as a single point for registering probes onto the tracepoints. With this, the web of config options for preempt/irq toggle tracepoints and its users becomes: PREEMPT_TRACER PREEMPTIRQ_EVENTS IRQSOFF_TRACER PROVE_LOCKING | | \ | | \ (selects) / \ \ (selects) / TRACE_PREEMPT_TOGGLE ----> TRACE_IRQFLAGS \ / \ (depends on) / PREEMPTIRQ_TRACEPOINTS Other than the performance tests mentioned in the previous patch, I also ran the locking API test suite. I verified that all tests cases are passing. I also injected issues by not registering lockdep probes onto the tracepoints and I see failures to confirm that the probes are indeed working. This series + lockdep probes not registered (just to inject errors): [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12:FAILED|FAILED| ok | [ 0.000000] sirq-safe-A => hirqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | With this series + lockdep probes registered, all locking tests pass: [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | Link: http://lkml.kernel.org/r/20180730222423.196630-4-joel@joelfernandes.org Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
328 lines
9.3 KiB
C
328 lines
9.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#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/linkage.h>
|
|
#include <linux/list.h>
|
|
|
|
/*
|
|
* We put the hardirq and softirq counter into the preemption
|
|
* counter. The bitmask has the following meaning:
|
|
*
|
|
* - bits 0-7 are the preemption count (max preemption depth: 256)
|
|
* - bits 8-15 are the softirq count (max # of softirqs: 256)
|
|
*
|
|
* The hardirq count could in theory be the same as the number of
|
|
* interrupts in the system, but we run all interrupt handlers with
|
|
* interrupts disabled, so we cannot have nesting interrupts. Though
|
|
* there are a few palaeontologic drivers which reenable interrupts in
|
|
* the handler, so we need more than one bit here.
|
|
*
|
|
* PREEMPT_MASK: 0x000000ff
|
|
* SOFTIRQ_MASK: 0x0000ff00
|
|
* HARDIRQ_MASK: 0x000f0000
|
|
* NMI_MASK: 0x00100000
|
|
* PREEMPT_NEED_RESCHED: 0x80000000
|
|
*/
|
|
#define PREEMPT_BITS 8
|
|
#define SOFTIRQ_BITS 8
|
|
#define HARDIRQ_BITS 4
|
|
#define NMI_BITS 1
|
|
|
|
#define PREEMPT_SHIFT 0
|
|
#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS)
|
|
#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS)
|
|
#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS)
|
|
|
|
#define __IRQ_MASK(x) ((1UL << (x))-1)
|
|
|
|
#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
|
|
#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
|
|
#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
|
|
#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT)
|
|
|
|
#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT)
|
|
#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT)
|
|
#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
|
|
#define NMI_OFFSET (1UL << NMI_SHIFT)
|
|
|
|
#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET)
|
|
|
|
/* We use the MSB mostly because its available */
|
|
#define PREEMPT_NEED_RESCHED 0x80000000
|
|
|
|
#define PREEMPT_DISABLED (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
|
|
|
|
/*
|
|
* Disable preemption until the scheduler is running -- use an unconditional
|
|
* value so that it also works on !PREEMPT_COUNT kernels.
|
|
*
|
|
* Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
|
|
*/
|
|
#define INIT_PREEMPT_COUNT PREEMPT_OFFSET
|
|
|
|
/*
|
|
* Initial preempt_count value; reflects the preempt_count schedule invariant
|
|
* which states that during context switches:
|
|
*
|
|
* preempt_count() == 2*PREEMPT_DISABLE_OFFSET
|
|
*
|
|
* Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
|
|
* Note: See finish_task_switch().
|
|
*/
|
|
#define FORK_PREEMPT_COUNT (2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
|
|
|
|
/* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */
|
|
#include <asm/preempt.h>
|
|
|
|
#define hardirq_count() (preempt_count() & HARDIRQ_MASK)
|
|
#define softirq_count() (preempt_count() & SOFTIRQ_MASK)
|
|
#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
|
|
| NMI_MASK))
|
|
|
|
/*
|
|
* Are we doing bottom half or hardware interrupt processing?
|
|
*
|
|
* in_irq() - We're in (hard) IRQ context
|
|
* in_softirq() - We have BH disabled, or are processing softirqs
|
|
* in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled
|
|
* in_serving_softirq() - We're in softirq context
|
|
* in_nmi() - We're in NMI context
|
|
* in_task() - We're in task context
|
|
*
|
|
* Note: due to the BH disabled confusion: in_softirq(),in_interrupt() really
|
|
* should not be used in new code.
|
|
*/
|
|
#define in_irq() (hardirq_count())
|
|
#define in_softirq() (softirq_count())
|
|
#define in_interrupt() (irq_count())
|
|
#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET)
|
|
#define in_nmi() (preempt_count() & NMI_MASK)
|
|
#define in_task() (!(preempt_count() & \
|
|
(NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
|
|
|
|
/*
|
|
* The preempt_count offset after preempt_disable();
|
|
*/
|
|
#if defined(CONFIG_PREEMPT_COUNT)
|
|
# define PREEMPT_DISABLE_OFFSET PREEMPT_OFFSET
|
|
#else
|
|
# define PREEMPT_DISABLE_OFFSET 0
|
|
#endif
|
|
|
|
/*
|
|
* The preempt_count offset after spin_lock()
|
|
*/
|
|
#define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET
|
|
|
|
/*
|
|
* The preempt_count offset needed for things like:
|
|
*
|
|
* spin_lock_bh()
|
|
*
|
|
* Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
|
|
* softirqs, such that unlock sequences of:
|
|
*
|
|
* spin_unlock();
|
|
* local_bh_enable();
|
|
*
|
|
* Work as expected.
|
|
*/
|
|
#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET)
|
|
|
|
/*
|
|
* Are we running in atomic context? WARNING: this macro cannot
|
|
* always detect atomic context; in particular, it cannot know about
|
|
* held spinlocks in non-preemptible kernels. Thus it should not be
|
|
* used in the general case to determine whether sleeping is possible.
|
|
* Do not use in_atomic() in driver code.
|
|
*/
|
|
#define in_atomic() (preempt_count() != 0)
|
|
|
|
/*
|
|
* Check whether we were atomic before we did preempt_disable():
|
|
* (used by the scheduler)
|
|
*/
|
|
#define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET)
|
|
|
|
#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE)
|
|
extern void preempt_count_add(int val);
|
|
extern void preempt_count_sub(int val);
|
|
#define preempt_count_dec_and_test() \
|
|
({ preempt_count_sub(1); should_resched(0); })
|
|
#else
|
|
#define preempt_count_add(val) __preempt_count_add(val)
|
|
#define preempt_count_sub(val) __preempt_count_sub(val)
|
|
#define preempt_count_dec_and_test() __preempt_count_dec_and_test()
|
|
#endif
|
|
|
|
#define __preempt_count_inc() __preempt_count_add(1)
|
|
#define __preempt_count_dec() __preempt_count_sub(1)
|
|
|
|
#define preempt_count_inc() preempt_count_add(1)
|
|
#define preempt_count_dec() preempt_count_sub(1)
|
|
|
|
#ifdef CONFIG_PREEMPT_COUNT
|
|
|
|
#define preempt_disable() \
|
|
do { \
|
|
preempt_count_inc(); \
|
|
barrier(); \
|
|
} while (0)
|
|
|
|
#define sched_preempt_enable_no_resched() \
|
|
do { \
|
|
barrier(); \
|
|
preempt_count_dec(); \
|
|
} while (0)
|
|
|
|
#define preempt_enable_no_resched() sched_preempt_enable_no_resched()
|
|
|
|
#define preemptible() (preempt_count() == 0 && !irqs_disabled())
|
|
|
|
#ifdef CONFIG_PREEMPT
|
|
#define preempt_enable() \
|
|
do { \
|
|
barrier(); \
|
|
if (unlikely(preempt_count_dec_and_test())) \
|
|
__preempt_schedule(); \
|
|
} while (0)
|
|
|
|
#define preempt_enable_notrace() \
|
|
do { \
|
|
barrier(); \
|
|
if (unlikely(__preempt_count_dec_and_test())) \
|
|
__preempt_schedule_notrace(); \
|
|
} while (0)
|
|
|
|
#define preempt_check_resched() \
|
|
do { \
|
|
if (should_resched(0)) \
|
|
__preempt_schedule(); \
|
|
} while (0)
|
|
|
|
#else /* !CONFIG_PREEMPT */
|
|
#define preempt_enable() \
|
|
do { \
|
|
barrier(); \
|
|
preempt_count_dec(); \
|
|
} while (0)
|
|
|
|
#define preempt_enable_notrace() \
|
|
do { \
|
|
barrier(); \
|
|
__preempt_count_dec(); \
|
|
} while (0)
|
|
|
|
#define preempt_check_resched() do { } while (0)
|
|
#endif /* CONFIG_PREEMPT */
|
|
|
|
#define preempt_disable_notrace() \
|
|
do { \
|
|
__preempt_count_inc(); \
|
|
barrier(); \
|
|
} while (0)
|
|
|
|
#define preempt_enable_no_resched_notrace() \
|
|
do { \
|
|
barrier(); \
|
|
__preempt_count_dec(); \
|
|
} 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_check_resched() do { } while (0)
|
|
|
|
#define preempt_disable_notrace() barrier()
|
|
#define preempt_enable_no_resched_notrace() barrier()
|
|
#define preempt_enable_notrace() barrier()
|
|
#define preemptible() 0
|
|
|
|
#endif /* CONFIG_PREEMPT_COUNT */
|
|
|
|
#ifdef MODULE
|
|
/*
|
|
* Modules have no business playing preemption tricks.
|
|
*/
|
|
#undef sched_preempt_enable_no_resched
|
|
#undef preempt_enable_no_resched
|
|
#undef preempt_enable_no_resched_notrace
|
|
#undef preempt_check_resched
|
|
#endif
|
|
|
|
#define preempt_set_need_resched() \
|
|
do { \
|
|
set_preempt_need_resched(); \
|
|
} while (0)
|
|
#define preempt_fold_need_resched() \
|
|
do { \
|
|
if (tif_need_resched()) \
|
|
set_preempt_need_resched(); \
|
|
} while (0)
|
|
|
|
#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_inc(void);
|
|
void preempt_notifier_dec(void);
|
|
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(¬ifier->link);
|
|
notifier->ops = ops;
|
|
}
|
|
|
|
#endif
|
|
|
|
#endif /* __LINUX_PREEMPT_H */
|