mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
synced 2026-10-29 13:23:23 +01:00
Sebastian Andrzej Siewior
912edebe85
There is rt_mutex_{pre|post}_schedule() around
rt_mutex_wait_proxy_lock() to ensure that sched_submit_work()/
sched_update_worker() is invoked before we schedule out and block on
rt_mutex while waiting for it become available.
The reason is that blocking on rt_mutex assigns a pi_waiter for the PI
chain and sched_submit_work() will also assign a pi_waiter if it blocks
on lock but a this point we already have a waiter assigned.
We can't skip sched_submit_work() entirely because I/O relies on the
fact that I/O queue is flushed while it blocks on a sleeping lock.
Therefore sched_submit_work() is moved before we block on the lock.
Sleeping lock in this context means mutex or rw_semaphore not spinlock_t
on PREEMPT_RT. Because the mutex abstraction on PREEMPT_RT uses the same
abstraction as the futex proxy lock, the futex code ended up using
rt_mutex_{pre|post}_schedule(), too.
Using it is/ was just to keep the task_struct::sched_rt_mutex assertion
happy. Futex proxy lock is used only in the syscall context of a task.
At this point it never got any I/O that needs to be flushed and it can't
be a workqueue that needs to notify that it will be scheduled out.
Therefore sched_submit_work() does nothing here.
By mistake futex_wait_requeue_pi() -> rt_mutex_wait_proxy_lock() did not
get the rt_mutex_{pre|post}_schedule() annotation. This was not noticed
because in this callchain the lock is (usually) not contended and so
rt_mutex_slowlock_block() does not schedule, triggering the assert.
Adding rt_mutex_pre_schedule() here looks wrong (as noted by PeterZ)
because at this point there is a pi_waiter recorded and invoking
sched_submit_work() with a possible lock contention would be wrong.
Add rt_mutex_futex_{pre|post}_schedule() which toggles the
sched_rt_mutex assert and does not involve sched_submit_work(). Add
asserts here to ensure that sched_submit_work() would do nothing. Use it
only in futex proxy lock case which is rt_mutex_wait_proxy_lock().
Remove it from futex_lock_pi().
Fixes: d14f9e930b ("locking/rtmutex: Use rt_mutex specific scheduler helpers")
Reported-by: Yao Kai <[email protected]>
Signed-off-by: Sebastian Andrzej Siewior <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: https://patch.msgid.link/[email protected]
Closes: https://lore.kernel.org/all/[email protected]
87 lines
2.1 KiB
C
87 lines
2.1 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_SCHED_RT_H
|
|
#define _LINUX_SCHED_RT_H
|
|
|
|
#include <linux/sched.h>
|
|
|
|
struct task_struct;
|
|
|
|
static inline bool rt_prio(int prio)
|
|
{
|
|
return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO);
|
|
}
|
|
|
|
static inline bool rt_or_dl_prio(int prio)
|
|
{
|
|
return unlikely(prio < MAX_RT_PRIO);
|
|
}
|
|
|
|
/*
|
|
* Returns true if a task has a priority that belongs to RT class. PI-boosted
|
|
* tasks will return true. Use rt_policy() to ignore PI-boosted tasks.
|
|
*/
|
|
static inline bool rt_task(struct task_struct *p)
|
|
{
|
|
return rt_prio(p->prio);
|
|
}
|
|
|
|
/*
|
|
* Returns true if a task has a priority that belongs to RT or DL classes.
|
|
* PI-boosted tasks will return true. Use rt_or_dl_task_policy() to ignore
|
|
* PI-boosted tasks.
|
|
*/
|
|
static inline bool rt_or_dl_task(struct task_struct *p)
|
|
{
|
|
return rt_or_dl_prio(p->prio);
|
|
}
|
|
|
|
/*
|
|
* Returns true if a task has a policy that belongs to RT or DL classes.
|
|
* PI-boosted tasks will return false.
|
|
*/
|
|
static inline bool rt_or_dl_task_policy(struct task_struct *tsk)
|
|
{
|
|
int policy = tsk->policy;
|
|
|
|
if (policy == SCHED_FIFO || policy == SCHED_RR)
|
|
return true;
|
|
if (policy == SCHED_DEADLINE)
|
|
return true;
|
|
return false;
|
|
}
|
|
|
|
#ifdef CONFIG_RT_MUTEXES
|
|
extern void rt_mutex_pre_schedule(void);
|
|
extern void rt_mutex_futex_pre_schedule(void);
|
|
extern void rt_mutex_schedule(void);
|
|
extern void rt_mutex_post_schedule(void);
|
|
extern void rt_mutex_futex_post_schedule(void);
|
|
|
|
/*
|
|
* Must hold either p->pi_lock or task_rq(p)->lock.
|
|
*/
|
|
static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p)
|
|
{
|
|
return p->pi_top_task;
|
|
}
|
|
extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task);
|
|
extern void rt_mutex_adjust_pi(struct task_struct *p);
|
|
#else
|
|
static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
|
|
{
|
|
return NULL;
|
|
}
|
|
# define rt_mutex_adjust_pi(p) do { } while (0)
|
|
#endif
|
|
|
|
extern void normalize_rt_tasks(void);
|
|
|
|
|
|
/*
|
|
* default timeslice is 100 msecs (used only for SCHED_RR tasks).
|
|
* Timeslices get refilled after they expire.
|
|
*/
|
|
#define RR_TIMESLICE (100 * HZ / 1000)
|
|
|
|
#endif /* _LINUX_SCHED_RT_H */
|