cfafcd117d
By changing futex_lock_pi() to use rt_mutex_*_proxy_lock() all wait_list modifications are done under both hb->lock and wait_lock. This closes the obvious interleave pattern between futex_lock_pi() and futex_unlock_pi(), but not entirely so. See below: Before: futex_lock_pi() futex_unlock_pi() unlock hb->lock lock hb->lock unlock hb->lock lock rt_mutex->wait_lock unlock rt_mutex_wait_lock -EAGAIN lock rt_mutex->wait_lock list_add unlock rt_mutex->wait_lock schedule() lock rt_mutex->wait_lock list_del unlock rt_mutex->wait_lock <idem> -EAGAIN lock hb->lock After: futex_lock_pi() futex_unlock_pi() lock hb->lock lock rt_mutex->wait_lock list_add unlock rt_mutex->wait_lock unlock hb->lock schedule() lock hb->lock unlock hb->lock lock hb->lock lock rt_mutex->wait_lock list_del unlock rt_mutex->wait_lock lock rt_mutex->wait_lock unlock rt_mutex_wait_lock -EAGAIN unlock hb->lock It does however solve the earlier starvation/live-lock scenario which got introduced with the -EAGAIN since unlike the before scenario; where the -EAGAIN happens while futex_unlock_pi() doesn't hold any locks; in the after scenario it happens while futex_unlock_pi() actually holds a lock, and then it is serialized on that lock. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: juri.lelli@arm.com Cc: bigeasy@linutronix.de Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: dvhart@infradead.org Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170322104152.062785528@infradead.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
131 lines
3.5 KiB
C
131 lines
3.5 KiB
C
/*
|
|
* RT Mutexes: blocking mutual exclusion locks with PI support
|
|
*
|
|
* started by Ingo Molnar and Thomas Gleixner:
|
|
*
|
|
* Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
|
|
* Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
|
|
*
|
|
* This file contains the private data structure and API definitions.
|
|
*/
|
|
|
|
#ifndef __KERNEL_RTMUTEX_COMMON_H
|
|
#define __KERNEL_RTMUTEX_COMMON_H
|
|
|
|
#include <linux/rtmutex.h>
|
|
#include <linux/sched/wake_q.h>
|
|
|
|
/*
|
|
* This is the control structure for tasks blocked on a rt_mutex,
|
|
* which is allocated on the kernel stack on of the blocked task.
|
|
*
|
|
* @tree_entry: pi node to enqueue into the mutex waiters tree
|
|
* @pi_tree_entry: pi node to enqueue into the mutex owner waiters tree
|
|
* @task: task reference to the blocked task
|
|
*/
|
|
struct rt_mutex_waiter {
|
|
struct rb_node tree_entry;
|
|
struct rb_node pi_tree_entry;
|
|
struct task_struct *task;
|
|
struct rt_mutex *lock;
|
|
#ifdef CONFIG_DEBUG_RT_MUTEXES
|
|
unsigned long ip;
|
|
struct pid *deadlock_task_pid;
|
|
struct rt_mutex *deadlock_lock;
|
|
#endif
|
|
int prio;
|
|
};
|
|
|
|
/*
|
|
* Various helpers to access the waiters-tree:
|
|
*/
|
|
static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
|
|
{
|
|
return !RB_EMPTY_ROOT(&lock->waiters);
|
|
}
|
|
|
|
static inline struct rt_mutex_waiter *
|
|
rt_mutex_top_waiter(struct rt_mutex *lock)
|
|
{
|
|
struct rt_mutex_waiter *w;
|
|
|
|
w = rb_entry(lock->waiters_leftmost, struct rt_mutex_waiter,
|
|
tree_entry);
|
|
BUG_ON(w->lock != lock);
|
|
|
|
return w;
|
|
}
|
|
|
|
static inline int task_has_pi_waiters(struct task_struct *p)
|
|
{
|
|
return !RB_EMPTY_ROOT(&p->pi_waiters);
|
|
}
|
|
|
|
static inline struct rt_mutex_waiter *
|
|
task_top_pi_waiter(struct task_struct *p)
|
|
{
|
|
return rb_entry(p->pi_waiters_leftmost, struct rt_mutex_waiter,
|
|
pi_tree_entry);
|
|
}
|
|
|
|
/*
|
|
* lock->owner state tracking:
|
|
*/
|
|
#define RT_MUTEX_HAS_WAITERS 1UL
|
|
|
|
static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
|
|
{
|
|
unsigned long owner = (unsigned long) READ_ONCE(lock->owner);
|
|
|
|
return (struct task_struct *) (owner & ~RT_MUTEX_HAS_WAITERS);
|
|
}
|
|
|
|
/*
|
|
* Constants for rt mutex functions which have a selectable deadlock
|
|
* detection.
|
|
*
|
|
* RT_MUTEX_MIN_CHAINWALK: Stops the lock chain walk when there are
|
|
* no further PI adjustments to be made.
|
|
*
|
|
* RT_MUTEX_FULL_CHAINWALK: Invoke deadlock detection with a full
|
|
* walk of the lock chain.
|
|
*/
|
|
enum rtmutex_chainwalk {
|
|
RT_MUTEX_MIN_CHAINWALK,
|
|
RT_MUTEX_FULL_CHAINWALK,
|
|
};
|
|
|
|
/*
|
|
* PI-futex support (proxy locking functions, etc.):
|
|
*/
|
|
extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
|
|
extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
|
|
struct task_struct *proxy_owner);
|
|
extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
|
|
struct task_struct *proxy_owner);
|
|
extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
|
|
extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
|
|
struct rt_mutex_waiter *waiter,
|
|
struct task_struct *task);
|
|
extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
|
|
struct hrtimer_sleeper *to,
|
|
struct rt_mutex_waiter *waiter);
|
|
extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
|
|
struct rt_mutex_waiter *waiter);
|
|
|
|
extern int rt_mutex_futex_trylock(struct rt_mutex *l);
|
|
|
|
extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
|
|
extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
|
|
struct wake_q_head *wqh);
|
|
|
|
extern void rt_mutex_adjust_prio(struct task_struct *task);
|
|
|
|
#ifdef CONFIG_DEBUG_RT_MUTEXES
|
|
# include "rtmutex-debug.h"
|
|
#else
|
|
# include "rtmutex.h"
|
|
#endif
|
|
|
|
#endif
|