mirror of
https://github.com/torvalds/linux.git
synced 2024-11-24 05:02:12 +00:00
fd6be105b8
Currently, we can hit a nasty case with optimistic spinning on mutexes: CPU A tries to take a mutex, while holding the BKL CPU B tried to take the BLK while holding the mutex This looks like a AB-BA scenario but in practice, is allowed and happens due to the auto-release on schedule() nature of the BKL. In that case, the optimistic spinning code can get us into a situation where instead of going to sleep, A will spin waiting for B who is spinning waiting for A, and the only way out of that loop is the need_resched() test in mutex_spin_on_owner(). This patch fixes it by completely disabling spinning if we own the BKL. This adds one more detail to the extensive list of reasons why it's a bad idea for kernel code to be holding the BKL. Signed-off-by: Tony Breeds <tony@bakeyournoodle.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: <stable@kernel.org> LKML-Reference: <20100519054636.GC12389@ozlabs.org> [ added an unlikely() attribute to the branch ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
508 lines
13 KiB
C
508 lines
13 KiB
C
/*
|
|
* kernel/mutex.c
|
|
*
|
|
* Mutexes: blocking mutual exclusion locks
|
|
*
|
|
* Started by Ingo Molnar:
|
|
*
|
|
* Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
|
|
*
|
|
* Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and
|
|
* David Howells for suggestions and improvements.
|
|
*
|
|
* - Adaptive spinning for mutexes by Peter Zijlstra. (Ported to mainline
|
|
* from the -rt tree, where it was originally implemented for rtmutexes
|
|
* by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale
|
|
* and Sven Dietrich.
|
|
*
|
|
* Also see Documentation/mutex-design.txt.
|
|
*/
|
|
#include <linux/mutex.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/module.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/debug_locks.h>
|
|
|
|
/*
|
|
* In the DEBUG case we are using the "NULL fastpath" for mutexes,
|
|
* which forces all calls into the slowpath:
|
|
*/
|
|
#ifdef CONFIG_DEBUG_MUTEXES
|
|
# include "mutex-debug.h"
|
|
# include <asm-generic/mutex-null.h>
|
|
#else
|
|
# include "mutex.h"
|
|
# include <asm/mutex.h>
|
|
#endif
|
|
|
|
/***
|
|
* mutex_init - initialize the mutex
|
|
* @lock: the mutex to be initialized
|
|
* @key: the lock_class_key for the class; used by mutex lock debugging
|
|
*
|
|
* Initialize the mutex to unlocked state.
|
|
*
|
|
* It is not allowed to initialize an already locked mutex.
|
|
*/
|
|
void
|
|
__mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
|
|
{
|
|
atomic_set(&lock->count, 1);
|
|
spin_lock_init(&lock->wait_lock);
|
|
INIT_LIST_HEAD(&lock->wait_list);
|
|
mutex_clear_owner(lock);
|
|
|
|
debug_mutex_init(lock, name, key);
|
|
}
|
|
|
|
EXPORT_SYMBOL(__mutex_init);
|
|
|
|
#ifndef CONFIG_DEBUG_LOCK_ALLOC
|
|
/*
|
|
* We split the mutex lock/unlock logic into separate fastpath and
|
|
* slowpath functions, to reduce the register pressure on the fastpath.
|
|
* We also put the fastpath first in the kernel image, to make sure the
|
|
* branch is predicted by the CPU as default-untaken.
|
|
*/
|
|
static __used noinline void __sched
|
|
__mutex_lock_slowpath(atomic_t *lock_count);
|
|
|
|
/***
|
|
* mutex_lock - acquire the mutex
|
|
* @lock: the mutex to be acquired
|
|
*
|
|
* Lock the mutex exclusively for this task. If the mutex is not
|
|
* available right now, it will sleep until it can get it.
|
|
*
|
|
* The mutex must later on be released by the same task that
|
|
* acquired it. Recursive locking is not allowed. The task
|
|
* may not exit without first unlocking the mutex. Also, kernel
|
|
* memory where the mutex resides mutex must not be freed with
|
|
* the mutex still locked. The mutex must first be initialized
|
|
* (or statically defined) before it can be locked. memset()-ing
|
|
* the mutex to 0 is not allowed.
|
|
*
|
|
* ( The CONFIG_DEBUG_MUTEXES .config option turns on debugging
|
|
* checks that will enforce the restrictions and will also do
|
|
* deadlock debugging. )
|
|
*
|
|
* This function is similar to (but not equivalent to) down().
|
|
*/
|
|
void __sched mutex_lock(struct mutex *lock)
|
|
{
|
|
might_sleep();
|
|
/*
|
|
* The locking fastpath is the 1->0 transition from
|
|
* 'unlocked' into 'locked' state.
|
|
*/
|
|
__mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath);
|
|
mutex_set_owner(lock);
|
|
}
|
|
|
|
EXPORT_SYMBOL(mutex_lock);
|
|
#endif
|
|
|
|
static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
|
|
|
|
/***
|
|
* mutex_unlock - release the mutex
|
|
* @lock: the mutex to be released
|
|
*
|
|
* Unlock a mutex that has been locked by this task previously.
|
|
*
|
|
* This function must not be used in interrupt context. Unlocking
|
|
* of a not locked mutex is not allowed.
|
|
*
|
|
* This function is similar to (but not equivalent to) up().
|
|
*/
|
|
void __sched mutex_unlock(struct mutex *lock)
|
|
{
|
|
/*
|
|
* The unlocking fastpath is the 0->1 transition from 'locked'
|
|
* into 'unlocked' state:
|
|
*/
|
|
#ifndef CONFIG_DEBUG_MUTEXES
|
|
/*
|
|
* When debugging is enabled we must not clear the owner before time,
|
|
* the slow path will always be taken, and that clears the owner field
|
|
* after verifying that it was indeed current.
|
|
*/
|
|
mutex_clear_owner(lock);
|
|
#endif
|
|
__mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath);
|
|
}
|
|
|
|
EXPORT_SYMBOL(mutex_unlock);
|
|
|
|
/*
|
|
* Lock a mutex (possibly interruptible), slowpath:
|
|
*/
|
|
static inline int __sched
|
|
__mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
|
|
unsigned long ip)
|
|
{
|
|
struct task_struct *task = current;
|
|
struct mutex_waiter waiter;
|
|
unsigned long flags;
|
|
|
|
preempt_disable();
|
|
mutex_acquire(&lock->dep_map, subclass, 0, ip);
|
|
|
|
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
|
|
/*
|
|
* Optimistic spinning.
|
|
*
|
|
* We try to spin for acquisition when we find that there are no
|
|
* pending waiters and the lock owner is currently running on a
|
|
* (different) CPU.
|
|
*
|
|
* The rationale is that if the lock owner is running, it is likely to
|
|
* release the lock soon.
|
|
*
|
|
* Since this needs the lock owner, and this mutex implementation
|
|
* doesn't track the owner atomically in the lock field, we need to
|
|
* track it non-atomically.
|
|
*
|
|
* We can't do this for DEBUG_MUTEXES because that relies on wait_lock
|
|
* to serialize everything.
|
|
*/
|
|
|
|
for (;;) {
|
|
struct thread_info *owner;
|
|
|
|
/*
|
|
* If we own the BKL, then don't spin. The owner of
|
|
* the mutex might be waiting on us to release the BKL.
|
|
*/
|
|
if (unlikely(current->lock_depth >= 0))
|
|
break;
|
|
|
|
/*
|
|
* If there's an owner, wait for it to either
|
|
* release the lock or go to sleep.
|
|
*/
|
|
owner = ACCESS_ONCE(lock->owner);
|
|
if (owner && !mutex_spin_on_owner(lock, owner))
|
|
break;
|
|
|
|
if (atomic_cmpxchg(&lock->count, 1, 0) == 1) {
|
|
lock_acquired(&lock->dep_map, ip);
|
|
mutex_set_owner(lock);
|
|
preempt_enable();
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* When there's no owner, we might have preempted between the
|
|
* owner acquiring the lock and setting the owner field. If
|
|
* we're an RT task that will live-lock because we won't let
|
|
* the owner complete.
|
|
*/
|
|
if (!owner && (need_resched() || rt_task(task)))
|
|
break;
|
|
|
|
/*
|
|
* The cpu_relax() call is a compiler barrier which forces
|
|
* everything in this loop to be re-loaded. We don't need
|
|
* memory barriers as we'll eventually observe the right
|
|
* values at the cost of a few extra spins.
|
|
*/
|
|
cpu_relax();
|
|
}
|
|
#endif
|
|
spin_lock_mutex(&lock->wait_lock, flags);
|
|
|
|
debug_mutex_lock_common(lock, &waiter);
|
|
debug_mutex_add_waiter(lock, &waiter, task_thread_info(task));
|
|
|
|
/* add waiting tasks to the end of the waitqueue (FIFO): */
|
|
list_add_tail(&waiter.list, &lock->wait_list);
|
|
waiter.task = task;
|
|
|
|
if (atomic_xchg(&lock->count, -1) == 1)
|
|
goto done;
|
|
|
|
lock_contended(&lock->dep_map, ip);
|
|
|
|
for (;;) {
|
|
/*
|
|
* Lets try to take the lock again - this is needed even if
|
|
* we get here for the first time (shortly after failing to
|
|
* acquire the lock), to make sure that we get a wakeup once
|
|
* it's unlocked. Later on, if we sleep, this is the
|
|
* operation that gives us the lock. We xchg it to -1, so
|
|
* that when we release the lock, we properly wake up the
|
|
* other waiters:
|
|
*/
|
|
if (atomic_xchg(&lock->count, -1) == 1)
|
|
break;
|
|
|
|
/*
|
|
* got a signal? (This code gets eliminated in the
|
|
* TASK_UNINTERRUPTIBLE case.)
|
|
*/
|
|
if (unlikely(signal_pending_state(state, task))) {
|
|
mutex_remove_waiter(lock, &waiter,
|
|
task_thread_info(task));
|
|
mutex_release(&lock->dep_map, 1, ip);
|
|
spin_unlock_mutex(&lock->wait_lock, flags);
|
|
|
|
debug_mutex_free_waiter(&waiter);
|
|
preempt_enable();
|
|
return -EINTR;
|
|
}
|
|
__set_task_state(task, state);
|
|
|
|
/* didnt get the lock, go to sleep: */
|
|
spin_unlock_mutex(&lock->wait_lock, flags);
|
|
preempt_enable_no_resched();
|
|
schedule();
|
|
preempt_disable();
|
|
spin_lock_mutex(&lock->wait_lock, flags);
|
|
}
|
|
|
|
done:
|
|
lock_acquired(&lock->dep_map, ip);
|
|
/* got the lock - rejoice! */
|
|
mutex_remove_waiter(lock, &waiter, current_thread_info());
|
|
mutex_set_owner(lock);
|
|
|
|
/* set it to 0 if there are no waiters left: */
|
|
if (likely(list_empty(&lock->wait_list)))
|
|
atomic_set(&lock->count, 0);
|
|
|
|
spin_unlock_mutex(&lock->wait_lock, flags);
|
|
|
|
debug_mutex_free_waiter(&waiter);
|
|
preempt_enable();
|
|
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
void __sched
|
|
mutex_lock_nested(struct mutex *lock, unsigned int subclass)
|
|
{
|
|
might_sleep();
|
|
__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, _RET_IP_);
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(mutex_lock_nested);
|
|
|
|
int __sched
|
|
mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
|
|
{
|
|
might_sleep();
|
|
return __mutex_lock_common(lock, TASK_KILLABLE, subclass, _RET_IP_);
|
|
}
|
|
EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
|
|
|
|
int __sched
|
|
mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
|
|
{
|
|
might_sleep();
|
|
return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
|
|
subclass, _RET_IP_);
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
|
|
#endif
|
|
|
|
/*
|
|
* Release the lock, slowpath:
|
|
*/
|
|
static inline void
|
|
__mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
|
|
{
|
|
struct mutex *lock = container_of(lock_count, struct mutex, count);
|
|
unsigned long flags;
|
|
|
|
spin_lock_mutex(&lock->wait_lock, flags);
|
|
mutex_release(&lock->dep_map, nested, _RET_IP_);
|
|
debug_mutex_unlock(lock);
|
|
|
|
/*
|
|
* some architectures leave the lock unlocked in the fastpath failure
|
|
* case, others need to leave it locked. In the later case we have to
|
|
* unlock it here
|
|
*/
|
|
if (__mutex_slowpath_needs_to_unlock())
|
|
atomic_set(&lock->count, 1);
|
|
|
|
if (!list_empty(&lock->wait_list)) {
|
|
/* get the first entry from the wait-list: */
|
|
struct mutex_waiter *waiter =
|
|
list_entry(lock->wait_list.next,
|
|
struct mutex_waiter, list);
|
|
|
|
debug_mutex_wake_waiter(lock, waiter);
|
|
|
|
wake_up_process(waiter->task);
|
|
}
|
|
|
|
spin_unlock_mutex(&lock->wait_lock, flags);
|
|
}
|
|
|
|
/*
|
|
* Release the lock, slowpath:
|
|
*/
|
|
static __used noinline void
|
|
__mutex_unlock_slowpath(atomic_t *lock_count)
|
|
{
|
|
__mutex_unlock_common_slowpath(lock_count, 1);
|
|
}
|
|
|
|
#ifndef CONFIG_DEBUG_LOCK_ALLOC
|
|
/*
|
|
* Here come the less common (and hence less performance-critical) APIs:
|
|
* mutex_lock_interruptible() and mutex_trylock().
|
|
*/
|
|
static noinline int __sched
|
|
__mutex_lock_killable_slowpath(atomic_t *lock_count);
|
|
|
|
static noinline int __sched
|
|
__mutex_lock_interruptible_slowpath(atomic_t *lock_count);
|
|
|
|
/***
|
|
* mutex_lock_interruptible - acquire the mutex, interruptable
|
|
* @lock: the mutex to be acquired
|
|
*
|
|
* Lock the mutex like mutex_lock(), and return 0 if the mutex has
|
|
* been acquired or sleep until the mutex becomes available. If a
|
|
* signal arrives while waiting for the lock then this function
|
|
* returns -EINTR.
|
|
*
|
|
* This function is similar to (but not equivalent to) down_interruptible().
|
|
*/
|
|
int __sched mutex_lock_interruptible(struct mutex *lock)
|
|
{
|
|
int ret;
|
|
|
|
might_sleep();
|
|
ret = __mutex_fastpath_lock_retval
|
|
(&lock->count, __mutex_lock_interruptible_slowpath);
|
|
if (!ret)
|
|
mutex_set_owner(lock);
|
|
|
|
return ret;
|
|
}
|
|
|
|
EXPORT_SYMBOL(mutex_lock_interruptible);
|
|
|
|
int __sched mutex_lock_killable(struct mutex *lock)
|
|
{
|
|
int ret;
|
|
|
|
might_sleep();
|
|
ret = __mutex_fastpath_lock_retval
|
|
(&lock->count, __mutex_lock_killable_slowpath);
|
|
if (!ret)
|
|
mutex_set_owner(lock);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(mutex_lock_killable);
|
|
|
|
static __used noinline void __sched
|
|
__mutex_lock_slowpath(atomic_t *lock_count)
|
|
{
|
|
struct mutex *lock = container_of(lock_count, struct mutex, count);
|
|
|
|
__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, _RET_IP_);
|
|
}
|
|
|
|
static noinline int __sched
|
|
__mutex_lock_killable_slowpath(atomic_t *lock_count)
|
|
{
|
|
struct mutex *lock = container_of(lock_count, struct mutex, count);
|
|
|
|
return __mutex_lock_common(lock, TASK_KILLABLE, 0, _RET_IP_);
|
|
}
|
|
|
|
static noinline int __sched
|
|
__mutex_lock_interruptible_slowpath(atomic_t *lock_count)
|
|
{
|
|
struct mutex *lock = container_of(lock_count, struct mutex, count);
|
|
|
|
return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, _RET_IP_);
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Spinlock based trylock, we take the spinlock and check whether we
|
|
* can get the lock:
|
|
*/
|
|
static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
|
|
{
|
|
struct mutex *lock = container_of(lock_count, struct mutex, count);
|
|
unsigned long flags;
|
|
int prev;
|
|
|
|
spin_lock_mutex(&lock->wait_lock, flags);
|
|
|
|
prev = atomic_xchg(&lock->count, -1);
|
|
if (likely(prev == 1)) {
|
|
mutex_set_owner(lock);
|
|
mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
|
|
}
|
|
|
|
/* Set it back to 0 if there are no waiters: */
|
|
if (likely(list_empty(&lock->wait_list)))
|
|
atomic_set(&lock->count, 0);
|
|
|
|
spin_unlock_mutex(&lock->wait_lock, flags);
|
|
|
|
return prev == 1;
|
|
}
|
|
|
|
/***
|
|
* mutex_trylock - try acquire the mutex, without waiting
|
|
* @lock: the mutex to be acquired
|
|
*
|
|
* Try to acquire the mutex atomically. Returns 1 if the mutex
|
|
* has been acquired successfully, and 0 on contention.
|
|
*
|
|
* NOTE: this function follows the spin_trylock() convention, so
|
|
* it is negated to the down_trylock() return values! Be careful
|
|
* about this when converting semaphore users to mutexes.
|
|
*
|
|
* This function must not be used in interrupt context. The
|
|
* mutex must be released by the same task that acquired it.
|
|
*/
|
|
int __sched mutex_trylock(struct mutex *lock)
|
|
{
|
|
int ret;
|
|
|
|
ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath);
|
|
if (ret)
|
|
mutex_set_owner(lock);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(mutex_trylock);
|
|
|
|
/**
|
|
* atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
|
|
* @cnt: the atomic which we are to dec
|
|
* @lock: the mutex to return holding if we dec to 0
|
|
*
|
|
* return true and hold lock if we dec to 0, return false otherwise
|
|
*/
|
|
int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
|
|
{
|
|
/* dec if we can't possibly hit 0 */
|
|
if (atomic_add_unless(cnt, -1, 1))
|
|
return 0;
|
|
/* we might hit 0, so take the lock */
|
|
mutex_lock(lock);
|
|
if (!atomic_dec_and_test(cnt)) {
|
|
/* when we actually did the dec, we didn't hit 0 */
|
|
mutex_unlock(lock);
|
|
return 0;
|
|
}
|
|
/* we hit 0, and we hold the lock */
|
|
return 1;
|
|
}
|
|
EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
|