linux/kernel/locking/mutex.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * kernel/locking/mutex.c
 *
 * Mutexes: blocking mutual exclusion locks
 *
 * Started by Ingo Molnar:
 *
 *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <[email protected]>
 *
 * 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/locking/mutex-design.rst.
 */
#include <linux/mutex.h>
#include <linux/ww_mutex.h>
#include <linux/sched/signal.h>
#include <linux/sched/rt.h>
#include <linux/sched/wake_q.h>
#include <linux/sched/debug.h>
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/debug_locks.h>
#include <linux/osq_lock.h>

#define CREATE_TRACE_POINTS
#include <trace/events/lock.h>

#ifndef CONFIG_PREEMPT_RT
#include "mutex.h"

#ifdef CONFIG_DEBUG_MUTEXES
#define MUTEX_WARN_ON(cond) …
#else
#define MUTEX_WARN_ON …
#endif

void
__mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
{ … }
EXPORT_SYMBOL(…);

/*
 * @owner: contains: 'struct task_struct *' to the current lock owner,
 * NULL means not owned. Since task_struct pointers are aligned at
 * at least L1_CACHE_BYTES, we have low bits to store extra state.
 *
 * Bit0 indicates a non-empty waiter list; unlock must issue a wakeup.
 * Bit1 indicates unlock needs to hand the lock to the top-waiter
 * Bit2 indicates handoff has been done and we're waiting for pickup.
 */
#define MUTEX_FLAG_WAITERS …
#define MUTEX_FLAG_HANDOFF …
#define MUTEX_FLAG_PICKUP …

#define MUTEX_FLAGS …

/*
 * Internal helper function; C doesn't allow us to hide it :/
 *
 * DO NOT USE (outside of mutex code).
 */
static inline struct task_struct *__mutex_owner(struct mutex *lock)
{ … }

static inline struct task_struct *__owner_task(unsigned long owner)
{ … }

bool mutex_is_locked(struct mutex *lock)
{ … }
EXPORT_SYMBOL(…);

static inline unsigned long __owner_flags(unsigned long owner)
{ … }

/*
 * Returns: __mutex_owner(lock) on failure or NULL on success.
 */
static inline struct task_struct *__mutex_trylock_common(struct mutex *lock, bool handoff)
{ … }

/*
 * Trylock or set HANDOFF
 */
static inline bool __mutex_trylock_or_handoff(struct mutex *lock, bool handoff)
{ … }

/*
 * Actual trylock that will work on any unlocked state.
 */
static inline bool __mutex_trylock(struct mutex *lock)
{ … }

#ifndef CONFIG_DEBUG_LOCK_ALLOC
/*
 * Lockdep annotations are contained to the slow paths for simplicity.
 * There is nothing that would stop spreading the lockdep annotations outwards
 * except more code.
 */

/*
 * Optimistic trylock that only works in the uncontended case. Make sure to
 * follow with a __mutex_trylock() before failing.
 */
static __always_inline bool __mutex_trylock_fast(struct mutex *lock)
{
	unsigned long curr = (unsigned long)current;
	unsigned long zero = 0UL;

	if (atomic_long_try_cmpxchg_acquire(&lock->owner, &zero, curr))
		return true;

	return false;
}

static __always_inline bool __mutex_unlock_fast(struct mutex *lock)
{
	unsigned long curr = (unsigned long)current;

	return atomic_long_try_cmpxchg_release(&lock->owner, &curr, 0UL);
}
#endif

static inline void __mutex_set_flag(struct mutex *lock, unsigned long flag)
{ … }

static inline void __mutex_clear_flag(struct mutex *lock, unsigned long flag)
{ … }

static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_waiter *waiter)
{ … }

/*
 * Add @waiter to a given location in the lock wait_list and set the
 * FLAG_WAITERS flag if it's the first waiter.
 */
static void
__mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
		   struct list_head *list)
{ … }

static void
__mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter)
{ … }

/*
 * Give up ownership to a specific task, when @task = NULL, this is equivalent
 * to a regular unlock. Sets PICKUP on a handoff, clears HANDOFF, preserves
 * WAITERS. Provides RELEASE semantics like a regular unlock, the
 * __mutex_trylock() provides a matching ACQUIRE semantics for the handoff.
 */
static void __mutex_handoff(struct mutex *lock, struct task_struct *task)
{ … }

#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 void __sched __mutex_lock_slowpath(struct mutex *lock);

/**
 * 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 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();

	if (!__mutex_trylock_fast(lock))
		__mutex_lock_slowpath(lock);
}
EXPORT_SYMBOL(mutex_lock);
#endif

#include "ww_mutex.h"

#ifdef CONFIG_MUTEX_SPIN_ON_OWNER

/*
 * Trylock variant that returns the owning task on failure.
 */
static inline struct task_struct *__mutex_trylock_or_owner(struct mutex *lock)
{ … }

static inline
bool ww_mutex_spin_on_owner(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
			    struct mutex_waiter *waiter)
{ … }

/*
 * Look out! "owner" is an entirely speculative pointer access and not
 * reliable.
 *
 * "noinline" so that this function shows up on perf profiles.
 */
static noinline
bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner,
			 struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter)
{ … }

/*
 * Initial check for entering the mutex spinning loop
 */
static inline int mutex_can_spin_on_owner(struct mutex *lock)
{ … }

/*
 * Optimistic spinning.
 *
 * We try to spin for acquisition when we find that the lock owner
 * is currently running on a (different) CPU and while we don't
 * need to reschedule. The rationale is that if the lock owner is
 * running, it is likely to release the lock soon.
 *
 * The mutex spinners are queued up using MCS lock so that only one
 * spinner can compete for the mutex. However, if mutex spinning isn't
 * going to happen, there is no point in going through the lock/unlock
 * overhead.
 *
 * Returns true when the lock was taken, otherwise false, indicating
 * that we need to jump to the slowpath and sleep.
 *
 * The waiter flag is set to true if the spinner is a waiter in the wait
 * queue. The waiter-spinner will spin on the lock directly and concurrently
 * with the spinner at the head of the OSQ, if present, until the owner is
 * changed to itself.
 */
static __always_inline bool
mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
		      struct mutex_waiter *waiter)
{ … }
#else
static __always_inline bool
mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
		      struct mutex_waiter *waiter)
{
	return false;
}
#endif

static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip);

/**
 * 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.
 *
 * The caller must ensure that the mutex stays alive until this function has
 * returned - mutex_unlock() can NOT directly be used to release an object such
 * that another concurrent task can free it.
 * Mutexes are different from spinlocks & refcounts in this aspect.
 *
 * This function is similar to (but not equivalent to) up().
 */
void __sched mutex_unlock(struct mutex *lock)
{ … }
EXPORT_SYMBOL(…);

/**
 * ww_mutex_unlock - release the w/w mutex
 * @lock: the mutex to be released
 *
 * Unlock a mutex that has been locked by this task previously with any of the
 * ww_mutex_lock* functions (with or without an acquire context). It is
 * forbidden to release the locks after releasing the acquire context.
 *
 * This function must not be used in interrupt context. Unlocking
 * of a unlocked mutex is not allowed.
 */
void __sched ww_mutex_unlock(struct ww_mutex *lock)
{ … }
EXPORT_SYMBOL(…);

/*
 * Lock a mutex (possibly interruptible), slowpath:
 */
static __always_inline int __sched
__mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclass,
		    struct lockdep_map *nest_lock, unsigned long ip,
		    struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
{ … }

static int __sched
__mutex_lock(struct mutex *lock, unsigned int state, unsigned int subclass,
	     struct lockdep_map *nest_lock, unsigned long ip)
{ … }

static int __sched
__ww_mutex_lock(struct mutex *lock, unsigned int state, unsigned int subclass,
		unsigned long ip, struct ww_acquire_ctx *ww_ctx)
{ … }

/**
 * ww_mutex_trylock - tries to acquire the w/w mutex with optional acquire context
 * @ww: mutex to lock
 * @ww_ctx: optional w/w acquire context
 *
 * Trylocks a mutex with the optional acquire context; no deadlock detection is
 * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise.
 *
 * Unlike ww_mutex_lock, no deadlock handling is performed. However, if a @ctx is
 * specified, -EALREADY handling may happen in calls to ww_mutex_trylock.
 *
 * A mutex acquired with this function must be released with ww_mutex_unlock.
 */
int ww_mutex_trylock(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
{ … }
EXPORT_SYMBOL(…);

#ifdef CONFIG_DEBUG_LOCK_ALLOC
void __sched
mutex_lock_nested(struct mutex *lock, unsigned int subclass)
{ … }

EXPORT_SYMBOL_GPL(…);

void __sched
_mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
{ … }
EXPORT_SYMBOL_GPL(…);

int __sched
mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
{ … }
EXPORT_SYMBOL_GPL(…);

int __sched
mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
{ … }
EXPORT_SYMBOL_GPL(…);

void __sched
mutex_lock_io_nested(struct mutex *lock, unsigned int subclass)
{ … }
EXPORT_SYMBOL_GPL(…);

static inline int
ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{ … }

int __sched
ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{ … }
EXPORT_SYMBOL_GPL(…);

int __sched
ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{ … }
EXPORT_SYMBOL_GPL(…);

#endif

/*
 * Release the lock, slowpath:
 */
static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip)
{ … }

#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(struct mutex *lock);

static noinline int __sched
__mutex_lock_interruptible_slowpath(struct mutex *lock);

/**
 * mutex_lock_interruptible() - Acquire the mutex, interruptible by signals.
 * @lock: The mutex to be acquired.
 *
 * Lock the mutex like mutex_lock().  If a signal is delivered while the
 * process is sleeping, this function will return without acquiring the
 * mutex.
 *
 * Context: Process context.
 * Return: 0 if the lock was successfully acquired or %-EINTR if a
 * signal arrived.
 */
int __sched mutex_lock_interruptible(struct mutex *lock)
{
	might_sleep();

	if (__mutex_trylock_fast(lock))
		return 0;

	return __mutex_lock_interruptible_slowpath(lock);
}

EXPORT_SYMBOL(mutex_lock_interruptible);

/**
 * mutex_lock_killable() - Acquire the mutex, interruptible by fatal signals.
 * @lock: The mutex to be acquired.
 *
 * Lock the mutex like mutex_lock().  If a signal which will be fatal to
 * the current process is delivered while the process is sleeping, this
 * function will return without acquiring the mutex.
 *
 * Context: Process context.
 * Return: 0 if the lock was successfully acquired or %-EINTR if a
 * fatal signal arrived.
 */
int __sched mutex_lock_killable(struct mutex *lock)
{
	might_sleep();

	if (__mutex_trylock_fast(lock))
		return 0;

	return __mutex_lock_killable_slowpath(lock);
}
EXPORT_SYMBOL(mutex_lock_killable);

/**
 * mutex_lock_io() - Acquire the mutex and mark the process as waiting for I/O
 * @lock: The mutex to be acquired.
 *
 * Lock the mutex like mutex_lock().  While the task is waiting for this
 * mutex, it will be accounted as being in the IO wait state by the
 * scheduler.
 *
 * Context: Process context.
 */
void __sched mutex_lock_io(struct mutex *lock)
{
	int token;

	token = io_schedule_prepare();
	mutex_lock(lock);
	io_schedule_finish(token);
}
EXPORT_SYMBOL_GPL(mutex_lock_io);

static noinline void __sched
__mutex_lock_slowpath(struct mutex *lock)
{
	__mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_);
}

static noinline int __sched
__mutex_lock_killable_slowpath(struct mutex *lock)
{
	return __mutex_lock(lock, TASK_KILLABLE, 0, NULL, _RET_IP_);
}

static noinline int __sched
__mutex_lock_interruptible_slowpath(struct mutex *lock)
{
	return __mutex_lock(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_);
}

static noinline int __sched
__ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
	return __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE, 0,
			       _RET_IP_, ctx);
}

static noinline int __sched
__ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
					    struct ww_acquire_ctx *ctx)
{
	return __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE, 0,
			       _RET_IP_, ctx);
}

#endif

/**
 * mutex_trylock - try to 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 from 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)
{ … }
EXPORT_SYMBOL(…);

#ifndef CONFIG_DEBUG_LOCK_ALLOC
int __sched
ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
	might_sleep();

	if (__mutex_trylock_fast(&lock->base)) {
		if (ctx)
			ww_mutex_set_context_fastpath(lock, ctx);
		return 0;
	}

	return __ww_mutex_lock_slowpath(lock, ctx);
}
EXPORT_SYMBOL(ww_mutex_lock);

int __sched
ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
	might_sleep();

	if (__mutex_trylock_fast(&lock->base)) {
		if (ctx)
			ww_mutex_set_context_fastpath(lock, ctx);
		return 0;
	}

	return __ww_mutex_lock_interruptible_slowpath(lock, ctx);
}
EXPORT_SYMBOL(ww_mutex_lock_interruptible);

#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
#endif /* !CONFIG_PREEMPT_RT */

EXPORT_TRACEPOINT_SYMBOL_GPL(…);
EXPORT_TRACEPOINT_SYMBOL_GPL(…);

/**
 * 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)
{ … }
EXPORT_SYMBOL(…);