Linux内核同步笔记

#define preempt_disable() \
do { \
	preempt_count_inc(); \
	barrier(); \
} while (0)

#define preempt_enable() \
do { \
	barrier(); \
	if (unlikely(preempt_count_dec_and_test())) \
		__preempt_schedule(); \
} while (0)

// 继续分析
#define preempt_count_dec_and_test() \
	({ preempt_count_sub(1); should_resched(0); })

static __always_inline bool should_resched(int preempt_offset)
{
	return unlikely(raw_cpu_read_4(pcpu_hot.preempt_count) == preempt_offset);
}

static __always_inline int preempt_count(void)
{
	return raw_cpu_read_4(pcpu_hot.preempt_count) & ~PREEMPT_NEED_RESCHED;
}

static __always_inline void __preempt_count_add(int val)
{
	raw_cpu_add_4(pcpu_hot.preempt_count, val);
}

static __always_inline void __preempt_count_sub(int val)
{
	raw_cpu_add_4(pcpu_hot.preempt_count, -val);
}

#include <linux/preempt.h>

void example_function(void) {
    preempt_disable();  // 禁用抢占

    // 临界区代码：不会被其他任务抢占
    access_shared_data();

    preempt_enable();   // 启用抢占，可能触发调度
}

typedef struct {
	int counter;
} atomic_t;

typedef struct {
	long long counter;
} atomic64_t;

static inline void set_bit(int nr, volatile unsigned long *addr)
{
	unsigned long mask = BIT_MASK(nr);
	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
	unsigned long flags;

	_atomic_spin_lock_irqsave(p, flags);
	*p  |= mask;
	_atomic_spin_unlock_irqrestore(p, flags);
}

static inline void clear_bit(int nr, volatile unsigned long *addr)
{
	unsigned long mask = BIT_MASK(nr);
	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
	unsigned long flags;

	_atomic_spin_lock_irqsave(p, flags);
	*p &= ~mask;
	_atomic_spin_unlock_irqrestore(p, flags);
}

#define atomic_read(v)	ACCESS_ONCE((v)->counter)
#define atomic_set(v,i)	(((v)->counter) = (i))

#define __ACCESS_ONCE(x) ({ \
	 __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \
	(volatile typeof(x) *)&(x); })
#define ACCESS_ONCE(x) (*__ACCESS_ONCE(x))

typedef struct raw_spinlock {
	arch_spinlock_t raw_lock;
#ifdef CONFIG_GENERIC_LOCKBREAK
	unsigned int break_lock;
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
	unsigned int magic, owner_cpu;
	void *owner;
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map dep_map;
#endif
} raw_spinlock_t;

typedef struct {
	union {
		u32 slock;
		struct __raw_tickets {
#ifdef __ARMEB__
			u16 next;
			u16 owner;
#else
			u16 owner;
			u16 next;
#endif
		} tickets;
	};
} arch_spinlock_t;

static inline void spin_lock(spinlock_t *lock)
{
	raw_spin_lock(&lock->rlock);
}

#define raw_spin_lock(lock)	_raw_spin_lock(lock)

static inline void __raw_spin_lock(raw_spinlock_t *lock)
{
	preempt_disable(); // 核心实现
	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); // lockdep检测
	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
}

static __always_inline void spin_lock_irq(spinlock_t *lock)
{
	raw_spin_lock_irq(&lock->rlock);
}

static inline void spin_lock_bh(spinlock_t *lock)
{
	raw_spin_lock_bh(&lock->rlock);
}

static inline void __raw_spin_lock_bh(raw_spinlock_t *lock)
{
	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
}

static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
	preempt_count_add(cnt);
	barrier();
}

static __always_inline void __preempt_count_add(int val)
{
	raw_cpu_add_4(pcpu_hot.preempt_count, val);
}

static inline int spin_trylock(spinlock_t *lock)
{
	return raw_spin_trylock(&lock->rlock);
}

static inline void spin_unlock(spinlock_t *lock)
{
	raw_spin_unlock(&lock->rlock);
}

static inline void spin_unlock_bh(spinlock_t *lock)
{
	raw_spin_unlock_bh(&lock->rlock);
}

static inline void spin_unlock_irq(spinlock_t *lock)
{
	raw_spin_unlock_irq(&lock->rlock);
}

typedef struct qspinlock {
	union {
		atomic_t val;

		/*
		 * By using the whole 2nd least significant byte for the
		 * pending bit, we can allow better optimization of the lock
		 * acquisition for the pending bit holder.
		 */
#ifdef __LITTLE_ENDIAN
		struct {
			u8	locked;
			u8	pending;
		};
		struct {
			u16	locked_pending;
			u16	tail;
		};
#else
		struct {
			u16	tail;
			u16	locked_pending;
		};
		struct {
			u8	reserved[2];
			u8	pending;
			u8	locked;
		};
#endif
	};
} arch_spinlock_t;

static __always_inline void queued_spin_lock(struct qspinlock *lock)
{
	int val = 0;

	if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)))
		return;

	queued_spin_lock_slowpath(lock, val);
}

void queued_spin_lock_slowpath(struct qspinlock *lock)
{
	/*
	 * This looks funny, but it induces the compiler to inline both
	 * sides of the branch rather than share code as when the condition
	 * is passed as the paravirt argument to the functions.
	 */
	if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && is_shared_processor()) {
		if (try_to_steal_lock(lock, true)) {
			spec_barrier();
			return;
		}
		queued_spin_lock_mcs_queue(lock, true);
	} else {
		if (try_to_steal_lock(lock, false)) {
			spec_barrier();
			return;
		}
		queued_spin_lock_mcs_queue(lock, false);
	}
}

static __always_inline void queued_spin_unlock(struct qspinlock *lock)
{
	/*
	 * unlock() needs release semantics:
	 */
	smp_store_release(&lock->locked, 0);
}

// 直接进行smp释放
#define smp_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0)

// 对locked直接释放
do {									\
	compiletime_assert_atomic_type(*p);				\
	__smp_mb();							\
	WRITE_ONCE(*p, v);						\
} while (0)

struct mutex {
	/* 1: unlocked, 0: locked, negative: locked, possible waiters */
	atomic_t		count;
	spinlock_t		wait_lock;
	struct list_head	wait_list;
#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
	struct task_struct	*owner;
#endif
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
	struct optimistic_spin_queue osq; /* Spinner MCS lock */
#endif
#ifdef CONFIG_DEBUG_MUTEXES
	void			*magic;
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map	dep_map;
#endif
};

/**
 * mutex_is_locked - is the mutex locked
 * @lock: the mutex to be queried
 *
 * Returns 1 if the mutex is locked, 0 if unlocked.
 */
static inline int mutex_is_locked(struct mutex *lock)
{
	return atomic_read(&lock->count) != 1;
}

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);
}

/* 直接设置owner */
static inline void mutex_set_owner(struct mutex *lock)
{
	lock->owner = current;
}

static inline void
__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
{
	if (unlikely(atomic_xchg(count, 0) != 1))
		if (likely(atomic_xchg(count, -1) != 1))
			fail_fn(count)
}

__visible 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,
			    NULL, _RET_IP_, NULL, 0);
}

void __sched mutex_unlock(struct mutex *lock)
{
#ifndef CONFIG_DEBUG_MUTEXES
	mutex_clear_owner(lock);
#endif
	__mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath);
}

static inline void
__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
{
	if (unlikely(atomic_xchg(count, 1) != 0))
		fail_fn(count);
}

struct semaphore {
	raw_spinlock_t		lock;
	unsigned int		count;
	struct list_head	wait_list;
};

#define __SEMAPHORE_INITIALIZER(name, n)				\
{									\
	.lock		= __RAW_SPIN_LOCK_UNLOCKED((name).lock),	\
	.count		= n,						\
	.wait_list	= LIST_HEAD_INIT((name).wait_list),		\
}

void down(struct semaphore *sem)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->lock, flags);
	if (likely(sem->count > 0))
		sem->count--;
	else
		__down(sem);
	raw_spin_unlock_irqrestore(&sem->lock, flags);
}

void up(struct semaphore *sem)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&sem->lock, flags);
	if (likely(list_empty(&sem->wait_list)))
		sem->count++;
	else
		__up(sem);
	raw_spin_unlock_irqrestore(&sem->lock, flags);
}

static noinline void __sched __up(struct semaphore *sem)
{
	struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
						struct semaphore_waiter, list);
	list_del(&waiter->list);
	waiter->up = true;
	wake_up_process(waiter->task);
}

// include/linux/rwlock_types.h
typedef struct {
    arch_rwlock_t raw_lock;  // 架构相关的底层锁表示
} rwlock_t;

// include/linux/rwsem.h
struct rw_semaphore {
    atomic_long_t count;      // 组合计数器：高32位为等待计数，低32位为活跃读者/写者标志
    struct list_head wait_list;  // 等待队列（读者或写者）
    // 其他调试和优化字段...
};