linux时钟处理机制(一)

计算机系统中的计时器

在计算机系统中存在着许多硬件计时器，例如 Real Timer Clock （ RTC ）、Time Stamp Counter （ TSC ） 和 Programmable Interval Timer （ PIT ） 等等。

• Real Timer Clock （ RTC ）：
  • 独立于整个计算机系统（例如： CPU 和其他 chip ）
  • 内核利用其获取系统当前时间和日期
• Time Stamp Counter （ TSC ）：
  • 从 Pentium 起，提供一个寄存器 TSC，用来累计每一次外部振荡器产生的时钟信号
  • 通过指令 rdtsc 访问这个寄存器
  • 比起 PIT，TSC 可以提供更精确的时间测量
• Programmable Interval Timer （ PIT ）：
  • 时间测量设备
  • 内核使用的产生时钟中断的设备，产生的时钟中断依赖于硬件的体系结构，慢的为 10 ms 一次，快的为 1 ms 一次
• High Precision Event Timer （ HPET ）：
  • PIT 和 RTC 的替代者，和之前的计时器相比，HPET 提供了更高的时钟频率（至少10 MHz ）以及更宽的计数器宽度（64位）
  • 一个 HPET 包括了一个固定频率的数值增加的计数器以及3到32个独立的计时器，这每一个计时器有包涵了一个比较器和一个寄存器（保存一个数值，表示触发中断的时机）。每一个比较器都比较计数器中的数值和寄存器中的数值，当这两个数值相等时，将产生一个中断

数据结构

和硬件计时器（本文又称作硬件时钟，区别于软件时钟）相关的数据结构主要有两个：

• struct clocksource ：对硬件设备的抽象，描述时钟源信息

• /**
   * struct cyclecounter - hardware abstraction for a free running counter
   *	Provides completely state-free accessors to the underlying hardware.
   *	Depending on which hardware it reads, the cycle counter may wrap
   *	around quickly. Locking rules (if necessary) have to be defined
   *	by the implementor and user of specific instances of this API.
   *
   * @read:		returns the current cycle value
   * @mask:		bitmask for two's complement
   *			subtraction of non 64 bit counters,
   *			see CLOCKSOURCE_MASK() helper macro
   * @mult:		cycle to nanosecond multiplier
   * @shift:		cycle to nanosecond divisor (power of two)
   */
  struct cyclecounter {
  	cycle_t (*read)(const struct cyclecounter *cc);
  	cycle_t mask;
  	u32 mult;
  	u32 shift;
  };
  
  /**
   * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds
   *	Contains the state needed by timecounter_read() to detect
   *	cycle counter wrap around. Initialize with
   *	timecounter_init(). Also used to convert cycle counts into the
   *	corresponding nanosecond counts with timecounter_cyc2time(). Users
   *	of this code are responsible for initializing the underlying
   *	cycle counter hardware, locking issues and reading the time
   *	more often than the cycle counter wraps around. The nanosecond
   *	counter will only wrap around after ~585 years.
   *
   * @cc:			the cycle counter used by this instance
   * @cycle_last:		most recent cycle counter value seen by
   *			timecounter_read()
   * @nsec:		continuously increasing count
   */
  struct timecounter {
  	const struct cyclecounter *cc;
  	cycle_t cycle_last;
  	u64 nsec;
  };
  
  /**
   * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds
   * @cc:		Pointer to cycle counter.
   * @cycles:	Cycles
   *
   * XXX - This could use some mult_lxl_ll() asm optimization. Same code
   * as in cyc2ns, but with unsigned result.
   */
  static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc,
  				      cycle_t cycles)
  {
  	u64 ret = (u64)cycles;
  	ret = (ret * cc->mult) >> cc->shift;
  	return ret;
  }
  
  /**
   * timecounter_init - initialize a time counter
   * @tc:			Pointer to time counter which is to be initialized/reset
   * @cc:			A cycle counter, ready to be used.
   * @start_tstamp:	Arbitrary initial time stamp.
   *
   * After this call the current cycle register (roughly) corresponds to
   * the initial time stamp. Every call to timecounter_read() increments
   * the time stamp counter by the number of elapsed nanoseconds.
   */
  extern void timecounter_init(struct timecounter *tc,
  			     const struct cyclecounter *cc,
  			     u64 start_tstamp);
  
  /**
   * timecounter_read - return nanoseconds elapsed since timecounter_init()
   *                    plus the initial time stamp
   * @tc:          Pointer to time counter.
   *
   * In other words, keeps track of time since the same epoch as
   * the function which generated the initial time stamp.
   */
  extern u64 timecounter_read(struct timecounter *tc);
  
  /**
   * timecounter_cyc2time - convert a cycle counter to same
   *                        time base as values returned by
   *                        timecounter_read()
   * @tc:		Pointer to time counter.
   * @cycle_tstamp:	a value returned by tc->cc->read()
   *
   * Cycle counts that are converted correctly as long as they
   * fall into the interval [-1/2 max cycle count, +1/2 max cycle count],
   * with "max cycle count" == cs->mask+1.
   *
   * This allows conversion of cycle counter values which were generated
   * in the past.
   */
  extern u64 timecounter_cyc2time(struct timecounter *tc,
  				cycle_t cycle_tstamp);
  
  /**
   * struct clocksource - hardware abstraction for a free running counter
   *	Provides mostly state-free accessors to the underlying hardware.
   *	This is the structure used for system time.
   *
   * @name:		ptr to clocksource name
   * @list:		list head for registration
   * @rating:		rating value for selection (higher is better)
   *			To avoid rating inflation the following
   *			list should give you a guide as to how
   *			to assign your clocksource a rating
   *			1-99: Unfit for real use
   *				Only available for bootup and testing purposes.
   *			100-199: Base level usability.
   *				Functional for real use, but not desired.
   *			200-299: Good.
   *				A correct and usable clocksource.
   *			300-399: Desired.
   *				A reasonably fast and accurate clocksource.
   *			400-499: Perfect
   *				The ideal clocksource. A must-use where
   *				available.
   * @read:		returns a cycle value, passes clocksource as argument
   * @enable:		optional function to enable the clocksource
   * @disable:		optional function to disable the clocksource
   * @mask:		bitmask for two's complement
   *			subtraction of non 64 bit counters
   * @mult:		cycle to nanosecond multiplier
   * @shift:		cycle to nanosecond divisor (power of two)
   * @max_idle_ns:	max idle time permitted by the clocksource (nsecs)
   * @maxadj:		maximum adjustment value to mult (~11%)
   * @flags:		flags describing special properties
   * @archdata:		arch-specific data
   * @suspend:		suspend function for the clocksource, if necessary
   * @resume:		resume function for the clocksource, if necessary
   * @cycle_last:		most recent cycle counter value seen by ::read()
   */
  struct clocksource {
  	/*
  	 * Hotpath data, fits in a single cache line when the
  	 * clocksource itself is cacheline aligned.
  	 */
  	cycle_t (*read)(struct clocksource *cs);
  	cycle_t cycle_last;
  	cycle_t mask;
  	u32 mult;
  	u32 shift;
  	u64 max_idle_ns;
  	u32 maxadj;
  #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
  	struct arch_clocksource_data archdata;
  #endif
  
  	const char *name;
  	struct list_head list;
  	int rating;
  	int (*enable)(struct clocksource *cs);
  	void (*disable)(struct clocksource *cs);
  	unsigned long flags;
  	void (*suspend)(struct clocksource *cs);
  	void (*resume)(struct clocksource *cs);
  
  	/* private: */
  #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
  	/* Watchdog related data, used by the framework */
  	struct list_head wd_list;
  	cycle_t cs_last;
  	cycle_t wd_last;
  #endif
  } ____cacheline_aligned;
  

  
  
  
• struct clock_event_device ：时钟的事件信息，包括当硬件时钟中断发生时要执行那些操作（实际上保存了相应函数的指针）。本文将该结构称作为“时钟事件设备”。

• /**
   * struct clock_event_device - clock event device descriptor
   * @event_handler:	Assigned by the framework to be called by the low
   *			level handler of the event source
   * @set_next_event:	set next event function using a clocksource delta
   * @set_next_ktime:	set next event function using a direct ktime value
   * @next_event:		local storage for the next event in oneshot mode
   * @max_delta_ns:	maximum delta value in ns
   * @min_delta_ns:	minimum delta value in ns
   * @mult:		nanosecond to cycles multiplier
   * @shift:		nanoseconds to cycles divisor (power of two)
   * @mode:		operating mode assigned by the management code
   * @features:		features
   * @retries:		number of forced programming retries
   * @set_mode:		set mode function
   * @broadcast:		function to broadcast events
   * @min_delta_ticks:	minimum delta value in ticks stored for reconfiguration
   * @max_delta_ticks:	maximum delta value in ticks stored for reconfiguration
   * @name:		ptr to clock event name
   * @rating:		variable to rate clock event devices
   * @irq:		IRQ number (only for non CPU local devices)
   * @cpumask:		cpumask to indicate for which CPUs this device works
   * @list:		list head for the management code
   */
  struct clock_event_device {
  	void			(*event_handler)(struct clock_event_device *);
  	int			(*set_next_event)(unsigned long evt,
  						  struct clock_event_device *);
  	int			(*set_next_ktime)(ktime_t expires,
  						  struct clock_event_device *);
  	ktime_t			next_event;
  	u64			max_delta_ns;
  	u64			min_delta_ns;
  	u32			mult;
  	u32			shift;
  	enum clock_event_mode	mode;
  	unsigned int		features;
  	unsigned long		retries;
  
  	void			(*broadcast)(const struct cpumask *mask);
  	void			(*set_mode)(enum clock_event_mode mode,
  					    struct clock_event_device *);
  	unsigned long		min_delta_ticks;
  	unsigned long		max_delta_ticks;
  
  	const char		*name;
  	int			rating;
  	int			irq;
  	const struct cpumask	*cpumask;
  	struct list_head	list;
  } ____cacheline_aligned;
  

  
  需要特别注意的是结构 clock_event_device 的成员 event_handler ，它指定了当硬件时钟中断发生时，内核应该执行那些操作，也就是真正的时钟中断处理函数。 在

Linux 内核维护了两个链表，分别存储了系统中所有时钟源的信息和时钟事件设备的信息。这两个链表的表头在内核中分别是 clocksource_list 和 clockevent_devices 。