聊聊内核中IO子系统-上篇

	// 驱动层的IO请求
struct request {
	// 指向包含请求的请求队列的指针
	struct request_queue *q;
	struct blk_mq_ctx *mq_ctx;

	int cpu;
	// 请求标志
	unsigned int cmd_flags;		/* op and common flags */
	req_flags_t rq_flags;

	int internal_tag;

	// 请求的数据长度
	unsigned int __data_len;	/* total data len */
	int tag;
	// 请求的起始扇区的编号
	sector_t __sector;		
	// 没完成传输的第一个bio
	struct bio *bio;
	// 租后一个bio
	struct bio *biotail;
	// request请求放入的I/O调度队列
	struct list_head queuelist;
	union {
		// 链入电梯算法哈希表，按照最后一个扇区的编号进行哈希，方便查找和合并对象
		struct hlist_node hash;	/* merge hash */
		struct list_head ipi_list;
	};

	union {
		struct rb_node rb_node;	/* sort/lookup */
		struct bio_vec special_vec;
		void *completion_data;
		int error_count; /* for legacy drivers, don't use */
	};
	union {
		struct {
			struct io_cq		*icq;
			void			*priv[2];
		} elv;

		struct {
			unsigned int		seq;
			struct list_head	list;
			rq_end_io_fn		*saved_end_io;
		} flush;
	};
	// IO请求所对应的磁盘结构指针
	struct gendisk *rq_disk;
	// IO请求所在的磁盘对应的分区
	struct hd_struct *part;

	// IO提交到内核的时间
	u64 start_time_ns;

	// IO提交到驱动层的时间
	u64 io_start_time_ns;

#ifdef CONFIG_BLK_WBT
	unsigned short wbt_flags;
#endif
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
	unsigned short throtl_size;
#endif

	/*
	 * Number of scatter-gather DMA addr+len pairs after
	 * physical address coalescing is performed.
	 */
	unsigned short nr_phys_segments;

#if defined(CONFIG_BLK_DEV_INTEGRITY)
	unsigned short nr_integrity_segments;
#endif

	unsigned short write_hint;
	unsigned short ioprio;

	void *special;		
	// 额外的树长度
	unsigned int extra_len;	/* length of alignment and padding */

	enum mq_rq_state state;
	refcount_t ref;

	// 请求的超时时间
	unsigned int timeout;

	/* access through blk_rq_set_deadline, blk_rq_deadline */
	unsigned long __deadline;

	struct list_head timeout_list;

	union {
		struct __call_single_data csd;
		u64 fifo_time;
	};

	// 请求完成的回调函数
	rq_end_io_fn *end_io;
	// 完成回调函数的参数
	void *end_io_data;

	// next_rq关联两个request实现SCSI双向指令
	struct request *next_rq;

#ifdef CONFIG_BLK_CGROUP
	struct request_list *rl;		/* rl this rq is alloced from */
#endif
};


// 来自用户态的IO请求在内核的表现形式bio
struct bio {
	// 指向属于同一个request的后一个bio
	struct bio		*bi_next;	
	// bio请求的磁盘
	struct gendisk		*bi_disk;
	unsigned int		bi_opf;		
	// bio的状态
	unsigned short		bi_flags;	/* status, etc and bvec pool number */
	unsigned short		bi_ioprio;
	unsigned short		bi_write_hint;
	blk_status_t		bi_status;
	// 磁盘对应的那个分区标识
	u8			bi_partno;

	// bio中的Segment的个数
	unsigned int		bi_phys_segments;

	// 缓存bio的第一个segment的长度，根据这个最大段长度快速判断是否能合并
	unsigned int		bi_seg_front_size;
	// 缓存bio的最后一个segment的长度
	unsigned int		bi_seg_back_size;

	struct bvec_iter	bi_iter;

	atomic_t		__bi_remaining;
	// bio的IO操作完成后回调函数
	bio_end_io_t		*bi_end_io;
	// 私有数据指针，在通用块设备层和驱动IO结束使用
	void			*bi_private;
#ifdef CONFIG_BLK_CGROUP
	/*
	 * Optional ioc and css associated with this bio.  Put on bio
	 * release.  Read comment on top of bio_associate_current().
	 */
	struct io_context	*bi_ioc;
	struct cgroup_subsys_state *bi_css;
	struct blkcg_gq		*bi_blkg;
	struct bio_issue	bi_issue;
#endif
	union {
#if defined(CONFIG_BLK_DEV_INTEGRITY)
		struct bio_integrity_payload *bi_integrity; /* data integrity */
#endif
	};
	// bio的bio_vec数组中包含segmnet的个数
	unsigned short		bi_vcnt;	/* how many bio_vec's */


	unsigned short		bi_max_vecs;	/* max bvl_vecs we can hold */

	atomic_t		__bi_cnt;	/* pin count */
	// 存储bio的数组
	struct bio_vec		*bi_io_vec;	

	struct bio_set		*bi_pool;
	// 内嵌的bio数组
	struct bio_vec		bi_inline_vecs[0];
};