arm64 kernel5.0
一、数据结构
一)generic block layer
gendisk
struct gendisk {
/* major, first_minor and minors are input parameters only,
* don't use directly. Use disk_devt() and disk_max_parts().
*/
int major; /* major number of driver */
int first_minor;
int minors; /* maximum number of minors, =1 for
* disks that can't be partitioned. */
char disk_name[DISK_NAME_LEN]; /* name of major driver :sdx、dm-x*/
char *(*devnode)(struct gendisk *gd, umode_t *mode);
unsigned int events; /* supported events */
unsigned int async_events; /* async events, subset of all */
struct disk_part_tbl __rcu *part_tbl; /*磁盘分区表描述符*/
struct hd_struct part0;/* 将整个磁盘作为一个分区,编号为0 */
const struct block_device_operations *fops;
struct request_queue *queue;
void *private_data;
int flags;
struct rw_semaphore lookup_sem;
struct kobject *slave_dir;
struct timer_rand_state *random;
atomic_t sync_io; /* RAID */
struct disk_events *ev;
#ifdef CONFIG_BLK_DEV_INTEGRITY
struct kobject integrity_kobj;
#endif /* CONFIG_BLK_DEV_INTEGRITY */
int node_id;
struct badblocks *bb;
struct lockdep_map lockdep_map;
};
hd_struct
struct hd_struct {
sector_t start_sect;
/*
* nr_sects is protected by sequence counter. One might extend a
* partition while IO is happening to it and update of nr_sects
* can be non-atomic on 32bit machines with 64bit sector_t.
*/
sector_t nr_sects;
seqcount_t nr_sects_seq;
sector_t alignment_offset;
unsigned int discard_alignment;
struct device __dev;
struct kobject *holder_dir;
int policy, partno;//分区只读,policy为0,否则为1
struct partition_meta_info *info;
#ifdef CONFIG_FAIL_MAKE_REQUEST
int make_it_fail;
#endif
unsigned long stamp; //用于修正分区统计信息的时间戳
#ifdef CONFIG_SMP
struct disk_stats __percpu *dkstats;//磁盘统计信息
#else
struct disk_stats dkstats;
#endif
struct percpu_ref ref;
struct rcu_work rcu_work;
};
block_device
表示内核中的一个块设备,可以表示整个磁盘或一个分区(通过bd_contains域来区分)
struct block_device {
dev_t bd_dev; /* not a kdev_t - it's a search key */
int bd_openers;
struct inode * bd_inode; /* will die */
struct super_block * bd_super;
struct mutex bd_mutex; /* open/close mutex */
void * bd_claiming;
void * bd_holder;
int bd_holders;
bool bd_write_holder;
#ifdef CONFIG_SYSFS
struct list_head bd_holder_disks;
#endif
struct block_device * bd_contains; //块设备表示一个分区,则指向整个磁盘的块设备描述符,否则指向自身
unsigned bd_block_size; //逻辑块长度
u8 bd_partno;
struct hd_struct * bd_part;
/* number of times partitions within this device have been opened. */
unsigned bd_part_count;
int bd_invalidated; //置位需要重新读入分区表
struct gendisk * bd_disk;
struct request_queue * bd_queue;
struct backing_dev_info *bd_bdi;
struct list_head bd_list; //连接到所有块设备链(all_bdevs)
/*
* Private data. You must have bd_claim'ed the block_device
* to use this. NOTE: bd_claim allows an owner to claim
* the same device multiple times, the owner must take special
* care to not mess up bd_private for that case.
*/
unsigned long bd_private;
/* The counter of freeze processes */
int bd_fsfreeze_count;
/* Mutex for freeze */
struct mutex bd_fsfreeze_mutex;
} __randomize_layout;
backing_dev_info
让每个设备或文件系统有一个专门的处理线程,每个请求队列内嵌一个bdi,提供专属的请求处理机制,如派生专门为其服务的flusher线程。
每个bdi可以管理至少一个回写线程,用bdi_writeback描述符表示,每个bdi_writeback对应一个处理线程,当前只有两种:forker和flusher
struct backing_dev_info {
struct list_head bdi_list;
unsigned long ra_pages; /* max readahead in PAGE_SIZE units */
unsigned long io_pages; /* max allowed IO size */
congested_fn *congested_fn; /* Function pointer if device is md/dm */
void *congested_data; /* Pointer to aux data for congested func */
const char *name;
struct kref refcnt; /* Reference counter for the structure */
unsigned int capabilities; /* Device capabilities */
unsigned int min_ratio;
unsigned int max_ratio, max_prop_frac;
/*
* Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are
* any dirty wbs, which is depended upon by bdi_has_dirty().
*/
atomic_long_t tot_write_bandwidth;
struct bdi_writeback wb; /* the root writeback info for this bdi */
struct list_head wb_list; /* list of all wbs */
#ifdef CONFIG_CGROUP_WRITEBACK
struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
struct rb_root cgwb_congested_tree; /* their congested states */
struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */
struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */
#else
struct bdi_writeback_congested *wb_congested;
#endif
wait_queue_head_t wb_waitq;
struct device *dev;
struct device *owner;
struct timer_list laptop_mode_wb_timer;
#ifdef CONFIG_DEBUG_FS
struct dentry *debug_dir;
struct dentry *debug_stats;
#endif
};
request_queue
struct request_queue {
/*
* Together with queue_head for cacheline sharing
*/
struct list_head queue_head; //需要向块设备提交的待处理请求链表
struct request *last_merge; //上次合并了bio的请求,新bio到来时首先尝试合并到这个请求
struct elevator_queue *elevator;
struct blk_queue_stats *stats;
struct rq_qos *rq_qos;
make_request_fn *make_request_fn;
dma_drain_needed_fn *dma_drain_needed;
const struct blk_mq_ops *mq_ops;
/* sw queues */
struct blk_mq_ctx __percpu *queue_ctx;
unsigned int nr_queues;
unsigned int queue_depth;
/* hw dispatch queues */
struct blk_mq_hw_ctx **queue_hw_ctx;
unsigned int nr_hw_queues;
struct backing_dev_info *backing_dev_info;
/*
* The queue owner gets to use this for whatever they like.
* ll_rw_blk doesn't touch it.
*/
void *queuedata;
/*
* various queue flags, see QUEUE_* below
*/
unsigned long queue_flags;
/*
* Number of contexts that have called blk_set_pm_only(). If this
* counter is above zero then only RQF_PM and RQF_PREEMPT requests are
* processed.
*/
atomic_t pm_only;
/*
* ida allocated id for this queue. Used to index queues from
* ioctx.
*/
int id;
/*
* queue needs bounce pages for pages above this limit
*/
gfp_t bounce_gfp;
spinlock_t queue_lock;
/*
* queue kobject
*/
struct kobject kobj;
/*
* mq queue kobject
*/
struct kobject *mq_kobj;
#ifdef CONFIG_BLK_DEV_INTEGRITY
struct blk_integrity integrity;
#endif /* CONFIG_BLK_DEV_INTEGRITY */
#ifdef CONFIG_PM
struct device *dev;
int rpm_status;
unsigned int nr_pending;
#endif
/*
* queue settings
*/
unsigned long nr_requests; /* Max # of requests */
unsigned int dma_drain_size;
void *dma_drain_buffer;
unsigned int dma_pad_mask;
unsigned int dma_alignment;
unsigned int rq_timeout;
int poll_nsec;
struct blk_stat_callback *poll_cb;
struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS];
struct timer_list timeout;
struct work_struct timeout_work;
struct list_head icq_list;
#ifdef CONFIG_BLK_CGROUP
DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS);
struct blkcg_gq *root_blkg;
struct list_head blkg_list;
#endif
struct queue_limits limits;
#ifdef CONFIG_BLK_DEV_ZONED
/*
* Zoned block device information for request dispatch control.
* nr_zones is the total number of zones of the device. This is always
* 0 for regular block devices. seq_zones_bitmap is a bitmap of nr_zones
* bits which indicates if a zone is conventional (bit clear) or
* sequential (bit set). seq_zones_wlock is a bitmap of nr_zones
* bits which indicates if a zone is write locked, that is, if a write
* request targeting the zone was dispatched. All three fields are
* initialized by the low level device driver (e.g. scsi/sd.c).
* Stacking drivers (device mappers) may or may not initialize
* these fields.
*
* Reads of this information must be protected with blk_queue_enter() /
* blk_queue_exit(). Modifying this information is only allowed while
* no requests are being processed. See also blk_mq_freeze_queue() and
* blk_mq_unfreeze_queue().
*/
unsigned int nr_zones;
unsigned long *seq_zones_bitmap;
unsigned long *seq_zones_wlock;
#endif /* CONFIG_BLK_DEV_ZONED */
/*
* sg stuff
*/
unsigned int sg_timeout;
unsigned int sg_reserved_size;
int node;
#ifdef CONFIG_BLK_DEV_IO_TRACE
struct blk_trace *blk_trace;
struct mutex blk_trace_mutex;
#endif
/*
* for flush operations
*/
struct blk_flush_queue *fq;
struct list_head requeue_list;
spinlock_t requeue_lock;
struct delayed_work requeue_work;
struct mutex sysfs_lock;
atomic_t mq_freeze_depth;
#if defined(CONFIG_BLK_DEV_BSG)
struct bsg_class_device bsg_dev;
#endif
#ifdef CONFIG_BLK_DEV_THROTTLING
/* Throttle data */
struct throtl_data *td;
#endif
struct rcu_head rcu_head;
wait_queue_head_t mq_freeze_wq;
struct percpu_ref q_usage_counter;
struct list_head all_q_node;
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
struct bio_set bio_split;
#ifdef CONFIG_BLK_DEBUG_FS
struct dentry *debugfs_dir;
struct dentry *sched_debugfs_dir;
struct dentry *rqos_debugfs_dir;
#endif
bool mq_sysfs_init_done;
size_t cmd_size;
struct work_struct release_work;
#define BLK_MAX_WRITE_HINTS 5
u64 write_hints[BLK_MAX_WRITE_HINTS];
};
request
/*
* Try to put the fields that are referenced together in the same cacheline.
*
* If you modify this structure, make sure to update blk_rq_init() and
* especially blk_mq_rq_ctx_init() to take care of the added fields.
*/
struct request {
struct request_queue *q;
struct blk_mq_ctx *mq_ctx;
struct blk_mq_hw_ctx *mq_hctx;
unsigned int cmd_flags; /* op and common flags */
req_flags_t rq_flags;
int internal_tag;
/* the following two fields are internal, NEVER access directly */
unsigned int __data_len; /* total data len */
int tag;
sector_t __sector; /* sector cursor */
struct bio *bio;
struct bio *biotail;
struct list_head queuelist;
/*
* The hash is used inside the scheduler, and killed once the
* request reaches the dispatch list. The ipi_list is only used
* to queue the request for softirq completion, which is long
* after the request has been unhashed (and even removed from
* the dispatch list).
*/
union {
struct hlist_node hash; /* merge hash */
struct list_head ipi_list;
};
/*
* The rb_node is only used inside the io scheduler, requests
* are pruned when moved to the dispatch queue. So let the
* completion_data share space with the rb_node.
*/
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 */
};
/*
* Three pointers are available for the IO schedulers, if they need
* more they have to dynamically allocate it. Flush requests are
* never put on the IO scheduler. So let the flush fields share
* space with the elevator data.
*/
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;
};
struct gendisk *rq_disk;
struct hd_struct *part;
/* Time that I/O was submitted to the kernel. */
u64 start_time_ns;
/* Time that I/O was submitted to the device. */
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; /* opaque pointer available for LLD use */
unsigned int extra_len; /* length of alignment and padding */
enum mq_rq_state state;
refcount_t ref;
unsigned int timeout;
unsigned long deadline;
union {
struct __call_single_data csd;
u64 fifo_time;
};
/*
* completion callback.
*/
rq_end_io_fn *end_io;=
void *end_io_data;
/* for bidi */
struct request *next_rq;
};
bio
/*
* main unit of I/O for the block layer and lower layers (ie drivers and
* stacking drivers)
*/
struct bio {
struct bio *bi_next; /* request queue link */
struct gendisk *bi_disk;
unsigned int bi_opf; /* bottom bits req flags,
* top bits REQ_OP. Use
* accessors.
*/
unsigned short bi_flags; /* status, etc and bvec pool number */
unsigned short bi_ioprio;
unsigned short bi_write_hint;
blk_status_t bi_status;
u8 bi_partno;
/* Number of segments in this BIO after
* physical address coalescing is performed.
*/
unsigned int bi_phys_segments;
/*
* To keep track of the max segment size, we account for the
* sizes of the first and last mergeable segments in this bio.
*/
unsigned int bi_seg_front_size;
unsigned int bi_seg_back_size;
struct bvec_iter bi_iter;
atomic_t __bi_remaining;
bio_end_io_t *bi_end_io;
void *bi_private;
#ifdef CONFIG_BLK_CGROUP
/*
* Represents the association of the css and request_queue for the bio.
* If a bio goes direct to device, it will not have a blkg as it will
* not have a request_queue associated with it. The reference is put
* on release of the bio.
*/
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
};
unsigned short bi_vcnt; /* how many bio_vec's */
/*
* Everything starting with bi_max_vecs will be preserved by bio_reset()
*/
unsigned short bi_max_vecs; /* max bvl_vecs we can hold */
atomic_t __bi_cnt; /* pin count */
struct bio_vec *bi_io_vec; /* the actual vec list */
struct bio_set *bi_pool;
/*
* We can inline a number of vecs at the end of the bio, to avoid
* double allocations for a small number of bio_vecs. This member
* MUST obviously be kept at the very end of the bio.
*/
struct bio_vec bi_inline_vecs[0];
};
bio_vec 、bvec_iter
struct bio_vec {
struct page *bv_page;
unsigned int bv_len;
unsigned int bv_offset;
};
struct bvec_iter {
sector_t bi_sector; /* device address in 512 byte
sectors */
unsigned int bi_size; /* residual I/O count */
unsigned int bi_idx; /* current index into bvl_vec */
unsigned int bi_bvec_done; /* number of bytes completed in
current bvec */
};
二)filesystem layer
superblock
struct super_block {
struct list_head s_list; /* Keep this first */
dev_t s_dev; /* search index; _not_ kdev_t */
unsigned char s_blocksize_bits;
unsigned long s_blocksize;
loff_t s_maxbytes; /* Max file size */
struct file_system_type *s_type;
const struct super_operations *s_op;
const struct dquot_operations *dq_op;
const struct quotactl_ops *s_qcop;
const struct export_operations *s_export_op;
unsigned long s_flags;
unsigned long s_iflags; /* internal SB_I_* flags */
unsigned long s_magic;
struct dentry *s_root;
struct rw_semaphore s_umount;
int s_count;
atomic_t s_active;
#ifdef CONFIG_SECURITY
void *s_security;
#endif
const struct xattr_handler **s_xattr;
#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
const struct fscrypt_operations *s_cop;
#endif
struct hlist_bl_head s_roots; /* alternate root dentries for NFS */
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
struct block_device *s_bdev;
struct backing_dev_info *s_bdi;
struct mtd_info *s_mtd;
struct hlist_node s_instances;
unsigned int s_quota_types; /* Bitmask of supported quota types */
struct quota_info s_dquot; /* Diskquota specific options */
struct sb_writers s_writers;
/*
* Keep s_fs_info, s_time_gran, s_fsnotify_mask, and
* s_fsnotify_marks together for cache efficiency. They are frequently
* accessed and rarely modified.
*/
void *s_fs_info; /* Filesystem private info */
/* Granularity of c/m/atime in ns (cannot be worse than a second) */
u32 s_time_gran;
#ifdef CONFIG_FSNOTIFY
__u32 s_fsnotify_mask;
struct fsnotify_mark_connector __rcu *s_fsnotify_marks;
#endif
char s_id[32]; /* Informational name */
uuid_t s_uuid; /* UUID */
unsigned int s_max_links;
fmode_t s_mode;
/*
* The next field is for VFS *only*. No filesystems have any business
* even looking at it. You had been warned.
*/
struct mutex s_vfs_rename_mutex; /* Kludge */
/*
* Filesystem subtype. If non-empty the filesystem type field
* in /proc/mounts will be "type.subtype"
*/
char *s_subtype;
const struct dentry_operations *s_d_op; /* default d_op for dentries */
/*
* Saved pool identifier for cleancache (-1 means none)
*/
int cleancache_poolid;
struct shrinker s_shrink; /* per-sb shrinker handle */
/* Number of inodes with nlink == 0 but still referenced */
atomic_long_t s_remove_count;
/* Pending fsnotify inode refs */
atomic_long_t s_fsnotify_inode_refs;
/* Being remounted read-only */
int s_readonly_remount;
/* AIO completions deferred from interrupt context */
struct workqueue_struct *s_dio_done_wq;
struct hlist_head s_pins;
/*
* Owning user namespace and default context in which to
* interpret filesystem uids, gids, quotas, device nodes,
* xattrs and security labels.
*/
struct user_namespace *s_user_ns;
/*
* The list_lru structure is essentially just a pointer to a table
* of per-node lru lists, each of which has its own spinlock.
* There is no need to put them into separate cachelines.
*/
struct list_lru s_dentry_lru;
struct list_lru s_inode_lru;
struct rcu_head rcu;
struct work_struct destroy_work;
struct mutex s_sync_lock; /* sync serialisation lock */
/*
* Indicates how deep in a filesystem stack this SB is
*/
int s_stack_depth;
/* s_inode_list_lock protects s_inodes */
spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp;
struct list_head s_inodes; /* all inodes */
spinlock_t s_inode_wblist_lock;
struct list_head s_inodes_wb; /* writeback inodes */
} __randomize_layout;
inode
struct fsnotify_mark_connector;
/*
* Keep mostly read-only and often accessed (especially for
* the RCU path lookup and 'stat' data) fields at the beginning
* of the 'struct inode'
*/
struct inode {
umode_t i_mode;
unsigned short i_opflags;
kuid_t i_uid;
kgid_t i_gid;
unsigned int i_flags;
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *i_acl;
struct posix_acl *i_default_acl;
#endif
const struct inode_operations *i_op;
struct super_block *i_sb;
struct address_space *i_mapping;
#ifdef CONFIG_SECURITY
void *i_security;
#endif
/* Stat data, not accessed from path walking */
unsigned long i_ino;
/*
* Filesystems may only read i_nlink directly. They shall use the
* following functions for modification:
*
* (set|clear|inc|drop)_nlink
* inode_(inc|dec)_link_count
*/
union {
const unsigned int i_nlink;
unsigned int __i_nlink;
};
dev_t i_rdev;
loff_t i_size;
struct timespec64 i_atime;
struct timespec64 i_mtime;
struct timespec64 i_ctime;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
u8 i_blkbits;
u8 i_write_hint;
blkcnt_t i_blocks;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
#endif
/* Misc */
unsigned long i_state;
struct rw_semaphore i_rwsem;
unsigned long dirtied_when; /* jiffies of first dirtying */
unsigned long dirtied_time_when;
struct hlist_node i_hash;
struct list_head i_io_list; /* backing dev IO list */
#ifdef CONFIG_CGROUP_WRITEBACK
struct bdi_writeback *i_wb; /* the associated cgroup wb */
/* foreign inode detection, see wbc_detach_inode() */
int i_wb_frn_winner;
u16 i_wb_frn_avg_time;
u16 i_wb_frn_history;
#endif
struct list_head i_lru; /* inode LRU list */
struct list_head i_sb_list;
struct list_head i_wb_list; /* backing dev writeback list */
union {
struct hlist_head i_dentry;
struct rcu_head i_rcu;
};
atomic64_t i_version;
atomic_t i_count;
atomic_t i_dio_count;
atomic_t i_writecount;
#ifdef CONFIG_IMA
atomic_t i_readcount; /* struct files open RO */
#endif
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
struct file_lock_context *i_flctx;
struct address_space i_data;
struct list_head i_devices;
union {
struct pipe_inode_info *i_pipe;
struct block_device *i_bdev;
struct cdev *i_cdev;
char *i_link;
unsigned i_dir_seq;
};
__u32 i_generation;
#ifdef CONFIG_FSNOTIFY
__u32 i_fsnotify_mask; /* all events this inode cares about */
struct fsnotify_mark_connector __rcu *i_fsnotify_marks;
#endif
#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
struct fscrypt_info *i_crypt_info;
#endif
void *i_private; /* fs or device private pointer */
} __randomize_layout;
file
struct file {
union {
struct llist_node fu_llist;
struct rcu_head fu_rcuhead;
} f_u;
struct path f_path;
struct inode *f_inode; /* cached value */
const struct file_operations *f_op;
/*
* Protects f_ep_links, f_flags.
* Must not be taken from IRQ context.
*/
spinlock_t f_lock;
enum rw_hint f_write_hint;
atomic_long_t f_count;
unsigned int f_flags;
fmode_t f_mode;
struct mutex f_pos_lock;
loff_t f_pos;
struct fown_struct f_owner;
const struct cred *f_cred;
struct file_ra_state f_ra;
u64 f_version;
#ifdef CONFIG_SECURITY
void *f_security;
#endif
/* needed for tty driver, and maybe others */
void *private_data;
#ifdef CONFIG_EPOLL
/* Used by fs/eventpoll.c to link all the hooks to this file */
struct list_head f_ep_links;
struct list_head f_tfile_llink;
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
errseq_t f_wb_err;
} __randomize_layout
dentry
文件系统对象在内核中所在文件系统树中的位置。
struct dentry {
/* RCU lookup touched fields */
unsigned int d_flags; /* protected by d_lock */
seqcount_t d_seq; /* per dentry seqlock */
struct hlist_bl_node d_hash; /* lookup hash list */
struct dentry *d_parent; /* parent directory */
struct qstr d_name;
struct inode *d_inode; /* Where the name belongs to - NULL is
* negative */
unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */
/* Ref lookup also touches following */
struct lockref d_lockref; /* per-dentry lock and refcount */
const struct dentry_operations *d_op;
struct super_block *d_sb; /* The root of the dentry tree */
unsigned long d_time; /* used by d_revalidate */
void *d_fsdata; /* fs-specific data */
union {
struct list_head d_lru; /* LRU list */
wait_queue_head_t *d_wait; /* in-lookup ones only */
};
struct list_head d_child; /* child of parent list */
struct list_head d_subdirs; /* our children */
/*
* d_alias and d_rcu can share memory
*/
union {
struct hlist_node d_alias; /* inode alias list */
struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */
struct rcu_head d_rcu;
} d_u;
} __randomize_layout;
address_space
struct address_space {
struct inode *host;
struct xarray i_pages;
gfp_t gfp_mask;
atomic_t i_mmap_writable;
struct rb_root_cached i_mmap;
struct rw_semaphore i_mmap_rwsem;
unsigned long nrpages;
unsigned long nrexceptional;
pgoff_t writeback_index;
const struct address_space_operations *a_ops;
unsigned long flags;
errseq_t wb_err;
spinlock_t private_lock;
struct list_head private_list;
void *private_data;
} __attribute__((aligned(sizeof(long)))) __randomize_layout;
kiocb
struct kiocb {
struct file *ki_filp;
/* The 'ki_filp' pointer is shared in a union for aio */
randomized_struct_fields_start
loff_t ki_pos;
void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
void *private;
int ki_flags;
u16 ki_hint;
u16 ki_ioprio; /* See linux/ioprio.h */
randomized_struct_fields_end
};
iov_iter
struct iov_iter {
unsigned int type;
size_t iov_offset;
size_t count;
union {
const struct iovec *iov;
const struct kvec *kvec;
const struct bio_vec *bvec;
struct pipe_inode_info *pipe;
};
union {
unsigned long nr_segs;
struct {
int idx;
int start_idx;
};
};
};
三)、驱动层
二、mount
三、read
vfs_read
vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) //对访问标志、内存读写权限等进行校验
|–>__vfs_read(file, buf, count, pos)
|–>new_sync_read(file, buf, count, pos)
const struct file_operations f2fs_file_operations = {
.llseek = f2fs_llseek,
.read_iter = generic_file_read_iter,
.write_iter = f2fs_file_write_iter,
.open = f2fs_file_open,
.release = f2fs_release_file,
.mmap = f2fs_file_mmap,
.flush = f2fs_file_flush,
.fsync = f2fs_sync_file,
.fallocate = f2fs_fallocate,
.unlocked_ioctl = f2fs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = f2fs_compat_ioctl,
#endif
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
};
new_sync_read
根据传入的偏移长度等参数初始化kiock和iov_iter,然后调用文件系统的read_iter函数,f2fs文件系统对应generic_file_read_iter.
kiocb和iov_iter分别描述io操作中文件和内存的处理进度。
static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
{
struct iovec iov = { .iov_base = buf, .iov_len = len };
struct kiocb kiocb;
struct iov_iter iter;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
iov_iter_init(&iter, READ, &iov, 1, len);
ret = call_read_iter(filp, &kiocb, &iter);
BUG_ON(ret == -EIOCBQUEUED);
*ppos = kiocb.ki_pos;
return ret;
}
generic_file_read_iter
generic_file_read_iter(&kiocb,&iter)
分别处理直接io和使用缓存的io。
1、DIRECT_IO(f2fs_direct_IO)😕/ TODO
2、generic_file_buffered_read(iocb, iter, retval)
generic_file_buffered_read
/**
* generic_file_buffered_read - generic file read routine
* @iocb: the iocb to read
* @iter: data destination
* @written: already copied
*
* This is a generic file read routine, and uses the
* mapping->a_ops->readpage() function for the actual low-level stuff.
*
* This is really ugly. But the goto's actually try to clarify some
* of the logic when it comes to error handling etc.
*/
static ssize_t generic_file_buffered_read(struct kiocb *iocb,
struct iov_iter *iter, ssize_t written)
{
struct file *filp = iocb->ki_filp;
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
struct file_ra_state *ra = &filp->f_ra;
loff_t *ppos = &iocb->ki_pos;
pgoff_t index;
pgoff_t last_index;
pgoff_t prev_index;
unsigned long offset; /* offset into pagecache page */
unsigned int prev_offset;
int error = 0;
if (unlikely(*ppos >= inode->i_sb->s_maxbytes))
return 0;
iov_iter_truncate(iter, inode->i_sb->s_maxbytes);
index = *ppos >> PAGE_SHIFT;
prev_index = ra->prev_pos >> PAGE_SHIFT;
prev_offset = ra->prev_pos & (PAGE_SIZE-1);
last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT;
offset = *ppos & ~PAGE_MASK;
for (;;) {
struct page *page;
pgoff_t end_index;
loff_t isize;
unsigned long nr, ret;
cond_resched();
find_page:
if (fatal_signal_pending(current)) {
error = -EINTR;
goto out;
}
page = find_get_page(mapping, index);
if (!page) {
if (iocb->ki_flags & IOCB_NOWAIT)
goto would_block;
page_cache_sync_readahead(mapping,
ra, filp,
index, last_index - index);
page = find_get_page(mapping, index);
if (unlikely(page == NULL))
goto no_cached_page;
}
if (PageReadahead(page)) {
page_cache_async_readahead(mapping,
ra, filp, page,
index, last_index - index);
}
if (!PageUptodate(page)) {
if (iocb->ki_flags & IOCB_NOWAIT) {
put_page(page);
goto would_block;
}
/*
* See comment in do_read_cache_page on why
* wait_on_page_locked is used to avoid unnecessarily
* serialisations and why it's safe.
*/
error = wait_on_page_locked_killable(page);
if (unlikely(error))
goto readpage_error;
if (PageUptodate(page))
goto page_ok;
if (inode->i_blkbits == PAGE_SHIFT ||
!mapping->a_ops->is_partially_uptodate)
goto page_not_up_to_date;
/* pipes can't handle partially uptodate pages */
if (unlikely(iov_iter_is_pipe(iter)))
goto page_not_up_to_date;
if (!trylock_page(page))
goto page_not_up_to_date;
/* Did it get truncated before we got the lock? */
if (!page->mapping)
goto page_not_up_to_date_locked;
if (!mapping->a_ops->is_partially_uptodate(page,
offset, iter->count))
goto page_not_up_to_date_locked;
unlock_page(page);
}
page_ok:
/*
* i_size must be checked after we know the page is Uptodate.
*
* Checking i_size after the check allows us to calculate
* the correct value for "nr", which means the zero-filled
* part of the page is not copied back to userspace (unless
* another truncate extends the file - this is desired though).
*/
isize = i_size_read(inode);
end_index = (isize - 1) >> PAGE_SHIFT;
if (unlikely(!isize || index > end_index)) {
put_page(page);
goto out;
}
/* nr is the maximum number of bytes to copy from this page */
nr = PAGE_SIZE;
if (index == end_index) {
nr = ((isize - 1) & ~PAGE_MASK) + 1;
if (nr <= offset) {
put_page(page);
goto out;
}
}
nr = nr - offset;
/* If users can be writing to this page using arbitrary
* virtual addresses, take care about potential aliasing
* before reading the page on the kernel side.
*/
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
/*
* When a sequential read accesses a page several times,
* only mark it as accessed the first time.
*/
if (prev_index != index || offset != prev_offset)
mark_page_accessed(page);
prev_index = index;
/*
* Ok, we have the page, and it's up-to-date, so
* now we can copy it to user space...
*/
ret = copy_page_to_iter(page, offset, nr, iter);
offset += ret;
index += offset >> PAGE_SHIFT;
offset &= ~PAGE_MASK;
prev_offset = offset;
put_page(page);
written += ret;
if (!iov_iter_count(iter))
goto out;
if (ret < nr) {
error = -EFAULT;
goto out;
}
continue;
page_not_up_to_date:
/* Get exclusive access to the page ... */
error = lock_page_killable(page);
if (unlikely(error))
goto readpage_error;
page_not_up_to_date_locked:
/* Did it get truncated before we got the lock? */
if (!page->mapping) {
unlock_page(page);
put_page(page);
continue;
}
/* Did somebody else fill it already? */
if (PageUptodate(page)) {
unlock_page(page);
goto page_ok;
}
readpage:
/*
* A previous I/O error may have been due to temporary
* failures, eg. multipath errors.
* PG_error will be set again if readpage fails.
*/
ClearPageError(page);
/* Start the actual read. The read will unlock the page. */
error = mapping->a_ops->readpage(filp, page);
if (unlikely(error)) {
if (error == AOP_TRUNCATED_PAGE) {
put_page(page);
error = 0;
goto find_page;
}
goto readpage_error;
}
if (!PageUptodate(page)) {
error = lock_page_killable(page);
if (unlikely(error))
goto readpage_error;
if (!PageUptodate(page)) {
if (page->mapping == NULL) {
/*
* invalidate_mapping_pages got it
*/
unlock_page(page);
put_page(page);
goto find_page;
}
unlock_page(page);
shrink_readahead_size_eio(filp, ra);
error = -EIO;
goto readpage_error;
}
unlock_page(page);
}
goto page_ok;
readpage_error:
/* UHHUH! A synchronous read error occurred. Report it */
put_page(page);
goto out;
no_cached_page:
/*
* Ok, it wasn't cached, so we need to create a new
* page..
*/
page = page_cache_alloc(mapping);
if (!page) {
error = -ENOMEM;
goto out;
}
error = add_to_page_cache_lru(page, mapping, index,
mapping_gfp_constraint(mapping, GFP_KERNEL));
if (error) {
put_page(page);
if (error == -EEXIST) {
error = 0;
goto find_page;
}
goto out;
}
goto readpage;
}
would_block:
error = -EAGAIN;
out:
ra->prev_pos = prev_index;
ra->prev_pos <<= PAGE_SHIFT;
ra->prev_pos |= prev_offset;
*ppos = ((loff_t)index << PAGE_SHIFT) + offset;
file_accessed(filp);
return written ? written : error;
}
f2fs_read_data_page
f2fs_mpage_readpages
计算内存页数据所在磁盘上的起始block和数量,构建bio之后调用__submit_bio(对f2fs文件系统的io操作进行统计,并添加对应trace点,之后调用submit_bio
submit_bio
对io进行统计,/proc/vmstat节点里的pgpgout、pgpgin等数据正是来源于此
同时可以看到对proc/sys/vm/block_dump写入1后,即可在内核log中看到io记录。
blk_qc_t submit_bio(struct bio *bio)
{
/*
* If it's a regular read/write or a barrier with data attached,
* go through the normal accounting stuff before submission.
*/
if (bio_has_data(bio)) {
unsigned int count;
if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
count = queue_logical_block_size(bio->bi_disk->queue) >> 9;
else
count = bio_sectors(bio);
if (op_is_write(bio_op(bio))) {
count_vm_events(PGPGOUT, count);
} else {
task_io_account_read(bio->bi_iter.bi_size);
count_vm_events(PGPGIN, count);
}
if (unlikely(block_dump)) {
char b[BDEVNAME_SIZE];
printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
current->comm, task_pid_nr(current),
op_is_write(bio_op(bio)) ? "WRITE" : "READ",
(unsigned long long)bio->bi_iter.bi_sector,
bio_devname(bio, b), count);
}
}
return generic_make_request(bio);
}
generic_make_request
/**
* generic_make_request - hand a buffer to its device driver for I/O
* @bio: The bio describing the location in memory and on the device.
*
* generic_make_request() is used to make I/O requests of block
* devices. It is passed a &struct bio, which describes the I/O that needs
* to be done.
*
* generic_make_request() does not return any status. The
* success/failure status of the request, along with notification of
* completion, is delivered asynchronously through the bio->bi_end_io
* function described (one day) else where.
*
* The caller of generic_make_request must make sure that bi_io_vec
* are set to describe the memory buffer, and that bi_dev and bi_sector are
* set to describe the device address, and the
* bi_end_io and optionally bi_private are set to describe how
* completion notification should be signaled.
*
* generic_make_request and the drivers it calls may use bi_next if this
* bio happens to be merged with someone else, and may resubmit the bio to
* a lower device by calling into generic_make_request recursively, which
* means the bio should NOT be touched after the call to ->make_request_fn.
*/
blk_qc_t generic_make_request(struct bio *bio)
{
/*
* bio_list_on_stack[0] contains bios submitted by the current
* make_request_fn.
* bio_list_on_stack[1] contains bios that were submitted before
* the current make_request_fn, but that haven't been processed
* yet.
*/
struct bio_list bio_list_on_stack[2];
blk_mq_req_flags_t flags = 0;
struct request_queue *q = bio->bi_disk->queue;
blk_qc_t ret = BLK_QC_T_NONE;
if (bio->bi_opf & REQ_NOWAIT)
flags = BLK_MQ_REQ_NOWAIT;
if (bio_flagged(bio, BIO_QUEUE_ENTERED))
blk_queue_enter_live(q);
else if (blk_queue_enter(q, flags) < 0) {
if (!blk_queue_dying(q) && (bio->bi_opf & REQ_NOWAIT))
bio_wouldblock_error(bio);
else
bio_io_error(bio);
return ret;
}
if (!generic_make_request_checks(bio))
goto out;
/*
* We only want one ->make_request_fn to be active at a time, else
* stack usage with stacked devices could be a problem. So use
* current->bio_list to keep a list of requests submited by a
* make_request_fn function. current->bio_list is also used as a
* flag to say if generic_make_request is currently active in this
* task or not. If it is NULL, then no make_request is active. If
* it is non-NULL, then a make_request is active, and new requests
* should be added at the tail
*/
if (current->bio_list) {
bio_list_add(¤t->bio_list[0], bio);
goto out;
}
/* following loop may be a bit non-obvious, and so deserves some
* explanation.
* Before entering the loop, bio->bi_next is NULL (as all callers
* ensure that) so we have a list with a single bio.
* We pretend that we have just taken it off a longer list, so
* we assign bio_list to a pointer to the bio_list_on_stack,
* thus initialising the bio_list of new bios to be
* added. ->make_request() may indeed add some more bios
* through a recursive call to generic_make_request. If it
* did, we find a non-NULL value in bio_list and re-enter the loop
* from the top. In this case we really did just take the bio
* of the top of the list (no pretending) and so remove it from
* bio_list, and call into ->make_request() again.
*/
BUG_ON(bio->bi_next);
bio_list_init(&bio_list_on_stack[0]);
current->bio_list = bio_list_on_stack;
do {
bool enter_succeeded = true;
if (unlikely(q != bio->bi_disk->queue)) {
if (q)
blk_queue_exit(q);
q = bio->bi_disk->queue;
flags = 0;
if (bio->bi_opf & REQ_NOWAIT)
flags = BLK_MQ_REQ_NOWAIT;
if (blk_queue_enter(q, flags) < 0) {
enter_succeeded = false;
q = NULL;
}
}
if (enter_succeeded) {
struct bio_list lower, same;
/* Create a fresh bio_list for all subordinate requests */
bio_list_on_stack[1] = bio_list_on_stack[0];
bio_list_init(&bio_list_on_stack[0]);
ret = q->make_request_fn(q, bio);
/* sort new bios into those for a lower level
* and those for the same level
*/
bio_list_init(&lower);
bio_list_init(&same);
while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
if (q == bio->bi_disk->queue)
bio_list_add(&same, bio);
else
bio_list_add(&lower, bio);
/* now assemble so we handle the lowest level first */
bio_list_merge(&bio_list_on_stack[0], &lower);
bio_list_merge(&bio_list_on_stack[0], &same);
bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
} else {
if (unlikely(!blk_queue_dying(q) &&
(bio->bi_opf & REQ_NOWAIT)))
bio_wouldblock_error(bio);
else
bio_io_error(bio);
}
bio = bio_list_pop(&bio_list_on_stack[0]);
} while (bio);
current->bio_list = NULL; /* deactivate */
out:
if (q)
blk_queue_exit(q);
return ret;
}
generic_make_request调用驱动的make_request_fn,对bio生成request。5.0内核中mmc和ufs对应的make_request_fn方法都是blk_mq_make_request
blk_mq_make_request
static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
{
const int is_sync = op_is_sync(bio->bi_opf);
const int is_flush_fua = op_is_flush(bio->bi_opf);
struct blk_mq_alloc_data data = { .flags = 0};
struct request *rq;
struct blk_plug *plug;
struct request *same_queue_rq = NULL;
blk_qc_t cookie;
blk_queue_bounce(q, &bio);
blk_queue_split(q, &bio);
if (!bio_integrity_prep(bio))
return BLK_QC_T_NONE;
if (!is_flush_fua && !blk_queue_nomerges(q) &&
blk_attempt_plug_merge(q, bio, &same_queue_rq))
return BLK_QC_T_NONE;
if (blk_mq_sched_bio_merge(q, bio))
return BLK_QC_T_NONE;
rq_qos_throttle(q, bio);
data.cmd_flags = bio->bi_opf;
rq = blk_mq_get_request(q, bio, &data);
if (unlikely(!rq)) {
rq_qos_cleanup(q, bio);
if (bio->bi_opf & REQ_NOWAIT)
bio_wouldblock_error(bio);
return BLK_QC_T_NONE;
}
trace_block_getrq(q, bio, bio->bi_opf);
rq_qos_track(q, rq, bio);
cookie = request_to_qc_t(data.hctx, rq);
plug = current->plug;
if (unlikely(is_flush_fua)) {
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
/* bypass scheduler for flush rq */
blk_insert_flush(rq);
blk_mq_run_hw_queue(data.hctx, true);
} else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs)) {
/*
* Use plugging if we have a ->commit_rqs() hook as well, as
* we know the driver uses bd->last in a smart fashion.
*/
unsigned int request_count = plug->rq_count;
struct request *last = NULL;
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
if (!request_count)
trace_block_plug(q);
else
last = list_entry_rq(plug->mq_list.prev);
if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
blk_flush_plug_list(plug, false);
trace_block_plug(q);
}
blk_add_rq_to_plug(plug, rq);
} else if (plug && !blk_queue_nomerges(q)) {
blk_mq_bio_to_request(rq, bio);
/*
* We do limited plugging. If the bio can be merged, do that.
* Otherwise the existing request in the plug list will be
* issued. So the plug list will have one request at most
* The plug list might get flushed before this. If that happens,
* the plug list is empty, and same_queue_rq is invalid.
*/
if (list_empty(&plug->mq_list))
same_queue_rq = NULL;
if (same_queue_rq) {
list_del_init(&same_queue_rq->queuelist);
plug->rq_count--;
}
blk_add_rq_to_plug(plug, rq);
blk_mq_put_ctx(data.ctx);
if (same_queue_rq) {
data.hctx = same_queue_rq->mq_hctx;
blk_mq_try_issue_directly(data.hctx, same_queue_rq,
&cookie, false, true);
}
} else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
!data.hctx->dispatch_busy)) {
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
blk_mq_try_issue_directly(data.hctx, rq, &cookie, false, true);
} else {
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
blk_mq_sched_insert_request(rq, false, true, true);
}
return cookie;
}
该函数会尝试将bio与进程的io队列、调度器队列、软件队列上的request合并,合并的依据是物理地址连续,如果无法合并则调用blk_mq_get_request为这个bio生成一个新的request。
最终调用驱动的queue_rq函数处理io请求
queue_rq
ufs对应blk_mq_ops如下
scsi_queue_rq–>scsi_dispatch_cmd–>ufshcd_queuecommand–>ufshcd_send_command–>ufshcd_writel
mmc对于blk_mq_ops如下
READ完成
ufshcd_intr–>ufshcd_sl_intr–>ufshcd_transfer_req_compl–>__ufshcd_transfer_req_compl–>scsi_mq_done(scsi_queue_rq中设置)–>scsi_softirq_done–>scsi_finish_command–>scsi_io_completion–>scsi_end_request–>blk_update_request<trace_block_rq_complete>–>req_bio_endio–>bio_endio<trace_block_bio_complete>–>f2fs_read_end_io–>__read_end_io–>unlock_page–>wake_up_page_bit