path: root/include/linux/fs.h

#ifndef _LINUX_FS_H
#define _LINUX_FS_H

#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
#include <linux/path.h>
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
#include <linux/list_lru.h>
#include <linux/llist.h>
#include <linux/radix-tree.h>
#include <linux/rbtree.h>
#include <linux/init.h>
#include <linux/pid.h>
#include <linux/bug.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
#include <linux/fiemap.h>
#include <linux/rculist_bl.h>
#include <linux/atomic.h>
#include <linux/shrinker.h>
#include <linux/migrate_mode.h>
#include <linux/uidgid.h>
#include <linux/lockdep.h>
#include <linux/percpu-rwsem.h>
#include <linux/blk_types.h>
#include <linux/workqueue.h>
#include <linux/percpu-rwsem.h>
#include <linux/delayed_call.h>

#include <asm/byteorder.h>
#include <uapi/linux/fs.h>

struct backing_dev_info;
struct bdi_writeback;
struct export_operations;
struct hd_geometry;
struct iovec;
struct kiocb;
struct kobject;
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
struct cred;
struct swap_info_struct;
struct seq_file;
struct workqueue_struct;
struct iov_iter;

extern void __init inode_init(void);
extern void __init inode_init_early(void);
extern void __init files_init(void);
extern void __init files_maxfiles_init(void);

extern struct files_stat_struct files_stat;
extern unsigned long get_max_files(void);
extern int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;

struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
			ssize_t bytes, void *private);
typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate);

#define MAY_EXEC		0x00000001
#define MAY_WRITE		0x00000002
#define MAY_READ		0x00000004
#define MAY_APPEND		0x00000008
#define MAY_ACCESS		0x00000010
#define MAY_OPEN		0x00000020
#define MAY_CHDIR		0x00000040
/* called from RCU mode, don't block */
#define MAY_NOT_BLOCK		0x00000080

/*
 * flags in file.f_mode.  Note that FMODE_READ and FMODE_WRITE must correspond
 * to O_WRONLY and O_RDWR via the strange trick in __dentry_open()
 */

/* file is open for reading */
#define FMODE_READ		((__force fmode_t)0x1)
/* file is open for writing */
#define FMODE_WRITE		((__force fmode_t)0x2)
/* file is seekable */
#define FMODE_LSEEK		((__force fmode_t)0x4)
/* file can be accessed using pread */
#define FMODE_PREAD		((__force fmode_t)0x8)
/* file can be accessed using pwrite */
#define FMODE_PWRITE		((__force fmode_t)0x10)
/* File is opened for execution with sys_execve / sys_uselib */
#define FMODE_EXEC		((__force fmode_t)0x20)
/* File is opened with O_NDELAY (only set for block devices) */
#define FMODE_NDELAY		((__force fmode_t)0x40)
/* File is opened with O_EXCL (only set for block devices) */
#define FMODE_EXCL		((__force fmode_t)0x80)
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
   (specialy hack for floppy.c) */
#define FMODE_WRITE_IOCTL	((__force fmode_t)0x100)
/* 32bit hashes as llseek() offset (for directories) */
#define FMODE_32BITHASH         ((__force fmode_t)0x200)
/* 64bit hashes as llseek() offset (for directories) */
#define FMODE_64BITHASH         ((__force fmode_t)0x400)

/*
 * Don't update ctime and mtime.
 *
 * Currently a special hack for the XFS open_by_handle ioctl, but we'll
 * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon.
 */
#define FMODE_NOCMTIME		((__force fmode_t)0x800)

/* Expect random access pattern */
#define FMODE_RANDOM		((__force fmode_t)0x1000)

/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
#define FMODE_UNSIGNED_OFFSET	((__force fmode_t)0x2000)

/* File is opened with O_PATH; almost nothing can be done with it */
#define FMODE_PATH		((__force fmode_t)0x4000)

/* File needs atomic accesses to f_pos */
#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
/* Write access to underlying fs */
#define FMODE_WRITER		((__force fmode_t)0x10000)
/* Has read method(s) */
#define FMODE_CAN_READ          ((__force fmode_t)0x20000)
/* Has write method(s) */
#define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)

/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY		((__force fmode_t)0x4000000)

/*
 * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
 * that indicates that they should check the contents of the iovec are
 * valid, but not check the memory that the iovec elements
 * points too.
 */
#define CHECK_IOVEC_ONLY -1

/*
 * The below are the various read and write types that we support. Some of
 * them include behavioral modifiers that send information down to the
 * block layer and IO scheduler. Terminology:
 *
 *	The block layer uses device plugging to defer IO a little bit, in
 *	the hope that we will see more IO very shortly. This increases
 *	coalescing of adjacent IO and thus reduces the number of IOs we
 *	have to send to the device. It also allows for better queuing,
 *	if the IO isn't mergeable. If the caller is going to be waiting
 *	for the IO, then he must ensure that the device is unplugged so
 *	that the IO is dispatched to the driver.
 *
 *	All IO is handled async in Linux. This is fine for background
 *	writes, but for reads or writes that someone waits for completion
 *	on, we want to notify the block layer and IO scheduler so that they
 *	know about it. That allows them to make better scheduling
 *	decisions. So when the below references 'sync' and 'async', it
 *	is referencing this priority hint.
 *
 * With that in mind, the available types are:
 *
 * READ			A normal read operation. Device will be plugged.
 * READ_SYNC		A synchronous read. Device is not plugged, caller can
 *			immediately wait on this read without caring about
 *			unplugging.
 * READA		Used for read-ahead operations. Lower priority, and the
 *			block layer could (in theory) choose to ignore this
 *			request if it runs into resource problems.
 * WRITE		A normal async write. Device will be plugged.
 * WRITE_SYNC		Synchronous write. Identical to WRITE, but passes down
 *			the hint that someone will be waiting on this IO
 *			shortly. The write equivalent of READ_SYNC.
 * WRITE_ODIRECT	Special case write for O_DIRECT only.
 * WRITE_FLUSH		Like WRITE_SYNC but with preceding cache flush.
 * WRITE_FUA		Like WRITE_SYNC but data is guaranteed to be on
 *			non-volatile media on completion.
 * WRITE_FLUSH_FUA	Combination of WRITE_FLUSH and FUA. The IO is preceded
 *			by a cache flush and data is guaranteed to be on
 *			non-volatile media on completion.
 *
 */
#define RW_MASK			REQ_WRITE
#define RWA_MASK		REQ_RAHEAD

#define READ			0
#define WRITE			RW_MASK
#define READA			RWA_MASK

#define READ_SYNC		(READ | REQ_SYNC)
#define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
#define WRITE_ODIRECT		(WRITE | REQ_SYNC)
#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)

/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
#define ATTR_MODE	(1 << 0)
#define ATTR_UID	(1 << 1)
#define ATTR_GID	(1 << 2)
#define ATTR_SIZE	(1 << 3)
#define ATTR_ATIME	(1 << 4)
#define ATTR_MTIME	(1 << 5)
#define ATTR_CTIME	(1 << 6)
#define ATTR_ATIME_SET	(1 << 7)
#define ATTR_MTIME_SET	(1 << 8)
#define ATTR_FORCE	(1 << 9) /* Not a change, but a change it */
#define ATTR_ATTR_FLAG	(1 << 10)
#define ATTR_KILL_SUID	(1 << 11)
#define ATTR_KILL_SGID	(1 << 12)
#define ATTR_FILE	(1 << 13)
#define ATTR_KILL_PRIV	(1 << 14)
#define ATTR_OPEN	(1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET	(1 << 16)

/*
 * Whiteout is represented by a char device.  The following constants define the
 * mode and device number to use.
 */
#define WHITEOUT_MODE 0
#define WHITEOUT_DEV 0

/*
 * This is the Inode Attributes structure, used for notify_change().  It
 * uses the above definitions as flags, to know which values have changed.
 * Also, in this manner, a Filesystem can look at only the values it cares
 * about.  Basically, these are the attributes that the VFS layer can
 * request to change from the FS layer.
 *
 * Derek Atkins <warlord@MIT.EDU> 94-10-20
 */
struct iattr {
	unsigned int	ia_valid;
	umode_t		ia_mode;
	kuid_t		ia_uid;
	kgid_t		ia_gid;
	loff_t		ia_size;
	struct timespec	ia_atime;
	struct timespec	ia_mtime;
	struct timespec	ia_ctime;

	/*
	 * Not an attribute, but an auxiliary info for filesystems wanting to
	 * implement an ftruncate() like method.  NOTE: filesystem should
	 * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
	 */
	struct file	*ia_file;
};

/*
 * Includes for diskquotas.
 */
#include <linux/quota.h>

/*
 * Maximum number of layers of fs stack.  Needs to be limited to
 * prevent kernel stack overflow
 */
#define FILESYSTEM_MAX_STACK_DEPTH 2

/** 
 * enum positive_aop_returns - aop return codes with specific semantics
 *
 * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has
 * 			    completed, that the page is still locked, and
 * 			    should be considered active.  The VM uses this hint
 * 			    to return the page to the active list -- it won't
 * 			    be a candidate for writeback again in the near
 * 			    future.  Other callers must be careful to unlock
 * 			    the page if they get this return.  Returned by
 * 			    writepage(); 
 *
 * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has
 *  			unlocked it and the page might have been truncated.
 *  			The caller should back up to acquiring a new page and
 *  			trying again.  The aop will be taking reasonable
 *  			precautions not to livelock.  If the caller held a page
 *  			reference, it should drop it before retrying.  Returned
 *  			by readpage().
 *
 * address_space_operation functions return these large constants to indicate
 * special semantics to the caller.  These are much larger than the bytes in a
 * page to allow for functions that return the number of bytes operated on in a
 * given page.
 */

enum positive_aop_returns {
	AOP_WRITEPAGE_ACTIVATE	= 0x80000,
	AOP_TRUNCATED_PAGE	= 0x80001,
};

#define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
#define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
#define AOP_FLAG_NOFS			0x0004 /* used by filesystem to direct
						* helper code (eg buffer layer)
						* to clear GFP_FS from alloc */

/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

#define IOCB_EVENTFD		(1 << 0)
#define IOCB_APPEND		(1 << 1)
#define IOCB_DIRECT		(1 << 2)

struct kiocb {
	struct file		*ki_filp;
	loff_t			ki_pos;
	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
	void			*private;
	int			ki_flags;
};

static inline bool is_sync_kiocb(struct kiocb *kiocb)
{
	return kiocb->ki_complete == NULL;
}

static inline int iocb_flags(struct file *file);

static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
{
	*kiocb = (struct kiocb) {
		.ki_filp = filp,
		.ki_flags = iocb_flags(filp),
	};
}

/*
 * "descriptor" for what we're up to with a read.
 * This allows us to use the same read code yet
 * have multiple different users of the data that
 * we read from a file.
 *
 * The simplest case just copies the data to user
 * mode.
 */
typedef struct {
	size_t written;
	size_t count;
	union {
		char __user *buf;
		void *data;
	} arg;
	int error;
} read_descriptor_t;

typedef int (*read_actor_t)(read_descriptor_t *, struct page *,
		unsigned long, unsigned long);

struct address_space_operations {
	int (*writepage)(struct page *page, struct writeback_control *wbc);
	int (*readpage)(struct file *, struct page *);

	/* Write back some dirty pages from this mapping. */
	int (*writepages)(struct address_space *, struct writeback_control *);

	/* Set a page dirty.  Return true if this dirtied it */
	int (*set_page_dirty)(struct page *page);

	int (*readpages)(struct file *filp, struct address_space *mapping,
			struct list_head *pages, unsigned nr_pages);

	int (*write_begin)(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata);
	int (*write_end)(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata);

	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
	int (*releasepage) (struct page *, gfp_t);
	void (*freepage)(struct page *);
	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset);
	/*
	 * migrate the contents of a page to the specified target. If
	 * migrate_mode is MIGRATE_ASYNC, it must not block.
	 */
	int (*migratepage) (struct address_space *,
			struct page *, struct page *, enum migrate_mode);
	int (*launder_page) (struct page *);
	int (*is_partially_uptodate) (struct page *, unsigned long,
					unsigned long);
	void (*is_dirty_writeback) (struct page *, bool *, bool *);
	int (*error_remove_page)(struct address_space *, struct page *);

	/* swapfile support */
	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
				sector_t *span);
	void (*swap_deactivate)(struct file *file);
};

extern const struct address_space_operations empty_aops;

/*
 * pagecache_write_begin/pagecache_write_end must be used by general code
 * to write into the pagecache.
 */
int pagecache_write_begin(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata);

int pagecache_write_end(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata);

struct address_space {
	struct inode		*host;		/* owner: inode, block_device */
	struct radix_tree_root	page_tree;	/* radix tree of all pages */
	spinlock_t		tree_lock;	/* and lock protecting it */
	atomic_t		i_mmap_writable;/* count VM_SHARED mappings */
	struct rb_root		i_mmap;		/* tree of private and shared mappings */
	struct rw_semaphore	i_mmap_rwsem;	/* protect tree, count, list */
	/* Protected by tree_lock together with the radix tree */
	unsigned long		nrpages;	/* number of total pages */
	/* number of shadow or DAX exceptional entries */
	unsigned long		nrexceptional;
	pgoff_t			writeback_index;/* writeback starts here */
	const struct address_space_operations *a_ops;	/* methods */
	unsigned long		flags;		/* error bits/gfp mask */
	spinlock_t		private_lock;	/* for use by the address_space */
	struct list_head	private_list;	/* ditto */
	void			*private_data;	/* ditto */
} __attribute__((aligned(sizeof(long))));
	/*
	 * On most architectures that alignment is already the case; but
	 * must be enforced here for CRIS, to let the least significant bit
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */
struct request_queue;

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 */
	struct list_head	bd_inodes;
	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;
	unsigned		bd_block_size;
	struct hd_struct *	bd_part;
	/* number of times partitions within this device have been opened. */
	unsigned		bd_part_count;
	int			bd_invalidated;
	struct gendisk *	bd_disk;
	struct request_queue *  bd_queue;
	struct list_head	bd_list;
	/*
	 * 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;
};

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1
#define PAGECACHE_TAG_TOWRITE	2

int mapping_tagged(struct address_space *mapping, int tag);

static inline void i_mmap_lock_write(struct address_space *mapping)
{
	down_write(&mapping->i_mmap_rwsem);
}

static inline void i_mmap_unlock_write(struct address_space *mapping)
{
	up_write(&mapping->i_mmap_rwsem);
}

static inline void i_mmap_lock_read(struct address_space *mapping)
{
	down_read(&mapping->i_mmap_rwsem);
}

static inline void i_mmap_unlock_read(struct address_space *mapping)
{
	up_read(&mapping->i_mmap_rwsem);
}

/*
 * Might pages of this file be mapped into userspace?
 */
static inline int mapping_mapped(struct address_space *mapping)
{
	return	!RB_EMPTY_ROOT(&mapping->i_mmap);
}

/*
 * Might pages of this file have been modified in userspace?
 * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff
 * marks vma as VM_SHARED if it is shared, and the file was opened for
 * writing i.e. vma may be mprotected writable even if now readonly.
 *
 * If i_mmap_writable is negative, no new writable mappings are allowed. You
 * can only deny writable mappings, if none exists right now.
 */
static inline int mapping_writably_mapped(struct address_space *mapping)
{
	return atomic_read(&mapping->i_mmap_writable) > 0;
}

static inline int mapping_map_writable(struct address_space *mapping)
{
	return atomic_inc_unless_negative(&mapping->i_mmap_writable) ?
		0 : -EPERM;
}

static inline void mapping_unmap_writable(struct address_space *mapping)
{
	atomic_dec(&mapping->i_mmap_writable);
}

static inline int mapping_deny_writable(struct address_space *mapping)
{
	return atomic_dec_unless_positive(&mapping->i_mmap_writable) ?
		0 : -EBUSY;
}

static inline void mapping_allow_writable(struct address_space *mapping)
{
	atomic_inc(&mapping->i_mmap_writable);
}

/*
 * Use sequence counter to get consistent i_size on 32-bit processors.
 */
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __NEED_I_SIZE_ORDERED
#define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount)
#else
#define i_size_ordered_init(inode) do { } while (0)
#endif

struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))

#define IOP_FASTPERM	0x0001
#define IOP_LOOKUP	0x0002
#define IOP_NOFOLLOW	0x0004

/*
 * 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 timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
	unsigned int		i_blkbits;
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
	struct mutex		i_mutex;

	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;
	union {
		struct hlist_head	i_dentry;
		struct rcu_head		i_rcu;
	};
	u64			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;
	};

	__u32			i_generation;

#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
	struct hlist_head	i_fsnotify_marks;
#endif

	void			*i_private; /* fs or device private pointer */
};

static inline int inode_unhashed(struct inode *inode)
{
	return hlist_unhashed(&inode->i_hash);
}

/*
 * inode->i_mutex nesting subclasses for the lock validator:
 *
 * 0: the object of the current VFS operation
 * 1: parent
 * 2: child/target
 * 3: xattr
 * 4: second non-directory
 * 5: second parent (when locking independent directories in rename)
 *
 * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
 * non-directories at once.
 *
 * The locking order between these classes is
 * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
	I_MUTEX_XATTR,
	I_MUTEX_NONDIR2,
	I_MUTEX_PARENT2,
};

static inline void inode_lock(struct inode *inode)
{
	mutex_lock(&inode->i_mutex);
}

static inline void inode_unlock(struct inode *inode)
{
	mutex_unlock(&inode->i_mutex);
}

static inline int inode_trylock(struct inode *inode)
{
	return mutex_trylock(&inode->i_mutex);
}

static inline int inode_is_locked(struct inode *inode)
{
	return mutex_is_locked(&inode->i_mutex);
}

static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
{
	mutex_lock_nested(&inode->i_mutex, subclass);
}

void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);

/*
 * NOTE: in a 32bit arch with a preemptable kernel and
 * an UP compile the i_size_read/write must be atomic
 * with respect to the local cpu (unlike with preempt disabled),
 * but they don't need to be atomic with respect to other cpus like in
 * true SMP (so they need either to either locally disable irq around
 * the read or for example on x86 they can be still implemented as a
 * cmpxchg8b without the need of the lock prefix). For SMP compiles
 * and 64bit archs it makes no difference if preempt is enabled or not.
 */
static inline loff_t i_size_read(const struct inode *inode)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
	loff_t i_size;
	unsigned int seq;

	do {
		seq = read_seqcount_begin(&inode->i_size_seqcount);
		i_size = inode->i_size;
	} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
	return i_size;
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	loff_t i_size;

	preempt_disable();
	i_size = inode->i_size;
	preempt_enable();
	return i_size;
#else
	return inode->i_size;
#endif
}

/*
 * NOTE: unlike i_size_read(), i_size_write() does need locking around it
 * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
 * can be lost, resulting in subsequent i_size_read() calls spinning forever.
 */
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
	preempt_disable();
	write_seqcount_begin(&inode->i_size_seqcount);
	inode->i_size = i_size;
	write_seqcount_end(&inode->i_size_seqcount);
	preempt_enable();
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	preempt_disable();
	inode->i_size = i_size;
	preempt_enable();
#else
	inode->i_size = i_size;
#endif
}

/* Helper functions so that in most cases filesystems will
 * not need to deal directly with kuid_t and kgid_t and can
 * instead deal with the raw numeric values that are stored
 * in the filesystem.
 */
static inline uid_t i_uid_read(const struct inode *inode)
{
	return from_kuid(&init_user_ns, inode->i_uid);
}

static inline gid_t i_gid_read(const struct inode *inode)
{
	return from_kgid(&init_user_ns, inode->i_gid);
}

static inline void i_uid_write(struct inode *inode, uid_t uid)
{
	inode->i_uid = make_kuid(&init_user_ns, uid);
}

static inline void i_gid_write(struct inode *inode, gid_t gid)
{
	inode->i_gid = make_kgid(&init_user_ns, gid);
}

static inline unsigned iminor(const struct inode *inode)
{
	return MINOR(inode->i_rdev);
}

static inline unsigned imajor(const struct inode *inode)
{
	return MAJOR(inode->i_rdev);
}

extern struct block_device *I_BDEV(struct inode *inode);

struct fown_struct {
	rwlock_t lock;          /* protects pid, uid, euid fields */
	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
	enum pid_type pid_type;	/* Kind of process group SIGIO should be sent to */
	kuid_t uid, euid;	/* uid/euid of process setting the owner */
	int signum;		/* posix.1b rt signal to be delivered on IO */
};

/*
 * Track a single file's readahead state
 */
struct file_ra_state {
	pgoff_t start;			/* where readahead started */
	unsigned int size;		/* # of readahead pages */
	unsigned int async_size;	/* do asynchronous readahead when
					   there are only # of pages ahead */

	unsigned int ra_pages;		/* Maximum readahead window */
	unsigned int mmap_miss;		/* Cache miss stat for mmap accesses */
	loff_t prev_pos;		/* Cache last read() position */
};

/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
	return (index >= ra->start &&
		index <  ra->start + ra->size);
}

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;
	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;
} __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */

struct file_handle {
	__u32 handle_bytes;
	int handle_type;
	/* file identifier */
	unsigned char f_handle[0];
};

static inline struct file *get_file(struct file *f)
{
	atomic_long_inc(&f->f_count);
	return f;
}
#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
#define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
#define file_count(x)	atomic_long_read(&(x)->f_count)

#define	MAX_NON_LFS	((1UL<<31) - 1)

/* Page cache limit. The filesystems should put that into their s_maxbytes 
   limits, otherwise bad things can happen in VM. */ 
#if BITS_PER_LONG==32
#define MAX_LFS_FILESIZE	(((loff_t)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) 
#elif BITS_PER_LONG==64
#define MAX_LFS_FILESIZE 	((loff_t)0x7fffffffffffffffLL)
#endif

#define FL_POSIX	1
#define FL_FLOCK	2
#define FL_DELEG	4	/* NFSv4 delegation */
#define FL_ACCESS	8	/* not trying to lock, just looking */
#define FL_EXISTS	16	/* when unlocking, test for existence */
#define FL_LEASE	32	/* lease held on this file */
#define FL_CLOSE	64	/* unlock on close */
#define FL_SLEEP	128	/* A blocking lock */
#define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
#define FL_UNLOCK_PENDING	512 /* Lease is being broken */
#define FL_OFDLCK	1024	/* lock is "owned" by struct file */
#define FL_LAYOUT	2048	/* outstanding pNFS layout */

/*
 * Special return value from posix_lock_file() and vfs_lock_file() for
 * asynchronous locking.
 */
#define FILE_LOCK_DEFERRED 1

/* legacy typedef, should eventually be removed */
typedef void *fl_owner_t;

struct file_lock;

struct file_lock_operations {
	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
	void (*fl_release_private)(struct file_lock *);
};

struct lock_manager_operations {
	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
	unsigned long (*lm_owner_key)(struct file_lock *);
	fl_owner_t (*lm_get_owner)(fl_owner_t);
	void (*lm_put_owner)(fl_owner_t);
	void (*lm_notify)(struct file_lock *);	/* unblock callback */
	int (*lm_grant)(struct file_lock *, int);
	bool (*lm_break)(struct file_lock *);
	int (*lm_change)(struct file_lock *, int, struct list_head *);
	void (*lm_setup)(struct file_lock *, void **);
};

struct lock_manager {
	struct list_head list;
	/*
	 * NFSv4 and up also want opens blocked during the grace period;
	 * NLM doesn't care:
	 */
	bool block_opens;
};

struct net;
void locks_start_grace(struct net *, struct lock_manager *);
void locks_end_grace(struct lock_manager *);
int locks_in_grace(struct net *);
int opens_in_grace(struct net *);

/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>

/*
 * struct file_lock represents a generic "file lock". It's used to represent
 * POSIX byte range locks, BSD (flock) locks, and leases. It's important to
 * note that the same struct is used to represent both a request for a lock and
 * the lock itself, but the same object is never used for both.
 *
 * FIXME: should we create a separate "struct lock_request" to help distinguish
 * these two uses?
 *
 * The varous i_flctx lists are ordered by:
 *
 * 1) lock owner
 * 2) lock range start
 * 3) lock range end
 *
 * Obviously, the last two criteria only matter for POSIX locks.
 */
struct file_lock {
	struct file_lock *fl_next;	/* singly linked list for this inode  */
	struct list_head fl_list;	/* link into file_lock_context */
	struct hlist_node fl_link;	/* node in global lists */
	struct list_head fl_block;	/* circular list of blocked processes */
	fl_owner_t fl_owner;
	unsigned int fl_flags;
	unsigned char fl_type;
	unsigned int fl_pid;
	int fl_link_cpu;		/* what cpu's list is this on? */
	struct pid *fl_nspid;
	wait_queue_head_t fl_wait;
	struct file *fl_file;
	loff_t fl_start;
	loff_t fl_end;

	struct fasync_struct *	fl_fasync; /* for lease break notifications */
	/* for lease breaks: */
	unsigned long fl_break_time;
	unsigned long fl_downgrade_time;

	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
	union {
		struct nfs_lock_info	nfs_fl;
		struct nfs4_lock_info	nfs4_fl;
		struct {
			struct list_head link;	/* link in AFS vnode's pending_locks list */
			int state;		/* state of grant or error if -ve */
		} afs;
	} fl_u;
};

struct file_lock_context {
	spinlock_t		flc_lock;
	struct list_head	flc_flock;
	struct list_head	flc_posix;
	struct list_head	flc_lease;
};

/* The following constant reflects the upper bound of the file/locking space */
#ifndef OFFSET_MAX
#define INT_LIMIT(x)	(~((x)1 << (sizeof(x)*8 - 1)))
#define OFFSET_MAX	INT_LIMIT(loff_t)
#define OFFT_OFFSET_MAX	INT_LIMIT(off_t)
#endif

#include <linux/fcntl.h>

extern void send_sigio(struct fown_struct *fown, int fd, int band);

#ifdef CONFIG_FILE_LOCKING
extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *);
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
			struct flock __user *);

#if BITS_PER_LONG == 32
extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 __user *);
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
			struct flock64 __user *);
#endif

extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
extern int fcntl_getlease(struct file *filp);

/* fs/locks.c */
void locks_free_lock_context(struct inode *inode);
void locks_free_lock(struct file_lock *fl);
extern void locks_init_lock(struct file_lock *);
extern struct file_lock * locks_alloc_lock(void);
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_file(struct file *);
extern void locks_release_private(struct file_lock *);
extern void posix_test_lock(struct file *, struct file_lock *);
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
extern int posix_unblock_lock(struct file_lock *);
extern int vfs_test_lock(struct file *, struct file_lock *);
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
extern void lease_get_mtime(struct inode *, struct timespec *time);
extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
extern int lease_modify(struct file_lock *, int, struct list_head *);
struct files_struct;
extern void show_fd_locks(struct seq_file *f,
			 struct file *filp, struct files_struct *files);
#else /* !CONFIG_FILE_LOCKING */
static inline int fcntl_getlk(struct file *file, unsigned int cmd,
			      struct flock __user *user)
{
	return -EINVAL;
}

static inline int fcntl_setlk(unsigned int fd, struct file *file,
			      unsigned int cmd, struct flock __user *user)
{
	return -EACCES;
}

#if BITS_PER_LONG == 32
static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
				struct flock64 __user *user)
{
	return -EINVAL;
}

static inline int fcntl_setlk64(unsigned int fd, struct file *file,
				unsigned int cmd, struct flock64 __user *user)
{
	return -EACCES;
}
#endif
static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
{
	return -EINVAL;
}

static inline int fcntl_getlease(struct file *filp)
{
	return F_UNLCK;
}

static inline void
locks_free_lock_context(struct inode *inode)
{
}

static inline void locks_init_lock(struct file_lock *fl)
{
	return;
}

static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
{
	return;
}

static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
	return;
}

static inline void locks_remove_posix(struct file *filp, fl_owner_t owner)
{
	return;
}

static inline void locks_remove_file(struct file *filp)
{
	return;
}

static inline void posix_test_lock(struct file *filp, struct file_lock *fl)
{
	return;
}

static inline int posix_lock_file(struct file *filp, struct file_lock *fl,
				  struct file_lock *conflock)
{
	return -ENOLCK;
}

static inline int posix_unblock_lock(struct file_lock *waiter)
{
	return -ENOENT;
}

static inline int vfs_test_lock(struct file *filp, struct file_lock *fl)
{
	return 0;
}

static inline int vfs_lock_file(struct file *filp, unsigned int cmd,
				struct file_lock *fl, struct file_lock *conf)
{
	return -ENOLCK;
}

static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
{
	return 0;
}

static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl)
{
	return -ENOLCK;
}

static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
{
	return 0;
}

static inline void lease_get_mtime(struct inode *inode, struct timespec *time)
{
	return;
}

static inline int generic_setlease(struct file *filp, long arg,
				    struct file_lock **flp, void **priv)
{
	return -EINVAL;
}

static inline int vfs_setlease(struct file *filp, long arg,
			       struct file_lock **lease, void **priv)
{
	return -EINVAL;
}

static inline int lease_modify(struct file_lock *fl, int arg,
			       struct list_head *dispose)
{
	return -EINVAL;
}

struct files_struct;
static inline void show_fd_locks(struct seq_file *f,
			struct file *filp, struct files_struct *files) {}
#endif /* !CONFIG_FILE_LOCKING */

static inline struct inode *file_inode(const struct file *f)
{
	return f->f_inode;
}

static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
{
	return locks_lock_inode_wait(file_inode(filp), fl);
}

struct fasync_struct {
	spinlock_t		fa_lock;
	int			magic;
	int			fa_fd;
	struct fasync_struct	*fa_next; /* singly linked list */
	struct file		*fa_file;
	struct rcu_head		fa_rcu;
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *);
extern int fasync_remove_entry(struct file *, struct fasync_struct **);
extern struct fasync_struct *fasync_alloc(void);
extern void fasync_free(struct fasync_struct *);

/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);

extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
extern void f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
extern pid_t f_getown(struct file *filp);
extern int send_sigurg(struct fown_struct *fown);

struct mm_struct;

/*
 *	Umount options
 */

#define MNT_FORCE	0x00000001	/* Attempt to forcibily umount */
#define MNT_DETACH	0x00000002	/* Just detach from the tree */
#define MNT_EXPIRE	0x00000004	/* Mark for expiry */
#define UMOUNT_NOFOLLOW	0x00000008	/* Don't follow symlink on umount */
#define UMOUNT_UNUSED	0x80000000	/* Flag guaranteed to be unused */

/* sb->s_iflags */
#define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
#define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */

/* Possible states of 'frozen' field */
enum {
	SB_UNFROZEN = 0,		/* FS is unfrozen */
	SB_FREEZE_WRITE	= 1,		/* Writes, dir ops, ioctls frozen */
	SB_FREEZE_PAGEFAULT = 2,	/* Page faults stopped as well */
	SB_FREEZE_FS = 3,		/* For internal FS use (e.g. to stop
					 * internal threads if needed) */
	SB_FREEZE_COMPLETE = 4,		/* ->freeze_fs finished successfully */
};

#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)

struct sb_writers {
	int				frozen;		/* Is sb frozen? */
	wait_queue_head_t		wait_unfrozen;	/* for get_super_thawed() */
	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
};

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;

	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
	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;

	char s_id[32];				/* Informational name */
	u8 s_uuid[16];				/* UUID */

	void 			*s_fs_info;	/* Filesystem private info */
	unsigned int		s_max_links;
	fmode_t			s_mode;

	/* Granularity of c/m/atime in ns.
	   Cannot be worse than a second */
	u32		   s_time_gran;

	/*
	 * 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;

	/*
	 * Saved mount options for lazy filesystems using
	 * generic_show_options()
	 */
	char __rcu *s_options;
	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;

	/* 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;

	/*
	 * Keep the lru lists last in the structure so they always sit on their
	 * own individual cachelines.
	 */
	struct list_lru		s_dentry_lru ____cacheline_aligned_in_smp;
	struct list_lru		s_inode_lru ____cacheline_aligned_in_smp;
	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 */
};

extern struct timespec current_fs_time(struct super_block *sb);

/*
 * Snapshotting support.
 */

void __sb_end_write(struct super_block *sb, int level);
int __sb_start_write(struct super_block *sb, int level, bool wait);

#define __sb_writers_acquired(sb, lev)	\
	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
#define __sb_writers_release(sb, lev)	\
	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)

/**
 * sb_end_write - drop write access to a superblock
 * @sb: the super we wrote to
 *
 * Decrement number of writers to the filesystem. Wake up possible waiters
 * wanting to freeze the filesystem.
 */
static inline void sb_end_write(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_WRITE);
}

/**
 * sb_end_pagefault - drop write access to a superblock from a page fault
 * @sb: the super we wrote to
 *
 * Decrement number of processes handling write page fault to the filesystem.
 * Wake up possible waiters wanting to freeze the filesystem.
 */
static inline void sb_end_pagefault(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
}

/**
 * sb_end_intwrite - drop write access to a superblock for internal fs purposes
 * @sb: the super we wrote to
 *
 * Decrement fs-internal number of writers to the filesystem.  Wake up possible
 * waiters wanting to freeze the filesystem.
 */
static inline void sb_end_intwrite(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_FS);
}

/**
 * sb_start_write - get write access to a superblock
 * @sb: the super we write to
 *
 * When a process wants to write data or metadata to a file system (i.e. dirty
 * a page or an inode), it should embed the operation in a sb_start_write() -
 * sb_end_write() pair to get exclusion against file system freezing. This
 * function increments number of writers preventing freezing. If the file
 * system is already frozen, the function waits until the file system is
 * thawed.
 *
 * Since freeze protection behaves as a lock, users have to preserve
 * ordering of freeze protection and other filesystem locks. Generally,
 * freeze protection should be the outermost lock. In particular, we have:
 *
 * sb_start_write
 *   -> i_mutex			(write path, truncate, directory ops, ...)
 *   -> s_umount		(freeze_super, thaw_super)
 */
static inline void sb_start_write(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_WRITE, true);
}

static inline int sb_start_write_trylock(struct super_block *sb)
{
	return __sb_start_write(sb, SB_FREEZE_WRITE, false);
}

/**
 * sb_start_pagefault - get write access to a superblock from a page fault
 * @sb: the super we write to
 *
 * When a process starts handling write page fault, it should embed the
 * operation into sb_start_pagefault() - sb_end_pagefault() pair to get
 * exclusion against file system freezing. This is needed since the page fault
 * is going to dirty a page. This function increments number of running page
 * faults preventing freezing. If the file system is already frozen, the
 * function waits until the file system is thawed.
 *
 * Since page fault freeze protection behaves as a lock, users have to preserve
 * ordering of freeze protection and other filesystem locks. It is advised to
 * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault
 * handling code implies lock dependency:
 *
 * mmap_sem
 *   -> sb_start_pagefault
 */
static inline void sb_start_pagefault(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
}

/*
 * sb_start_intwrite - get write access to a superblock for internal fs purposes
 * @sb: the super we write to
 *
 * This is the third level of protection against filesystem freezing. It is
 * free for use by a filesystem. The only requirement is that it must rank
 * below sb_start_pagefault.
 *
 * For example filesystem can call sb_start_intwrite() when starting a
 * transaction which somewhat eases handling of freezing for internal sources
 * of filesystem changes (internal fs threads, discarding preallocation on file
 * close, etc.).
 */
static inline void sb_start_intwrite(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_FS, true);
}


extern bool inode_owner_or_capable(const struct inode *inode);

/*
 * VFS helper functions..
 */
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
extern int vfs_rmdir(struct inode *, struct dentry *);
extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
extern int vfs_whiteout(struct inode *, struct dentry *);

/*
 * VFS dentry helper functions.
 */
extern void dentry_unhash(struct dentry *dentry);

/*
 * VFS file helper functions.
 */
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
			umode_t mode);
/*
 * VFS FS_IOC_FIEMAP helper definitions.
 */
struct fiemap_extent_info {
	unsigned int fi_flags;		/* Flags as passed from user */
	unsigned int fi_extents_mapped;	/* Number of mapped extents */
	unsigned int fi_extents_max;	/* Size of fiemap_extent array */
	struct fiemap_extent __user *fi_extents_start; /* Start of
							fiemap_extent array */
};
int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
			    u64 phys, u64 len, u32 flags);
int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);

/*
 * File types
 *
 * NOTE! These match bits 12..15 of stat.st_mode
 * (ie "(i_mode >> 12) & 15").
 */
#define DT_UNKNOWN	0
#define DT_FIFO		1
#define DT_CHR		2
#define DT_DIR		4
#define DT_BLK		6
#define DT_REG		8
#define DT_LNK		10
#define DT_SOCK		12
#define DT_WHT		14

/*
 * This is the "filldir" function type, used by readdir() to let
 * the kernel specify what kind of dirent layout it wants to have.
 * This allows the kernel to read directories into kernel space or
 * to have different dirent layouts depending on the binary type.
 */
struct dir_context;
typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
			 unsigned);

struct dir_context {
	const filldir_t actor;
	loff_t pos;
};

struct block_device_operations;

/* These macros are for out of kernel modules to test that
 * the kernel supports the unlocked_ioctl and compat_ioctl
 * fields in struct file_operations. */
#define HAVE_COMPAT_IOCTL 1
#define HAVE_UNLOCKED_IOCTL 1

/*
 * These flags let !MMU mmap() govern direct device mapping vs immediate
 * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
 *
 * NOMMU_MAP_COPY:	Copy can be mapped (MAP_PRIVATE)
 * NOMMU_MAP_DIRECT:	Can be mapped directly (MAP_SHARED)
 * NOMMU_MAP_READ:	Can be mapped for reading
 * NOMMU_MAP_WRITE:	Can be mapped for writing
 * NOMMU_MAP_EXEC:	Can be mapped for execution
 */
#define NOMMU_MAP_COPY		0x00000001
#define NOMMU_MAP_DIRECT	0x00000008
#define NOMMU_MAP_READ		VM_MAYREAD
#define NOMMU_MAP_WRITE		VM_MAYWRITE
#define NOMMU_MAP_EXEC		VM_MAYEXEC

#define NOMMU_VMFLAGS \
	(NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)


struct iov_iter;

struct file_operations {
	struct module *owner;
	loff_t (*llseek) (struct file *, loff_t, int);
	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
	int (*iterate) (struct file *, struct dir_context *);
	unsigned int (*poll) (struct file *, struct poll_table_struct *);
	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
	int (*mmap) (struct file *, struct vm_area_struct *);
	int (*open) (struct inode *, struct file *);
	int (*flush) (struct file *, fl_owner_t id);
	int (*release) (struct inode *, struct file *);
	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
	int (*aio_fsync) (struct kiocb *, int datasync);
	int (*fasync) (int, struct file *, int);
	int (*lock) (struct file *, int, struct file_lock *);
	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
	int (*check_flags)(int);
	int (*flock) (struct file *, int, struct file_lock *);
	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
	int (*setlease)(struct file *, long, struct file_lock **, void **);
	long (*fallocate)(struct file *file, int mode, loff_t offset,
			  loff_t len);
	void (*show_fdinfo)(struct seq_file *m, struct file *f);
#ifndef CONFIG_MMU
	unsigned (*mmap_capabilities)(struct file *);
#endif
	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
			loff_t, size_t, unsigned int);
	int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t,
			u64);
	ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *,
			u64);
};

struct inode_operations {
	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
	const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
	int (*permission) (struct inode *, int);
	struct posix_acl * (*get_acl)(struct inode *, int);

	int (*readlink) (struct dentry *, char __user *,int);

	int (*create) (struct inode *,struct dentry *, umode_t, bool);
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct inode *,struct dentry *,const char *);
	int (*mkdir) (struct inode *,struct dentry *,umode_t);
	int (*rmdir) (struct inode *,struct dentry *);
	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
	int (*rename) (struct inode *, struct dentry *,
			struct inode *, struct dentry *);
	int (*rename2) (struct inode *, struct dentry *,
			struct inode *, struct dentry *, unsigned int);
	int (*setattr) (struct dentry *, struct iattr *);
	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
	ssize_t (*listxattr) (struct dentry *, char *, size_t);
	int (*removexattr) (struct dentry *, const char *);
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
		      u64 len);
	int (*update_time)(struct inode *, struct timespec *, int);
	int (*atomic_open)(struct inode *, struct dentry *,
			   struct file *, unsigned open_flag,
			   umode_t create_mode, int *opened);
	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
	int (*set_acl)(struct inode *, struct posix_acl *, int);
} ____cacheline_aligned;

ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
			      unsigned long nr_segs, unsigned long fast_segs,
			      struct