X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=include%2Flinux%2Ffs.h;h=72feb9716043048dfac27ee3656750d7916ec62d;hb=refs%2Fheads%2Fvserver;hp=71e297368e9b4f9a1e5b81340c2144aadcf21853;hpb=9213980e6a70d8473e0ffd4b39ab5b6caaba9ff5;p=linux-2.6.git diff --git a/include/linux/fs.h b/include/linux/fs.h index 71e297368..72feb9716 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -6,27 +6,8 @@ * structures etc. */ -#include -#include #include -#include -#include -#include #include -#include -#include -#include -#include -#include -#include - -struct iovec; -struct nameidata; -struct pipe_inode_info; -struct poll_table_struct; -struct kstatfs; -struct vm_area_struct; -struct vfsmount; /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change @@ -46,6 +27,10 @@ struct vfsmount; #define BLOCK_SIZE_BITS 10 #define BLOCK_SIZE (1<i_sb->s_flags & (flg)) -#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY) +#define IS_RDONLY(inode) __IS_FLG(inode, MS_RDONLY) #define IS_SYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK) +#define IS_TAGGED(inode) __IS_FLG(inode, MS_TAGGED) -#define IS_QUOTAINIT(inode) ((inode)->i_flags & S_QUOTA) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) #define IS_IUNLINK(inode) ((inode)->i_flags & S_IUNLINK) #define IS_IXORUNLINK(inode) ((IS_IUNLINK(inode) ? S_IMMUTABLE : 0) ^ IS_IMMUTABLE(inode)) -#define IS_NOATIME(inode) (__IS_FLG(inode, MS_NOATIME) || ((inode)->i_flags & S_NOATIME)) -#define IS_NODIRATIME(inode) __IS_FLG(inode, MS_NODIRATIME) #define IS_POSIXACL(inode) __IS_FLG(inode, MS_POSIXACL) -#define IS_ONE_SECOND(inode) __IS_FLG(inode, MS_ONE_SECOND) #define IS_BARRIER(inode) (S_ISDIR((inode)->i_mode) && ((inode)->i_flags & S_BARRIER)) #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) +#define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) +#define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) + +#ifdef CONFIG_VSERVER_COWBL +# define IS_COW(inode) (IS_IUNLINK(inode) && IS_IMMUTABLE(inode)) +# define IS_COW_LINK(inode) (S_ISREG((inode)->i_mode) && ((inode)->i_nlink > 1)) +#else +# define IS_COW(inode) (0) +# define IS_COW_LINK(inode) (0) +#endif /* the read-only stuff doesn't really belong here, but any other place is probably as bad and I don't want to create yet another include file. */ @@ -210,33 +225,107 @@ extern int leases_enable, dir_notify_enable, lease_break_time; #define BLKBSZGET _IOR(0x12,112,size_t) #define BLKBSZSET _IOW(0x12,113,size_t) #define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */ +#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup) +#define BLKTRACESTART _IO(0x12,116) +#define BLKTRACESTOP _IO(0x12,117) +#define BLKTRACETEARDOWN _IO(0x12,118) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ #define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */ +#define FS_IOC_GETFLAGS _IOR('f', 1, long) +#define FS_IOC_SETFLAGS _IOW('f', 2, long) +#define FS_IOC_GETVERSION _IOR('v', 1, long) +#define FS_IOC_SETVERSION _IOW('v', 2, long) +#define FS_IOC32_GETFLAGS _IOR('f', 1, int) +#define FS_IOC32_SETFLAGS _IOW('f', 2, int) +#define FS_IOC32_GETVERSION _IOR('v', 1, int) +#define FS_IOC32_SETVERSION _IOW('v', 2, int) + +/* + * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) + */ +#define FS_SECRM_FL 0x00000001 /* Secure deletion */ +#define FS_UNRM_FL 0x00000002 /* Undelete */ +#define FS_COMPR_FL 0x00000004 /* Compress file */ +#define FS_SYNC_FL 0x00000008 /* Synchronous updates */ +#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define FS_APPEND_FL 0x00000020 /* writes to file may only append */ +#define FS_NODUMP_FL 0x00000040 /* do not dump file */ +#define FS_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define FS_DIRTY_FL 0x00000100 +#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define FS_NOCOMP_FL 0x00000400 /* Don't compress */ +#define FS_ECOMPR_FL 0x00000800 /* Compression error */ +/* End compression flags --- maybe not all used */ +#define FS_BTREE_FL 0x00001000 /* btree format dir */ +#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define FS_IMAGIC_FL 0x00002000 /* AFS directory */ +#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */ +#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define FS_EXTENT_FL 0x00080000 /* Extents */ +#define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */ +#define FS_BARRIER_FL 0x04000000 /* Barrier for chroot() */ +#define FS_IUNLINK_FL 0x08000000 /* Immutable unlink */ +#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ + +#ifdef CONFIG_VSERVER_LEGACY +#define FS_FL_USER_VISIBLE 0x0803DFFF /* User visible flags */ +#define FS_FL_USER_MODIFIABLE 0x080380FF /* User modifiable flags */ +#else +#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ +#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ +#endif + +#define SYNC_FILE_RANGE_WAIT_BEFORE 1 +#define SYNC_FILE_RANGE_WRITE 2 +#define SYNC_FILE_RANGE_WAIT_AFTER 4 + #ifdef __KERNEL__ +#include +#include +#include +#include +#include +#include +#include +#include +#include #include #include -#include +#include +#include +#include +#include + +#include #include #include -/* Used to be a macro which just called the function, now just a function */ -extern void update_atime (struct inode *); +struct hd_geometry; +struct iovec; +struct nameidata; +struct kiocb; +struct pipe_inode_info; +struct poll_table_struct; +struct kstatfs; +struct vm_area_struct; +struct vfsmount; -extern void inode_init(unsigned long); -extern void mnt_init(unsigned long); -extern void files_init(unsigned long); +extern void __init inode_init(unsigned long); +extern void __init inode_init_early(void); +extern void __init mnt_init(unsigned long); +extern void __init files_init(unsigned long); struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); -typedef int (get_blocks_t)(struct inode *inode, sector_t iblock, - unsigned long max_blocks, - struct buffer_head *bh_result, int create); -typedef void (dio_iodone_t)(struct inode *inode, loff_t offset, +typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); /* @@ -256,7 +345,8 @@ typedef void (dio_iodone_t)(struct inode *inode, loff_t offset, #define ATTR_ATTR_FLAG 1024 #define ATTR_KILL_SUID 2048 #define ATTR_KILL_SGID 4096 -#define ATTR_XID 8192 +#define ATTR_FILE 8192 +#define ATTR_TAG 16384 /* * This is the Inode Attributes structure, used for notify_change(). It @@ -272,22 +362,19 @@ struct iattr { umode_t ia_mode; uid_t ia_uid; gid_t ia_gid; - xid_t ia_xid; + tag_t ia_tag; loff_t ia_size; struct timespec ia_atime; struct timespec ia_mtime; struct timespec ia_ctime; - unsigned int ia_attr_flags; -}; -/* - * This is the inode attributes flag definitions - */ -#define ATTR_FLAG_SYNCRONOUS 1 /* Syncronous write */ -#define ATTR_FLAG_NOATIME 2 /* Don't update atime */ -#define ATTR_FLAG_APPEND 4 /* Append-only file */ -#define ATTR_FLAG_IMMUTABLE 8 /* Immutable file */ -#define ATTR_FLAG_NODIRATIME 16 /* Don't update atime for directory */ + /* + * Not an attribute, but an auxilary 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; +}; #define ATTR_FLAG_BARRIER 512 /* Barrier for chroot() */ #define ATTR_FLAG_IUNLINK 1024 /* Immutable unlink */ @@ -297,23 +384,53 @@ struct iattr { */ #include +/** + * 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(), prepare_write(), and commit_write(). + * + * 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, +}; + /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; -struct kiocb; struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); - int (*sync_page)(struct page *); + void (*sync_page)(struct page *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); - /* Set a page dirty */ + /* 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, @@ -327,44 +444,59 @@ struct address_space_operations { int (*commit_write)(struct file *, struct page *, unsigned, unsigned); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); - int (*invalidatepage) (struct page *, unsigned long); - int (*releasepage) (struct page *, int); + void (*invalidatepage) (struct page *, unsigned long); + int (*releasepage) (struct page *, gfp_t); ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, loff_t offset, unsigned long nr_segs); + struct page* (*get_xip_page)(struct address_space *, sector_t, + int); + /* migrate the contents of a page to the specified target */ + int (*migratepage) (struct address_space *, + struct page *, struct page *); + int (*launder_page) (struct page *); }; struct backing_dev_info; 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 spinlock protecting it */ - unsigned long nrpages; /* number of total pages */ - pgoff_t writeback_index;/* writeback starts here */ - struct address_space_operations *a_ops; /* methods */ - struct prio_tree_root i_mmap; /* tree of private mappings */ + rwlock_t tree_lock; /* and rwlock protecting it */ unsigned int i_mmap_writable;/* count VM_SHARED mappings */ + struct prio_tree_root i_mmap; /* tree of private and shared mappings */ struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ spinlock_t i_mmap_lock; /* protect tree, count, list */ - atomic_t truncate_count; /* Cover race condition with truncate */ + unsigned int truncate_count; /* Cover race condition with truncate */ + unsigned long nrpages; /* number of total pages */ + pgoff_t writeback_index;/* writeback starts here */ + const struct address_space_operations *a_ops; /* methods */ unsigned long flags; /* error bits/gfp mask */ struct backing_dev_info *backing_dev_info; /* device readahead, etc */ spinlock_t private_lock; /* for use by the address_space */ struct list_head private_list; /* ditto */ struct address_space *assoc_mapping; /* 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 signficant bit + * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. + */ struct block_device { dev_t bd_dev; /* not a kdev_t - it's a search key */ struct inode * bd_inode; /* will die */ int bd_openers; - struct semaphore bd_sem; /* open/close mutex */ - struct semaphore bd_mount_sem; /* mount mutex */ + struct mutex bd_mutex; /* open/close mutex */ + struct semaphore bd_mount_sem; struct list_head bd_inodes; void * bd_holder; int bd_holders; +#ifdef CONFIG_SYSFS + struct list_head bd_holder_list; +#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; @@ -422,29 +554,32 @@ static inline int mapping_writably_mapped(struct address_space *mapping) struct inode { struct hlist_node i_hash; struct list_head i_list; + struct list_head i_sb_list; struct list_head i_dentry; unsigned long i_ino; atomic_t i_count; - umode_t i_mode; unsigned int i_nlink; uid_t i_uid; gid_t i_gid; - xid_t i_xid; + tag_t i_tag; dev_t i_rdev; + unsigned long i_version; loff_t i_size; +#ifdef __NEED_I_SIZE_ORDERED + seqcount_t i_size_seqcount; +#endif struct timespec i_atime; struct timespec i_mtime; struct timespec i_ctime; unsigned int i_blkbits; - unsigned long i_blksize; - unsigned long i_version; - unsigned long i_blocks; + blkcnt_t i_blocks; unsigned short i_bytes; + umode_t i_mode; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ - struct semaphore i_sem; + struct mutex i_mutex; struct rw_semaphore i_alloc_sem; struct inode_operations *i_op; - struct file_operations *i_fop; /* former ->i_op->default_file_ops */ + const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct super_block *i_sb; struct file_lock *i_flock; struct address_space *i_mapping; @@ -452,33 +587,61 @@ struct inode { #ifdef CONFIG_QUOTA struct dquot *i_dquot[MAXQUOTAS]; #endif - /* These three should probably be a union */ struct list_head i_devices; - struct pipe_inode_info *i_pipe; - struct block_device *i_bdev; - struct cdev *i_cdev; + union { + struct pipe_inode_info *i_pipe; + struct block_device *i_bdev; + struct cdev *i_cdev; + }; int i_cindex; + __u32 i_generation; + +#ifdef CONFIG_DNOTIFY unsigned long i_dnotify_mask; /* Directory notify events */ struct dnotify_struct *i_dnotify; /* for directory notifications */ +#endif + +#ifdef CONFIG_INOTIFY + struct list_head inotify_watches; /* watches on this inode */ + struct mutex inotify_mutex; /* protects the watches list */ +#endif unsigned long i_state; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned int i_flags; - unsigned char i_sock; atomic_t i_writecount; +#ifdef CONFIG_SECURITY void *i_security; - __u32 i_generation; - union { - void *generic_ip; - } u; -#ifdef __NEED_I_SIZE_ORDERED - seqcount_t i_size_seqcount; #endif + void *i_private; /* fs or device private pointer */ }; +/* + * inode->i_mutex nesting subclasses for the lock validator: + * + * 0: the object of the current VFS operation + * 1: parent + * 2: child/target + * 3: quota file + * + * The locking order between these classes is + * parent -> child -> normal -> xattr -> quota + */ +enum inode_i_mutex_lock_class +{ + I_MUTEX_NORMAL, + I_MUTEX_PARENT, + I_MUTEX_CHILD, + I_MUTEX_XATTR, + I_MUTEX_QUOTA +}; + +extern void inode_double_lock(struct inode *inode1, struct inode *inode2); +extern void inode_double_unlock(struct inode *inode1, struct inode *inode2); + /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic @@ -489,7 +652,7 @@ struct inode { * 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(struct inode *inode) +static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; @@ -512,7 +675,11 @@ static inline loff_t i_size_read(struct inode *inode) #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) @@ -528,12 +695,12 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) #endif } -static inline unsigned iminor(struct inode *inode) +static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } -static inline unsigned imajor(struct inode *inode) +static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } @@ -542,9 +709,9 @@ extern struct block_device *I_BDEV(struct inode *inode); struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ - int pid; /* pid or -pgrp where SIGIO should be sent */ + 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 */ uid_t uid, euid; /* uid/euid of process setting the owner */ - void *security; int signum; /* posix.1b rt signal to be delivered on IO */ }; @@ -554,34 +721,45 @@ struct fown_struct { struct file_ra_state { unsigned long start; /* Current window */ unsigned long size; - unsigned long next_size; /* Next window size */ + unsigned long flags; /* ra flags RA_FLAG_xxx*/ + unsigned long cache_hit; /* cache hit count*/ unsigned long prev_page; /* Cache last read() position */ unsigned long ahead_start; /* Ahead window */ unsigned long ahead_size; - unsigned long serial_cnt; /* measure of sequentiality */ - unsigned long average; /* another measure of sequentiality */ unsigned long ra_pages; /* Maximum readahead window */ unsigned long mmap_hit; /* Cache hit stat for mmap accesses */ unsigned long mmap_miss; /* Cache miss stat for mmap accesses */ + unsigned int offset; /* Offset where last read() ended in a page */ }; +#define RA_FLAG_MISS 0x01 /* a cache miss occured against this file */ +#define RA_FLAG_INCACHE 0x02 /* file is already in cache */ struct file { - struct list_head f_list; - struct dentry *f_dentry; - struct vfsmount *f_vfsmnt; - struct file_operations *f_op; + /* + * fu_list becomes invalid after file_free is called and queued via + * fu_rcuhead for RCU freeing + */ + union { + struct list_head fu_list; + struct rcu_head fu_rcuhead; + } f_u; + struct path f_path; +#define f_dentry f_path.dentry +#define f_vfsmnt f_path.mnt + const struct file_operations *f_op; atomic_t f_count; unsigned int f_flags; mode_t f_mode; - int f_error; loff_t f_pos; struct fown_struct f_owner; unsigned int f_uid, f_gid; + xid_t f_xid; struct file_ra_state f_ra; unsigned long f_version; +#ifdef CONFIG_SECURITY void *f_security; - +#endif /* needed for tty driver, and maybe others */ void *private_data; @@ -599,11 +777,6 @@ extern spinlock_t files_lock; #define get_file(x) atomic_inc(&(x)->f_count) #define file_count(x) atomic_read(&(x)->f_count) -/* Initialize and open a private file and allocate its security structure. */ -extern int open_private_file(struct file *, struct dentry *, int); -/* Release a private file and free its security structure. */ -extern void close_private_file(struct file *file); - #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes @@ -617,8 +790,9 @@ extern void close_private_file(struct file *file); #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_ACCESS 8 /* not trying to lock, just looking */ -#define FL_LOCKD 16 /* lock held by rpc.lockd */ +#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 */ /* @@ -630,6 +804,23 @@ extern void close_private_file(struct file *file); */ typedef struct files_struct *fl_owner_t; +struct file_lock_operations { + void (*fl_insert)(struct file_lock *); /* lock insertion callback */ + void (*fl_remove)(struct file_lock *); /* lock removal callback */ + void (*fl_copy_lock)(struct file_lock *, struct file_lock *); + void (*fl_release_private)(struct file_lock *); +}; + +struct lock_manager_operations { + int (*fl_compare_owner)(struct file_lock *, struct file_lock *); + void (*fl_notify)(struct file_lock *); /* unblock callback */ + void (*fl_copy_lock)(struct file_lock *, struct file_lock *); + void (*fl_release_private)(struct file_lock *); + void (*fl_break)(struct file_lock *); + int (*fl_mylease)(struct file_lock *, struct file_lock *); + int (*fl_change)(struct file_lock **, int); +}; + /* that will die - we need it for nfs_lock_info */ #include @@ -645,16 +836,16 @@ struct file_lock { unsigned char fl_type; loff_t fl_start; loff_t fl_end; - - void (*fl_notify)(struct file_lock *); /* unblock callback */ - void (*fl_insert)(struct file_lock *); /* lock insertion callback */ - void (*fl_remove)(struct file_lock *); /* lock removal callback */ + xid_t fl_xid; struct fasync_struct * fl_fasync; /* for lease break notifications */ unsigned long fl_break_time; /* for nonblocking lease breaks */ + struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ + struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; + struct nfs4_lock_info nfs4_fl; } fl_u; }; @@ -665,40 +856,43 @@ struct file_lock { #define OFFT_OFFSET_MAX INT_LIMIT(off_t) #endif -extern struct list_head file_lock_list; - #include -extern long generic_file_fcntl(int fd, unsigned int cmd, - unsigned long arg, struct file *filp); - extern int fcntl_getlk(struct file *, struct flock __user *); -extern int fcntl_setlk(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 *, struct flock64 __user *); -extern int fcntl_setlk64(struct file *, unsigned int, struct flock64 __user *); +extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, + struct flock64 __user *); #endif extern void send_sigio(struct fown_struct *fown, int fd, int band); extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); +/* fs/sync.c */ +extern int do_sync_file_range(struct file *file, loff_t offset, loff_t endbyte, + unsigned int flags); + /* fs/locks.c */ extern void locks_init_lock(struct file_lock *); extern void locks_copy_lock(struct file_lock *, struct file_lock *); extern void locks_remove_posix(struct file *, fl_owner_t); extern void locks_remove_flock(struct file *); -extern struct file_lock *posix_test_lock(struct file *, struct file_lock *); +extern int posix_test_lock(struct file *, struct file_lock *, struct file_lock *); +extern int posix_lock_file_conf(struct file *, struct file_lock *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *); -extern void posix_block_lock(struct file_lock *, struct file_lock *); -extern void posix_unblock_lock(struct file *, struct file_lock *); -extern int posix_locks_deadlock(struct file_lock *, struct file_lock *); +extern int posix_lock_file_wait(struct file *, struct file_lock *); +extern int posix_unblock_lock(struct file *, struct file_lock *); +extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags); extern void lease_get_mtime(struct inode *, struct timespec *time); +extern int setlease(struct file *, long, struct file_lock **); +extern int lease_modify(struct file_lock **, int); extern int lock_may_read(struct inode *, loff_t start, unsigned long count); extern int lock_may_write(struct inode *, loff_t start, unsigned long count); -extern void steal_locks(fl_owner_t from); struct fasync_struct { int magic; @@ -716,8 +910,10 @@ extern void kill_fasync(struct fasync_struct **, int, int); /* only for net: no internal synchronization */ extern void __kill_fasync(struct fasync_struct *, int, int); +extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int 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); /* @@ -726,6 +922,7 @@ extern int send_sigurg(struct fown_struct *fown); #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ +#define MNT_EXPIRE 0x00000004 /* Mark for expiry */ extern struct list_head super_blocks; extern spinlock_t sb_lock; @@ -736,7 +933,6 @@ struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned long s_blocksize; - unsigned long s_old_blocksize; unsigned char s_blocksize_bits; unsigned char s_dirt; unsigned long long s_maxbytes; /* Max file size */ @@ -749,13 +945,17 @@ struct super_block { unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; - struct semaphore s_lock; + struct mutex s_lock; int s_count; int s_syncing; int s_need_sync_fs; atomic_t s_active; +#ifdef CONFIG_SECURITY void *s_security; +#endif + struct xattr_handler **s_xattr; + struct list_head s_inodes; /* all inodes */ struct list_head s_dirty; /* dirty inodes */ struct list_head s_io; /* parked for writeback */ struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */ @@ -776,9 +976,15 @@ struct super_block { * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ - struct semaphore s_vfs_rename_sem; /* Kludge */ + struct mutex s_vfs_rename_mutex; /* Kludge */ + + /* Granularity of c/m/atime in ns. + Cannot be worse than a second */ + u32 s_time_gran; }; +extern struct timespec current_fs_time(struct super_block *sb); + /* * Snapshotting support. */ @@ -791,31 +997,37 @@ enum { #define vfs_check_frozen(sb, level) \ wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level))) -/* - * Superblock locking. - */ -static inline void lock_super(struct super_block * sb) -{ - down(&sb->s_lock); -} +#define get_fs_excl() atomic_inc(¤t->fs_excl) +#define put_fs_excl() atomic_dec(¤t->fs_excl) +#define has_fs_excl() atomic_read(¤t->fs_excl) -static inline void unlock_super(struct super_block * sb) -{ - up(&sb->s_lock); -} +/* not quite ready to be deprecated, but... */ +extern void lock_super(struct super_block *); +extern void unlock_super(struct super_block *); /* * VFS helper functions.. */ +extern int vfs_permission(struct nameidata *, int); extern int vfs_create(struct inode *, struct dentry *, int, struct nameidata *); -extern int vfs_mkdir(struct inode *, struct dentry *, int); -extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t); -extern int vfs_symlink(struct inode *, struct dentry *, const char *, int); -extern int vfs_link(struct dentry *, struct inode *, struct dentry *); -extern int vfs_rmdir(struct inode *, struct dentry *); -extern int vfs_unlink(struct inode *, struct dentry *); +extern int vfs_mkdir(struct inode *, struct dentry *, int, struct nameidata *); +extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t, struct nameidata *); +extern int vfs_symlink(struct inode *, struct dentry *, const char *, int, struct nameidata *); +extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct nameidata *); +extern int vfs_rmdir(struct inode *, struct dentry *, struct nameidata *); +extern int vfs_unlink(struct inode *, struct dentry *, struct nameidata *); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); +/* + * VFS dentry helper functions. + */ +extern void dentry_unhash(struct dentry *dentry); + +/* + * VFS file helper functions. + */ +extern int file_permission(struct file *, int); + /* * File types * @@ -832,20 +1044,29 @@ extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct de #define DT_SOCK 12 #define DT_WHT 14 +#define OSYNC_METADATA (1<<0) +#define OSYNC_DATA (1<<1) +#define OSYNC_INODE (1<<2) +int generic_osync_inode(struct inode *, struct address_space *, int); + /* * 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. */ -typedef int (*filldir_t)(void *, const char *, int, loff_t, ino_t, unsigned); +typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned); struct block_device_operations { int (*open) (struct inode *, struct file *); int (*release) (struct inode *, struct file *); int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long); + long (*unlocked_ioctl) (struct file *, unsigned, unsigned long); + long (*compat_ioctl) (struct file *, unsigned, unsigned long); + int (*direct_access) (struct block_device *, sector_t, unsigned long *); int (*media_changed) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); + int (*getgeo)(struct block_device *, struct hd_geometry *); struct module *owner; }; @@ -861,42 +1082,54 @@ struct block_device_operations { typedef struct { size_t written; size_t count; - char __user * buf; + 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); +/* 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 + /* * NOTE: - * read, write, poll, fsync, readv, writev can be called - * without the big kernel lock held in all filesystems. + * read, write, poll, fsync, readv, writev, unlocked_ioctl and compat_ioctl + * can be called without the big kernel lock held in all filesystems. */ 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 (*aio_read) (struct kiocb *, char __user *, size_t, loff_t); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t); + ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); + ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long); + 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 *); + int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, struct dentry *, 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 (*readv) (struct file *, const struct iovec *, unsigned long, loff_t *); - ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, loff_t *); - ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void __user *); + ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void *); 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); - long (*fcntl)(int fd, unsigned int cmd, - unsigned long arg, struct file *filp); + int (*check_flags)(int); + int (*dir_notify)(struct file *filp, unsigned long arg); + 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); }; struct inode_operations { @@ -911,7 +1144,8 @@ struct inode_operations { int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *); int (*readlink) (struct dentry *, char __user *,int); - int (*follow_link) (struct dentry *, struct nameidata *); + void * (*follow_link) (struct dentry *, struct nameidata *); + void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); int (*permission) (struct inode *, int, struct nameidata *); int (*setattr) (struct dentry *, struct iattr *); @@ -920,16 +1154,24 @@ struct inode_operations { ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); + void (*truncate_range)(struct inode *, loff_t, loff_t); + int (*sync_flags) (struct inode *); }; struct seq_file; +ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, + unsigned long nr_segs, unsigned long fast_segs, + struct iovec *fast_pointer, + struct iovec **ret_pointer); + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *); extern ssize_t vfs_writev(struct file *, const struct iovec __user *, unsigned long, loff_t *); +ssize_t vfs_sendfile(struct file *, struct file *, loff_t *, size_t, loff_t); /* * NOTE: write_inode, delete_inode, clear_inode, put_inode can be called @@ -942,7 +1184,7 @@ struct super_operations { void (*read_inode) (struct inode *); void (*dirty_inode) (struct inode *); - void (*write_inode) (struct inode *, int); + int (*write_inode) (struct inode *, int); void (*put_inode) (struct inode *); void (*drop_inode) (struct inode *); void (*delete_inode) (struct inode *); @@ -951,22 +1193,29 @@ struct super_operations { int (*sync_fs)(struct super_block *sb, int wait); void (*write_super_lockfs) (struct super_block *); void (*unlockfs) (struct super_block *); - int (*statfs) (struct super_block *, struct kstatfs *); + int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*clear_inode) (struct inode *); - void (*umount_begin) (struct super_block *); + void (*umount_begin) (struct vfsmount *, int); int (*show_options)(struct seq_file *, struct vfsmount *); + int (*show_stats)(struct seq_file *, struct vfsmount *); +#ifdef CONFIG_QUOTA + ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); + ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); +#endif }; /* Inode state bits. Protected by inode_lock. */ #define I_DIRTY_SYNC 1 /* Not dirty enough for O_DATASYNC */ #define I_DIRTY_DATASYNC 2 /* Data-related inode changes pending */ #define I_DIRTY_PAGES 4 /* Data-related inode changes pending */ -#define I_LOCK 8 +#define __I_LOCK 3 +#define I_LOCK (1 << __I_LOCK) #define I_FREEING 16 #define I_CLEAR 32 #define I_NEW 64 +#define I_WILL_FREE 128 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) @@ -981,97 +1230,126 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } -static inline void touch_atime(struct vfsmount *mnt, struct dentry *dentry) +static inline void inc_nlink(struct inode *inode) +{ + inode->i_nlink++; +} + +static inline void inode_inc_link_count(struct inode *inode) +{ + inc_nlink(inode); + mark_inode_dirty(inode); +} + +static inline void drop_nlink(struct inode *inode) +{ + inode->i_nlink--; +} + +static inline void clear_nlink(struct inode *inode) +{ + inode->i_nlink = 0; +} + +static inline void inode_dec_link_count(struct inode *inode) { - /* per-mountpoint checks will go here */ - update_atime(dentry->d_inode); + drop_nlink(inode); + mark_inode_dirty(inode); } +extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry); static inline void file_accessed(struct file *file) { - touch_atime(file->f_vfsmnt, file->f_dentry); + if (!(file->f_flags & O_NOATIME)) + touch_atime(file->f_path.mnt, file->f_path.dentry); } int sync_inode(struct inode *inode, struct writeback_control *wbc); /** - * &export_operations - for nfsd to communicate with file systems - * decode_fh: decode a file handle fragment and return a &struct dentry - * encode_fh: encode a file handle fragment from a dentry - * get_name: find the name for a given inode in a given directory - * get_parent: find the parent of a given directory - * get_dentry: find a dentry for the inode given a file handle sub-fragment + * struct export_operations - for nfsd to communicate with file systems + * @decode_fh: decode a file handle fragment and return a &struct dentry + * @encode_fh: encode a file handle fragment from a dentry + * @get_name: find the name for a given inode in a given directory + * @get_parent: find the parent of a given directory + * @get_dentry: find a dentry for the inode given a file handle sub-fragment + * @find_exported_dentry: + * set by the exporting module to a standard helper function. * * Description: * The export_operations structure provides a means for nfsd to communicate * with a particular exported file system - particularly enabling nfsd and * the filesystem to co-operate when dealing with file handles. * - * export_operations contains two basic operation for dealing with file handles, - * decode_fh() and encode_fh(), and allows for some other operations to be defined - * which standard helper routines use to get specific information from the - * filesystem. + * export_operations contains two basic operation for dealing with file + * handles, decode_fh() and encode_fh(), and allows for some other + * operations to be defined which standard helper routines use to get + * specific information from the filesystem. * * nfsd encodes information use to determine which filesystem a filehandle - * applies to in the initial part of the file handle. The remainder, termed a - * file handle fragment, is controlled completely by the filesystem. - * The standard helper routines assume that this fragment will contain one or two - * sub-fragments, one which identifies the file, and one which may be used to - * identify the (a) directory containing the file. + * applies to in the initial part of the file handle. The remainder, termed + * a file handle fragment, is controlled completely by the filesystem. The + * standard helper routines assume that this fragment will contain one or + * two sub-fragments, one which identifies the file, and one which may be + * used to identify the (a) directory containing the file. * * In some situations, nfsd needs to get a dentry which is connected into a - * specific part of the file tree. To allow for this, it passes the function - * acceptable() together with a @context which can be used to see if the dentry - * is acceptable. As there can be multiple dentrys for a given file, the filesystem - * should check each one for acceptability before looking for the next. As soon - * as an acceptable one is found, it should be returned. + * specific part of the file tree. To allow for this, it passes the + * function acceptable() together with a @context which can be used to see + * if the dentry is acceptable. As there can be multiple dentrys for a + * given file, the filesystem should check each one for acceptability before + * looking for the next. As soon as an acceptable one is found, it should + * be returned. * * decode_fh: - * @decode_fh is given a &struct super_block (@sb), a file handle fragment (@fh, @fh_len) - * and an acceptability testing function (@acceptable, @context). It should return - * a &struct dentry which refers to the same file that the file handle fragment refers - * to, and which passes the acceptability test. If it cannot, it should return - * a %NULL pointer if the file was found but no acceptable &dentries were available, or - * a %ERR_PTR error code indicating why it couldn't be found (e.g. %ENOENT or %ENOMEM). + * @decode_fh is given a &struct super_block (@sb), a file handle fragment + * (@fh, @fh_len) and an acceptability testing function (@acceptable, + * @context). It should return a &struct dentry which refers to the same + * file that the file handle fragment refers to, and which passes the + * acceptability test. If it cannot, it should return a %NULL pointer if + * the file was found but no acceptable &dentries were available, or a + * %ERR_PTR error code indicating why it couldn't be found (e.g. %ENOENT or + * %ENOMEM). * * encode_fh: - * @encode_fh should store in the file handle fragment @fh (using at most @max_len bytes) - * information that can be used by @decode_fh to recover the file refered to by the - * &struct dentry @de. If the @connectable flag is set, the encode_fh() should store - * sufficient information so that a good attempt can be made to find not only - * the file but also it's place in the filesystem. This typically means storing - * a reference to de->d_parent in the filehandle fragment. - * encode_fh() should return the number of bytes stored or a negative error code - * such as %-ENOSPC + * @encode_fh should store in the file handle fragment @fh (using at most + * @max_len bytes) information that can be used by @decode_fh to recover the + * file refered to by the &struct dentry @de. If the @connectable flag is + * set, the encode_fh() should store sufficient information so that a good + * attempt can be made to find not only the file but also it's place in the + * filesystem. This typically means storing a reference to de->d_parent in + * the filehandle fragment. encode_fh() should return the number of bytes + * stored or a negative error code such as %-ENOSPC * * get_name: - * @get_name should find a name for the given @child in the given @parent directory. - * The name should be stored in the @name (with the understanding that it is already - * pointing to a a %NAME_MAX+1 sized buffer. get_name() should return %0 on success, - * a negative error code or error. - * @get_name will be called without @parent->i_sem held. + * @get_name should find a name for the given @child in the given @parent + * directory. The name should be stored in the @name (with the + * understanding that it is already pointing to a a %NAME_MAX+1 sized + * buffer. get_name() should return %0 on success, a negative error code + * or error. @get_name will be called without @parent->i_mutex held. * * get_parent: - * @get_parent should find the parent directory for the given @child which is also - * a directory. In the event that it cannot be found, or storage space cannot be - * allocated, a %ERR_PTR should be returned. + * @get_parent should find the parent directory for the given @child which + * is also a directory. In the event that it cannot be found, or storage + * space cannot be allocated, a %ERR_PTR should be returned. * * get_dentry: - * Given a &super_block (@sb) and a pointer to a file-system specific inode identifier, - * possibly an inode number, (@inump) get_dentry() should find the identified inode and - * return a dentry for that inode. - * Any suitable dentry can be returned including, if necessary, a new dentry created - * with d_alloc_root. The caller can then find any other extant dentrys by following the - * d_alias links. If a new dentry was created using d_alloc_root, DCACHE_NFSD_DISCONNECTED - * should be set, and the dentry should be d_rehash()ed. + * Given a &super_block (@sb) and a pointer to a file-system specific inode + * identifier, possibly an inode number, (@inump) get_dentry() should find + * the identified inode and return a dentry for that inode. Any suitable + * dentry can be returned including, if necessary, a new dentry created with + * d_alloc_root. The caller can then find any other extant dentrys by + * following the d_alias links. If a new dentry was created using + * d_alloc_root, DCACHE_NFSD_DISCONNECTED should be set, and the dentry + * should be d_rehash()ed. * - * If the inode cannot be found, either a %NULL pointer or an %ERR_PTR code can be returned. - * The @inump will be whatever was passed to nfsd_find_fh_dentry() in either the - * @obj or @parent parameters. + * If the inode cannot be found, either a %NULL pointer or an %ERR_PTR code + * can be returned. The @inump will be whatever was passed to + * nfsd_find_fh_dentry() in either the @obj or @parent parameters. * * Locking rules: - * get_parent is called with child->d_inode->i_sem down - * get_name is not (which is possibly inconsistent) + * get_parent is called with child->d_inode->i_mutex down + * get_name is not (which is possibly inconsistent) */ struct export_operations { @@ -1096,27 +1374,36 @@ struct export_operations { }; +extern struct dentry * +find_exported_dentry(struct super_block *sb, void *obj, void *parent, + int (*acceptable)(void *context, struct dentry *de), + void *context); struct file_system_type { const char *name; int fs_flags; - struct super_block *(*get_sb) (struct file_system_type *, int, - const char *, void *); + int (*get_sb) (struct file_system_type *, int, + const char *, void *, struct vfsmount *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct list_head fs_supers; + struct lock_class_key s_lock_key; + struct lock_class_key s_umount_key; }; -struct super_block *get_sb_bdev(struct file_system_type *fs_type, +extern int get_sb_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)); -struct super_block *get_sb_single(struct file_system_type *fs_type, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt); +extern int get_sb_single(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); -struct super_block *get_sb_nodev(struct file_system_type *fs_type, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt); +extern int get_sb_nodev(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); @@ -1127,9 +1414,12 @@ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), void *data); -struct super_block *get_sb_pseudo(struct file_system_type *, char *, - struct super_operations *ops, unsigned long); +extern int get_sb_pseudo(struct file_system_type *, char *, + struct super_operations *ops, unsigned long, + struct vfsmount *mnt); +extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb); int __put_super(struct super_block *sb); +int __put_super_and_need_restart(struct super_block *sb); void unnamed_dev_init(void); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ @@ -1143,14 +1433,17 @@ extern int unregister_filesystem(struct file_system_type *); extern struct vfsmount *kern_mount(struct file_system_type *); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); +extern void umount_tree(struct vfsmount *, int, struct list_head *); +extern void release_mounts(struct list_head *); extern long do_mount(char *, char *, char *, unsigned long, void *); +extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int); +extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *, + struct vfsmount *); -extern int vfs_statfs(struct super_block *, struct kstatfs *); +extern int vfs_statfs(struct dentry *, struct kstatfs *); -/* Return value for VFS lock functions - tells locks.c to lock conventionally - * REALLY kosha for root NFS and nfs_lock - */ -#define LOCK_USE_CLNT 1 +/* /sys/fs */ +extern struct subsystem fs_subsys; #define FLOCK_VERIFY_READ 1 #define FLOCK_VERIFY_WRITE 2 @@ -1172,14 +1465,7 @@ static inline int locks_verify_locked(struct inode *inode) return 0; } -static inline int locks_verify_area(int read_write, struct inode *inode, - struct file *filp, loff_t offset, - size_t count) -{ - if (inode->i_flock && MANDATORY_LOCK(inode)) - return locks_mandatory_area(read_write, inode, filp, offset, count); - return 0; -} +extern int rw_verify_area(int, struct file *, loff_t *, size_t); static inline int locks_verify_truncate(struct inode *inode, struct file *filp, @@ -1204,65 +1490,90 @@ static inline int break_lease(struct inode *inode, unsigned int mode) /* fs/open.c */ -extern int do_truncate(struct dentry *, loff_t start); +extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, + struct file *filp); +extern long do_sys_open(int fdf, const char __user *filename, int flags, + int mode); extern struct file *filp_open(const char *, int, int); extern struct file * dentry_open(struct dentry *, struct vfsmount *, int); extern int filp_close(struct file *, fl_owner_t id); extern char * getname(const char __user *); /* fs/dcache.c */ -extern void vfs_caches_init(unsigned long); +extern void __init vfs_caches_init_early(void); +extern void __init vfs_caches_init(unsigned long); -#define __getname() kmem_cache_alloc(names_cachep, SLAB_KERNEL) +extern struct kmem_cache *names_cachep; + +#define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) #ifndef CONFIG_AUDITSYSCALL #define putname(name) __putname(name) #else -#define putname(name) \ - do { \ - if (unlikely(current->audit_context)) \ - audit_putname(name); \ - else \ - __putname(name); \ - } while (0) +extern void putname(const char *name); #endif +#ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); extern int unregister_blkdev(unsigned int, const char *); extern struct block_device *bdget(dev_t); extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); -extern int blkdev_open(struct inode *, struct file *); extern struct block_device *open_by_devnum(dev_t, unsigned); -extern struct file_operations def_blk_fops; -extern struct address_space_operations def_blk_aops; -extern struct file_operations def_chr_fops; -extern struct file_operations bad_sock_fops; -extern struct file_operations def_fifo_fops; +extern const struct address_space_operations def_blk_aops; +#else +static inline void bd_forget(struct inode *inode) {} +#endif +extern const struct file_operations def_blk_fops; +extern const struct file_operations def_chr_fops; +extern const struct file_operations bad_sock_fops; +extern const struct file_operations def_fifo_fops; +#ifdef CONFIG_BLOCK extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long); +extern int blkdev_driver_ioctl(struct inode *inode, struct file *file, + struct gendisk *disk, unsigned cmd, + unsigned long arg); +extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); extern int blkdev_get(struct block_device *, mode_t, unsigned); extern int blkdev_put(struct block_device *); extern int bd_claim(struct block_device *, void *); extern void bd_release(struct block_device *); +#ifdef CONFIG_SYSFS +extern int bd_claim_by_disk(struct block_device *, void *, struct gendisk *); +extern void bd_release_from_disk(struct block_device *, struct gendisk *); +#else +#define bd_claim_by_disk(bdev, holder, disk) bd_claim(bdev, holder) +#define bd_release_from_disk(bdev, disk) bd_release(bdev) +#endif +#endif /* fs/char_dev.c */ -extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, char *); -extern int register_chrdev_region(dev_t, unsigned, char *); +#define CHRDEV_MAJOR_HASH_SIZE 255 +extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); +extern int register_chrdev_region(dev_t, unsigned, const char *); extern int register_chrdev(unsigned int, const char *, - struct file_operations *); + const struct file_operations *); extern int unregister_chrdev(unsigned int, const char *); extern void unregister_chrdev_region(dev_t, unsigned); extern int chrdev_open(struct inode *, struct file *); +extern void chrdev_show(struct seq_file *,off_t); /* fs/block_dev.c */ #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ + +#ifdef CONFIG_BLOCK +#define BLKDEV_MAJOR_HASH_SIZE 255 extern const char *__bdevname(dev_t, char *buffer); extern const char *bdevname(struct block_device *bdev, char *buffer); extern struct block_device *lookup_bdev(const char *); extern struct block_device *open_bdev_excl(const char *, int, void *); extern void close_bdev_excl(struct block_device *); +extern void blkdev_show(struct seq_file *,off_t); +#else +#define BLKDEV_MAJOR_HASH_SIZE 0 +#endif extern void init_special_inode(struct inode *, umode_t, dev_t); @@ -1270,15 +1581,13 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern int is_bad_inode(struct inode *); -extern struct file_operations read_fifo_fops; -extern struct file_operations write_fifo_fops; -extern struct file_operations rdwr_fifo_fops; -extern struct file_operations read_pipe_fops; -extern struct file_operations write_pipe_fops; -extern struct file_operations rdwr_pipe_fops; +extern const struct file_operations read_fifo_fops; +extern const struct file_operations write_fifo_fops; +extern const struct file_operations rdwr_fifo_fops; extern int fs_may_remount_ro(struct super_block *); +#ifdef CONFIG_BLOCK /* * return READ, READA, or WRITE */ @@ -1290,9 +1599,10 @@ extern int fs_may_remount_ro(struct super_block *); #define bio_data_dir(bio) ((bio)->bi_rw & 1) extern int check_disk_change(struct block_device *); -extern int invalidate_inodes(struct super_block *); -extern int __invalidate_device(struct block_device *, int); +extern int __invalidate_device(struct block_device *); extern int invalidate_partition(struct gendisk *, int); +#endif +extern int invalidate_inodes(struct super_block *); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); unsigned long invalidate_inode_pages(struct address_space *mapping); @@ -1302,23 +1612,37 @@ static inline void invalidate_remote_inode(struct inode *inode) S_ISLNK(inode->i_mode)) invalidate_inode_pages(inode->i_mapping); } -extern void invalidate_inode_pages2(struct address_space *mapping); -extern void write_inode_now(struct inode *, int); +extern int invalidate_inode_pages2(struct address_space *mapping); +extern int invalidate_inode_pages2_range(struct address_space *mapping, + pgoff_t start, pgoff_t end); +extern int write_inode_now(struct inode *, int); extern int filemap_fdatawrite(struct address_space *); extern int filemap_flush(struct address_space *); extern int filemap_fdatawait(struct address_space *); extern int filemap_write_and_wait(struct address_space *mapping); +extern int filemap_write_and_wait_range(struct address_space *mapping, + loff_t lstart, loff_t lend); +extern int wait_on_page_writeback_range(struct address_space *mapping, + pgoff_t start, pgoff_t end); +extern int __filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end, int sync_mode); + +extern long do_fsync(struct file *file, int datasync); extern void sync_supers(void); extern void sync_filesystems(int wait); +extern void __fsync_super(struct super_block *sb); extern void emergency_sync(void); extern void emergency_remount(void); extern int do_remount_sb(struct super_block *sb, int flags, void *data, int force); +#ifdef CONFIG_BLOCK extern sector_t bmap(struct inode *, sector_t); -extern int setattr_mask(unsigned int); +#endif extern int notify_change(struct dentry *, struct iattr *); extern int permission(struct inode *, int, struct nameidata *); -extern int vfs_permission(struct inode *, int); +extern int generic_permission(struct inode *, int, + int (*check_acl)(struct inode *, int)); + extern int get_write_access(struct inode *); extern int deny_write_access(struct file *); static inline void put_write_access(struct inode * inode) @@ -1328,11 +1652,14 @@ static inline void put_write_access(struct inode * inode) static inline void allow_write_access(struct file *file) { if (file) - atomic_inc(&file->f_dentry->d_inode->i_writecount); + atomic_inc(&file->f_path.dentry->d_inode->i_writecount); } extern int do_pipe(int *); +extern struct file *create_read_pipe(struct file *f); +extern struct file *create_write_pipe(void); +extern void free_write_pipe(struct file *); -extern int open_namei(const char *, int, int, struct nameidata *); +extern int open_namei(int dfd, const char *, int, int, struct nameidata *); extern int may_open(struct nameidata *, int, int); extern int kernel_read(struct file *, unsigned long, char *, unsigned long); @@ -1347,13 +1674,19 @@ extern ino_t find_inode_number(struct dentry *, struct qstr *); /* needed for stackable file system support */ extern loff_t default_llseek(struct file *file, loff_t offset, int origin); +extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin); + extern void inode_init_once(struct inode *); extern void iput(struct inode *); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern void generic_delete_inode(struct inode *inode); +extern void generic_drop_inode(struct inode *inode); +extern struct inode *ilookup5_nowait(struct super_block *sb, + unsigned long hashval, int (*test)(struct inode *, void *), + void *data); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); @@ -1378,7 +1711,10 @@ extern void __iget(struct inode * inode); extern void clear_inode(struct inode *); extern void destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); +extern int __remove_suid(struct dentry *, int); +extern int should_remove_suid(struct dentry *); extern int remove_suid(struct dentry *); +extern void remove_dquot_ref(struct super_block *, int, struct list_head *); extern void __insert_inode_hash(struct inode *, unsigned long hashval); extern void remove_inode_hash(struct inode *); @@ -1389,9 +1725,11 @@ static inline void insert_inode_hash(struct inode *inode) { extern struct file * get_empty_filp(void); extern void file_move(struct file *f, struct list_head *list); extern void file_kill(struct file *f); +#ifdef CONFIG_BLOCK struct bio; extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); +#endif extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); @@ -1400,34 +1738,61 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); -extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); -extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *); -extern ssize_t generic_file_aio_read(struct kiocb *, char __user *, size_t, loff_t); -extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *); -extern ssize_t generic_file_aio_write(struct kiocb *, const char __user *, size_t, loff_t); +extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); +extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *, - unsigned long, loff_t *); + unsigned long, loff_t); +extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, + unsigned long *, loff_t, loff_t *, size_t, size_t); +extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, + unsigned long, loff_t, loff_t *, size_t, ssize_t); +extern int generic_file_buffered_write_one_kernel_page(struct address_space *, + pgoff_t, struct page *); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); -ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); -extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void __user *); +extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *); +extern ssize_t generic_file_sendpage(struct file *, struct page *, int, size_t, loff_t *, int); extern void do_generic_mapping_read(struct address_space *mapping, struct file_ra_state *, struct file *, loff_t *, read_descriptor_t *, read_actor_t); + +/* fs/splice.c */ +extern ssize_t generic_file_splice_read(struct file *, loff_t *, + struct pipe_inode_info *, size_t, unsigned int); +extern ssize_t generic_file_splice_write(struct pipe_inode_info *, + struct file *, loff_t *, size_t, unsigned int); +extern ssize_t generic_file_splice_write_nolock(struct pipe_inode_info *, + struct file *, loff_t *, size_t, unsigned int); +extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, + struct file *out, loff_t *, size_t len, unsigned int flags); +extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, + size_t len, unsigned int flags); + extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); -extern ssize_t generic_file_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs); -extern ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); -ssize_t generic_file_writev(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos); extern loff_t no_llseek(struct file *file, loff_t offset, int origin); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin); extern loff_t remote_llseek(struct file *file, loff_t offset, int origin); extern int generic_file_open(struct inode * inode, struct file * filp); +extern int nonseekable_open(struct inode * inode, struct file * filp); + +#ifdef CONFIG_FS_XIP +extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len, + loff_t *ppos); +extern ssize_t xip_file_sendfile(struct file *in_file, loff_t *ppos, + size_t count, read_actor_t actor, + void *target); +extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma); +extern ssize_t xip_file_write(struct file *filp, const char __user *buf, + size_t len, loff_t *ppos); +extern int xip_truncate_page(struct address_space *mapping, loff_t from); +#else +static inline int xip_truncate_page(struct address_space *mapping, loff_t from) +{ + return 0; +} +#endif static inline void do_generic_file_read(struct file * filp, loff_t *ppos, read_descriptor_t * desc, @@ -1441,42 +1806,60 @@ static inline void do_generic_file_read(struct file * filp, loff_t *ppos, actor); } +#ifdef CONFIG_BLOCK ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, - unsigned long nr_segs, get_blocks_t get_blocks, dio_iodone_t end_io, - int needs_special_locking); + unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, + int lock_type); + +enum { + DIO_LOCKING = 1, /* need locking between buffered and direct access */ + DIO_NO_LOCKING, /* bdev; no locking at all between buffered/direct */ + DIO_OWN_LOCKING, /* filesystem locks buffered and direct internally */ +}; -/* - * For filesystems which need locking between buffered and direct access - */ static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, - loff_t offset, unsigned long nr_segs, get_blocks_t get_blocks, + loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io) { return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_blocks, end_io, 1); + nr_segs, get_block, end_io, DIO_LOCKING); } static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, - loff_t offset, unsigned long nr_segs, get_blocks_t get_blocks, + loff_t offset, unsigned long nr_segs, get_block_t get_block, + dio_iodone_t end_io) +{ + return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, + nr_segs, get_block, end_io, DIO_NO_LOCKING); +} + +static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb, + struct inode *inode, struct block_device *bdev, const struct iovec *iov, + loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io) { return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_blocks, end_io, 0); + nr_segs, get_block, end_io, DIO_OWN_LOCKING); } +#endif -extern struct file_operations generic_ro_fops; +extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int vfs_readlink(struct dentry *, char __user *, int, const char *); extern int vfs_follow_link(struct nameidata *, const char *); extern int page_readlink(struct dentry *, char __user *, int); -extern int page_follow_link(struct dentry *, struct nameidata *); +extern void *page_follow_link_light(struct dentry *, struct nameidata *); +extern void page_put_link(struct dentry *, struct nameidata *, void *); +extern int __page_symlink(struct inode *inode, const char *symname, int len, + gfp_t gfp_mask); extern int page_symlink(struct inode *inode, const char *symname, int len); extern struct inode_operations page_symlink_inode_operations; +extern int generic_readlink(struct dentry *, char __user *, int); extern void generic_fillattr(struct inode *, struct kstat *); extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); void inode_add_bytes(struct inode *inode, loff_t bytes); @@ -1488,8 +1871,12 @@ extern int vfs_readdir(struct file *, filldir_t, void *); extern int vfs_stat(char __user *, struct kstat *); extern int vfs_lstat(char __user *, struct kstat *); +extern int vfs_stat_fd(int dfd, char __user *, struct kstat *); +extern int vfs_lstat_fd(int dfd, char __user *, struct kstat *); extern int vfs_fstat(unsigned int, struct kstat *); +extern int vfs_ioctl(struct file *, unsigned int, unsigned int, unsigned long); + extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); extern struct super_block *user_get_super(dev_t); @@ -1499,8 +1886,9 @@ extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, void *, filldir_t); +extern int dcache_readdir_filter(struct file *, void *, filldir_t, int (*)(struct dentry *)); extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *); -extern int simple_statfs(struct super_block *, struct kstatfs *); +extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); @@ -1515,17 +1903,27 @@ extern int simple_commit_write(struct file *file, struct page *page, extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); -extern struct file_operations simple_dir_operations; +extern const struct file_operations simple_dir_operations; extern struct inode_operations simple_dir_inode_operations; -struct tree_descr { char *name; struct file_operations *ops; int mode; }; +struct tree_descr { char *name; const struct file_operations *ops; int mode; }; +struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, int, struct tree_descr *); -extern int simple_pin_fs(char *name, struct vfsmount **mount, int *count); +extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); +extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t); + +#ifdef CONFIG_MIGRATION +extern int buffer_migrate_page(struct address_space *, + struct page *, struct page *); +#else +#define buffer_migrate_page NULL +#endif + extern int inode_change_ok(struct inode *, struct iattr *); -extern int inode_setattr(struct inode *, struct iattr *); +extern int __must_check inode_setattr(struct inode *, struct iattr *); -extern void inode_update_time(struct inode *inode, int ctime_too); +extern void file_update_time(struct file *file); static inline ino_t parent_ino(struct dentry *dentry) { @@ -1540,6 +1938,85 @@ static inline ino_t parent_ino(struct dentry *dentry) /* kernel/fork.c */ extern int unshare_files(void); +/* Transaction based IO helpers */ + +/* + * An argresp is stored in an allocated page and holds the + * size of the argument or response, along with its content + */ +struct simple_transaction_argresp { + ssize_t size; + char data[0]; +}; + +#define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) + +char *simple_transaction_get(struct file *file, const char __user *buf, + size_t size); +ssize_t simple_transaction_read(struct file *file, char __user *buf, + size_t size, loff_t *pos); +int simple_transaction_release(struct inode *inode, struct file *file); + +static inline void simple_transaction_set(struct file *file, size_t n) +{ + struct simple_transaction_argresp *ar = file->private_data; + + BUG_ON(n > SIMPLE_TRANSACTION_LIMIT); + + /* + * The barrier ensures that ar->size will really remain zero until + * ar->data is ready for reading. + */ + smp_mb(); + ar->size = n; +} + +/* + * simple attribute files + * + * These attributes behave similar to those in sysfs: + * + * Writing to an attribute immediately sets a value, an open file can be + * written to multiple times. + * + * Reading from an attribute creates a buffer from the value that might get + * read with multiple read calls. When the attribute has been read + * completely, no further read calls are possible until the file is opened + * again. + * + * All attributes contain a text representation of a numeric value + * that are accessed with the get() and set() functions. + */ +#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ +static int __fops ## _open(struct inode *inode, struct file *file) \ +{ \ + __simple_attr_check_format(__fmt, 0ull); \ + return simple_attr_open(inode, file, __get, __set, __fmt); \ +} \ +static struct file_operations __fops = { \ + .owner = THIS_MODULE, \ + .open = __fops ## _open, \ + .release = simple_attr_close, \ + .read = simple_attr_read, \ + .write = simple_attr_write, \ +}; + +static inline void __attribute__((format(printf, 1, 2))) +__simple_attr_check_format(const char *fmt, ...) +{ + /* don't do anything, just let the compiler check the arguments; */ +} + +int simple_attr_open(struct inode *inode, struct file *file, + u64 (*get)(void *), void (*set)(void *, u64), + const char *fmt); +int simple_attr_close(struct inode *inode, struct file *file); +ssize_t simple_attr_read(struct file *file, char __user *buf, + size_t len, loff_t *ppos); +ssize_t simple_attr_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos); + + #ifdef CONFIG_SECURITY static inline char *alloc_secdata(void) {