summaryrefslogtreecommitdiffstats
path: root/include/linux/fs.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/fs.h')
-rw-r--r--include/linux/fs.h160
1 files changed, 111 insertions, 49 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dbd860af080..f23bcb77260 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -23,7 +23,8 @@
/* Fixed constants first: */
#undef NR_OPEN
-#define INR_OPEN 1024 /* Initial setting for nfile rlimits */
+#define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */
+#define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */
#define BLOCK_SIZE_BITS 10
#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
@@ -31,7 +32,9 @@
#define SEEK_SET 0 /* seek relative to beginning of file */
#define SEEK_CUR 1 /* seek relative to current file position */
#define SEEK_END 2 /* seek relative to end of file */
-#define SEEK_MAX SEEK_END
+#define SEEK_DATA 3 /* seek to the next data */
+#define SEEK_HOLE 4 /* seek to the next hole */
+#define SEEK_MAX SEEK_HOLE
struct fstrim_range {
__u64 start;
@@ -62,6 +65,7 @@ struct inodes_stat_t {
#define MAY_ACCESS 16
#define MAY_OPEN 32
#define MAY_CHDIR 64
+#define MAY_NOT_BLOCK 128 /* called from RCU mode, don't block */
/*
* flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond
@@ -207,6 +211,7 @@ struct inodes_stat_t {
#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */
#define MS_I_VERSION (1<<23) /* Update inode I_version field */
#define MS_STRICTATIME (1<<24) /* Always perform atime updates */
+#define MS_NOSEC (1<<28)
#define MS_BORN (1<<29)
#define MS_ACTIVE (1<<30)
#define MS_NOUSER (1<<31)
@@ -236,6 +241,7 @@ struct inodes_stat_t {
#define S_PRIVATE 512 /* Inode is fs-internal */
#define S_IMA 1024 /* Inode has an associated IMA struct */
#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */
+#define S_NOSEC 4096 /* no suid or xattr security attributes */
/*
* Note that nosuid etc flags are inode-specific: setting some file-system
@@ -272,6 +278,7 @@ struct inodes_stat_t {
#define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE)
#define IS_IMA(inode) ((inode)->i_flags & S_IMA)
#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
+#define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC)
/* 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. */
@@ -358,7 +365,6 @@ struct inodes_stat_t {
#define FS_EXTENT_FL 0x00080000 /* Extents */
#define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */
#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
-#define FS_COW_FL 0x02000000 /* Cow file */
#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */
#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */
@@ -373,7 +379,6 @@ struct inodes_stat_t {
#include <linux/linkage.h>
#include <linux/wait.h>
-#include <linux/types.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
#include <linux/path.h>
@@ -389,8 +394,9 @@ struct inodes_stat_t {
#include <linux/semaphore.h>
#include <linux/fiemap.h>
#include <linux/rculist_bl.h>
+#include <linux/shrinker.h>
+#include <linux/atomic.h>
-#include <asm/atomic.h>
#include <asm/byteorder.h>
struct export_operations;
@@ -635,8 +641,8 @@ struct address_space {
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 */
- unsigned int truncate_count; /* Cover race condition with truncate */
+ struct mutex i_mmap_mutex; /* protect tree, count, list */
+ /* Protected by tree_lock together with the radix tree */
unsigned long nrpages; /* number of total pages */
pgoff_t writeback_index;/* writeback starts here */
const struct address_space_operations *a_ops; /* methods */
@@ -645,7 +651,6 @@ struct address_space {
spinlock_t private_lock; /* for use by the address_space */
struct list_head private_list; /* ditto */
struct address_space *assoc_mapping; /* ditto */
- struct mutex unmap_mutex; /* to protect unmapping */
} __attribute__((aligned(sizeof(long))));
/*
* On most architectures that alignment is already the case; but
@@ -743,9 +748,13 @@ struct inode {
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned int i_flags;
+ unsigned long i_state;
+#ifdef CONFIG_SECURITY
+ void *i_security;
+#endif
struct mutex i_mutex;
- unsigned long i_state;
+
unsigned long dirtied_when; /* jiffies of first dirtying */
struct hlist_node i_hash;
@@ -771,7 +780,7 @@ struct inode {
struct timespec i_ctime;
blkcnt_t i_blocks;
unsigned short i_bytes;
- struct rw_semaphore i_alloc_sem;
+ atomic_t i_dio_count;
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
struct file_lock *i_flock;
struct address_space *i_mapping;
@@ -797,9 +806,6 @@ struct inode {
atomic_t i_readcount; /* struct files open RO */
#endif
atomic_t i_writecount;
-#ifdef CONFIG_SECURITY
- void *i_security;
-#endif
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *i_acl;
struct posix_acl *i_default_acl;
@@ -1066,12 +1072,12 @@ struct file_lock_operations {
};
struct lock_manager_operations {
- int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
- void (*fl_notify)(struct file_lock *); /* unblock callback */
- int (*fl_grant)(struct file_lock *, struct file_lock *, int);
- void (*fl_release_private)(struct file_lock *);
- void (*fl_break)(struct file_lock *);
- int (*fl_change)(struct file_lock **, int);
+ int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
+ void (*lm_notify)(struct file_lock *); /* unblock callback */
+ int (*lm_grant)(struct file_lock *, struct file_lock *, int);
+ void (*lm_release_private)(struct file_lock *);
+ void (*lm_break)(struct file_lock *);
+ int (*lm_change)(struct file_lock **, int);
};
struct lock_manager {
@@ -1393,6 +1399,11 @@ struct super_block {
struct list_head s_dentry_lru; /* unused dentry lru */
int s_nr_dentry_unused; /* # of dentry on lru */
+ /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */
+ spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp;
+ struct list_head s_inode_lru; /* unused inode lru */
+ int s_nr_inodes_unused; /* # of inodes on lru */
+
struct block_device *s_bdev;
struct backing_dev_info *s_bdi;
struct mtd_info *s_mtd;
@@ -1430,8 +1441,19 @@ struct super_block {
*/
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 */
};
+/* superblock cache pruning functions */
+extern void prune_icache_sb(struct super_block *sb, int nr_to_scan);
+extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan);
+
extern struct timespec current_fs_time(struct super_block *sb);
/*
@@ -1446,10 +1468,6 @@ enum {
#define vfs_check_frozen(sb, level) \
wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))
-#define get_fs_excl() atomic_inc(&current->fs_excl)
-#define put_fs_excl() atomic_dec(&current->fs_excl)
-#define has_fs_excl() atomic_read(&current->fs_excl)
-
/*
* until VFS tracks user namespaces for inodes, just make all files
* belong to init_user_ns
@@ -1482,7 +1500,6 @@ extern void dentry_unhash(struct dentry *dentry);
/*
* VFS file helper functions.
*/
-extern int file_permission(struct file *, int);
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
mode_t mode);
/*
@@ -1530,11 +1547,6 @@ struct block_device_operations;
#define HAVE_COMPAT_IOCTL 1
#define HAVE_UNLOCKED_IOCTL 1
-/*
- * NOTE:
- * all file operations except setlease 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);
@@ -1550,7 +1562,7 @@ struct file_operations {
int (*open) (struct inode *, struct file *);
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
- int (*fsync) (struct file *, int datasync);
+ 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 *);
@@ -1565,13 +1577,11 @@ struct file_operations {
loff_t len);
};
-#define IPERM_FLAG_RCU 0x0001
-
struct inode_operations {
struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
void * (*follow_link) (struct dentry *, struct nameidata *);
- int (*permission) (struct inode *, int, unsigned int);
- int (*check_acl)(struct inode *, int, unsigned int);
+ int (*permission) (struct inode *, int);
+ struct posix_acl * (*get_acl)(struct inode *, int);
int (*readlink) (struct dentry *, char __user *,int);
void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -1615,7 +1625,7 @@ struct super_operations {
struct inode *(*alloc_inode)(struct super_block *sb);
void (*destroy_inode)(struct inode *);
- void (*dirty_inode) (struct inode *);
+ void (*dirty_inode) (struct inode *, int flags);
int (*write_inode) (struct inode *, struct writeback_control *wbc);
int (*drop_inode) (struct inode *);
void (*evict_inode) (struct inode *);
@@ -1637,6 +1647,8 @@ struct super_operations {
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
#endif
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
+ int (*nr_cached_objects)(struct super_block *);
+ void (*free_cached_objects)(struct super_block *, int);
};
/*
@@ -1685,6 +1697,10 @@ struct super_operations {
* set during data writeback, and cleared with a wakeup
* on the bit address once it is done.
*
+ * I_REFERENCED Marks the inode as recently references on the LRU list.
+ *
+ * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit().
+ *
* Q: What is the difference between I_WILL_FREE and I_FREEING?
*/
#define I_DIRTY_SYNC (1 << 0)
@@ -1698,6 +1714,8 @@ struct super_operations {
#define __I_SYNC 7
#define I_SYNC (1 << __I_SYNC)
#define I_REFERENCED (1 << 8)
+#define __I_DIO_WAKEUP 9
+#define I_DIO_WAKEUP (1 << I_DIO_WAKEUP)
#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
@@ -1808,7 +1826,6 @@ struct file_system_type {
struct lock_class_key i_lock_key;
struct lock_class_key i_mutex_key;
struct lock_class_key i_mutex_dir_key;
- struct lock_class_key i_alloc_sem_key;
};
extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
@@ -1829,6 +1846,8 @@ void kill_litter_super(struct super_block *sb);
void deactivate_super(struct super_block *sb);
void deactivate_locked_super(struct super_block *sb);
int set_anon_super(struct super_block *s, void *data);
+int get_anon_bdev(dev_t *);
+void free_anon_bdev(dev_t);
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
@@ -1861,6 +1880,7 @@ extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
#define kern_mount(type) kern_mount_data(type, NULL)
+extern void kern_unmount(struct vfsmount *mnt);
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
extern long do_mount(char *, char *, char *, unsigned long, void *);
@@ -2180,16 +2200,38 @@ extern sector_t bmap(struct inode *, sector_t);
#endif
extern int notify_change(struct dentry *, struct iattr *);
extern int inode_permission(struct inode *, int);
-extern int generic_permission(struct inode *, int, unsigned int,
- int (*check_acl)(struct inode *, int, unsigned int));
+extern int generic_permission(struct inode *, int);
static inline bool execute_ok(struct inode *inode)
{
return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}
-extern int get_write_access(struct inode *);
-extern int deny_write_access(struct file *);
+/*
+ * get_write_access() gets write permission for a file.
+ * put_write_access() releases this write permission.
+ * This is used for regular files.
+ * We cannot support write (and maybe mmap read-write shared) accesses and
+ * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
+ * can have the following values:
+ * 0: no writers, no VM_DENYWRITE mappings
+ * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
+ * > 0: (i_writecount) users are writing to the file.
+ *
+ * Normally we operate on that counter with atomic_{inc,dec} and it's safe
+ * except for the cases where we don't hold i_writecount yet. Then we need to
+ * use {get,deny}_write_access() - these functions check the sign and refuse
+ * to do the change if sign is wrong.
+ */
+static inline int get_write_access(struct inode *inode)
+{
+ return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY;
+}
+static inline int deny_write_access(struct file *file)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
+}
static inline void put_write_access(struct inode * inode)
{
atomic_dec(&inode->i_writecount);
@@ -2268,7 +2310,8 @@ extern void __iget(struct inode * inode);
extern void iget_failed(struct inode *);
extern void end_writeback(struct inode *);
extern void __destroy_inode(struct inode *);
-extern struct inode *new_inode(struct super_block *);
+extern struct inode *new_inode_pseudo(struct super_block *sb);
+extern struct inode *new_inode(struct super_block *sb);
extern void free_inode_nonrcu(struct inode *inode);
extern int should_remove_suid(struct dentry *);
extern int file_remove_suid(struct file *);
@@ -2309,7 +2352,8 @@ extern int generic_segment_checks(const struct iovec *iov,
/* fs/block_dev.c */
extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos);
-extern int blkdev_fsync(struct file *filp, int datasync);
+extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
+ int datasync);
/* fs/splice.c */
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
@@ -2360,6 +2404,8 @@ enum {
};
void dio_end_io(struct bio *bio, int error);
+void inode_dio_wait(struct inode *inode);
+void inode_dio_done(struct inode *inode);
ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, const struct iovec *iov, loff_t offset,
@@ -2367,14 +2413,17 @@ ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
dio_submit_t submit_io, int flags);
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_block_t get_block,
- dio_iodone_t end_io)
+ struct inode *inode, const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs, get_block_t get_block)
{
- return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
- nr_segs, get_block, end_io, NULL,
+ return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
+ offset, nr_segs, get_block, NULL, NULL,
DIO_LOCKING | DIO_SKIP_HOLES);
}
+#else
+static inline void inode_dio_wait(struct inode *inode)
+{
+}
#endif
extern const struct file_operations generic_ro_fops;
@@ -2424,6 +2473,8 @@ extern struct super_block *get_active_super(struct block_device *bdev);
extern struct super_block *user_get_super(dev_t);
extern void drop_super(struct super_block *sb);
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
+extern void iterate_supers_type(struct file_system_type *,
+ void (*)(struct super_block *, void *), void *);
extern int dcache_dir_open(struct inode *, struct file *);
extern int dcache_dir_close(struct inode *, struct file *);
@@ -2436,7 +2487,7 @@ 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 *);
extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
-extern int noop_fsync(struct file *, int);
+extern int noop_fsync(struct file *, loff_t, loff_t, int);
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
extern int simple_write_begin(struct file *file, struct address_space *mapping,
@@ -2461,7 +2512,7 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
const void __user *from, size_t count);
-extern int generic_file_fsync(struct file *, int);
+extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
extern int generic_check_addressable(unsigned, u64);
@@ -2579,5 +2630,16 @@ int __init get_filesystem_list(char *buf);
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
(flag & __FMODE_NONOTIFY)))
+static inline int is_sxid(mode_t mode)
+{
+ return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
+}
+
+static inline void inode_has_no_xattr(struct inode *inode)
+{
+ if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
+ inode->i_flags |= S_NOSEC;
+}
+
#endif /* __KERNEL__ */
#endif /* _LINUX_FS_H */
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-03-30 07:02:32 +0000