1 files changed, 133 insertions, 66 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8d5834bcb89..78987e9a384 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -32,7 +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;
@@ -63,6 +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
@@ -159,10 +162,8 @@ struct inodes_stat_t {
 #define READA                   RWA_MASK
 
 #define READ_SYNC               (READ | REQ_SYNC)
-#define READ_META               (READ | REQ_META)
 #define WRITE_SYNC              (WRITE | REQ_SYNC | REQ_NOIDLE)
 #define WRITE_ODIRECT           (WRITE | REQ_SYNC)
-#define WRITE_META              (WRITE | REQ_META)
 #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)
@@ -376,7 +377,6 @@ 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>
@@ -392,8 +392,9 @@ 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;
@@ -736,22 +737,54 @@ struct posix_acl;
 #define ACL_NOT_CACHED ((void *)(-1))
 struct inode_obj_id_table;
 
+#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 {
-        /* RCU path lookup touches following: */
         umode_t                 i_mode;
+        unsigned short          i_opflags;
         uid_t                   i_uid;
         gid_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;
 
-        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;
 
+        /* Stat data, not accessed from path walking */
+        unsigned long           i_ino;
+        unsigned int            i_nlink;
+        dev_t                   i_rdev;
+        loff_t                  i_size;
+        struct timespec         i_atime;
+        struct timespec         i_mtime;
+        struct timespec         i_ctime;
+        unsigned int            i_blkbits;
+        blkcnt_t                i_blocks;
+
+#ifdef __NEED_I_SIZE_ORDERED
+        seqcount_t              i_size_seqcount;
+#endif
+
+        /* Misc */
+        unsigned long           i_state;
+        spinlock_t              i_lock; /* i_blocks, i_bytes, maybe i_size */
+        struct mutex            i_mutex;
 
         unsigned long           dirtied_when;   /* jiffies of first dirtying */
 
@@ -763,25 +796,12 @@ struct inode {
                 struct list_head        i_dentry;
                 struct rcu_head         i_rcu;
         };
-        unsigned long           i_ino;
         atomic_t                i_count;
-        unsigned int            i_nlink;
-        dev_t                   i_rdev;
-        unsigned int            i_blkbits;
         u64                     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;
-        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;
         struct address_space    i_data;
 #ifdef CONFIG_QUOTA
         struct dquot            *i_dquot[MAXQUOTAS];
@@ -804,12 +824,6 @@ struct inode {
         atomic_t                i_readcount; /* struct files open RO */
 #endif
         atomic_t                i_writecount;
-#ifdef CONFIG_FS_POSIX_ACL
-        struct posix_acl        *i_acl;
-        struct posix_acl        *i_default_acl;
-#endif
-        struct list_head        i_obj_list;
-        struct mutex            i_obj_mutex;
         void                    *i_private; /* fs or device private pointer */
 };
 
@@ -1072,12 +1086,12 @@ 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 {
@@ -1399,6 +1413,11 @@ 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;
@@ -1441,8 +1460,14 @@ struct super_block {
          * 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);
 
 /*
@@ -1457,10 +1482,6 @@ 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
@@ -1493,7 +1514,6 @@ 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);
 /*
@@ -1541,11 +1561,6 @@ 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);
@@ -1561,7 +1576,7 @@ 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 *);
@@ -1576,13 +1591,11 @@ 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 *);
@@ -1648,6 +1661,8 @@ 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);
 };
 
 /*
@@ -1696,6 +1711,10 @@ 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)
@@ -1709,6 +1728,8 @@ 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)
 
@@ -1819,7 +1840,6 @@ 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,
@@ -1840,6 +1860,8 @@ 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 *),
@@ -1872,6 +1894,7 @@ 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 *);
@@ -1885,6 +1908,7 @@ extern int fd_statfs(int, struct kstatfs *);
 extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
+extern bool our_mnt(struct vfsmount *mnt);
 
 extern int current_umask(void);
 
@@ -2191,16 +2215,38 @@ 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);
@@ -2272,6 +2318,11 @@ extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*te
 extern struct inode * iget_locked(struct super_block *, unsigned long);
 extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
 extern int insert_inode_locked(struct inode *);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
+#else
+static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
+#endif
 extern void unlock_new_inode(struct inode *);
 extern unsigned int get_next_ino(void);
 
@@ -2279,17 +2330,25 @@ 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 *);
 
 extern void __insert_inode_hash(struct inode *, unsigned long hashval);
-extern void remove_inode_hash(struct inode *);
 static inline void insert_inode_hash(struct inode *inode)
 {
         __insert_inode_hash(inode, inode->i_ino);
 }
+
+extern void __remove_inode_hash(struct inode *);
+static inline void remove_inode_hash(struct inode *inode)
+{
+        if (!inode_unhashed(inode))
+                __remove_inode_hash(inode);
+}
+
 extern void inode_sb_list_add(struct inode *inode);
 
 #ifdef CONFIG_BLOCK
@@ -2320,7 +2379,8 @@ 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 *,
@@ -2371,6 +2431,8 @@ 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,
@@ -2378,14 +2440,17 @@ 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;
@@ -2435,6 +2500,8 @@ 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 *);
@@ -2447,7 +2514,7 @@ 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,
@@ -2472,7 +2539,7 @@ 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);