1 files changed, 102 insertions, 54 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9a96b4d83fc1..334d68a17108 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -9,6 +9,7 @@
 #include <linux/limits.h>
 #include <linux/ioctl.h>
 #include <linux/blk_types.h>
+#include <linux/types.h>
 
 /*
  * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
@@ -32,11 +33,17 @@
 #define SEEK_END        2       /* seek relative to end of file */
 #define SEEK_MAX        SEEK_END
 
+struct fstrim_range {
+        uint64_t start;
+        uint64_t len;
+        uint64_t minlen;
+};
+
 /* And dynamically-tunable limits and defaults: */
 struct files_stat_struct {
-        int nr_files;           /* read only */
-        int nr_free_files;      /* read only */
-        int max_files;          /* tunable */
+        unsigned long nr_files;         /* read only */
+        unsigned long nr_free_files;    /* read only */
+        unsigned long max_files;                /* tunable */
 };
 
 struct inodes_stat_t {
@@ -92,6 +99,9 @@ struct inodes_stat_t {
 /* Expect random access pattern */
 #define FMODE_RANDOM            ((__force fmode_t)0x1000)
 
+/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
+#define FMODE_UNSIGNED_OFFSET   ((__force fmode_t)0x2000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY          ((__force fmode_t)0x1000000)
 
@@ -125,9 +135,6 @@ struct inodes_stat_t {
  *                      block layer could (in theory) choose to ignore this
  *                      request if it runs into resource problems.
  * WRITE                A normal async write. Device will be plugged.
- * SWRITE               Like WRITE, but a special case for ll_rw_block() that
- *                      tells it to lock the buffer first. Normally a buffer
- *                      must be locked before doing IO.
  * WRITE_SYNC_PLUG      Synchronous write. Identical to WRITE, but passes down
  *                      the hint that someone will be waiting on this IO
  *                      shortly. The device must still be unplugged explicitly,
@@ -138,15 +145,12 @@ struct inodes_stat_t {
  *                      immediately after submission. The write equivalent
  *                      of READ_SYNC.
  * WRITE_ODIRECT_PLUG   Special case write for O_DIRECT only.
- * SWRITE_SYNC
- * SWRITE_SYNC_PLUG     Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer.
- *                      See SWRITE.
- * WRITE_BARRIER        Like WRITE_SYNC, but tells the block layer that all
- *                      previously submitted writes must be safely on storage
- *                      before this one is started. Also guarantees that when
- *                      this write is complete, it itself is also safely on
- *                      storage. Prevents reordering of writes on both sides
- *                      of this IO.
+ * WRITE_FLUSH          Like WRITE_SYNC but with preceding cache flush.
+ * WRITE_FUA            Like WRITE_SYNC but data is guaranteed to be on
+ *                      non-volatile media on completion.
+ * WRITE_FLUSH_FUA      Combination of WRITE_FLUSH and FUA. The IO is preceded
+ *                      by a cache flush and data is guaranteed to be on
+ *                      non-volatile media on completion.
  *
  */
 #define RW_MASK                 REQ_WRITE
@@ -155,7 +159,6 @@ struct inodes_stat_t {
 #define READ                    0
 #define WRITE                   RW_MASK
 #define READA                   RWA_MASK
-#define SWRITE                  (WRITE | READA)
 
 #define READ_SYNC               (READ | REQ_SYNC | REQ_UNPLUG)
 #define READ_META               (READ | REQ_META)
@@ -163,18 +166,12 @@ struct inodes_stat_t {
 #define WRITE_SYNC              (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
 #define WRITE_ODIRECT_PLUG      (WRITE | REQ_SYNC)
 #define WRITE_META              (WRITE | REQ_META)
-#define WRITE_BARRIER           (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
-                                 REQ_HARDBARRIER)
-#define SWRITE_SYNC_PLUG        (SWRITE | REQ_SYNC | REQ_NOIDLE)
-#define SWRITE_SYNC             (SWRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
-
-/*
- * These aren't really reads or writes, they pass down information about
- * parts of device that are now unused by the file system.
- */
-#define DISCARD_NOBARRIER       (WRITE | REQ_DISCARD)
-#define DISCARD_BARRIER         (WRITE | REQ_DISCARD | REQ_HARDBARRIER)
-#define DISCARD_SECURE          (DISCARD_NOBARRIER | REQ_SECURE)
+#define WRITE_FLUSH             (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+                                 REQ_FLUSH)
+#define WRITE_FUA               (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+                                 REQ_FUA)
+#define WRITE_FLUSH_FUA         (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+                                 REQ_FLUSH | REQ_FUA)
 
 #define SEL_IN          1
 #define SEL_OUT         2
@@ -244,6 +241,7 @@ struct inodes_stat_t {
 #define S_NOCMTIME      128     /* Do not update file c/mtime */
 #define S_SWAPFILE      256     /* Do not truncate: swapon got its bmaps */
 #define S_PRIVATE       512     /* Inode is fs-internal */
+#define S_IMA           1024    /* Inode has an associated IMA struct */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
@@ -278,6 +276,7 @@ struct inodes_stat_t {
 #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)
+#define IS_IMA(inode)           ((inode)->i_flags & S_IMA)
 
 /* 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. */
@@ -325,6 +324,7 @@ struct inodes_stat_t {
 #define FIGETBSZ   _IO(0x00,2)  /* get the block size used for bmap */
 #define FIFREEZE        _IOWR('X', 119, int)    /* Freeze */
 #define FITHAW          _IOWR('X', 120, int)    /* Thaw */
+#define FITRIM          _IOWR('X', 121, struct fstrim_range)    /* Trim */
 
 #define FS_IOC_GETFLAGS                 _IOR('f', 1, long)
 #define FS_IOC_SETFLAGS                 _IOW('f', 2, long)
@@ -413,7 +413,7 @@ extern void __init inode_init_early(void);
 extern void __init files_init(unsigned long);
 
 extern struct files_stat_struct files_stat;
-extern int get_max_files(void);
+extern unsigned long get_max_files(void);
 extern int sysctl_nr_open;
 extern struct inodes_stat_t inodes_stat;
 extern int leases_enable, lease_break_time;
@@ -733,7 +733,8 @@ struct posix_acl;
 
 struct inode {
         struct hlist_node       i_hash;
-        struct list_head        i_list;         /* backing dev IO list */
+        struct list_head        i_wb_list;      /* backing dev IO list */
+        struct list_head        i_lru;          /* inode LRU list */
         struct list_head        i_sb_list;
         struct list_head        i_dentry;
         unsigned long           i_ino;
@@ -785,6 +786,10 @@ struct inode {
 
         unsigned int            i_flags;
 
+#ifdef CONFIG_IMA
+        /* protected by i_lock */
+        unsigned int            i_readcount; /* struct files open RO */
+#endif
         atomic_t                i_writecount;
 #ifdef CONFIG_SECURITY
         void                    *i_security;
@@ -796,6 +801,11 @@ struct inode {
         void                    *i_private; /* fs or device private pointer */
 };
 
+static inline int inode_unhashed(struct inode *inode)
+{
+        return hlist_unhashed(&inode->i_hash);
+}
+
 /*
  * inode->i_mutex nesting subclasses for the lock validator:
  *
@@ -929,6 +939,9 @@ struct file {
 #define f_vfsmnt        f_path.mnt
         const struct file_operations    *f_op;
         spinlock_t              f_lock;  /* f_ep_links, f_flags, no IRQ */
+#ifdef CONFIG_SMP
+        int                     f_sb_list_cpu;
+#endif
         atomic_long_t           f_count;
         unsigned int            f_flags;
         fmode_t                 f_mode;
@@ -953,9 +966,6 @@ struct file {
         unsigned long f_mnt_write_state;
 #endif
 };
-extern spinlock_t files_lock;
-#define file_list_lock() spin_lock(&files_lock);
-#define file_list_unlock() spin_unlock(&files_lock);
 
 #define get_file(x)     atomic_long_inc(&(x)->f_count)
 #define fput_atomic(x)  atomic_long_add_unless(&(x)->f_count, -1, 1)
@@ -1046,7 +1056,6 @@ 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_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 *);
@@ -1119,7 +1128,9 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
 extern int fcntl_getlease(struct file *filp);
 
 /* fs/locks.c */
+void locks_free_lock(struct file_lock *fl);
 extern void locks_init_lock(struct file_lock *);
+extern struct file_lock * locks_alloc_lock(void);
 extern void locks_copy_lock(struct file_lock *, struct file_lock *);
 extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
 extern void locks_remove_posix(struct file *, fl_owner_t);
@@ -1140,6 +1151,8 @@ extern int vfs_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 lock_flocks(void);
+extern void unlock_flocks(void);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, struct flock __user *user)
 {
@@ -1282,6 +1295,14 @@ static inline int lock_may_write(struct inode *inode, loff_t start,
         return 1;
 }
 
+static inline void lock_flocks(void)
+{
+}
+
+static inline void unlock_flocks(void)
+{
+}
+
 #endif /* !CONFIG_FILE_LOCKING */
 
 
@@ -1298,6 +1319,11 @@ struct fasync_struct {
 
 /* SMP safe fasync helpers: */
 extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
+extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *);
+extern int fasync_remove_entry(struct file *, struct fasync_struct **);
+extern struct fasync_struct *fasync_alloc(void);
+extern void fasync_free(struct fasync_struct *);
+
 /* can be called from interrupts */
 extern void kill_fasync(struct fasync_struct **, int, int);
 
@@ -1346,7 +1372,11 @@ struct super_block {
 
         struct list_head        s_inodes;       /* all inodes */
         struct hlist_head       s_anon;         /* anonymous dentries for (nfs) exporting */
+#ifdef CONFIG_SMP
+        struct list_head __percpu *s_files;
+#else
         struct list_head        s_files;
+#endif
         /* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */
         struct list_head        s_dentry_lru;   /* unused dentry lru */
         int                     s_nr_dentry_unused;     /* # of dentry on lru */
@@ -1385,7 +1415,7 @@ struct super_block {
          * Saved mount options for lazy filesystems using
          * generic_show_options()
          */
-        char *s_options;
+        char __rcu *s_options;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
@@ -1582,6 +1612,7 @@ 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 (*trim_fs) (struct super_block *, struct fstrim_range *);
 };
 
 /*
@@ -1632,16 +1663,17 @@ struct super_operations {
  *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
-#define I_DIRTY_SYNC            1
-#define I_DIRTY_DATASYNC        2
-#define I_DIRTY_PAGES           4
+#define I_DIRTY_SYNC            (1 << 0)
+#define I_DIRTY_DATASYNC        (1 << 1)
+#define I_DIRTY_PAGES           (1 << 2)
 #define __I_NEW                 3
 #define I_NEW                   (1 << __I_NEW)
-#define I_WILL_FREE             16
-#define I_FREEING               32
-#define I_CLEAR                 64
+#define I_WILL_FREE             (1 << 4)
+#define I_FREEING               (1 << 5)
+#define I_CLEAR                 (1 << 6)
 #define __I_SYNC                7
 #define I_SYNC                  (1 << __I_SYNC)
+#define I_REFERENCED            (1 << 8)
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
 
@@ -1733,12 +1765,15 @@ static inline void file_accessed(struct file *file)
 }
 
 int sync_inode(struct inode *inode, struct writeback_control *wbc);
+int sync_inode_metadata(struct inode *inode, int wait);
 
 struct file_system_type {
         const char *name;
         int fs_flags;
         int (*get_sb) (struct file_system_type *, int,
                        const char *, void *, struct vfsmount *);
+        struct dentry *(*mount) (struct file_system_type *, int,
+                       const char *, void *);
         void (*kill_sb) (struct super_block *);
         struct module *owner;
         struct file_system_type * next;
@@ -1754,17 +1789,25 @@ struct file_system_type {
         struct lock_class_key i_alloc_sem_key;
 };
 
-extern int get_sb_ns(struct file_system_type *fs_type, int flags, void *data,
-        int (*fill_super)(struct super_block *, void *, int),
-        struct vfsmount *mnt);
+extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
+        void *data, int (*fill_super)(struct super_block *, void *, int));
+extern struct dentry *mount_bdev(struct file_system_type *fs_type,
+        int flags, const char *dev_name, void *data,
+        int (*fill_super)(struct super_block *, void *, int));
 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 vfsmount *mnt);
+extern struct dentry *mount_single(struct file_system_type *fs_type,
+        int flags, void *data,
+        int (*fill_super)(struct super_block *, void *, int));
 extern int get_sb_single(struct file_system_type *fs_type,
         int flags, void *data,
         int (*fill_super)(struct super_block *, void *, int),
         struct vfsmount *mnt);
+extern struct dentry *mount_nodev(struct file_system_type *fs_type,
+        int flags, void *data,
+        int (*fill_super)(struct super_block *, void *, int));
 extern int get_sb_nodev(struct file_system_type *fs_type,
         int flags, void *data,
         int (*fill_super)(struct super_block *, void *, int),
@@ -1780,9 +1823,8 @@ struct super_block *sget(struct file_system_type *type,
                         int (*test)(struct super_block *,void *),
                         int (*set)(struct super_block *,void *),
                         void *data);
-extern int get_sb_pseudo(struct file_system_type *, char *,
-        const struct super_operations *ops, unsigned long,
-        struct vfsmount *mnt);
+extern struct dentry *mount_pseudo(struct file_system_type *, char *,
+        const struct super_operations *ops, unsigned long);
 extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
 
 static inline void sb_mark_dirty(struct super_block *sb)
@@ -1825,6 +1867,7 @@ extern int current_umask(void);
 /* /sys/fs */
 extern struct kobject *fs_kobj;
 
+#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
 extern int rw_verify_area(int, struct file *, loff_t *, size_t);
 
 #define FLOCK_VERIFY_READ  1
@@ -2077,7 +2120,6 @@ extern int check_disk_change(struct block_device *);
 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);
 
@@ -2161,7 +2203,7 @@ extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
 
 extern int inode_init_always(struct super_block *, struct inode *);
 extern void inode_init_once(struct inode *);
-extern void inode_add_to_lists(struct super_block *, struct inode *);
+extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
 extern struct inode * igrab(struct inode *);
 extern ino_t iunique(struct super_block *, ino_t);
@@ -2181,11 +2223,11 @@ 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 *);
 extern void unlock_new_inode(struct inode *);
+extern unsigned int get_next_ino(void);
 
 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 void __destroy_inode(struct inode *);
 extern struct inode *new_inode(struct super_block *);
 extern int should_remove_suid(struct dentry *);
@@ -2193,12 +2235,12 @@ 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) {
+static inline void insert_inode_hash(struct inode *inode)
+{
         __insert_inode_hash(inode, inode->i_ino);
 }
+extern void inode_sb_list_add(struct inode *inode);
 
-extern void file_move(struct file *f, struct list_head *list);
-extern void file_kill(struct file *f);
 #ifdef CONFIG_BLOCK
 extern void submit_bio(int, struct bio *);
 extern int bdev_read_only(struct block_device *);
@@ -2381,6 +2423,8 @@ extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
 
 extern int generic_file_fsync(struct file *, int);
 
+extern int generic_check_addressable(unsigned, u64);
+
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
                                 struct page *, struct page *);
@@ -2457,6 +2501,7 @@ static const struct file_operations __fops = {				\
         .release = simple_attr_release,                                 \
         .read    = simple_attr_read,                                    \
         .write   = simple_attr_write,                                   \
+        .llseek  = generic_file_llseek,                                 \
 };
 
 static inline void __attribute__((format(printf, 1, 2)))
@@ -2477,7 +2522,10 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf,
 struct ctl_table;
 int proc_nr_files(struct ctl_table *table, int write,
                   void __user *buffer, size_t *lenp, loff_t *ppos);
-
+int proc_nr_dentry(struct ctl_table *table, int write,
+                  void __user *buffer, size_t *lenp, loff_t *ppos);
+int proc_nr_inodes(struct ctl_table *table, int write,
+                   void __user *buffer, size_t *lenp, loff_t *ppos);
 int __init get_filesystem_list(char *buf);
 
 #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])