Merge 'Linux v3.0' into Litmus

Some notes:
* Litmus^RT scheduling class is the topmost scheduling class
  (above stop_sched_class).
* scheduler_ipi() function (e.g., in smp_reschedule_interrupt())
  may increase IPI latencies.
* Added path into schedule() to quickly re-evaluate scheduling
  decision without becoming preemptive again. This used to be
  a standard path before the removal of BKL.

Conflicts:
	Makefile
	arch/arm/kernel/calls.S
	arch/arm/kernel/smp.c
	arch/x86/include/asm/unistd_32.h
	arch/x86/kernel/smp.c
	arch/x86/kernel/syscall_table_32.S
	include/linux/hrtimer.h
	kernel/printk.c
	kernel/sched.c
	kernel/sched_fair.c

1 files changed, 248 insertions, 131 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 29a672458d27..8d5834bcb891 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
@@ -22,7 +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)
@@ -32,11 +34,17 @@
 #define SEEK_END        2       /* seek relative to end of file */
 #define SEEK_MAX        SEEK_END
 
+struct fstrim_range {
+        __u64 start;
+        __u64 len;
+        __u64 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 +100,12 @@ 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 is opened with O_PATH; almost nothing can be done with it */
+#define FMODE_PATH              ((__force fmode_t)0x4000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY          ((__force fmode_t)0x1000000)
 
@@ -125,22 +139,16 @@ 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.
- * WRITE_SYNC_PLUG      Synchronous write. Identical to WRITE, but passes down
+ * WRITE_SYNC           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,
- *                      WRITE_SYNC_PLUG does not do this as we could be
- *                      submitting more writes before we actually wait on any
- *                      of them.
- * WRITE_SYNC           Like WRITE_SYNC_PLUG, but also unplugs the device
- *                      immediately after submission. The write equivalent
- *                      of READ_SYNC.
- * WRITE_ODIRECT_PLUG   Special case write for O_DIRECT only.
- * 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.
+ *                      shortly. The write equivalent of READ_SYNC.
+ * WRITE_ODIRECT        Special case write for O_DIRECT only.
+ * WRITE_FLUSH          Like WRITE_SYNC but with preceding cache flush.
+ * WRITE_FUA            Like WRITE_SYNC but data is guaranteed to be on
+ *                      non-volatile media on completion.
+ * WRITE_FLUSH_FUA      Combination of WRITE_FLUSH and FUA. The IO is preceded
+ *                      by a cache flush and data is guaranteed to be on
+ *                      non-volatile media on completion.
  *
  */
 #define RW_MASK                 REQ_WRITE
@@ -150,22 +158,14 @@ struct inodes_stat_t {
 #define WRITE                   RW_MASK
 #define READA                   RWA_MASK
 
-#define READ_SYNC               (READ | REQ_SYNC | REQ_UNPLUG)
+#define READ_SYNC               (READ | REQ_SYNC)
 #define READ_META               (READ | REQ_META)
-#define WRITE_SYNC_PLUG         (WRITE | REQ_SYNC | REQ_NOIDLE)
-#define WRITE_SYNC              (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
-#define WRITE_ODIRECT_PLUG      (WRITE | REQ_SYNC)
+#define WRITE_SYNC              (WRITE | REQ_SYNC | REQ_NOIDLE)
+#define WRITE_ODIRECT           (WRITE | REQ_SYNC)
 #define WRITE_META              (WRITE | REQ_META)
-#define WRITE_BARRIER           (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
-                                 REQ_HARDBARRIER)
-
-/*
- * 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_FLUSH)
+#define WRITE_FUA               (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
+#define WRITE_FLUSH_FUA         (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
 
 #define SEL_IN          1
 #define SEL_OUT         2
@@ -208,6 +208,7 @@ 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)
@@ -235,6 +236,9 @@ 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 */
+#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
@@ -269,6 +273,9 @@ 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)
+#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. */
@@ -316,6 +323,7 @@ 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)
@@ -353,6 +361,7 @@ struct inodes_stat_t {
 #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_NOCOW_FL                     0x00800000 /* Do not cow file */
 #define FS_RESERVED_FL                  0x80000000 /* reserved for ext2 lib */
 
 #define FS_FL_USER_VISIBLE              0x0003DFFF /* User visible flags */
@@ -373,7 +382,6 @@ struct inodes_stat_t {
 #include <linux/path.h>
 #include <linux/stat.h>
 #include <linux/cache.h>
-#include <linux/kobject.h>
 #include <linux/list.h>
 #include <linux/radix-tree.h>
 #include <linux/prio_tree.h>
@@ -383,6 +391,7 @@ struct inodes_stat_t {
 #include <linux/capability.h>
 #include <linux/semaphore.h>
 #include <linux/fiemap.h>
+#include <linux/rculist_bl.h>
 
 #include <asm/atomic.h>
 #include <asm/byteorder.h>
@@ -392,6 +401,7 @@ struct hd_geometry;
 struct iovec;
 struct nameidata;
 struct kiocb;
+struct kobject;
 struct pipe_inode_info;
 struct poll_table_struct;
 struct kstatfs;
@@ -404,7 +414,7 @@ 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;
@@ -458,7 +468,7 @@ struct iattr {
         struct timespec ia_ctime;
 
         /*
-         * Not an attribute, but an auxilary info for filesystems wanting to
+         * Not an attribute, but an auxiliary info for filesystems wanting to
          * implement an ftruncate() like method.  NOTE: filesystem should
          * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
          */
@@ -571,7 +581,6 @@ typedef int (*read_actor_t)(read_descriptor_t *, struct page *,
 struct address_space_operations {
         int (*writepage)(struct page *page, struct writeback_control *wbc);
         int (*readpage)(struct file *, struct page *);
-        void (*sync_page)(struct page *);
 
         /* Write back some dirty pages from this mapping. */
         int (*writepages)(struct address_space *, struct writeback_control *);
@@ -593,6 +602,7 @@ struct address_space_operations {
         sector_t (*bmap)(struct address_space *, sector_t);
         void (*invalidatepage) (struct page *, unsigned long);
         int (*releasepage) (struct page *, gfp_t);
+        void (*freepage)(struct page *);
         ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
                         loff_t offset, unsigned long nr_segs);
         int (*get_xip_mem)(struct address_space *, pgoff_t, int,
@@ -606,6 +616,8 @@ struct address_space_operations {
         int (*error_remove_page)(struct address_space *, struct page *);
 };
 
+extern const struct address_space_operations empty_aops;
+
 /*
  * pagecache_write_begin/pagecache_write_end must be used by general code
  * to write into the pagecache.
@@ -626,8 +638,8 @@ 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 */
@@ -639,22 +651,23 @@ struct address_space {
 } __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
+         * must be enforced here for CRIS, to let the least significant bit
          * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
          */
 
 struct block_device {
         dev_t                   bd_dev;  /* not a kdev_t - it's a search key */
+        int                     bd_openers;
         struct inode *          bd_inode;       /* will die */
         struct super_block *    bd_super;
-        int                     bd_openers;
         struct mutex            bd_mutex;       /* open/close mutex */
         struct list_head        bd_inodes;
         void *                  bd_claiming;
         void *                  bd_holder;
         int                     bd_holders;
+        bool                    bd_write_holder;
 #ifdef CONFIG_SYSFS
-        struct list_head        bd_holder_list;
+        struct list_head        bd_holder_disks;
 #endif
         struct block_device *   bd_contains;
         unsigned                bd_block_size;
@@ -724,15 +737,35 @@ struct posix_acl;
 struct inode_obj_id_table;
 
 struct inode {
+        /* RCU path lookup touches following: */
+        umode_t                 i_mode;
+        uid_t                   i_uid;
+        gid_t                   i_gid;
+        const struct inode_operations   *i_op;
+        struct super_block      *i_sb;
+
+        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           dirtied_when;   /* jiffies of first dirtying */
+
         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;
+        union {
+                struct list_head        i_dentry;
+                struct rcu_head         i_rcu;
+        };
         unsigned long           i_ino;
         atomic_t                i_count;
         unsigned int            i_nlink;
-        uid_t                   i_uid;
-        gid_t                   i_gid;
         dev_t                   i_rdev;
         unsigned int            i_blkbits;
         u64                     i_version;
@@ -745,13 +778,8 @@ struct inode {
         struct timespec         i_ctime;
         blkcnt_t                i_blocks;
         unsigned short          i_bytes;
-        umode_t                 i_mode;
-        spinlock_t              i_lock; /* i_blocks, i_bytes, maybe i_size */
-        struct mutex            i_mutex;
         struct rw_semaphore     i_alloc_sem;
-        const struct inode_operations   *i_op;
         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;
         struct address_space    i_data;
@@ -772,15 +800,10 @@ struct inode {
         struct hlist_head       i_fsnotify_marks;
 #endif
 
-        unsigned long           i_state;
-        unsigned long           dirtied_when;   /* jiffies of first dirtying */
-
-        unsigned int            i_flags;
-
-        atomic_t                i_writecount;
-#ifdef CONFIG_SECURITY
-        void                    *i_security;
+#ifdef CONFIG_IMA
+        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;
@@ -790,6 +813,11 @@ 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:
  *
@@ -951,6 +979,13 @@ struct file {
 #endif
 };
 
+struct file_handle {
+        __u32 handle_bytes;
+        int handle_type;
+        /* file identifier */
+        unsigned char f_handle[0];
+};
+
 #define get_file(x)     atomic_long_inc(&(x)->f_count)
 #define fput_atomic(x)  atomic_long_add_unless(&(x)->f_count, -1, 1)
 #define file_count(x)   atomic_long_read(&(x)->f_count)
@@ -1040,10 +1075,8 @@ 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 *);
         int (*fl_change)(struct file_lock **, int);
 };
 
@@ -1096,10 +1129,6 @@ struct file_lock {
 
 #include <linux/fcntl.h>
 
-/* temporary stubs for BKL removal */
-#define lock_flocks() lock_kernel()
-#define unlock_flocks() unlock_kernel()
-
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
 #ifdef CONFIG_FILE_LOCKING
@@ -1117,7 +1146,9 @@ 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);
@@ -1138,6 +1169,8 @@ 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)
 {
@@ -1280,6 +1313,14 @@ 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 */
 
 
@@ -1296,6 +1337,11 @@ 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);
 
@@ -1343,13 +1389,13 @@ struct super_block {
         const struct xattr_handler **s_xattr;
 
         struct list_head        s_inodes;       /* all inodes */
-        struct hlist_head       s_anon;         /* anonymous dentries for (nfs) exporting */
+        struct hlist_bl_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 */
+        /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
         struct list_head        s_dentry_lru;   /* unused dentry lru */
         int                     s_nr_dentry_unused;     /* # of dentry on lru */
 
@@ -1363,6 +1409,7 @@ struct super_block {
         wait_queue_head_t       s_wait_unfrozen;
 
         char s_id[32];                          /* Informational name */
+        u8 s_uuid[16];                          /* UUID */
 
         void                    *s_fs_info;     /* Filesystem private info */
         fmode_t                 s_mode;
@@ -1387,7 +1434,13 @@ struct super_block {
          * Saved mount options for lazy filesystems using
          * generic_show_options()
          */
-        char *s_options;
+        char __rcu *s_options;
+        const struct dentry_operations *s_d_op; /* default d_op for dentries */
+
+        /*
+         * Saved pool identifier for cleancache (-1 means none)
+         */
+        int cleancache_poolid;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
@@ -1408,8 +1461,13 @@ enum {
 #define put_fs_excl() atomic_dec(&current->fs_excl)
 #define has_fs_excl() atomic_read(&current->fs_excl)
 
-#define is_owner_or_cap(inode)  \
-        ((current_fsuid() == (inode)->i_uid) || capable(CAP_FOWNER))
+/*
+ * until VFS tracks user namespaces for inodes, just make all files
+ * belong to init_user_ns
+ */
+extern struct user_namespace init_user_ns;
+#define inode_userns(inode) (&init_user_ns)
+extern bool inode_owner_or_capable(const struct inode *inode);
 
 /* not quite ready to be deprecated, but... */
 extern void lock_super(struct super_block *);
@@ -1445,8 +1503,8 @@ struct fiemap_extent_info {
         unsigned int fi_flags;          /* Flags as passed from user */
         unsigned int fi_extents_mapped; /* Number of mapped extents */
         unsigned int fi_extents_max;    /* Size of fiemap_extent array */
-        struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent
-                                                 * array */
+        struct fiemap_extent __user *fi_extents_start; /* Start of
+                                                        fiemap_extent array */
 };
 int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
                             u64 phys, u64 len, u32 flags);
@@ -1514,11 +1572,22 @@ struct file_operations {
         ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
         ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
         int (*setlease)(struct file *, long, struct file_lock **);
+        long (*fallocate)(struct file *file, int mode, loff_t offset,
+                          loff_t len);
 };
 
+#define IPERM_FLAG_RCU  0x0001
+
 struct inode_operations {
-        int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
         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 (*readlink) (struct dentry *, char __user *,int);
+        void (*put_link) (struct dentry *, struct nameidata *, void *);
+
+        int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
         int (*link) (struct dentry *,struct inode *,struct dentry *);
         int (*unlink) (struct inode *,struct dentry *);
         int (*symlink) (struct inode *,struct dentry *,const char *);
@@ -1527,12 +1596,7 @@ struct inode_operations {
         int (*mknod) (struct inode *,struct dentry *,int,dev_t);
         int (*rename) (struct inode *, struct dentry *,
                         struct inode *, struct dentry *);
-        int (*readlink) (struct dentry *, char __user *,int);
-        void * (*follow_link) (struct dentry *, struct nameidata *);
-        void (*put_link) (struct dentry *, struct nameidata *, void *);
         void (*truncate) (struct inode *);
-        int (*permission) (struct inode *, int);
-        int (*check_acl)(struct inode *, int);
         int (*setattr) (struct dentry *, struct iattr *);
         int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
         int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
@@ -1540,11 +1604,9 @@ struct inode_operations {
         ssize_t (*listxattr) (struct dentry *, char *, size_t);
         int (*removexattr) (struct dentry *, const char *);
         void (*truncate_range)(struct inode *, loff_t, loff_t);
-        long (*fallocate)(struct inode *inode, int mode, loff_t offset,
-                          loff_t len);
         int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
                       u64 len);
-};
+} ____cacheline_aligned;
 
 struct seq_file;
 
@@ -1564,7 +1626,7 @@ 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 *);
@@ -1578,6 +1640,8 @@ struct super_operations {
         void (*umount_begin) (struct super_block *);
 
         int (*show_options)(struct seq_file *, struct vfsmount *);
+        int (*show_devname)(struct seq_file *, struct vfsmount *);
+        int (*show_path)(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);
@@ -1587,7 +1651,7 @@ struct super_operations {
 };
 
 /*
- * Inode state bits.  Protected by inode_lock.
+ * Inode state bits.  Protected by inode->i_lock
  *
  * Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
  * I_DIRTY_DATASYNC and I_DIRTY_PAGES.
@@ -1634,16 +1698,17 @@ 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)
 
@@ -1735,12 +1800,13 @@ 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;
@@ -1756,21 +1822,17 @@ 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 int get_sb_bdev(struct file_system_type *fs_type,
+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),
-        struct vfsmount *mnt);
-extern int get_sb_single(struct file_system_type *fs_type,
+        int (*fill_super)(struct super_block *, void *, int));
+extern struct dentry *mount_single(struct file_system_type *fs_type,
         int flags, void *data,
-        int (*fill_super)(struct super_block *, void *, int),
-        struct vfsmount *mnt);
-extern int get_sb_nodev(struct file_system_type *fs_type,
+        int (*fill_super)(struct super_block *, void *, int));
+extern struct dentry *mount_nodev(struct file_system_type *fs_type,
         int flags, void *data,
-        int (*fill_super)(struct super_block *, void *, int),
-        struct vfsmount *mnt);
+        int (*fill_super)(struct super_block *, void *, int));
 void generic_shutdown_super(struct super_block *sb);
 void kill_block_super(struct super_block *sb);
 void kill_anon_super(struct super_block *sb);
@@ -1782,10 +1844,10 @@ 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 void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
+extern struct dentry *mount_pseudo(struct file_system_type *, char *,
+        const struct super_operations *ops,
+        const struct dentry_operations *dops,
+        unsigned long);
 
 static inline void sb_mark_dirty(struct super_block *sb)
 {
@@ -1818,6 +1880,8 @@ extern void drop_collected_mounts(struct vfsmount *);
 extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
                           struct vfsmount *);
 extern int vfs_statfs(struct path *, struct kstatfs *);
+extern int user_statfs(const char __user *, struct kstatfs *);
+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);
@@ -1827,6 +1891,7 @@ 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
@@ -1933,6 +1998,8 @@ extern int do_fallocate(struct file *file, int mode, loff_t offset,
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
                         int mode);
 extern struct file *filp_open(const char *, int, int);
+extern struct file *file_open_root(struct dentry *, struct vfsmount *,
+                                   const char *, int);
 extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
                                  const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
@@ -1965,7 +2032,6 @@ extern struct block_device *bdgrab(struct block_device *bdev);
 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 struct block_device *open_by_devnum(dev_t, fmode_t);
 extern void invalidate_bdev(struct block_device *);
 extern int sync_blockdev(struct block_device *bdev);
 extern struct super_block *freeze_bdev(struct block_device *);
@@ -1996,16 +2062,26 @@ extern const struct file_operations def_fifo_fops;
 extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
 extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
-extern int blkdev_get(struct block_device *, fmode_t);
-extern int blkdev_put(struct block_device *, fmode_t);
-extern int bd_claim(struct block_device *, void *);
-extern void bd_release(struct block_device *);
+extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
+extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
+                                               void *holder);
+extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
+                                              void *holder);
+extern int blkdev_put(struct block_device *bdev, fmode_t mode);
 #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 *);
+extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
+extern void bd_unlink_disk_holder(struct block_device *bdev,
+                                  struct gendisk *disk);
 #else
-#define bd_claim_by_disk(bdev, holder, disk)    bd_claim(bdev, holder)
-#define bd_release_from_disk(bdev, disk)        bd_release(bdev)
+static inline int bd_link_disk_holder(struct block_device *bdev,
+                                      struct gendisk *disk)
+{
+        return 0;
+}
+static inline void bd_unlink_disk_holder(struct block_device *bdev,
+                                         struct gendisk *disk)
+{
+}
 #endif
 #endif
 
@@ -2041,8 +2117,6 @@ static inline void unregister_chrdev(unsigned int major, const char *name)
 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_exclusive(const char *, fmode_t, void *);
-extern void close_bdev_exclusive(struct block_device *, fmode_t);
 extern void blkdev_show(struct seq_file *,off_t);
 
 #else
@@ -2076,10 +2150,9 @@ extern void check_disk_size_change(struct gendisk *disk,
                                    struct block_device *bdev);
 extern int revalidate_disk(struct gendisk *);
 extern int check_disk_change(struct block_device *);
-extern int __invalidate_device(struct block_device *);
+extern int __invalidate_device(struct block_device *, bool);
 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);
 
@@ -2118,8 +2191,8 @@ 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,
-                int (*check_acl)(struct inode *, int));
+extern int generic_permission(struct inode *, int, unsigned int,
+                int (*check_acl)(struct inode *, int, unsigned int));
 
 static inline bool execute_ok(struct inode *inode)
 {
@@ -2137,15 +2210,31 @@ static inline void allow_write_access(struct file *file)
         if (file)
                 atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
 }
+#ifdef CONFIG_IMA
+static inline void i_readcount_dec(struct inode *inode)
+{
+        BUG_ON(!atomic_read(&inode->i_readcount));
+        atomic_dec(&inode->i_readcount);
+}
+static inline void i_readcount_inc(struct inode *inode)
+{
+        atomic_inc(&inode->i_readcount);
+}
+#else
+static inline void i_readcount_dec(struct inode *inode)
+{
+        return;
+}
+static inline void i_readcount_inc(struct inode *inode)
+{
+        return;
+}
+#endif
 extern int do_pipe_flags(int *, int);
 extern struct file *create_read_pipe(struct file *f, int flags);
 extern struct file *create_write_pipe(int flags);
 extern void free_write_pipe(struct file *);
 
-extern struct file *do_filp_open(int dfd, const char *pathname,
-                int open_flag, int mode, int acc_mode);
-extern int may_open(struct path *, int, int);
-
 extern int kernel_read(struct file *, loff_t, char *, unsigned long);
 extern struct file * open_exec(const char *);
 
@@ -2163,7 +2252,8 @@ 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 address_space_init_once(struct address_space *mapping);
+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);
@@ -2183,21 +2273,24 @@ 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 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) {
+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);
 
 #ifdef CONFIG_BLOCK
 extern void submit_bio(int, struct bio *);
@@ -2381,6 +2474,8 @@ 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 *);
@@ -2402,6 +2497,10 @@ static inline ino_t parent_ino(struct dentry *dentry)
 {
         ino_t res;
 
+        /*
+         * Don't strictly need d_lock here? If the parent ino could change
+         * then surely we'd have a deeper race in the caller?
+         */
         spin_lock(&dentry->d_lock);
         res = dentry->d_parent->d_inode->i_ino;
         spin_unlock(&dentry->d_lock);
@@ -2457,6 +2556,7 @@ 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)))
@@ -2477,12 +2577,29 @@ 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 __FMODE_EXEC            ((__force int) FMODE_EXEC)
+#define __FMODE_NONOTIFY        ((__force int) FMODE_NONOTIFY)
+
 #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
 #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
-                                            (flag & FMODE_NONOTIFY)))
+                                            (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 */