1 files changed, 74 insertions, 47 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 334d68a17108..32b38cd829d3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -34,9 +34,9 @@
 #define SEEK_MAX        SEEK_END
 
 struct fstrim_range {
-        uint64_t start;
-        uint64_t len;
-        uint64_t minlen;
+        __u64 start;
+        __u64 len;
+        __u64 minlen;
 };
 
 /* And dynamically-tunable limits and defaults: */
@@ -242,6 +242,7 @@ struct inodes_stat_t {
 #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 */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
@@ -277,6 +278,7 @@ struct inodes_stat_t {
 #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)
 
 /* 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. */
@@ -382,7 +384,6 @@ 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>
@@ -392,6 +393,7 @@ 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>
@@ -401,6 +403,7 @@ struct hd_geometry;
 struct iovec;
 struct nameidata;
 struct kiocb;
+struct kobject;
 struct pipe_inode_info;
 struct poll_table_struct;
 struct kstatfs;
@@ -602,6 +605,7 @@ 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,
@@ -662,8 +666,9 @@ struct block_device {
         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;
@@ -732,16 +737,31 @@ struct posix_acl;
 #define ACL_NOT_CACHED ((void *)(-1))
 
 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;
+        struct mutex            i_mutex;
+
+        unsigned long           i_state;
+        unsigned long           dirtied_when;   /* jiffies of first dirtying */
+
         struct hlist_node       i_hash;
         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;
@@ -754,13 +774,8 @@ 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;
@@ -781,11 +796,6 @@ 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;
-
 #ifdef CONFIG_IMA
         /* protected by i_lock */
         unsigned int            i_readcount; /* struct files open RO */
@@ -1058,7 +1068,6 @@ struct lock_manager_operations {
         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_mylease)(struct file_lock *, struct file_lock *);
         int (*fl_change)(struct file_lock **, int);
 };
 
@@ -1371,13 +1380,13 @@ 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 */
 
@@ -1416,6 +1425,7 @@ struct super_block {
          * generic_show_options()
          */
         char __rcu *s_options;
+        const struct dentry_operations *s_d_op; /* default d_op for dentries */
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
@@ -1473,8 +1483,8 @@ 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);
@@ -1542,11 +1552,22 @@ 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 *);
@@ -1555,12 +1576,7 @@ 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);
@@ -1568,11 +1584,9 @@ 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;
 
@@ -1612,7 +1626,6 @@ 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 *);
 };
 
 /*
@@ -1824,7 +1837,9 @@ struct super_block *sget(struct file_system_type *type,
                         int (*set)(struct super_block *,void *),
                         void *data);
 extern struct dentry *mount_pseudo(struct file_system_type *, char *,
-        const struct super_operations *ops, unsigned long);
+        const struct super_operations *ops,
+        const struct dentry_operations *dops,
+        unsigned long);
 extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
 
 static inline void sb_mark_dirty(struct super_block *sb)
@@ -2006,7 +2021,6 @@ 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 *);
@@ -2037,16 +2051,26 @@ 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
 
@@ -2082,8 +2106,6 @@ 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
@@ -2158,8 +2180,8 @@ 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)
 {
@@ -2230,6 +2252,7 @@ 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 void free_inode_nonrcu(struct inode *inode);
 extern int should_remove_suid(struct dentry *);
 extern int file_remove_suid(struct file *);
 
@@ -2446,6 +2469,10 @@ 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);