Merge branch 'next' into for-linus

Prepare first round of input updates for 3.20.

1 files changed, 112 insertions, 54 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 94187721ad4..42efe13077b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -18,6 +18,7 @@
 #include <linux/pid.h>
 #include <linux/bug.h>
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/capability.h>
 #include <linux/semaphore.h>
 #include <linux/fiemap.h>
@@ -134,7 +135,7 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
 
 /* File was opened by fanotify and shouldn't generate fanotify events */
-#define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
+#define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
@@ -192,8 +193,6 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define READ			0
 #define WRITE			RW_MASK
 #define READA			RWA_MASK
-#define KERNEL_READ		(READ|REQ_KERNEL)
-#define KERNEL_WRITE		(WRITE|REQ_KERNEL)
 
 #define READ_SYNC		(READ | REQ_SYNC)
 #define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
@@ -225,6 +224,13 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define ATTR_TIMES_SET	(1 << 16)
 
 /*
+ * Whiteout is represented by a char device.  The following constants define the
+ * mode and device number to use.
+ */
+#define WHITEOUT_MODE 0
+#define WHITEOUT_DEV 0
+
+/*
  * This is the Inode Attributes structure, used for notify_change().  It
  * uses the above definitions as flags, to know which values have changed.
  * Also, in this manner, a Filesystem can look at only the values it cares
@@ -256,6 +262,12 @@ struct iattr {
  */
 #include <linux/quota.h>
 
+/*
+ * Maximum number of layers of fs stack.  Needs to be limited to
+ * prevent kernel stack overflow
+ */
+#define FILESYSTEM_MAX_STACK_DEPTH 2
+
 /** 
  * enum positive_aop_returns - aop return codes with specific semantics
  *
@@ -390,7 +402,7 @@ struct address_space {
 	atomic_t		i_mmap_writable;/* count VM_SHARED mappings */
 	struct rb_root		i_mmap;		/* tree of private and shared mappings */
 	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
-	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
+	struct rw_semaphore	i_mmap_rwsem;	/* protect tree, count, list */
 	/* Protected by tree_lock together with the radix tree */
 	unsigned long		nrpages;	/* number of total pages */
 	unsigned long		nrshadows;	/* number of shadow entries */
@@ -456,6 +468,26 @@ struct block_device {
 
 int mapping_tagged(struct address_space *mapping, int tag);
 
+static inline void i_mmap_lock_write(struct address_space *mapping)
+{
+	down_write(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_unlock_write(struct address_space *mapping)
+{
+	up_write(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_lock_read(struct address_space *mapping)
+{
+	down_read(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_unlock_read(struct address_space *mapping)
+{
+	up_read(&mapping->i_mmap_rwsem);
+}
+
 /*
  * Might pages of this file be mapped into userspace?
  */
@@ -595,9 +627,6 @@ struct inode {
 	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
 	struct file_lock	*i_flock;
 	struct address_space	i_data;
-#ifdef CONFIG_QUOTA
-	struct dquot		*i_dquot[MAXQUOTAS];
-#endif
 	struct list_head	i_devices;
 	union {
 		struct pipe_inode_info	*i_pipe;
@@ -628,11 +657,13 @@ static inline int inode_unhashed(struct inode *inode)
  * 2: child/target
  * 3: xattr
  * 4: second non-directory
- * The last is for certain operations (such as rename) which lock two
+ * 5: second parent (when locking independent directories in rename)
+ *
+ * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
  * non-directories at once.
  *
  * The locking order between these classes is
- * parent -> child -> normal -> xattr -> second non-directory
+ * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
  */
 enum inode_i_mutex_lock_class
 {
@@ -640,7 +671,8 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_PARENT,
 	I_MUTEX_CHILD,
 	I_MUTEX_XATTR,
-	I_MUTEX_NONDIR2
+	I_MUTEX_NONDIR2,
+	I_MUTEX_PARENT2,
 };
 
 void lock_two_nondirectories(struct inode *, struct inode*);
@@ -775,7 +807,6 @@ struct file {
 		struct rcu_head 	fu_rcuhead;
 	} f_u;
 	struct path		f_path;
-#define f_dentry	f_path.dentry
 	struct inode		*f_inode;	/* cached value */
 	const struct file_operations	*f_op;
 
@@ -851,13 +882,7 @@ static inline struct file *get_file(struct file *f)
  */
 #define FILE_LOCK_DEFERRED 1
 
-/*
- * The POSIX file lock owner is determined by
- * the "struct files_struct" in the thread group
- * (or NULL for no owner - BSD locks).
- *
- * Lockd stuffs a "host" pointer into this.
- */
+/* legacy typedef, should eventually be removed */
 typedef void *fl_owner_t;
 
 struct file_lock_operations {
@@ -868,10 +893,13 @@ struct file_lock_operations {
 struct lock_manager_operations {
 	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
 	unsigned long (*lm_owner_key)(struct file_lock *);
+	void (*lm_get_owner)(struct file_lock *, struct file_lock *);
+	void (*lm_put_owner)(struct file_lock *);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
-	int (*lm_grant)(struct file_lock *, struct file_lock *, int);
-	void (*lm_break)(struct file_lock *);
-	int (*lm_change)(struct file_lock **, int);
+	int (*lm_grant)(struct file_lock *, int);
+	bool (*lm_break)(struct file_lock *);
+	int (*lm_change)(struct file_lock **, int, struct list_head *);
+	void (*lm_setup)(struct file_lock *, void **);
 };
 
 struct lock_manager {
@@ -966,7 +994,7 @@ 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_copy_conflock(struct file_lock *, struct file_lock *);
 extern void locks_remove_posix(struct file *, fl_owner_t);
 extern void locks_remove_file(struct file *);
 extern void locks_release_private(struct file_lock *);
@@ -980,11 +1008,9 @@ extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
 extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
 extern void lease_get_mtime(struct inode *, struct timespec *time);
-extern int generic_setlease(struct file *, long, struct file_lock **);
-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 int generic_setlease(struct file *, long, struct file_lock **, void **priv);
+extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
+extern int lease_modify(struct file_lock **, int, struct list_head *);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
 			      struct flock __user *user)
@@ -1013,12 +1039,12 @@ static inline int fcntl_setlk64(unsigned int fd, struct file *file,
 #endif
 static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
-	return 0;
+	return -EINVAL;
 }
 
 static inline int fcntl_getlease(struct file *filp)
 {
-	return 0;
+	return F_UNLCK;
 }
 
 static inline void locks_init_lock(struct file_lock *fl)
@@ -1026,7 +1052,7 @@ static inline void locks_init_lock(struct file_lock *fl)
 	return;
 }
 
-static inline void __locks_copy_lock(struct file_lock *new, struct file_lock *fl)
+static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
 	return;
 }
@@ -1100,33 +1126,22 @@ static inline void lease_get_mtime(struct inode *inode, struct timespec *time)
 }
 
 static inline int generic_setlease(struct file *filp, long arg,
-				    struct file_lock **flp)
+				    struct file_lock **flp, void **priv)
 {
 	return -EINVAL;
 }
 
 static inline int vfs_setlease(struct file *filp, long arg,
-			       struct file_lock **lease)
+			       struct file_lock **lease, void **priv)
 {
 	return -EINVAL;
 }
 
-static inline int lease_modify(struct file_lock **before, int arg)
+static inline int lease_modify(struct file_lock **before, int arg,
+			       struct list_head *dispose)
 {
 	return -EINVAL;
 }
-
-static inline int lock_may_read(struct inode *inode, loff_t start,
-				unsigned long len)
-{
-	return 1;
-}
-
-static inline int lock_may_write(struct inode *inode, loff_t start,
-				 unsigned long len)
-{
-	return 1;
-}
 #endif /* !CONFIG_FILE_LOCKING */
 
 
@@ -1151,8 +1166,8 @@ extern void fasync_free(struct fasync_struct *);
 /* can be called from interrupts */
 extern void kill_fasync(struct fasync_struct **, int, int);
 
-extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
-extern int f_setown(struct file *filp, unsigned long arg, int force);
+extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
+extern void f_setown(struct file *filp, unsigned long arg, int force);
 extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
 extern int send_sigurg(struct fown_struct *fown);
@@ -1226,6 +1241,7 @@ struct super_block {
 	struct backing_dev_info *s_bdi;
 	struct mtd_info		*s_mtd;
 	struct hlist_node	s_instances;
+	unsigned int		s_quota_types;	/* Bitmask of supported quota types */
 	struct quota_info	s_dquot;	/* Diskquota specific options */
 
 	struct sb_writers	s_writers;
@@ -1284,6 +1300,11 @@ struct super_block {
 	struct list_lru		s_dentry_lru ____cacheline_aligned_in_smp;
 	struct list_lru		s_inode_lru ____cacheline_aligned_in_smp;
 	struct rcu_head		rcu;
+
+	/*
+	 * Indicates how deep in a filesystem stack this SB is
+	 */
+	int s_stack_depth;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
@@ -1416,6 +1437,7 @@ extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct ino
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
+extern int vfs_whiteout(struct inode *, struct dentry *);
 
 /*
  * VFS dentry helper functions.
@@ -1463,7 +1485,10 @@ int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
  * This allows the kernel to read directories into kernel space or
  * to have different dirent layouts depending on the binary type.
  */
-typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
+struct dir_context;
+typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
+			 unsigned);
+
 struct dir_context {
 	const filldir_t actor;
 	loff_t pos;
@@ -1493,6 +1518,7 @@ struct file_operations {
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
+	void (*mremap)(struct file *, struct vm_area_struct *);
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *, fl_owner_t id);
 	int (*release) (struct inode *, struct file *);
@@ -1506,10 +1532,10 @@ struct file_operations {
 	int (*flock) (struct file *, int, struct file_lock *);
 	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 **);
+	int (*setlease)(struct file *, long, struct file_lock **, void **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
-	int (*show_fdinfo)(struct seq_file *m, struct file *f);
+	void (*show_fdinfo)(struct seq_file *m, struct file *f);
 };
 
 struct inode_operations {
@@ -1546,6 +1572,9 @@ struct inode_operations {
 			   umode_t create_mode, int *opened);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
+
+	/* WARNING: probably going away soon, do not use! */
+	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 } ____cacheline_aligned;
 
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
@@ -1553,6 +1582,7 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      struct iovec *fast_pointer,
 			      struct iovec **ret_pointer);
 
+extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
@@ -1570,7 +1600,9 @@ struct super_operations {
 	void (*evict_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
 	int (*sync_fs)(struct super_block *sb, int wait);
+	int (*freeze_super) (struct super_block *);
 	int (*freeze_fs) (struct super_block *);
+	int (*thaw_super) (struct super_block *);
 	int (*unfreeze_fs) (struct super_block *);
 	int (*statfs) (struct dentry *, struct kstatfs *);
 	int (*remount_fs) (struct super_block *, int *, char *);
@@ -1583,6 +1615,7 @@ struct super_operations {
 #ifdef CONFIG_QUOTA
 	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
+	struct dquot **(*get_dquots)(struct inode *);
 #endif
 	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
 	long (*nr_cached_objects)(struct super_block *, int);
@@ -1643,6 +1676,9 @@ struct super_operations {
 #define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
 #define IS_NOSEC(inode)		((inode)->i_flags & S_NOSEC)
 
+#define IS_WHITEOUT(inode)	(S_ISCHR(inode->i_mode) && \
+				 (inode)->i_rdev == WHITEOUT_DEV)
+
 /*
  * Inode state bits.  Protected by inode->i_lock
  *
@@ -1855,7 +1891,8 @@ extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
 extern void kern_unmount(struct vfsmount *mnt);
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
-extern long do_mount(const char *, const char *, const char *, unsigned long, void *);
+extern long do_mount(const char *, const char __user *,
+		     const char *, unsigned long, void *);
 extern struct vfsmount *collect_mounts(struct path *);
 extern void drop_collected_mounts(struct vfsmount *);
 extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
@@ -1874,7 +1911,7 @@ extern int current_umask(void);
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
 
-static inline struct inode *file_inode(struct file *f)
+static inline struct inode *file_inode(const struct file *f)
 {
 	return f->f_inode;
 }
@@ -2049,7 +2086,7 @@ struct filename {
 extern long vfs_truncate(struct path *, loff_t);
 extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
 		       struct file *filp);
-extern int do_fallocate(struct file *file, int mode, loff_t offset,
+extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
 			loff_t len);
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
 			umode_t mode);
@@ -2057,9 +2094,11 @@ extern struct file *file_open_name(struct filename *, int, umode_t);
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int);
+extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 
+extern struct filename *getname_flags(const char __user *, int, int *);
 extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
 
@@ -2137,7 +2176,6 @@ static inline int sb_is_blkdev_sb(struct super_block *sb)
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
-extern const struct file_operations bad_sock_fops;
 #ifdef CONFIG_BLOCK
 extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
 extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
@@ -2270,7 +2308,9 @@ extern sector_t bmap(struct inode *, sector_t);
 #endif
 extern int notify_change(struct dentry *, struct iattr *, struct inode **);
 extern int inode_permission(struct inode *, int);
+extern int __inode_permission(struct inode *, int);
 extern int generic_permission(struct inode *, int);
+extern int __check_sticky(struct inode *dir, struct inode *inode);
 
 static inline bool execute_ok(struct inode *inode)
 {
@@ -2455,6 +2495,7 @@ extern ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 extern ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 
 /* fs/block_dev.c */
+extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
 extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from);
 extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
 			int datasync);
@@ -2469,6 +2510,9 @@ extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
 		struct file *out, loff_t *, size_t len, unsigned int flags);
+extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
+		loff_t *opos, size_t len, unsigned int flags);
+
 
 extern void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
@@ -2611,6 +2655,7 @@ extern int simple_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata);
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
+extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
 extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
@@ -2753,12 +2798,25 @@ static inline int is_sxid(umode_t mode)
 	return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
 }
 
+static inline int check_sticky(struct inode *dir, struct inode *inode)
+{
+	if (!(dir->i_mode & S_ISVTX))
+		return 0;
+
+	return __check_sticky(dir, inode);
+}
+
 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;
 }
 
+static inline bool is_root_inode(struct inode *inode)
+{
+	return inode == inode->i_sb->s_root->d_inode;
+}
+
 static inline bool dir_emit(struct dir_context *ctx,
 			    const char *name, int namelen,
 			    u64 ino, unsigned type)