1 files changed, 177 insertions, 24 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 17fd887c798f..38dba16c4176 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -165,6 +165,8 @@ struct inodes_stat_t {
 #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)
@@ -412,6 +414,7 @@ struct inodes_stat_t {
 #include <linux/shrinker.h>
 #include <linux/migrate_mode.h>
 #include <linux/uidgid.h>
+#include <linux/lockdep.h>
 
 #include <asm/byteorder.h>
 
@@ -427,6 +430,7 @@ struct kstatfs;
 struct vm_area_struct;
 struct vfsmount;
 struct cred;
+struct swap_info_struct;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -437,6 +441,8 @@ 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;
+extern int sysctl_protected_symlinks;
+extern int sysctl_protected_hardlinks;
 
 struct buffer_head;
 typedef int (get_block_t)(struct inode *inode, sector_t iblock,
@@ -636,6 +642,11 @@ struct address_space_operations {
 	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
 					unsigned long);
 	int (*error_remove_page)(struct address_space *, struct page *);
+
+	/* swapfile support */
+	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
+				sector_t *span);
+	void (*swap_deactivate)(struct file *file);
 };
 
 extern const struct address_space_operations empty_aops;
@@ -826,7 +837,7 @@ struct inode {
 	struct list_head	i_lru;		/* inode LRU list */
 	struct list_head	i_sb_list;
 	union {
-		struct list_head	i_dentry;
+		struct hlist_head	i_dentry;
 		struct rcu_head		i_rcu;
 	};
 	u64			i_version;
@@ -1154,7 +1165,6 @@ struct lock_manager_operations {
 	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
 	int (*lm_grant)(struct file_lock *, struct file_lock *, int);
-	void (*lm_release_private)(struct file_lock *);
 	void (*lm_break)(struct file_lock *);
 	int (*lm_change)(struct file_lock **, int);
 };
@@ -1163,9 +1173,10 @@ struct lock_manager {
 	struct list_head list;
 };
 
-void locks_start_grace(struct lock_manager *);
+struct net;
+void locks_start_grace(struct net *, struct lock_manager *);
 void locks_end_grace(struct lock_manager *);
-int locks_in_grace(void);
+int locks_in_grace(struct net *);
 
 /* that will die - we need it for nfs_lock_info */
 #include <linux/nfs_fs_i.h>
@@ -1437,6 +1448,8 @@ extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
 extern int send_sigurg(struct fown_struct *fown);
 
+struct mm_struct;
+
 /*
  *	Umount options
  */
@@ -1450,6 +1463,31 @@ extern int send_sigurg(struct fown_struct *fown);
 extern struct list_head super_blocks;
 extern spinlock_t sb_lock;
 
+/* Possible states of 'frozen' field */
+enum {
+	SB_UNFROZEN = 0,		/* FS is unfrozen */
+	SB_FREEZE_WRITE	= 1,		/* Writes, dir ops, ioctls frozen */
+	SB_FREEZE_PAGEFAULT = 2,	/* Page faults stopped as well */
+	SB_FREEZE_FS = 3,		/* For internal FS use (e.g. to stop
+					 * internal threads if needed) */
+	SB_FREEZE_COMPLETE = 4,		/* ->freeze_fs finished successfully */
+};
+
+#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
+
+struct sb_writers {
+	/* Counters for counting writers at each level */
+	struct percpu_counter	counter[SB_FREEZE_LEVELS];
+	wait_queue_head_t	wait;		/* queue for waiting for
+						   writers / faults to finish */
+	int			frozen;		/* Is sb frozen? */
+	wait_queue_head_t	wait_unfrozen;	/* queue for waiting for
+						   sb to be thawed */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	lock_map[SB_FREEZE_LEVELS];
+#endif
+};
+
 struct super_block {
 	struct list_head	s_list;		/* Keep this first */
 	dev_t			s_dev;		/* search index; _not_ kdev_t */
@@ -1497,8 +1535,7 @@ struct super_block {
 	struct hlist_node	s_instances;
 	struct quota_info	s_dquot;	/* Diskquota specific options */
 
-	int			s_frozen;
-	wait_queue_head_t	s_wait_unfrozen;
+	struct sb_writers	s_writers;
 
 	char s_id[32];				/* Informational name */
 	u8 s_uuid[16];				/* UUID */
@@ -1553,14 +1590,117 @@ extern struct timespec current_fs_time(struct super_block *sb);
 /*
  * Snapshotting support.
  */
-enum {
-	SB_UNFROZEN = 0,
-	SB_FREEZE_WRITE	= 1,
-	SB_FREEZE_TRANS = 2,
-};
 
-#define vfs_check_frozen(sb, level) \
-	wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))
+void __sb_end_write(struct super_block *sb, int level);
+int __sb_start_write(struct super_block *sb, int level, bool wait);
+
+/**
+ * sb_end_write - drop write access to a superblock
+ * @sb: the super we wrote to
+ *
+ * Decrement number of writers to the filesystem. Wake up possible waiters
+ * wanting to freeze the filesystem.
+ */
+static inline void sb_end_write(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * sb_end_pagefault - drop write access to a superblock from a page fault
+ * @sb: the super we wrote to
+ *
+ * Decrement number of processes handling write page fault to the filesystem.
+ * Wake up possible waiters wanting to freeze the filesystem.
+ */
+static inline void sb_end_pagefault(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
+}
+
+/**
+ * sb_end_intwrite - drop write access to a superblock for internal fs purposes
+ * @sb: the super we wrote to
+ *
+ * Decrement fs-internal number of writers to the filesystem.  Wake up possible
+ * waiters wanting to freeze the filesystem.
+ */
+static inline void sb_end_intwrite(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_FS);
+}
+
+/**
+ * sb_start_write - get write access to a superblock
+ * @sb: the super we write to
+ *
+ * When a process wants to write data or metadata to a file system (i.e. dirty
+ * a page or an inode), it should embed the operation in a sb_start_write() -
+ * sb_end_write() pair to get exclusion against file system freezing. This
+ * function increments number of writers preventing freezing. If the file
+ * system is already frozen, the function waits until the file system is
+ * thawed.
+ *
+ * Since freeze protection behaves as a lock, users have to preserve
+ * ordering of freeze protection and other filesystem locks. Generally,
+ * freeze protection should be the outermost lock. In particular, we have:
+ *
+ * sb_start_write
+ *   -> i_mutex			(write path, truncate, directory ops, ...)
+ *   -> s_umount		(freeze_super, thaw_super)
+ */
+static inline void sb_start_write(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_WRITE, true);
+}
+
+static inline int sb_start_write_trylock(struct super_block *sb)
+{
+	return __sb_start_write(sb, SB_FREEZE_WRITE, false);
+}
+
+/**
+ * sb_start_pagefault - get write access to a superblock from a page fault
+ * @sb: the super we write to
+ *
+ * When a process starts handling write page fault, it should embed the
+ * operation into sb_start_pagefault() - sb_end_pagefault() pair to get
+ * exclusion against file system freezing. This is needed since the page fault
+ * is going to dirty a page. This function increments number of running page
+ * faults preventing freezing. If the file system is already frozen, the
+ * function waits until the file system is thawed.
+ *
+ * Since page fault freeze protection behaves as a lock, users have to preserve
+ * ordering of freeze protection and other filesystem locks. It is advised to
+ * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault
+ * handling code implies lock dependency:
+ *
+ * mmap_sem
+ *   -> sb_start_pagefault
+ */
+static inline void sb_start_pagefault(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
+}
+
+/*
+ * sb_start_intwrite - get write access to a superblock for internal fs purposes
+ * @sb: the super we write to
+ *
+ * This is the third level of protection against filesystem freezing. It is
+ * free for use by a filesystem. The only requirement is that it must rank
+ * below sb_start_pagefault.
+ *
+ * For example filesystem can call sb_start_intwrite() when starting a
+ * transaction which somewhat eases handling of freezing for internal sources
+ * of filesystem changes (internal fs threads, discarding preallocation on file
+ * close, etc.).
+ */
+static inline void sb_start_intwrite(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_FS, true);
+}
+
 
 extern bool inode_owner_or_capable(const struct inode *inode);
 
@@ -1571,7 +1711,7 @@ extern void unlock_super(struct super_block *);
 /*
  * VFS helper functions..
  */
-extern int vfs_create(struct inode *, struct dentry *, umode_t, struct nameidata *);
+extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
 extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
 extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 extern int vfs_symlink(struct inode *, struct dentry *, const char *);
@@ -1666,7 +1806,7 @@ struct file_operations {
 };
 
 struct inode_operations {
-	struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
+	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 	void * (*follow_link) (struct dentry *, struct nameidata *);
 	int (*permission) (struct inode *, int);
 	struct posix_acl * (*get_acl)(struct inode *, int);
@@ -1674,7 +1814,7 @@ struct inode_operations {
 	int (*readlink) (struct dentry *, char __user *,int);
 	void (*put_link) (struct dentry *, struct nameidata *, void *);
 
-	int (*create) (struct inode *,struct dentry *,umode_t,struct nameidata *);
+	int (*create) (struct inode *,struct dentry *, umode_t, bool);
 	int (*link) (struct dentry *,struct inode *,struct dentry *);
 	int (*unlink) (struct inode *,struct dentry *);
 	int (*symlink) (struct inode *,struct dentry *,const char *);
@@ -1693,6 +1833,9 @@ struct inode_operations {
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
 		      u64 len);
 	int (*update_time)(struct inode *, struct timespec *, int);
+	int (*atomic_open)(struct inode *, struct dentry *,
+			   struct file *, unsigned open_flag,
+			   umode_t create_mode, int *opened);
 } ____cacheline_aligned;
 
 struct seq_file;
@@ -1881,6 +2024,7 @@ struct file_system_type {
 	struct lock_class_key s_lock_key;
 	struct lock_class_key s_umount_key;
 	struct lock_class_key s_vfs_rename_key;
+	struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
 
 	struct lock_class_key i_lock_key;
 	struct lock_class_key i_mutex_key;
@@ -1911,7 +2055,7 @@ void free_anon_bdev(dev_t);
 struct super_block *sget(struct file_system_type *type,
 			int (*test)(struct super_block *,void *),
 			int (*set)(struct super_block *,void *),
-			void *data);
+			int flags, void *data);
 extern struct dentry *mount_pseudo(struct file_system_type *, char *,
 	const struct super_operations *ops,
 	const struct dentry_operations *dops,
@@ -2057,10 +2201,17 @@ extern long do_sys_open(int dfd, const char __user *filename, int flags,
 extern struct file *filp_open(const char *, int, umode_t);
 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 struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 extern char * getname(const char __user *);
+enum {
+	FILE_CREATED = 1,
+	FILE_OPENED = 2
+};
+extern int finish_open(struct file *file, struct dentry *dentry,
+			int (*open)(struct inode *, struct file *),
+			int *opened);
+extern int finish_no_open(struct file *file, struct dentry *dentry);
 
 /* fs/ioctl.c */
 
@@ -2091,6 +2242,7 @@ extern sector_t blkdev_max_block(struct block_device *bdev);
 extern void bd_forget(struct inode *inode);
 extern void bdput(struct block_device *);
 extern void invalidate_bdev(struct block_device *);
+extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
 extern int sync_blockdev(struct block_device *bdev);
 extern void kill_bdev(struct block_device *);
 extern struct super_block *freeze_bdev(struct block_device *);
@@ -2112,6 +2264,10 @@ static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
 {
 	return 0;
 }
+
+static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
+{
+}
 #endif
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
@@ -2311,9 +2467,6 @@ static inline void i_readcount_inc(struct inode *inode)
 }
 #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 int kernel_read(struct file *, loff_t, char *, unsigned long);
 extern struct file * open_exec(const char *);
@@ -2438,7 +2591,7 @@ extern loff_t noop_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
-		int origin, loff_t maxsize);
+		int origin, loff_t maxsize, loff_t eof);
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
@@ -2560,7 +2713,7 @@ extern int simple_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata);
 
-extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *);
+extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
 extern const struct file_operations simple_dir_operations;
 extern const struct inode_operations simple_dir_inode_operations;