[PATCH] inotify

inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:

        * dnotify requires the opening of one fd per each directory
          that you intend to watch. This quickly results in too many
          open files and pins removable media, preventing unmount.
        * dnotify is directory-based. You only learn about changes to
          directories. Sure, a change to a file in a directory affects
          the directory, but you are then forced to keep a cache of
          stat structures.
        * dnotify's interface to user-space is awful.  Signals?

inotify provides a more usable, simple, powerful solution to file change
notification:

        * inotify's interface is a system call that returns a fd, not SIGIO.
	  You get a single fd, which is select()-able.
        * inotify has an event that says "the filesystem that the item
          you were watching is on was unmounted."
        * inotify can watch directories or files.

Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.

See Documentation/filesystems/inotify.txt.

Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

6 files changed, 379 insertions, 3 deletions

diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index e25e4c71a879..a7cb377745bf 100644
--- a/include/asm-i386/unistd.h
+++ b/include/asm-i386/unistd.h
@@ -296,8 +296,11 @@
 #define __NR_keyctl		288
 #define __NR_ioprio_set		289
 #define __NR_ioprio_get		290
+#define __NR_inotify_init	291
+#define __NR_inotify_add_watch	292
+#define __NR_inotify_rm_watch	293
 
-#define NR_syscalls 291
+#define NR_syscalls 294
 
 /*
  * user-visible error numbers are in the range -1 - -128: see
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 302ec20838ca..c9bf3746a9fb 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -474,6 +474,11 @@ struct inode {
 	struct dnotify_struct	*i_dnotify; /* for directory notifications */
 #endif
 
+#ifdef CONFIG_INOTIFY
+	struct list_head	inotify_watches; /* watches on this inode */
+	struct semaphore	inotify_sem;	/* protects the watches list */
+#endif
+
 	unsigned long		i_state;
 	unsigned long		dirtied_when;	/* jiffies of first dirtying */
 
@@ -1393,7 +1398,6 @@ extern void emergency_remount(void);
 extern int do_remount_sb(struct super_block *sb, int flags,
 			 void *data, int force);
 extern sector_t bmap(struct inode *, sector_t);
-extern int setattr_mask(unsigned int);
 extern int notify_change(struct dentry *, struct iattr *);
 extern int permission(struct inode *, int, struct nameidata *);
 extern int generic_permission(struct inode *, int,
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
new file mode 100644
index 000000000000..eb581b6cfca9
--- /dev/null
+++ b/include/linux/fsnotify.h
@@ -0,0 +1,248 @@
+#ifndef _LINUX_FS_NOTIFY_H
+#define _LINUX_FS_NOTIFY_H
+
+/*
+ * include/linux/fsnotify.h - generic hooks for filesystem notification, to
+ * reduce in-source duplication from both dnotify and inotify.
+ *
+ * We don't compile any of this away in some complicated menagerie of ifdefs.
+ * Instead, we rely on the code inside to optimize away as needed.
+ *
+ * (C) Copyright 2005 Robert Love
+ */
+
+#ifdef __KERNEL__
+
+#include <linux/dnotify.h>
+#include <linux/inotify.h>
+
+/*
+ * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir
+ */
+static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
+				 const char *old_name, const char *new_name,
+				 int isdir)
+{
+	u32 cookie = inotify_get_cookie();
+
+	if (old_dir == new_dir)
+		inode_dir_notify(old_dir, DN_RENAME);
+	else {
+		inode_dir_notify(old_dir, DN_DELETE);
+		inode_dir_notify(new_dir, DN_CREATE);
+	}
+
+	if (isdir)
+		isdir = IN_ISDIR;
+	inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir,cookie,old_name);
+	inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, cookie, new_name);
+}
+
+/*
+ * fsnotify_unlink - file was unlinked
+ */
+static inline void fsnotify_unlink(struct dentry *dentry, struct inode *dir)
+{
+	struct inode *inode = dentry->d_inode;
+
+	inode_dir_notify(dir, DN_DELETE);
+	inotify_inode_queue_event(dir, IN_DELETE, 0, dentry->d_name.name);
+	inotify_inode_queue_event(inode, IN_DELETE_SELF, 0, NULL);
+
+	inotify_inode_is_dead(inode);
+}
+
+/*
+ * fsnotify_rmdir - directory was removed
+ */
+static inline void fsnotify_rmdir(struct dentry *dentry, struct inode *inode,
+				  struct inode *dir)
+{
+	inode_dir_notify(dir, DN_DELETE);
+	inotify_inode_queue_event(dir,IN_DELETE|IN_ISDIR,0,dentry->d_name.name);
+	inotify_inode_queue_event(inode, IN_DELETE_SELF | IN_ISDIR, 0, NULL);
+	inotify_inode_is_dead(inode);
+}
+
+/*
+ * fsnotify_create - 'name' was linked in
+ */
+static inline void fsnotify_create(struct inode *inode, const char *name)
+{
+	inode_dir_notify(inode, DN_CREATE);
+	inotify_inode_queue_event(inode, IN_CREATE, 0, name);
+}
+
+/*
+ * fsnotify_mkdir - directory 'name' was created
+ */
+static inline void fsnotify_mkdir(struct inode *inode, const char *name)
+{
+	inode_dir_notify(inode, DN_CREATE);
+	inotify_inode_queue_event(inode, IN_CREATE | IN_ISDIR, 0, name);
+}
+
+/*
+ * fsnotify_access - file was read
+ */
+static inline void fsnotify_access(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	u32 mask = IN_ACCESS;
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= IN_ISDIR;
+
+	dnotify_parent(dentry, DN_ACCESS);
+	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
+	inotify_inode_queue_event(inode, mask, 0, NULL);
+}
+
+/*
+ * fsnotify_modify - file was modified
+ */
+static inline void fsnotify_modify(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	u32 mask = IN_MODIFY;
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= IN_ISDIR;
+
+	dnotify_parent(dentry, DN_MODIFY);
+	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
+	inotify_inode_queue_event(inode, mask, 0, NULL);
+}
+
+/*
+ * fsnotify_open - file was opened
+ */
+static inline void fsnotify_open(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	u32 mask = IN_OPEN;
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= IN_ISDIR;
+
+	inotify_inode_queue_event(inode, mask, 0, NULL);
+	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
+}
+
+/*
+ * fsnotify_close - file was closed
+ */
+static inline void fsnotify_close(struct file *file)
+{
+	struct dentry *dentry = file->f_dentry;
+	struct inode *inode = dentry->d_inode;
+	const char *name = dentry->d_name.name;
+	mode_t mode = file->f_mode;
+	u32 mask = (mode & FMODE_WRITE) ? IN_CLOSE_WRITE : IN_CLOSE_NOWRITE;
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= IN_ISDIR;
+
+	inotify_dentry_parent_queue_event(dentry, mask, 0, name);
+	inotify_inode_queue_event(inode, mask, 0, NULL);
+}
+
+/*
+ * fsnotify_xattr - extended attributes were changed
+ */
+static inline void fsnotify_xattr(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	u32 mask = IN_ATTRIB;
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= IN_ISDIR;
+
+	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
+	inotify_inode_queue_event(inode, mask, 0, NULL);
+}
+
+/*
+ * fsnotify_change - notify_change event.  file was modified and/or metadata
+ * was changed.
+ */
+static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
+{
+	struct inode *inode = dentry->d_inode;
+	int dn_mask = 0;
+	u32 in_mask = 0;
+
+	if (ia_valid & ATTR_UID) {
+		in_mask |= IN_ATTRIB;
+		dn_mask |= DN_ATTRIB;
+	}
+	if (ia_valid & ATTR_GID) {
+		in_mask |= IN_ATTRIB;
+		dn_mask |= DN_ATTRIB;
+	}
+	if (ia_valid & ATTR_SIZE) {
+		in_mask |= IN_MODIFY;
+		dn_mask |= DN_MODIFY;
+	}
+	/* both times implies a utime(s) call */
+	if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME))
+	{
+		in_mask |= IN_ATTRIB;
+		dn_mask |= DN_ATTRIB;
+	} else if (ia_valid & ATTR_ATIME) {
+		in_mask |= IN_ACCESS;
+		dn_mask |= DN_ACCESS;
+	} else if (ia_valid & ATTR_MTIME) {
+		in_mask |= IN_MODIFY;
+		dn_mask |= DN_MODIFY;
+	}
+	if (ia_valid & ATTR_MODE) {
+		in_mask |= IN_ATTRIB;
+		dn_mask |= DN_ATTRIB;
+	}
+
+	if (dn_mask)
+		dnotify_parent(dentry, dn_mask);
+	if (in_mask) {
+		if (S_ISDIR(inode->i_mode))
+			in_mask |= IN_ISDIR;
+		inotify_inode_queue_event(inode, in_mask, 0, NULL);
+		inotify_dentry_parent_queue_event(dentry, in_mask, 0,
+						  dentry->d_name.name);
+	}
+}
+
+#ifdef CONFIG_INOTIFY	/* inotify helpers */
+
+/*
+ * fsnotify_oldname_init - save off the old filename before we change it
+ */
+static inline const char *fsnotify_oldname_init(const char *name)
+{
+	return kstrdup(name, GFP_KERNEL);
+}
+
+/*
+ * fsnotify_oldname_free - free the name we got from fsnotify_oldname_init
+ */
+static inline void fsnotify_oldname_free(const char *old_name)
+{
+	kfree(old_name);
+}
+
+#else	/* CONFIG_INOTIFY */
+
+static inline const char *fsnotify_oldname_init(const char *name)
+{
+	return NULL;
+}
+
+static inline void fsnotify_oldname_free(const char *old_name)
+{
+}
+
+#endif	/* ! CONFIG_INOTIFY */
+
+#endif	/* __KERNEL__ */
+
+#endif	/* _LINUX_FS_NOTIFY_H */
diff --git a/include/linux/inotify.h b/include/linux/inotify.h
new file mode 100644
index 000000000000..a40c2bf0408e
--- /dev/null
+++ b/include/linux/inotify.h
@@ -0,0 +1,108 @@
+/*
+ * Inode based directory notification for Linux
+ *
+ * Copyright (C) 2005 John McCutchan
+ */
+
+#ifndef _LINUX_INOTIFY_H
+#define _LINUX_INOTIFY_H
+
+#include <linux/types.h>
+
+/*
+ * struct inotify_event - structure read from the inotify device for each event
+ *
+ * When you are watching a directory, you will receive the filename for events
+ * such as IN_CREATE, IN_DELETE, IN_OPEN, IN_CLOSE, ..., relative to the wd.
+ */
+struct inotify_event {
+	__s32		wd;		/* watch descriptor */
+	__u32		mask;		/* watch mask */
+	__u32		cookie;		/* cookie to synchronize two events */
+	__u32		len;		/* length (including nulls) of name */
+	char		name[0];	/* stub for possible name */
+};
+
+/* the following are legal, implemented events that user-space can watch for */
+#define IN_ACCESS		0x00000001	/* File was accessed */
+#define IN_MODIFY		0x00000002	/* File was modified */
+#define IN_ATTRIB		0x00000004	/* Metadata changed */
+#define IN_CLOSE_WRITE		0x00000008	/* Writtable file was closed */
+#define IN_CLOSE_NOWRITE	0x00000010	/* Unwrittable file closed */
+#define IN_OPEN			0x00000020	/* File was opened */
+#define IN_MOVED_FROM		0x00000040	/* File was moved from X */
+#define IN_MOVED_TO		0x00000080	/* File was moved to Y */
+#define IN_CREATE		0x00000100	/* Subfile was created */
+#define IN_DELETE		0x00000200	/* Subfile was deleted */
+#define IN_DELETE_SELF		0x00000400	/* Self was deleted */
+
+/* the following are legal events.  they are sent as needed to any watch */
+#define IN_UNMOUNT		0x00002000	/* Backing fs was unmounted */
+#define IN_Q_OVERFLOW		0x00004000	/* Event queued overflowed */
+#define IN_IGNORED		0x00008000	/* File was ignored */
+
+/* helper events */
+#define IN_CLOSE		(IN_CLOSE_WRITE | IN_CLOSE_NOWRITE) /* close */
+#define IN_MOVE			(IN_MOVED_FROM | IN_MOVED_TO) /* moves */
+
+/* special flags */
+#define IN_ISDIR		0x40000000	/* event occurred against dir */
+#define IN_ONESHOT		0x80000000	/* only send event once */
+
+/*
+ * All of the events - we build the list by hand so that we can add flags in
+ * the future and not break backward compatibility.  Apps will get only the
+ * events that they originally wanted.  Be sure to add new events here!
+ */
+#define IN_ALL_EVENTS	(IN_ACCESS | IN_MODIFY | IN_ATTRIB | IN_CLOSE_WRITE | \
+			 IN_CLOSE_NOWRITE | IN_OPEN | IN_MOVED_FROM | \
+			 IN_MOVED_TO | IN_DELETE | IN_CREATE | IN_DELETE_SELF)
+
+#ifdef __KERNEL__
+
+#include <linux/dcache.h>
+#include <linux/fs.h>
+#include <linux/config.h>
+
+#ifdef CONFIG_INOTIFY
+
+extern void inotify_inode_queue_event(struct inode *, __u32, __u32,
+				      const char *);
+extern void inotify_dentry_parent_queue_event(struct dentry *, __u32, __u32,
+					      const char *);
+extern void inotify_unmount_inodes(struct list_head *);
+extern void inotify_inode_is_dead(struct inode *);
+extern u32 inotify_get_cookie(void);
+
+#else
+
+static inline void inotify_inode_queue_event(struct inode *inode,
+					     __u32 mask, __u32 cookie,
+					     const char *filename)
+{
+}
+
+static inline void inotify_dentry_parent_queue_event(struct dentry *dentry,
+						     __u32 mask, __u32 cookie,
+						     const char *filename)
+{
+}
+
+static inline void inotify_unmount_inodes(struct list_head *list)
+{
+}
+
+static inline void inotify_inode_is_dead(struct inode *inode)
+{
+}
+
+static inline u32 inotify_get_cookie(void)
+{
+	return 0;
+}
+
+#endif	/* CONFIG_INOTIFY */
+
+#endif	/* __KERNEL __ */
+
+#endif	/* _LINUX_INOTIFY_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ff48815bd3a2..dec5827c7742 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -410,6 +410,10 @@ struct user_struct {
 	atomic_t processes;	/* How many processes does this user have? */
 	atomic_t files;		/* How many open files does this user have? */
 	atomic_t sigpending;	/* How many pending signals does this user have? */
+#ifdef CONFIG_INOTIFY
+	atomic_t inotify_watches; /* How many inotify watches does this user have? */
+	atomic_t inotify_devs;	/* How many inotify devs does this user have opened? */
+#endif
 	/* protected by mq_lock	*/
 	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 5b5f434ac9a0..ce19a2aa0b21 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -61,7 +61,8 @@ enum
 	CTL_DEV=7,		/* Devices */
 	CTL_BUS=8,		/* Busses */
 	CTL_ABI=9,		/* Binary emulation */
-	CTL_CPU=10		/* CPU stuff (speed scaling, etc) */
+	CTL_CPU=10,		/* CPU stuff (speed scaling, etc) */
+	CTL_INOTIFY=11		/* Inotify */
 };
 
 /* CTL_BUS names: */
@@ -70,6 +71,14 @@ enum
 	CTL_BUS_ISA=1		/* ISA */
 };
 
+/* CTL_INOTIFY names: */
+enum
+{
+	INOTIFY_MAX_USER_DEVICES=1,	/* max number of inotify device instances per user */
+	INOTIFY_MAX_USER_WATCHES=2,	/* max number of inotify watches per user */
+	INOTIFY_MAX_QUEUED_EVENTS=3	/* Max number of queued events per inotify device instance */
+};
+
 /* CTL_KERN names: */
 enum
 {