[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>

kernel/sys_ni.c

@@ -80,6 +80,9 @@ cond_syscall(sys_keyctl);
 cond_syscall(compat_sys_keyctl);
 cond_syscall(compat_sys_socketcall);
 cond_syscall(sys_set_zone_reclaim);
+cond_syscall(sys_inotify_init);
+cond_syscall(sys_inotify_add_watch);
+cond_syscall(sys_inotify_rm_watch);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);

kernel/sysctl.c

@@ -67,6 +67,12 @@ extern int printk_ratelimit_jiffies;
 extern int printk_ratelimit_burst;
 extern int pid_max_min, pid_max_max;
 
+#ifdef CONFIG_INOTIFY
+extern int inotify_max_user_devices;
+extern int inotify_max_user_watches;
+extern int inotify_max_queued_events;
+#endif
+
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
 int unknown_nmi_panic;
 extern int proc_unknown_nmi_panic(ctl_table *, int, struct file *,
@@ -218,6 +224,7 @@ static ctl_table root_table[] = {
 		.mode		= 0555,
 		.child		= dev_table,
 	},
+
 	{ .ctl_name = 0 }
 };
 
@@ -959,6 +966,40 @@ static ctl_table fs_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+#ifdef CONFIG_INOTIFY
+	{
+		.ctl_name	= INOTIFY_MAX_USER_DEVICES,
+		.procname	= "max_user_devices",
+		.data		= &inotify_max_user_devices,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
+
+	{
+		.ctl_name	= INOTIFY_MAX_USER_WATCHES,
+		.procname	= "max_user_watches",
+		.data		= &inotify_max_user_watches,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero, 
+	},
+
+	{
+		.ctl_name	= INOTIFY_MAX_QUEUED_EVENTS,
+		.procname	= "max_queued_events",
+		.data		= &inotify_max_queued_events,
+		.maxlen		= sizeof(int),
+		.mode		= 0644, 
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec, 
+		.extra1		= &zero
+	},
+#endif
 	{ .ctl_name = 0 }
 };
 
@@ -968,7 +1009,7 @@ static ctl_table debug_table[] = {
 
 static ctl_table dev_table[] = {
 	{ .ctl_name = 0 }
-};  
+};
 
 extern void init_irq_proc (void);
 

kernel/user.c

@@ -120,6 +120,10 @@ struct user_struct * alloc_uid(uid_t uid)
 		atomic_set(&new->processes, 0);
 		atomic_set(&new->files, 0);
 		atomic_set(&new->sigpending, 0);
+#ifdef CONFIG_INOTIFY
+		atomic_set(&new->inotify_watches, 0);
+		atomic_set(&new->inotify_devs, 0);
+#endif
 
 		new->mq_bytes = 0;
 		new->locked_shm = 0;