fanotify: fscking all notification system

fanotify is a novel file notification system which bases notification on
giving userspace both an event type (open, close, read, write) and an open
file descriptor to the object in question.  This should address a number of
races and problems with other notification systems like inotify and dnotify
and should allow the future implementation of blocking or access controlled
notification.  These are useful for on access scanners or hierachical storage
management schemes.

This patch just implements the basics of the fsnotify functions.

Signed-off-by: Eric Paris <eparis@redhat.com>

fs/notify/Kconfig

@@ -3,3 +3,4 @@ config FSNOTIFY
 
 source "fs/notify/dnotify/Kconfig"
 source "fs/notify/inotify/Kconfig"
+source "fs/notify/fanotify/Kconfig"

fs/notify/Makefile

@@ -2,3 +2,4 @@ obj-$(CONFIG_FSNOTIFY)		+= fsnotify.o notification.o group.o inode_mark.o
 
 obj-y			+= dnotify/
 obj-y			+= inotify/
+obj-y			+= fanotify/

fs/notify/fanotify/Kconfig

@@ -0,0 +1,11 @@
+config FANOTIFY
+	bool "Filesystem wide access notification"
+	select FSNOTIFY
+	default y
+	---help---
+	   Say Y here to enable fanotify suport.  fanotify is a file access
+	   notification system which differs from inotify in that it sends
+	   and open file descriptor to the userspace listener along with
+	   the event.
+
+	   If unsure, say Y.

fs/notify/fanotify/Makefile

@@ -0,0 +1 @@
+obj-$(CONFIG_FANOTIFY)		+= fanotify.o

fs/notify/fanotify/fanotify.c

@@ -0,0 +1,78 @@
+#include <linux/fdtable.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/init.h>
+#include <linux/kernel.h> /* UINT_MAX */
+#include <linux/types.h>
+
+#include "fanotify.h"
+
+static int fanotify_handle_event(struct fsnotify_group *group, struct fsnotify_event *event)
+{
+	int ret;
+
+
+	BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS);
+	BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY);
+	BUILD_BUG_ON(FAN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
+	BUILD_BUG_ON(FAN_CLOSE_WRITE != FS_CLOSE_WRITE);
+	BUILD_BUG_ON(FAN_OPEN != FS_OPEN);
+	BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD);
+	BUILD_BUG_ON(FAN_Q_OVERFLOW != FS_Q_OVERFLOW);
+
+	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+	ret = fsnotify_add_notify_event(group, event, NULL, NULL);
+
+	return ret;
+}
+
+static bool fanotify_should_send_event(struct fsnotify_group *group, struct inode *inode,
+				       struct vfsmount *mnt, __u32 mask, void *data,
+				       int data_type)
+{
+	struct fsnotify_mark *fsn_mark;
+	bool send;
+
+	pr_debug("%s: group=%p inode=%p mask=%x data=%p data_type=%d\n",
+		 __func__, group, inode, mask, data, data_type);
+
+	/* sorry, fanotify only gives a damn about files and dirs */
+	if (!S_ISREG(inode->i_mode) &&
+	    !S_ISDIR(inode->i_mode))
+		return false;
+
+	/* if we don't have enough info to send an event to userspace say no */
+	if (data_type != FSNOTIFY_EVENT_PATH)
+		return false;
+
+	fsn_mark = fsnotify_find_mark(group, inode);
+	if (!fsn_mark)
+		return false;
+
+	/* if the event is for a child and this inode doesn't care about
+	 * events on the child, don't send it! */
+	if ((mask & FS_EVENT_ON_CHILD) &&
+	    !(fsn_mark->mask & FS_EVENT_ON_CHILD)) {
+		send = false;
+	} else {
+		/*
+		 * We care about children, but do we care about this particular
+		 * type of event?
+		 */
+		mask = (mask & ~FS_EVENT_ON_CHILD);
+		send = (fsn_mark->mask & mask);
+	}
+
+	/* find took a reference */
+	fsnotify_put_mark(fsn_mark);
+
+	return send;
+}
+
+const struct fsnotify_ops fanotify_fsnotify_ops = {
+	.handle_event = fanotify_handle_event,
+	.should_send_event = fanotify_should_send_event,
+	.free_group_priv = NULL,
+	.free_event_priv = NULL,
+	.freeing_mark = NULL,
+};

fs/notify/fanotify/fanotify.h

@@ -0,0 +1,12 @@
+#include <linux/fanotify.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/net.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+static inline bool fanotify_mask_valid(__u32 mask)
+{
+	if (mask & ~((__u32)FAN_ALL_INCOMING_EVENTS))
+		return false;
+	return true;
+}

include/linux/Kbuild

@@ -210,6 +210,7 @@ unifdef-y += ethtool.h
 unifdef-y += eventpoll.h
 unifdef-y += signalfd.h
 unifdef-y += ext2_fs.h
+unifdef-y += fanotify.h
 unifdef-y += fb.h
 unifdef-y += fcntl.h
 unifdef-y += filter.h

include/linux/fanotify.h

@@ -0,0 +1,40 @@
+#ifndef _LINUX_FANOTIFY_H
+#define _LINUX_FANOTIFY_H
+
+#include <linux/types.h>
+
+/* the following events that user-space can register for */
+#define FAN_ACCESS		0x00000001	/* File was accessed */
+#define FAN_MODIFY		0x00000002	/* File was modified */
+#define FAN_CLOSE_WRITE		0x00000008	/* Unwrittable file closed */
+#define FAN_CLOSE_NOWRITE	0x00000010	/* Writtable file closed */
+#define FAN_OPEN		0x00000020	/* File was opened */
+
+#define FAN_EVENT_ON_CHILD	0x08000000	/* interested in child events */
+
+/* FIXME currently Q's have no limit.... */
+#define FAN_Q_OVERFLOW		0x00004000	/* Event queued overflowed */
+
+/* helper events */
+#define FAN_CLOSE		(FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */
+
+/*
+ * 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 FAN_ALL_EVENTS (FAN_ACCESS |\
+			FAN_MODIFY |\
+			FAN_CLOSE |\
+			FAN_OPEN)
+
+/*
+ * All legal FAN bits userspace can request (although possibly not all
+ * at the same time.
+ */
+#define FAN_ALL_INCOMING_EVENTS	(FAN_ALL_EVENTS |\
+				 FAN_EVENT_ON_CHILD)
+#ifdef __KERNEL__
+
+#endif /* __KERNEL__ */
+#endif /* _LINUX_FANOTIFY_H */