vfs: introduce FMODE_UNSIGNED_OFFSET for allowing negative f_pos

Now, rw_verify_area() checsk f_pos is negative or not. And if negative,
returns -EINVAL.

But, some special files as /dev/(k)mem and /proc/<pid>/mem etc.. has
negative offsets. And we can't do any access via read/write to the
file(device).

So introduce FMODE_UNSIGNED_OFFSET to allow negative file offsets.

Signed-off-by: Wu Fengguang <[e-mail]>
Signed-off-by: KAMEZAWA Hiroyuki <[e-mail]>
Cc: Al Viro <[e-mail]>
Cc: Heiko Carstens <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Al Viro <[e-mail]>

drivers/char/mem.c

···
 	if (dev->dev_info)
 		filp->f_mapping->backing_dev_info = dev->dev_info;
 
+	/* Is /dev/mem or /dev/kmem ? */
+	if (dev->dev_info == &directly_mappable_cdev_bdi)
+		filp->f_mode |= FMODE_UNSIGNED_OFFSET;
+
 	if (dev->fops->open)
 		return dev->fops->open(inode, filp);
 

fs/proc/base.c

···
 static int mem_open(struct inode* inode, struct file* file)
 {
 	file->private_data = (void*)((long)current->self_exec_id);
+	/* OK to pass negative loff_t, we can catch out-of-range */
+	file->f_mode |= FMODE_UNSIGNED_OFFSET;
 	return 0;
 }
 

fs/read_write.c

···
 
 EXPORT_SYMBOL(generic_ro_fops);
 
+static int
+__negative_fpos_check(struct file *file, loff_t pos, size_t count)
+{
+	/*
+	 * pos or pos+count is negative here, check overflow.
+	 * too big "count" will be caught in rw_verify_area().
+	 */
+	if ((pos < 0) && (pos + count < pos))
+		return -EOVERFLOW;
+	if (file->f_mode & FMODE_UNSIGNED_OFFSET)
+		return 0;
+	return -EINVAL;
+}
+
 /**
  * generic_file_llseek_unlocked - lockless generic llseek implementation
  * @file:	file structure to seek on
···
 		break;
 	}
 
-	if (offset < 0 || offset > inode->i_sb->s_maxbytes)
+	if (offset < 0 && __negative_fpos_check(file, offset, 0))
+		return -EINVAL;
+	if (offset > inode->i_sb->s_maxbytes)
 		return -EINVAL;
 
 	/* Special lock needed here? */
···
 			offset += file->f_pos;
 	}
 	retval = -EINVAL;
-	if (offset >= 0) {
+	if (offset >= 0 || !__negative_fpos_check(file, offset, 0)) {
 		if (offset != file->f_pos) {
 			file->f_pos = offset;
 			file->f_version = 0;
···
 }
 #endif
 
+
 /*
  * rw_verify_area doesn't like huge counts. We limit
  * them to something that fits in "int" so that others
···
 	if (unlikely((ssize_t) count < 0))
 		return retval;
 	pos = *ppos;
-	if (unlikely((pos < 0) || (loff_t) (pos + count) < 0))
-		return retval;
+	if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) {
+		retval = __negative_fpos_check(file, pos, count);
+		if (retval)
+			return retval;
+	}
 
 	if (unlikely(inode->i_flock && mandatory_lock(inode))) {
 		retval = locks_mandatory_area(

include/linux/fs.h

···
 /* Expect random access pattern */
 #define FMODE_RANDOM		((__force fmode_t)0x1000)
 
+/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
+#define FMODE_UNSIGNED_OFFSET	((__force fmode_t)0x2000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x1000000)