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 <fengguang.wu@intel.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

4 files changed, 33 insertions, 4 deletions

diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index e985b1c2730e..1256454b2d43 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -876,6 +876,10 @@ static int memory_open(struct inode *inode, struct file *filp)
 	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);
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index dc5d5f51f3fe..fb2a5abd4e4f 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -771,6 +771,8 @@ static const struct file_operations proc_single_file_operations = {
 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;
 }
 
diff --git a/fs/read_write.c b/fs/read_write.c
index e757ef26e4ce..9cd9d148105d 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -31,6 +31,20 @@ const struct file_operations generic_ro_fops = {
 
 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
@@ -62,7 +76,9 @@ generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin)
 		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? */
@@ -137,7 +153,7 @@ loff_t default_llseek(struct file *file, loff_t offset, int origin)
 			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;
@@ -221,6 +237,7 @@ bad:
 }
 #endif
 
+
 /*
  * rw_verify_area doesn't like huge counts. We limit
  * them to something that fits in "int" so that others
@@ -238,8 +255,11 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count
 	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(
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0cd6821013a0..7fc126df1c42 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -92,6 +92,9 @@ struct inodes_stat_t {
 /* 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)