btrfs: fix infinite directory reads

The readdir implementation currently processes always up to the last index
it finds. This however can result in an infinite loop if the directory has
a large number of entries such that they won't all fit in the given buffer
passed to the readdir callback, that is, dir_emit() returns a non-zero
value. Because in that case readdir() will be called again and if in the
meanwhile new directory entries were added and we still can't put all the
remaining entries in the buffer, we keep repeating this over and over.

The following C program and test script reproduce the problem:

  $ cat /mnt/readdir_prog.c
  #include <sys/types.h>
  #include <dirent.h>
  #include <stdio.h>

  int main(int argc, char *argv[])
  {
    DIR *dir = opendir(".");
    struct dirent *dd;

    while ((dd = readdir(dir))) {
      printf("%s\n", dd->d_name);
      rename(dd->d_name, "TEMPFILE");
      rename("TEMPFILE", dd->d_name);
    }
    closedir(dir);
  }

  $ gcc -o /mnt/readdir_prog /mnt/readdir_prog.c

  $ cat test.sh
  #!/bin/bash

  DEV=/dev/sdi
  MNT=/mnt/sdi

  mkfs.btrfs -f $DEV &> /dev/null
  #mkfs.xfs -f $DEV &> /dev/null
  #mkfs.ext4 -F $DEV &> /dev/null

  mount $DEV $MNT

  mkdir $MNT/testdir
  for ((i = 1; i <= 2000; i++)); do
      echo -n > $MNT/testdir/file_$i
  done

  cd $MNT/testdir
  /mnt/readdir_prog

  cd /mnt

  umount $MNT

This behaviour is surprising to applications and it's unlike ext4, xfs,
tmpfs, vfat and other filesystems, which always finish. In this case where
new entries were added due to renames, some file names may be reported
more than once, but this varies according to each filesystem - for example
ext4 never reported the same file more than once while xfs reports the
first 13 file names twice.

So change our readdir implementation to track the last index number when
opendir() is called and then make readdir() never process beyond that
index number. This gives the same behaviour as ext4.

Reported-by: Rob Landley <rob@landley.net>
Link: https://lore.kernel.org/linux-btrfs/2c8c55ec-04c6-e0dc-9c5c-8c7924778c35@landley.net/
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217681
CC: stable@vger.kernel.org # 6.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 3 insertions, 2 deletions

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 6b457b010cbc..6d51db066503 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1632,6 +1632,7 @@ int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode)
 }
 
 bool btrfs_readdir_get_delayed_items(struct inode *inode,
+				     u64 last_index,
 				     struct list_head *ins_list,
 				     struct list_head *del_list)
 {
@@ -1651,14 +1652,14 @@ bool btrfs_readdir_get_delayed_items(struct inode *inode,
 
 	mutex_lock(&delayed_node->mutex);
 	item = __btrfs_first_delayed_insertion_item(delayed_node);
-	while (item) {
+	while (item && item->index <= last_index) {
 		refcount_inc(&item->refs);
 		list_add_tail(&item->readdir_list, ins_list);
 		item = __btrfs_next_delayed_item(item);
 	}
 
 	item = __btrfs_first_delayed_deletion_item(delayed_node);
-	while (item) {
+	while (item && item->index <= last_index) {
 		refcount_inc(&item->refs);
 		list_add_tail(&item->readdir_list, del_list);
 		item = __btrfs_next_delayed_item(item);