summaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2018-04-18 03:17:34 +0300
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2018-08-09 13:16:39 +0300
commit6f021e4ef39ace7f58c415856aef9308c70e89b9 (patch)
tree362a06a1fe7630813760c953d500922dc20b79b3 /fs/xfs
parent27c41b170183d5d4ebbb6e4fdf41f035ef8617f8 (diff)
downloadlinux-6f021e4ef39ace7f58c415856aef9308c70e89b9.tar.xz
xfs: validate cached inodes are free when allocated
commit afca6c5b2595fc44383919fba740c194b0b76aff upstream. A recent fuzzed filesystem image cached random dcache corruption when the reproducer was run. This often showed up as panics in lookup_slow() on a null inode->i_ops pointer when doing pathwalks. BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 .... Call Trace: lookup_slow+0x44/0x60 walk_component+0x3dd/0x9f0 link_path_walk+0x4a7/0x830 path_lookupat+0xc1/0x470 filename_lookup+0x129/0x270 user_path_at_empty+0x36/0x40 path_listxattr+0x98/0x110 SyS_listxattr+0x13/0x20 do_syscall_64+0xf5/0x280 entry_SYSCALL_64_after_hwframe+0x42/0xb7 but had many different failure modes including deadlocks trying to lock the inode that was just allocated or KASAN reports of use-after-free violations. The cause of the problem was a corrupt INOBT on a v4 fs where the root inode was marked as free in the inobt record. Hence when we allocated an inode, it chose the root inode to allocate, found it in the cache and re-initialised it. We recently fixed a similar inode allocation issue caused by inobt record corruption problem in xfs_iget_cache_miss() in commit ee457001ed6c ("xfs: catch inode allocation state mismatch corruption"). This change adds similar checks to the cache-hit path to catch it, and turns the reproducer into a corruption shutdown situation. Reported-by: Wen Xu <wen.xu@gatech.edu> Signed-Off-By: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> [darrick: fix typos in comment] Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Cc: Eduardo Valentin <eduval@amazon.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/xfs_icache.c73
1 files changed, 48 insertions, 25 deletions
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 26f9e66a3ec9..544b5211221c 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -306,6 +306,46 @@ xfs_reinit_inode(
}
/*
+ * If we are allocating a new inode, then check what was returned is
+ * actually a free, empty inode. If we are not allocating an inode,
+ * then check we didn't find a free inode.
+ *
+ * Returns:
+ * 0 if the inode free state matches the lookup context
+ * -ENOENT if the inode is free and we are not allocating
+ * -EFSCORRUPTED if there is any state mismatch at all
+ */
+static int
+xfs_iget_check_free_state(
+ struct xfs_inode *ip,
+ int flags)
+{
+ if (flags & XFS_IGET_CREATE) {
+ /* should be a free inode */
+ if (VFS_I(ip)->i_mode != 0) {
+ xfs_warn(ip->i_mount,
+"Corruption detected! Free inode 0x%llx not marked free! (mode 0x%x)",
+ ip->i_ino, VFS_I(ip)->i_mode);
+ return -EFSCORRUPTED;
+ }
+
+ if (ip->i_d.di_nblocks != 0) {
+ xfs_warn(ip->i_mount,
+"Corruption detected! Free inode 0x%llx has blocks allocated!",
+ ip->i_ino);
+ return -EFSCORRUPTED;
+ }
+ return 0;
+ }
+
+ /* should be an allocated inode */
+ if (VFS_I(ip)->i_mode == 0)
+ return -ENOENT;
+
+ return 0;
+}
+
+/*
* Check the validity of the inode we just found it the cache
*/
static int
@@ -354,12 +394,12 @@ xfs_iget_cache_hit(
}
/*
- * If lookup is racing with unlink return an error immediately.
+ * Check the inode free state is valid. This also detects lookup
+ * racing with unlinks.
*/
- if (VFS_I(ip)->i_mode == 0 && !(flags & XFS_IGET_CREATE)) {
- error = -ENOENT;
+ error = xfs_iget_check_free_state(ip, flags);
+ if (error)
goto out_error;
- }
/*
* If IRECLAIMABLE is set, we've torn down the VFS inode already.
@@ -477,29 +517,12 @@ xfs_iget_cache_miss(
/*
- * If we are allocating a new inode, then check what was returned is
- * actually a free, empty inode. If we are not allocating an inode,
- * the check we didn't find a free inode.
+ * Check the inode free state is valid. This also detects lookup
+ * racing with unlinks.
*/
- if (flags & XFS_IGET_CREATE) {
- if (VFS_I(ip)->i_mode != 0) {
- xfs_warn(mp,
-"Corruption detected! Free inode 0x%llx not marked free on disk",
- ino);
- error = -EFSCORRUPTED;
- goto out_destroy;
- }
- if (ip->i_d.di_nblocks != 0) {
- xfs_warn(mp,
-"Corruption detected! Free inode 0x%llx has blocks allocated!",
- ino);
- error = -EFSCORRUPTED;
- goto out_destroy;
- }
- } else if (VFS_I(ip)->i_mode == 0) {
- error = -ENOENT;
+ error = xfs_iget_check_free_state(ip, flags);
+ if (error)
goto out_destroy;
- }
/*
* Preload the radix tree so we can insert safely under the