Re: [PATCH 04/11] vfs: check unlinked ancestors before mount

[Miklos Szeredi]

This one actually has a slight chance of working.

Thanks,
Miklos

---
Subject: vfs: check unlinked ancestors before mount
From: Miklos Szeredi <mszeredi@xxxxxxx>

We check submounts before doing d_drop() on a non-empty directory dentry in
NFS (have_submounts()), but we do not exclude a racing mount.  Nor do we
prevent mounts to be added to the disconnected subtree using relative paths
after the d_drop().

This patch fixes these issues by checking for unlinked (unhashed, non-root)
ancestors before proceeding with the mount.  This is done after setting
DCACHE_MOUNTED on the soon-to-be mountpoint and with the rename seqlock
taken for write.  This ensures that the only one of
check_submounts_and_drop() or has_unlinked_ancestor() can succeed.

Signed-off-by: Miklos Szeredi <mszeredi@xxxxxxx>
CC: David Howells <dhowells@xxxxxxxxxx>
CC: Steven Whitehouse <swhiteho@xxxxxxxxxx>
CC: Trond Myklebust <Trond.Myklebust@xxxxxxxxxx>
CC: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 fs/dcache.c    |   52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/internal.h  |    1 +
 fs/namespace.c |   11 +++++------
 3 files changed, 58 insertions(+), 6 deletions(-)

--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1159,6 +1159,58 @@ int have_submounts(struct dentry *parent
 }
 EXPORT_SYMBOL(have_submounts);
 
+static bool __has_unlinked_ancestor(struct dentry *dentry)
+{
+	struct dentry *this;
+
+	for (this = dentry; !IS_ROOT(this); this = this->d_parent) {
+		int is_unhashed;
+
+		/* Need exclusion wrt. check_submounts_and_drop() */
+		spin_lock(&this->d_lock);
+		is_unhashed = d_unhashed(this);
+		spin_unlock(&this->d_lock);
+
+		if (is_unhashed)
+			return true;
+	}
+	return false;
+}
+
+/*
+ * Called by mount code to set a mountpoint and check if the mountpoint is
+ * reachable (e.g. NFS can unhash a directory dentry and then the complete
+ * subtree can become unreachable).
+ *
+ * Only one of check_submounts_and_drop() and d_set_mounted() must succeed.  For
+ * this reason take rename_lock and d_lock on dentry and ancestors.
+ */
+int d_set_mounted(struct dentry *dentry)
+{
+	int ret = -ENOENT;
+
+	write_seqlock(&rename_lock);
+	spin_lock(&dentry->d_lock);
+	if (d_unlinked(dentry)) {
+		spin_unlock(&dentry->d_lock);
+		goto out;
+	}
+
+	dentry->d_flags |= DCACHE_MOUNTED;
+	spin_unlock(&dentry->d_lock);
+
+	if (__has_unlinked_ancestor(dentry->d_parent)) {
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags &= ~DCACHE_MOUNTED;
+		spin_unlock(&dentry->d_lock);
+		goto out;
+	}
+	ret = 0;
+out:
+	write_sequnlock(&rename_lock);
+	return ret;
+}
+
 /*
  * Search the dentry child list of the specified parent,
  * and move any unused dentries to the end of the unused
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -126,6 +126,7 @@ extern int invalidate_inodes(struct supe
  * dcache.c
  */
 extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
+extern int d_set_mounted(struct dentry *dentry);
 
 /*
  * read_write.c
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -611,6 +611,7 @@ static struct mountpoint *new_mountpoint
 {
 	struct list_head *chain = mountpoint_hashtable + hash(NULL, dentry);
 	struct mountpoint *mp;
+	int ret;
 
 	list_for_each_entry(mp, chain, m_hash) {
 		if (mp->m_dentry == dentry) {
@@ -626,14 +627,12 @@ static struct mountpoint *new_mountpoint
 	if (!mp)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock(&dentry->d_lock);
-	if (d_unlinked(dentry)) {
-		spin_unlock(&dentry->d_lock);
+	ret = d_set_mounted(dentry);
+	if (ret) {
 		kfree(mp);
-		return ERR_PTR(-ENOENT);
+		return ERR_PTR(ret);
 	}
-	dentry->d_flags |= DCACHE_MOUNTED;
-	spin_unlock(&dentry->d_lock);
+
 	mp->m_dentry = dentry;
 	mp->m_count = 1;
 	list_add(&mp->m_hash, chain);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/