linux-kernel - [PATCH 15/16] vfs: retry last component if opening stale dentry

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1335357857-16416-16-git-send-email-miklos@szeredi.hu>
Date:	Wed, 25 Apr 2012 14:44:16 +0200
From:	Miklos Szeredi <miklos@...redi.hu>
To:	viro@...IV.linux.org.uk
Cc:	linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
	hch@...radead.org, torvalds@...ux-foundation.org, mszeredi@...e.cz
Subject: [PATCH 15/16] vfs: retry last component if opening stale dentry

From: Miklos Szeredi <mszeredi@...e.cz>

NFS optimizes away d_revalidates for last component of open.  This means that
open itself can find the dentry stale.

This patch allows the filesystem to return EOPENSTALE and the VFS will retry the
lookup on just the last component if possible.

If the lookup was done using RCU mode, including the last component, then this
is not possible since the parent dentry is lost.  In this case fall back to
non-RCU lookup.  Currently this is not used since NFS will always leave RCU
mode.

Signed-off-by: Miklos Szeredi <mszeredi@...e.cz>
---
 fs/namei.c            |   37 +++++++++++++++++++++++++++++++++++--
 include/linux/errno.h |    1 +
 2 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index f7e7d76..e34df8d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2204,6 +2204,8 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	struct file *filp;
 	struct inode *inode;
 	int symlink_ok = 0;
+	struct path save_parent = { .dentry = NULL, .mnt = NULL };
+	bool retried = false;
 	int error;
 
 	nd->flags &= ~LOOKUP_PARENT;
@@ -2269,6 +2271,7 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	if (nd->last.name[nd->last.len])
 		goto exit;
 
+retry_lookup:
 	mutex_lock(&dir->d_inode->i_mutex);
 
 	dentry = lookup_hash(nd);
@@ -2349,12 +2352,21 @@ finish_lookup:
 		return NULL;
 	}
 
-	path_to_nameidata(path, nd);
+	if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path->mnt) {
+		path_to_nameidata(path, nd);
+	} else {
+		save_parent.dentry = nd->path.dentry;
+		save_parent.mnt = mntget(path->mnt);
+		nd->path.dentry = path->dentry;
+
+	}
 	nd->inode = inode;
 	/* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
 	error = complete_walk(nd);
-	if (error)
+	if (error) {
+		path_put(&save_parent);
 		return ERR_PTR(error);
+	}
 	error = -EISDIR;
 	if ((open_flag & O_CREAT) && S_ISDIR(nd->inode->i_mode))
 		goto exit;
@@ -2377,6 +2389,20 @@ common:
 	if (error)
 		goto exit;
 	filp = nameidata_to_filp(nd);
+	if (filp == ERR_PTR(-EOPENSTALE) && save_parent.dentry && !retried) {
+		BUG_ON(save_parent.dentry != dir);
+		path_put(&nd->path);
+		nd->path = save_parent;
+		nd->inode = dir->d_inode;
+		save_parent.mnt = NULL;
+		save_parent.dentry = NULL;
+		if (want_write) {
+			mnt_drop_write(nd->path.mnt);
+			want_write = 0;
+		}
+		retried = true;
+		goto retry_lookup;
+	}
 	if (!IS_ERR(filp)) {
 		error = ima_file_check(filp, op->acc_mode);
 		if (error) {
@@ -2396,6 +2422,7 @@ common:
 out:
 	if (want_write)
 		mnt_drop_write(nd->path.mnt);
+	path_put(&save_parent);
 	terminate_walk(nd);
 	return filp;
 
@@ -2459,6 +2486,12 @@ out:
 	if (base)
 		fput(base);
 	release_open_intent(nd);
+	if (filp == ERR_PTR(-EOPENSTALE)) {
+		if (flags & LOOKUP_RCU)
+			filp = ERR_PTR(-ECHILD);
+		else
+			filp = ERR_PTR(-ESTALE);
+	}
 	return filp;
 
 out_filp:
diff --git a/include/linux/errno.h b/include/linux/errno.h
index 2d09bfa..e0de516 100644
--- a/include/linux/errno.h
+++ b/include/linux/errno.h
@@ -17,6 +17,7 @@
 #define ENOIOCTLCMD	515	/* No ioctl command */
 #define ERESTART_RESTARTBLOCK 516 /* restart by calling sys_restart_syscall */
 #define EPROBE_DEFER	517	/* Driver requests probe retry */
+#define EOPENSTALE	518	/* open found a stale dentry */
 
 /* Defined for the NFSv3 protocol */
 #define EBADHANDLE	521	/* Illegal NFS file handle */
-- 
1.7.7

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/