vfs: kill FS_REVAL_DOT by adding a d_weak_revalidate dentry op

The following set of operations on a NFS client and server will cause

    server# mkdir a
    client# cd a
    server# mv a a.bak
    client# sleep 30  # (or whatever the dir attrcache timeout is)
    client# stat .
    stat: cannot stat `.': Stale NFS file handle

Obviously, we should not be getting an ESTALE error back there since the
inode still exists on the server. The problem is that the lookup code
will call d_revalidate on the dentry that "." refers to, because NFS has
FS_REVAL_DOT set.

nfs_lookup_revalidate will see that the parent directory has changed and
will try to reverify the dentry by redoing a LOOKUP. That of course
fails, so the lookup code returns ESTALE.

The problem here is that d_revalidate is really a bad fit for this case.
What we really want to know at this point is whether the inode is still
good or not, but we don't really care what name it goes by or whether
the dcache is still valid.

Add a new d_op->d_weak_revalidate operation and have complete_walk call
that instead of d_revalidate. The intent there is to allow for a
"weaker" d_revalidate that just checks to see whether the inode is still
good. This is also gives us an opportunity to kill off the FS_REVAL_DOT
special casing.

[AV: changed method name, added note in porting, fixed confusion re
having it possibly called from RCU mode (it won't be)]

Cc: NeilBrown <neilb@suse.de>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

7 files changed, 53 insertions, 13 deletions

diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index 64600b5d0522..9ad68628522c 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -137,6 +137,7 @@ out_valid:
 
 const struct dentry_operations v9fs_cached_dentry_operations = {
 	.d_revalidate = v9fs_lookup_revalidate,
+	.d_weak_revalidate = v9fs_lookup_revalidate,
 	.d_delete = v9fs_cached_dentry_delete,
 	.d_release = v9fs_dentry_release,
 };
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 137d50396898..91dad63e5a2d 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -363,5 +363,5 @@ struct file_system_type v9fs_fs_type = {
 	.mount = v9fs_mount,
 	.kill_sb = v9fs_kill_super,
 	.owner = THIS_MODULE,
-	.fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT,
+	.fs_flags = FS_RENAME_DOES_D_MOVE,
 };
diff --git a/fs/dcache.c b/fs/dcache.c
index ebab049826c0..68220dd0c135 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1358,6 +1358,7 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 	WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH	|
 				DCACHE_OP_COMPARE	|
 				DCACHE_OP_REVALIDATE	|
+				DCACHE_OP_WEAK_REVALIDATE	|
 				DCACHE_OP_DELETE ));
 	dentry->d_op = op;
 	if (!op)
@@ -1368,6 +1369,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 		dentry->d_flags |= DCACHE_OP_COMPARE;
 	if (op->d_revalidate)
 		dentry->d_flags |= DCACHE_OP_REVALIDATE;
+	if (op->d_weak_revalidate)
+		dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE;
 	if (op->d_delete)
 		dentry->d_flags |= DCACHE_OP_DELETE;
 	if (op->d_prune)
diff --git a/fs/namei.c b/fs/namei.c
index 052c095c2808..dc984fee5532 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -600,14 +600,10 @@ static int complete_walk(struct nameidata *nd)
 	if (likely(!(nd->flags & LOOKUP_JUMPED)))
 		return 0;
 
-	if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
+	if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE)))
 		return 0;
 
-	if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
-		return 0;
-
-	/* Note: we do not d_invalidate() */
-	status = d_revalidate(dentry, nd->flags);
+	status = dentry->d_op->d_weak_revalidate(dentry, nd->flags);
 	if (status > 0)
 		return 0;
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index a8bd28cde7e2..f23f455be42b 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1136,6 +1136,45 @@ out_error:
 }
 
 /*
+ * A weaker form of d_revalidate for revalidating just the dentry->d_inode
+ * when we don't really care about the dentry name. This is called when a
+ * pathwalk ends on a dentry that was not found via a normal lookup in the
+ * parent dir (e.g.: ".", "..", procfs symlinks or mountpoint traversals).
+ *
+ * In this situation, we just want to verify that the inode itself is OK
+ * since the dentry might have changed on the server.
+ */
+static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	int error;
+	struct inode *inode = dentry->d_inode;
+
+	/*
+	 * I believe we can only get a negative dentry here in the case of a
+	 * procfs-style symlink. Just assume it's correct for now, but we may
+	 * eventually need to do something more here.
+	 */
+	if (!inode) {
+		dfprintk(LOOKUPCACHE, "%s: %s/%s has negative inode\n",
+				__func__, dentry->d_parent->d_name.name,
+				dentry->d_name.name);
+		return 1;
+	}
+
+	if (is_bad_inode(inode)) {
+		dfprintk(LOOKUPCACHE, "%s: %s/%s has dud inode\n",
+				__func__, dentry->d_parent->d_name.name,
+				dentry->d_name.name);
+		return 0;
+	}
+
+	error = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	dfprintk(LOOKUPCACHE, "NFS: %s: inode %lu is %s\n",
+			__func__, inode->i_ino, error ? "invalid" : "valid");
+	return !error;
+}
+
+/*
  * This is called from dput() when d_count is going to 0.
  */
 static int nfs_dentry_delete(const struct dentry *dentry)
@@ -1202,6 +1241,7 @@ static void nfs_d_release(struct dentry *dentry)
 
 const struct dentry_operations nfs_dentry_operations = {
 	.d_revalidate	= nfs_lookup_revalidate,
+	.d_weak_revalidate	= nfs_weak_revalidate,
 	.d_delete	= nfs_dentry_delete,
 	.d_iput		= nfs_dentry_iput,
 	.d_automount	= nfs_d_automount,
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 84d2e9e2f313..569b166cc050 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -28,7 +28,7 @@ static struct file_system_type nfs4_remote_fs_type = {
 	.name		= "nfs4",
 	.mount		= nfs4_remote_mount,
 	.kill_sb	= nfs_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
 };
 
 static struct file_system_type nfs4_remote_referral_fs_type = {
@@ -36,7 +36,7 @@ static struct file_system_type nfs4_remote_referral_fs_type = {
 	.name		= "nfs4",
 	.mount		= nfs4_remote_referral_mount,
 	.kill_sb	= nfs_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
 };
 
 struct file_system_type nfs4_referral_fs_type = {
@@ -44,7 +44,7 @@ struct file_system_type nfs4_referral_fs_type = {
 	.name		= "nfs4",
 	.mount		= nfs4_referral_mount,
 	.kill_sb	= nfs_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
 };
 
 static const struct super_operations nfs4_sops = {
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2e7e8c878e5d..92acc26f9c5f 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -292,7 +292,7 @@ struct file_system_type nfs_fs_type = {
 	.name		= "nfs",
 	.mount		= nfs_fs_mount,
 	.kill_sb	= nfs_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
 };
 EXPORT_SYMBOL_GPL(nfs_fs_type);
 
@@ -301,7 +301,7 @@ struct file_system_type nfs_xdev_fs_type = {
 	.name		= "nfs",
 	.mount		= nfs_xdev_mount,
 	.kill_sb	= nfs_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
 };
 
 const struct super_operations nfs_sops = {
@@ -331,7 +331,7 @@ struct file_system_type nfs4_fs_type = {
 	.name		= "nfs4",
 	.mount		= nfs_fs_mount,
 	.kill_sb	= nfs_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
 };
 EXPORT_SYMBOL_GPL(nfs4_fs_type);