NFS: Ensure the client submounts, when it crosses a server mountpoint.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

fs/nfs/Makefile

@@ -5,7 +5,8 @@
 obj-$(CONFIG_NFS_FS) += nfs.o
 
 nfs-y 			:= dir.o file.o inode.o nfs2xdr.o pagelist.o \
-			   proc.o read.o symlink.o unlink.o write.o
+			   proc.o read.o symlink.o unlink.o write.o \
+			   namespace.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o mount_clnt.o      
 nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o
 nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o

fs/nfs/dir.c

@@ -868,6 +868,17 @@ int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
 	return (nd->intent.open.flags & O_EXCL) != 0;
 }
 
+static inline int nfs_reval_fsid(struct inode *dir,
+		struct nfs_fh *fh, struct nfs_fattr *fattr)
+{
+	struct nfs_server *server = NFS_SERVER(dir);
+
+	if (!nfs_fsid_equal(&server->fsid, &fattr->fsid))
+		/* Revalidate fsid on root dir */
+		return __nfs_revalidate_inode(server, dir->i_sb->s_root->d_inode);
+	return 0;
+}
+
 static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
 {
 	struct dentry *res;
@@ -900,6 +911,11 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 		res = ERR_PTR(error);
 		goto out_unlock;
 	}
+	error = nfs_reval_fsid(dir, &fhandle, &fattr);
+	if (error < 0) {
+		res = ERR_PTR(error);
+		goto out_unlock;
+	}
 	inode = nfs_fhget(dentry->d_sb, &fhandle, &fattr);
 	res = (struct dentry *)inode;
 	if (IS_ERR(res))

fs/nfs/namespace.c

+/*
+ * linux/fs/nfs/namespace.c
+ *
+ * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com>
+ *
+ * NFS namespace
+ */
+
+#include <linux/config.h>
+
+#include <linux/dcache.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/nfs_fs.h>
+#include <linux/string.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/vfs.h>
+
+#define NFSDBG_FACILITY		NFSDBG_VFS
+
+/*
+ * nfs_follow_mountpoint - handle crossing a mountpoint on the server
+ * @dentry - dentry of mountpoint
+ * @nd - nameidata info
+ *
+ * When we encounter a mountpoint on the server, we want to set up
+ * a mountpoint on the client too, to prevent inode numbers from
+ * colliding, and to allow "df" to work properly.
+ * On NFSv4, we also want to allow for the fact that different
+ * filesystems may be migrated to different servers in a failover
+ * situation, and that different filesystems may want to use
+ * different security flavours.
+ */
+static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
+{
+	struct vfsmount *mnt;
+	struct nfs_server *server = NFS_SERVER(dentry->d_inode);
+	struct dentry *parent;
+	struct nfs_fh fh;
+	struct nfs_fattr fattr;
+	int err;
+
+	BUG_ON(IS_ROOT(dentry));
+	dprintk("%s: enter\n", __FUNCTION__);
+	dput(nd->dentry);
+	nd->dentry = dget(dentry);
+	if (d_mountpoint(nd->dentry))
+		goto out_follow;
+	/* Look it up again */
+	parent = dget_parent(nd->dentry);
+	err = server->rpc_ops->lookup(parent->d_inode, &nd->dentry->d_name, &fh, &fattr);
+	dput(parent);
+	if (err != 0)
+		goto out_err;
+
+	mnt = nfs_do_submount(nd->mnt, nd->dentry, &fh, &fattr);
+	err = PTR_ERR(mnt);
+	if (IS_ERR(mnt))
+		goto out_err;
+
+	mntget(mnt);
+	err = do_add_mount(mnt, nd, nd->mnt->mnt_flags, NULL);
+	if (err < 0) {
+		mntput(mnt);
+		if (err == -EBUSY)
+			goto out_follow;
+		goto out_err;
+	}
+	mntput(nd->mnt);
+	dput(nd->dentry);
+	nd->mnt = mnt;
+	nd->dentry = dget(mnt->mnt_root);
+out:
+	dprintk("%s: done, returned %d\n", __FUNCTION__, err);
+	return ERR_PTR(err);
+out_err:
+	path_release(nd);
+	goto out;
+out_follow:
+	while(d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry))
+		;
+	err = 0;
+	goto out;
+}
+
+struct inode_operations nfs_mountpoint_inode_operations = {
+	.follow_link	= nfs_follow_mountpoint,
+	.getattr	= nfs_getattr,
+};

fs/nfs/nfs4_fs.h

@@ -217,6 +217,7 @@ extern int nfs4_proc_renew(struct nfs4_client *, struct rpc_cred *);
 extern int nfs4_do_close(struct inode *inode, struct nfs4_state *state);
 extern struct dentry *nfs4_atomic_open(struct inode *, struct dentry *, struct nameidata *);
 extern int nfs4_open_revalidate(struct inode *, struct dentry *, int, struct nameidata *);
+extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
 
 extern struct nfs4_state_recovery_ops nfs4_reboot_recovery_ops;
 extern struct nfs4_state_recovery_ops nfs4_network_partition_recovery_ops;

fs/nfs/nfs4proc.c

@@ -1331,7 +1331,7 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 	return status;
 }
 
-static int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
+int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
 {
 	struct nfs4_exception exception = { };
 	int err;

include/linux/nfs_fs.h

@@ -313,6 +313,10 @@ extern void nfs_end_data_update(struct inode *);
 extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx);
 extern void put_nfs_open_context(struct nfs_open_context *ctx);
 extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, int mode);
+extern struct vfsmount *nfs_do_submount(const struct vfsmount *mnt_parent,
+					const struct dentry *dentry,
+					struct nfs_fh *fh,
+					struct nfs_fattr *fattr);
 
 /* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */
 extern u32 root_nfs_parse_addr(char *name); /*__init*/
@@ -398,6 +402,11 @@ extern void nfs_unregister_sysctl(void);
 #define nfs_unregister_sysctl() do { } while(0)
 #endif
 
+/*
+ * linux/fs/nfs/namespace.c
+ */
+extern struct inode_operations nfs_mountpoint_inode_operations;
+
 /*
  * linux/fs/nfs/unlink.c
  */