Merge tag 'afs-next-20180208' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

Pull afs updates from David Howells:
 "Four fixes:

   - add a missing put

   - two fixes to reset the address iteration cursor correctly

   - fix setting up the fileserver iteration cursor.

  Two cleanups:

   - remove some dead code

   - rearrange a function to be more logically laid out

  And one new feature:

   - Support AFS dynamic root.

     With this one should be able to do, say:

        mkdir /afs
        mount -t afs none /afs -o dyn

     to create a dynamic root and then, provided you have keyutils
     installed, do:

        ls /afs/grand.central.org

     and:

        ls /afs/umich.edu

     to list the root volumes of both those organisations' AFS cells
     without requiring any other setup (the kernel upcall to a program
     in the keyutils package to do DNS access as does NFS)"

* tag 'afs-next-20180208' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs:
  afs: Support the AFS dynamic root
  afs: Rearrange afs_select_fileserver() a little
  afs: Remove unused code
  afs: Fix server list handling
  afs: Need to clear responded flag in addr cursor
  afs: Fix missing cursor clearance
  afs: Add missing afs_put_cell()

Documentation/filesystems/afs.txt

@@ -7,6 +7,7 @@ Contents:
  - Overview.
  - Usage.
  - Mountpoints.
+ - Dynamic root.
  - Proc filesystem.
  - The cell database.
  - Security.
@@ -127,6 +128,22 @@ mounted on /afs in one go by doing:
 	umount /afs
 
 
+============
+DYNAMIC ROOT
+============
+
+A mount option is available to create a serverless mount that is only usable
+for dynamic lookup.  Creating such a mount can be done by, for example:
+
+	mount -t afs none /afs -o dyn
+
+This creates a mount that just has an empty directory at the root.  Attempting
+to look up a name in this directory will cause a mountpoint to be created that
+looks up a cell of the same name, for example:
+
+	ls /afs/grand.central.org/
+
+
 ===============
 PROC FILESYSTEM
 ===============

fs/afs/addr_list.c

@@ -332,11 +332,18 @@ bool afs_iterate_addresses(struct afs_addr_cursor *ac)
  */
 int afs_end_cursor(struct afs_addr_cursor *ac)
 {
-	if (ac->responded && ac->index != ac->start)
-		WRITE_ONCE(ac->alist->index, ac->index);
+	struct afs_addr_list *alist;
+
+	alist = ac->alist;
+	if (alist) {
+		if (ac->responded && ac->index != ac->start)
+			WRITE_ONCE(alist->index, ac->index);
+		afs_put_addrlist(alist);
+	}
 
-	afs_put_addrlist(ac->alist);
+	ac->addr = NULL;
 	ac->alist = NULL;
+	ac->begun = false;
 	return ac->error;
 }
 

fs/afs/dir.c

@@ -17,10 +17,13 @@
 #include <linux/pagemap.h>
 #include <linux/ctype.h>
 #include <linux/sched.h>
+#include <linux/dns_resolver.h>
 #include "internal.h"
 
 static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 				 unsigned int flags);
+static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry,
+					 unsigned int flags);
 static int afs_dir_open(struct inode *inode, struct file *file);
 static int afs_readdir(struct file *file, struct dir_context *ctx);
 static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
@@ -64,6 +67,17 @@ const struct inode_operations afs_dir_inode_operations = {
 	.listxattr	= afs_listxattr,
 };
 
+const struct file_operations afs_dynroot_file_operations = {
+	.open		= dcache_dir_open,
+	.release	= dcache_dir_close,
+	.iterate_shared	= dcache_readdir,
+	.llseek		= dcache_dir_lseek,
+};
+
+const struct inode_operations afs_dynroot_inode_operations = {
+	.lookup		= afs_dynroot_lookup,
+};
+
 const struct dentry_operations afs_fs_dentry_operations = {
 	.d_revalidate	= afs_d_revalidate,
 	.d_delete	= afs_d_delete,
@@ -467,26 +481,59 @@ static int afs_do_lookup(struct inode *dir, struct dentry *dentry,
 	return 0;
 }
 
+/*
+ * Probe to see if a cell may exist.  This prevents positive dentries from
+ * being created unnecessarily.
+ */
+static int afs_probe_cell_name(struct dentry *dentry)
+{
+	struct afs_cell *cell;
+	const char *name = dentry->d_name.name;
+	size_t len = dentry->d_name.len;
+	int ret;
+
+	/* Names prefixed with a dot are R/W mounts. */
+	if (name[0] == '.') {
+		if (len == 1)
+			return -EINVAL;
+		name++;
+		len--;
+	}
+
+	cell = afs_lookup_cell_rcu(afs_d2net(dentry), name, len);
+	if (!IS_ERR(cell)) {
+		afs_put_cell(afs_d2net(dentry), cell);
+		return 0;
+	}
+
+	ret = dns_query("afsdb", name, len, "ipv4", NULL, NULL);
+	if (ret == -ENODATA)
+		ret = -EDESTADDRREQ;
+	return ret;
+}
+
 /*
  * Try to auto mount the mountpoint with pseudo directory, if the autocell
  * operation is setted.
  */
-static struct inode *afs_try_auto_mntpt(
-	int ret, struct dentry *dentry, struct inode *dir, struct key *key,
-	struct afs_fid *fid)
+static struct inode *afs_try_auto_mntpt(struct dentry *dentry,
+					struct inode *dir, struct afs_fid *fid)
 {
-	const char *devname = dentry->d_name.name;
 	struct afs_vnode *vnode = AFS_FS_I(dir);
 	struct inode *inode;
+	int ret = -ENOENT;
 
-	_enter("%d, %p{%pd}, {%x:%u}, %p",
-	       ret, dentry, dentry, vnode->fid.vid, vnode->fid.vnode, key);
+	_enter("%p{%pd}, {%x:%u}",
+	       dentry, dentry, vnode->fid.vid, vnode->fid.vnode);
+
+	if (!test_bit(AFS_VNODE_AUTOCELL, &vnode->flags))
+		goto out;
 
-	if (ret != -ENOENT ||
-	    !test_bit(AFS_VNODE_AUTOCELL, &vnode->flags))
+	ret = afs_probe_cell_name(dentry);
+	if (ret < 0)
 		goto out;
 
-	inode = afs_iget_autocell(dir, devname, strlen(devname), key);
+	inode = afs_iget_pseudo_dir(dir->i_sb, false);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
 		goto out;
@@ -545,13 +592,16 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 
 	ret = afs_do_lookup(dir, dentry, &fid, key);
 	if (ret < 0) {
-		inode = afs_try_auto_mntpt(ret, dentry, dir, key, &fid);
-		if (!IS_ERR(inode)) {
-			key_put(key);
-			goto success;
+		if (ret == -ENOENT) {
+			inode = afs_try_auto_mntpt(dentry, dir, &fid);
+			if (!IS_ERR(inode)) {
+				key_put(key);
+				goto success;
+			}
+
+			ret = PTR_ERR(inode);
 		}
 
-		ret = PTR_ERR(inode);
 		key_put(key);
 		if (ret == -ENOENT) {
 			d_add(dentry, NULL);
@@ -582,6 +632,46 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 	return NULL;
 }
 
+/*
+ * Look up an entry in a dynroot directory.
+ */
+static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry,
+					 unsigned int flags)
+{
+	struct afs_vnode *vnode;
+	struct afs_fid fid;
+	struct inode *inode;
+	int ret;
+
+	vnode = AFS_FS_I(dir);
+
+	_enter("%pd", dentry);
+
+	ASSERTCMP(d_inode(dentry), ==, NULL);
+
+	if (dentry->d_name.len >= AFSNAMEMAX) {
+		_leave(" = -ENAMETOOLONG");
+		return ERR_PTR(-ENAMETOOLONG);
+	}
+
+	inode = afs_try_auto_mntpt(dentry, dir, &fid);
+	if (IS_ERR(inode)) {
+		ret = PTR_ERR(inode);
+		if (ret == -ENOENT) {
+			d_add(dentry, NULL);
+			_leave(" = NULL [negative]");
+			return NULL;
+		}
+		_leave(" = %d [do]", ret);
+		return ERR_PTR(ret);
+	}
+
+	d_add(dentry, inode);
+	_leave(" = 0 { ino=%lu v=%u }",
+	       d_inode(dentry)->i_ino, d_inode(dentry)->i_generation);
+	return NULL;
+}
+
 /*
  * check that a dentry lookup hit has found a valid entry
  * - NOTE! the hit can be a negative hit too, so we can't assume we have an
@@ -589,6 +679,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
  */
 static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
+	struct afs_super_info *as = dentry->d_sb->s_fs_info;
 	struct afs_vnode *vnode, *dir;
 	struct afs_fid uninitialized_var(fid);
 	struct dentry *parent;
@@ -600,6 +691,9 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
+	if (as->dyn_root)
+		return 1;
+
 	if (d_really_is_positive(dentry)) {
 		vnode = AFS_FS_I(d_inode(dentry));
 		_enter("{v={%x:%u} n=%pd fl=%lx},",

fs/afs/inode.c

@@ -147,7 +147,7 @@ int afs_iget5_test(struct inode *inode, void *opaque)
  *
  * These pseudo inodes don't match anything.
  */
-static int afs_iget5_autocell_test(struct inode *inode, void *opaque)
+static int afs_iget5_pseudo_dir_test(struct inode *inode, void *opaque)
 {
 	return 0;
 }
@@ -169,31 +169,34 @@ static int afs_iget5_set(struct inode *inode, void *opaque)
 }
 
 /*
- * inode retrieval for autocell
+ * Create an inode for a dynamic root directory or an autocell dynamic
+ * automount dir.
  */
-struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name,
-				int namesz, struct key *key)
+struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
 {
 	struct afs_iget_data data;
 	struct afs_super_info *as;
 	struct afs_vnode *vnode;
-	struct super_block *sb;
 	struct inode *inode;
 	static atomic_t afs_autocell_ino;
 
-	_enter("{%x:%u},%*.*s,",
-	       AFS_FS_I(dir)->fid.vid, AFS_FS_I(dir)->fid.vnode,
-	       namesz, namesz, dev_name ?: "");
+	_enter("");
 
-	sb = dir->i_sb;
 	as = sb->s_fs_info;
-	data.volume = as->volume;
-	data.fid.vid = as->volume->vid;
-	data.fid.unique = 0;
-	data.fid.vnode = 0;
+	if (as->volume) {
+		data.volume = as->volume;
+		data.fid.vid = as->volume->vid;
+	}
+	if (root) {
+		data.fid.vnode = 1;
+		data.fid.unique = 1;
+	} else {
+		data.fid.vnode = atomic_inc_return(&afs_autocell_ino);
+		data.fid.unique = 0;
+	}
 
-	inode = iget5_locked(sb, atomic_inc_return(&afs_autocell_ino),
-			     afs_iget5_autocell_test, afs_iget5_set,
+	inode = iget5_locked(sb, data.fid.vnode,
+			     afs_iget5_pseudo_dir_test, afs_iget5_set,
 			     &data);
 	if (!inode) {
 		_leave(" = -ENOMEM");
@@ -211,7 +214,12 @@ struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name,
 
 	inode->i_size		= 0;
 	inode->i_mode		= S_IFDIR | S_IRUGO | S_IXUGO;
-	inode->i_op		= &afs_autocell_inode_operations;
+	if (root) {
+		inode->i_op	= &afs_dynroot_inode_operations;
+		inode->i_fop	= &afs_dynroot_file_operations;
+	} else {
+		inode->i_op	= &afs_autocell_inode_operations;
+	}
 	set_nlink(inode, 2);
 	inode->i_uid		= GLOBAL_ROOT_UID;
 	inode->i_gid		= GLOBAL_ROOT_GID;
@@ -223,8 +231,12 @@ struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name,
 	inode->i_generation	= 0;
 
 	set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags);
-	set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
-	inode->i_flags |= S_AUTOMOUNT | S_NOATIME;
+	if (!root) {
+		set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
+		inode->i_flags |= S_AUTOMOUNT;
+	}
+
+	inode->i_flags |= S_NOATIME;
 	unlock_new_inode(inode);
 	_leave(" = %p", inode);
 	return inode;

fs/afs/internal.h

@@ -36,6 +36,7 @@ struct afs_mount_params {
 	bool			rwpath;		/* T if the parent should be considered R/W */
 	bool			force;		/* T to force cell type */
 	bool			autocell;	/* T if set auto mount operation */
+	bool			dyn_root;	/* T if dynamic root */
 	afs_voltype_t		type;		/* type of volume requested */
 	int			volnamesz;	/* size of volume name */
 	const char		*volname;	/* name of volume to mount */
@@ -186,6 +187,7 @@ struct afs_super_info {
 	struct afs_net		*net;		/* Network namespace */
 	struct afs_cell		*cell;		/* The cell in which the volume resides */
 	struct afs_volume	*volume;	/* volume record */
+	bool			dyn_root;	/* True if dynamic root */
 };
 
 static inline struct afs_super_info *AFS_FS_S(struct super_block *sb)
@@ -634,10 +636,13 @@ extern bool afs_cm_incoming_call(struct afs_call *);
 /*
  * dir.c
  */
-extern bool afs_dir_check_page(struct inode *, struct page *);
+extern const struct file_operations afs_dir_file_operations;
 extern const struct inode_operations afs_dir_inode_operations;
+extern const struct file_operations afs_dynroot_file_operations;
+extern const struct inode_operations afs_dynroot_inode_operations;
 extern const struct dentry_operations afs_fs_dentry_operations;
-extern const struct file_operations afs_dir_file_operations;
+
+extern bool afs_dir_check_page(struct inode *, struct page *);
 
 /*
  * file.c
@@ -695,8 +700,7 @@ extern int afs_fs_get_capabilities(struct afs_net *, struct afs_server *,
  */
 extern int afs_fetch_status(struct afs_vnode *, struct key *);
 extern int afs_iget5_test(struct inode *, void *);
-extern struct inode *afs_iget_autocell(struct inode *, const char *, int,
-				       struct key *);
+extern struct inode *afs_iget_pseudo_dir(struct super_block *, bool);
 extern struct inode *afs_iget(struct super_block *, struct key *,
 			      struct afs_fid *, struct afs_file_status *,
 			      struct afs_callback *,

fs/afs/mntpt.c

@@ -72,7 +72,7 @@ static int afs_mntpt_open(struct inode *inode, struct file *file)
  */
 static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 {
-	struct afs_super_info *super;
+	struct afs_super_info *as;
 	struct vfsmount *mnt;
 	struct afs_vnode *vnode;
 	struct page *page;
@@ -104,13 +104,13 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 			goto error_no_page;
 
 		if (mntpt->d_name.name[0] == '.') {
-			devname[0] = '#';
-			memcpy(devname + 1, mntpt->d_name.name, size - 1);
+			devname[0] = '%';
+			memcpy(devname + 1, mntpt->d_name.name + 1, size - 1);
 			memcpy(devname + size, afs_root_cell,
 			       sizeof(afs_root_cell));
 			rwpath = true;
 		} else {
-			devname[0] = '%';
+			devname[0] = '#';
 			memcpy(devname + 1, mntpt->d_name.name, size);
 			memcpy(devname + size + 1, afs_root_cell,
 			       sizeof(afs_root_cell));
@@ -142,11 +142,13 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 	}
 
 	/* work out what options we want */
-	super = AFS_FS_S(mntpt->d_sb);
-	memcpy(options, "cell=", 5);
-	strcpy(options + 5, super->volume->cell->name);
-	if (super->volume->type == AFSVL_RWVOL || rwpath)
-		strcat(options, ",rwpath");
+	as = AFS_FS_S(mntpt->d_sb);
+	if (as->cell) {
+		memcpy(options, "cell=", 5);
+		strcpy(options + 5, as->cell->name);
+		if ((as->volume && as->volume->type == AFSVL_RWVOL) || rwpath)
+			strcat(options, ",rwpath");
+	}
 
 	/* try and do the mount */
 	_debug("--- attempting mount %s -o %s ---", devname, options);

fs/afs/rotate.c

@@ -330,26 +330,6 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 
 	if (!afs_start_fs_iteration(fc, vnode))
 		goto failed;
-	goto use_server;
-
-next_server:
-	_debug("next");
-	afs_put_cb_interest(afs_v2net(vnode), fc->cbi);
-	fc->cbi = NULL;
-	fc->index++;
-	if (fc->index >= fc->server_list->nr_servers)
-		fc->index = 0;
-	if (fc->index != fc->start)
-		goto use_server;
-
-	/* That's all the servers poked to no good effect.  Try again if some
-	 * of them were busy.
-	 */
-	if (fc->flags & AFS_FS_CURSOR_VBUSY)
-		goto restart_from_beginning;
-
-	fc->ac.error = -EDESTADDRREQ;
-	goto failed;
 
 use_server:
 	_debug("use");
@@ -383,6 +363,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 	afs_get_addrlist(alist);
 	read_unlock(&server->fs_lock);
 
+	memset(&fc->ac, 0, sizeof(fc->ac));
 
 	/* Probe the current fileserver if we haven't done so yet. */
 	if (!test_bit(AFS_SERVER_FL_PROBED, &server->flags)) {
@@ -397,12 +378,8 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 	else
 		afs_put_addrlist(alist);
 
-	fc->ac.addr  = NULL;
 	fc->ac.start = READ_ONCE(alist->index);
 	fc->ac.index = fc->ac.start;
-	fc->ac.error = 0;
-	fc->ac.begun = false;
-	goto iterate_address;
 
 iterate_address:
 	ASSERT(fc->ac.alist);
@@ -410,16 +387,35 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 	/* Iterate over the current server's address list to try and find an
 	 * address on which it will respond to us.
 	 */
-	if (afs_iterate_addresses(&fc->ac)) {
-		_leave(" = t");
-		return true;
-	}
+	if (!afs_iterate_addresses(&fc->ac))
+		goto next_server;
+
+	_leave(" = t");
+	return true;
 
+next_server:
+	_debug("next");
 	afs_end_cursor(&fc->ac);
-	goto next_server;
+	afs_put_cb_interest(afs_v2net(vnode), fc->cbi);
+	fc->cbi = NULL;
+	fc->index++;
+	if (fc->index >= fc->server_list->nr_servers)
+		fc->index = 0;
+	if (fc->index != fc->start)
+		goto use_server;
+
+	/* That's all the servers poked to no good effect.  Try again if some
+	 * of them were busy.
+	 */
+	if (fc->flags & AFS_FS_CURSOR_VBUSY)
+		goto restart_from_beginning;
+
+	fc->ac.error = -EDESTADDRREQ;
+	goto failed;
 
 failed:
 	fc->flags |= AFS_FS_CURSOR_STOP;
+	afs_end_cursor(&fc->ac);
 	_leave(" = f [failed %d]", fc->ac.error);
 	return false;
 }
@@ -458,12 +454,10 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc)
 			return false;
 		}
 
+		memset(&fc->ac, 0, sizeof(fc->ac));
 		fc->ac.alist = alist;
-		fc->ac.addr  = NULL;
 		fc->ac.start = READ_ONCE(alist->index);
 		fc->ac.index = fc->ac.start;
-		fc->ac.error = 0;
-		fc->ac.begun = false;
 		goto iterate_address;
 
 	case 0:
@@ -520,238 +514,3 @@ int afs_end_vnode_operation(struct afs_fs_cursor *fc)
 
 	return fc->ac.error;
 }
-
-#if 0
-/*
- * Set a filesystem server cursor for using a specific FS server.
- */
-int afs_set_fs_cursor(struct afs_fs_cursor *fc, struct afs_vnode *vnode)
-{
-	afs_init_fs_cursor(fc, vnode);
-
-	read_seqlock_excl(&vnode->cb_lock);
-	if (vnode->cb_interest) {
-		if (vnode->cb_interest->server->fs_state == 0)
-			fc->server = afs_get_server(vnode->cb_interest->server);
-		else
-			fc->ac.error = vnode->cb_interest->server->fs_state;
-	} else {
-		fc->ac.error = -ESTALE;
-	}
-	read_sequnlock_excl(&vnode->cb_lock);
-
-	return fc->ac.error;
-}
-
-/*
- * pick a server to use to try accessing this volume
- * - returns with an elevated usage count on the server chosen
- */
-bool afs_volume_pick_fileserver(struct afs_fs_cursor *fc, struct afs_vnode *vnode)
-{
-	struct afs_volume *volume = vnode->volume;
-	struct afs_server *server;
-	int ret, state, loop;
-
-	_enter("%s", volume->vlocation->vldb.name);
-
-	/* stick with the server we're already using if we can */
-	if (vnode->cb_interest && vnode->cb_interest->server->fs_state == 0) {
-		fc->server = afs_get_server(vnode->cb_interest->server);
-		goto set_server;
-	}
-
-	down_read(&volume->server_sem);
-
-	/* handle the no-server case */
-	if (volume->nservers == 0) {
-		fc->ac.error = volume->rjservers ? -ENOMEDIUM : -ESTALE;
-		up_read(&volume->server_sem);
-		_leave(" = f [no servers %d]", fc->ac.error);
-		return false;
-	}
-
-	/* basically, just search the list for the first live server and use
-	 * that */
-	ret = 0;
-	for (loop = 0; loop < volume->nservers; loop++) {
-		server = volume->servers[loop];
-		state = server->fs_state;
-
-		_debug("consider %d [%d]", loop, state);
-
-		switch (state) {
-		case 0:
-			goto picked_server;
-
-		case -ENETUNREACH:
-			if (ret == 0)
-				ret = state;
-			break;
-
-		case -EHOSTUNREACH:
-			if (ret == 0 ||
-			    ret == -ENETUNREACH)
-				ret = state;
-			break;
-
-		case -ECONNREFUSED:
-			if (ret == 0 ||
-			    ret == -ENETUNREACH ||
-			    ret == -EHOSTUNREACH)
-				ret = state;
-			break;
-
-		default:
-		case -EREMOTEIO:
-			if (ret == 0 ||
-			    ret == -ENETUNREACH ||
-			    ret == -EHOSTUNREACH ||
-			    ret == -ECONNREFUSED)
-				ret = state;
-			break;
-		}
-	}
-
-error:
-	fc->ac.error = ret;
-
-	/* no available servers
-	 * - TODO: handle the no active servers case better
-	 */
-	up_read(&volume->server_sem);
-	_leave(" = f [%d]", fc->ac.error);
-	return false;
-
-picked_server:
-	/* Found an apparently healthy server.  We need to register an interest
-	 * in receiving callbacks before we talk to it.
-	 */
-	ret = afs_register_server_cb_interest(vnode,
-					      &volume->cb_interests[loop], server);
-	if (ret < 0)
-		goto error;
-
-	fc->server = afs_get_server(server);
-	up_read(&volume->server_sem);
-set_server:
-	fc->ac.alist = afs_get_addrlist(fc->server->addrs);
-	fc->ac.addr = &fc->ac.alist->addrs[0];
-	_debug("USING SERVER: %pIS\n", &fc->ac.addr->transport);
-	_leave(" = t (picked %pIS)", &fc->ac.addr->transport);
-	return true;
-}
-
-/*
- * release a server after use
- * - releases the ref on the server struct that was acquired by picking
- * - records result of using a particular server to access a volume
- * - return true to try again, false if okay or to issue error
- * - the caller must release the server struct if result was false
- */
-bool afs_iterate_fs_cursor(struct afs_fs_cursor *fc,
-			   struct afs_vnode *vnode)
-{
-	struct afs_volume *volume = vnode->volume;
-	struct afs_server *server = fc->server;
-	unsigned loop;
-
-	_enter("%s,%pIS,%d",
-	       volume->vlocation->vldb.name, &fc->ac.addr->transport,
-	       fc->ac.error);
-
-	switch (fc->ac.error) {
-		/* success */
-	case 0:
-		server->fs_state = 0;
-		_leave(" = f");
-		return false;
-
-		/* the fileserver denied all knowledge of the volume */
-	case -ENOMEDIUM:
-		down_write(&volume->server_sem);
-
-		/* firstly, find where the server is in the active list (if it
-		 * is) */
-		for (loop = 0; loop < volume->nservers; loop++)
-			if (volume->servers[loop] == server)
-				goto present;
-
-		/* no longer there - may have been discarded by another op */
-		goto try_next_server_upw;
-
-	present:
-		volume->nservers--;
-		memmove(&volume->servers[loop],
-			&volume->servers[loop + 1],
-			sizeof(volume->servers[loop]) *
-			(volume->nservers - loop));
-		volume->servers[volume->nservers] = NULL;
-		afs_put_server(afs_v2net(vnode), server);
-		volume->rjservers++;
-
-		if (volume->nservers > 0)
-			/* another server might acknowledge its existence */
-			goto try_next_server_upw;
-
-		/* handle the case where all the fileservers have rejected the
-		 * volume
-		 * - TODO: try asking the fileservers for volume information
-		 * - TODO: contact the VL server again to see if the volume is
-		 *         no longer registered
-		 */
-		up_write(&volume->server_sem);
-		afs_put_server(afs_v2net(vnode), server);
-		fc->server = NULL;
-		_leave(" = f [completely rejected]");
-		return false;
-
-		/* problem reaching the server */
-	case -ENETUNREACH:
-	case -EHOSTUNREACH:
-	case -ECONNREFUSED:
-	case -ETIME:
-	case -ETIMEDOUT:
-	case -EREMOTEIO:
-		/* mark the server as dead
-		 * TODO: vary dead timeout depending on error
-		 */
-		spin_lock(&server->fs_lock);
-		if (!server->fs_state) {
-			server->fs_state = fc->ac.error;
-			printk("kAFS: SERVER DEAD state=%d\n", fc->ac.error);
-		}
-		spin_unlock(&server->fs_lock);
-		goto try_next_server;
-
-		/* miscellaneous error */
-	default:
-	case -ENOMEM:
-	case -ENONET:
-		/* tell the caller to accept the result */
-		afs_put_server(afs_v2net(vnode), server);
-		fc->server = NULL;
-		_leave(" = f [local failure]");
-		return false;
-	}
-
-	/* tell the caller to loop around and try the next server */
-try_next_server_upw:
-	up_write(&volume->server_sem);
-try_next_server:
-	afs_put_server(afs_v2net(vnode), server);
-	_leave(" = t [try next server]");
-	return true;
-}
-
-/*
- * Clean up a fileserver cursor.
- */
-int afs_end_fs_cursor(struct afs_fs_cursor *fc, struct afs_net *net)
-{
-	afs_end_cursor(&fc->ac);
-	afs_put_server(net, fc->server);
-	return fc->ac.error;
-}
-
-#endif

fs/afs/server_list.c

@@ -58,7 +58,8 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
 		server = afs_lookup_server(cell, key, &vldb->fs_server[i]);
 		if (IS_ERR(server)) {
 			ret = PTR_ERR(server);
-			if (ret == -ENOENT)
+			if (ret == -ENOENT ||
+			    ret == -ENOMEDIUM)
 				continue;
 			goto error_2;
 		}

fs/afs/super.c

@@ -64,6 +64,7 @@ static atomic_t afs_count_active_inodes;
 enum {
 	afs_no_opt,
 	afs_opt_cell,
+	afs_opt_dyn,
 	afs_opt_rwpath,
 	afs_opt_vol,
 	afs_opt_autocell,
@@ -71,6 +72,7 @@ enum {
 
 static const match_table_t afs_options_list = {
 	{ afs_opt_cell,		"cell=%s"	},
+	{ afs_opt_dyn,		"dyn"		},
 	{ afs_opt_rwpath,	"rwpath"	},
 	{ afs_opt_vol,		"vol=%s"	},
 	{ afs_opt_autocell,	"autocell"	},
@@ -148,6 +150,11 @@ static int afs_show_devname(struct seq_file *m, struct dentry *root)
 	const char *suf = "";
 	char pref = '%';
 
+	if (as->dyn_root) {
+		seq_puts(m, "none");
+		return 0;
+	}
+	
 	switch (volume->type) {
 	case AFSVL_RWVOL:
 		break;
@@ -171,8 +178,12 @@ static int afs_show_devname(struct seq_file *m, struct dentry *root)
  */
 static int afs_show_options(struct seq_file *m, struct dentry *root)
 {
+	struct afs_super_info *as = AFS_FS_S(root->d_sb);
+
+	if (as->dyn_root)
+		seq_puts(m, ",dyn");
 	if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags))
-		seq_puts(m, "autocell");
+		seq_puts(m, ",autocell");
 	return 0;
 }
 
@@ -212,7 +223,7 @@ static int afs_parse_options(struct afs_mount_params *params,
 			break;
 
 		case afs_opt_rwpath:
-			params->rwpath = 1;
+			params->rwpath = true;
 			break;
 
 		case afs_opt_vol:
@@ -220,7 +231,11 @@ static int afs_parse_options(struct afs_mount_params *params,
 			break;
 
 		case afs_opt_autocell:
-			params->autocell = 1;
+			params->autocell = true;
+			break;
+
+		case afs_opt_dyn:
+			params->dyn_root = true;
 			break;
 
 		default:
@@ -254,7 +269,7 @@ static int afs_parse_device_name(struct afs_mount_params *params,
 	int cellnamesz;
 
 	_enter(",%s", name);
-
+	
 	if (!name) {
 		printk(KERN_ERR "kAFS: no volume name specified\n");
 		return -EINVAL;
@@ -336,7 +351,14 @@ static int afs_test_super(struct super_block *sb, void *data)
 	struct afs_super_info *as1 = data;
 	struct afs_super_info *as = AFS_FS_S(sb);
 
-	return as->net == as1->net && as->volume->vid == as1->volume->vid;
+	return (as->net == as1->net &&
+		as->volume &&
+		as->volume->vid == as1->volume->vid);
+}
+
+static int afs_dynroot_test_super(struct super_block *sb, void *data)
+{
+	return false;
 }
 
 static int afs_set_super(struct super_block *sb, void *data)
@@ -365,24 +387,30 @@ static int afs_fill_super(struct super_block *sb,
 	sb->s_blocksize_bits	= PAGE_SHIFT;
 	sb->s_magic		= AFS_FS_MAGIC;
 	sb->s_op		= &afs_super_ops;
-	sb->s_xattr		= afs_xattr_handlers;
+	if (!as->dyn_root)
+		sb->s_xattr	= afs_xattr_handlers;
 	ret = super_setup_bdi(sb);
 	if (ret)
 		return ret;
 	sb->s_bdi->ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
-	sprintf(sb->s_id, "%u", as->volume->vid);
-
-	afs_activate_volume(as->volume);
 
 	/* allocate the root inode and dentry */
-	fid.vid		= as->volume->vid;
-	fid.vnode	= 1;
-	fid.unique	= 1;
-	inode = afs_iget(sb, params->key, &fid, NULL, NULL, NULL);
+	if (as->dyn_root) {
+		inode = afs_iget_pseudo_dir(sb, true);
+		sb->s_flags	|= SB_RDONLY;
+	} else {
+		sprintf(sb->s_id, "%u", as->volume->vid);
+		afs_activate_volume(as->volume);
+		fid.vid		= as->volume->vid;
+		fid.vnode	= 1;
+		fid.unique	= 1;
+		inode = afs_iget(sb, params->key, &fid, NULL, NULL, NULL);
+	}
+
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
-	if (params->autocell)
+	if (params->autocell || params->dyn_root)
 		set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags);
 
 	ret = -ENOMEM;
@@ -407,7 +435,10 @@ static struct afs_super_info *afs_alloc_sbi(struct afs_mount_params *params)
 	as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL);
 	if (as) {
 		as->net = afs_get_net(params->net);
-		as->cell = afs_get_cell(params->cell);
+		if (params->dyn_root)
+			as->dyn_root = true;
+		else
+			as->cell = afs_get_cell(params->cell);
 	}
 	return as;
 }
@@ -451,18 +482,20 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
 			goto error;
 	}
 
-	ret = afs_parse_device_name(&params, dev_name);
-	if (ret < 0)
-		goto error;
+	if (!params.dyn_root) {
+		ret = afs_parse_device_name(&params, dev_name);
+		if (ret < 0)
+			goto error;
 
-	/* try and do the mount securely */
-	key = afs_request_key(params.cell);
-	if (IS_ERR(key)) {
-		_leave(" = %ld [key]", PTR_ERR(key));
-		ret = PTR_ERR(key);
-		goto error;
+		/* try and do the mount securely */
+		key = afs_request_key(params.cell);
+		if (IS_ERR(key)) {
+			_leave(" = %ld [key]", PTR_ERR(key));
+			ret = PTR_ERR(key);
+			goto error;
+		}
+		params.key = key;
 	}
-	params.key = key;
 
 	/* allocate a superblock info record */
 	ret = -ENOMEM;
@@ -470,20 +503,25 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
 	if (!as)
 		goto error_key;
 
-	/* Assume we're going to need a volume record; at the very least we can
-	 * use it to update the volume record if we have one already.  This
-	 * checks that the volume exists within the cell.
-	 */
-	candidate = afs_create_volume(&params);
-	if (IS_ERR(candidate)) {
-		ret = PTR_ERR(candidate);
-		goto error_as;
-	}
+	if (!params.dyn_root) {
+		/* Assume we're going to need a volume record; at the very
+		 * least we can use it to update the volume record if we have
+		 * one already.  This checks that the volume exists within the
+		 * cell.
+		 */
+		candidate = afs_create_volume(&params);
+		if (IS_ERR(candidate)) {
+			ret = PTR_ERR(candidate);
+			goto error_as;
+		}
 
-	as->volume = candidate;
+		as->volume = candidate;
+	}
 
 	/* allocate a deviceless superblock */
-	sb = sget(fs_type, afs_test_super, afs_set_super, flags, as);
+	sb = sget(fs_type,
+		  as->dyn_root ? afs_dynroot_test_super : afs_test_super,
+		  afs_set_super, flags, as);
 	if (IS_ERR(sb)) {
 		ret = PTR_ERR(sb);
 		goto error_as;
@@ -529,9 +567,11 @@ static void afs_kill_super(struct super_block *sb)
 	/* Clear the callback interests (which will do ilookup5) before
 	 * deactivating the superblock.
 	 */
-	afs_clear_callback_interests(as->net, as->volume->servers);
+	if (as->volume)
+		afs_clear_callback_interests(as->net, as->volume->servers);
 	kill_anon_super(sb);
-	afs_deactivate_volume(as->volume);
+	if (as->volume)
+		afs_deactivate_volume(as->volume);
 	afs_destroy_sbi(as);
 }
 
@@ -619,12 +659,24 @@ static void afs_destroy_inode(struct inode *inode)
  */
 static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
+	struct afs_super_info *as = AFS_FS_S(dentry->d_sb);
 	struct afs_fs_cursor fc;
 	struct afs_volume_status vs;
 	struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
 	struct key *key;
 	int ret;
 
+	buf->f_type	= dentry->d_sb->s_magic;
+	buf->f_bsize	= AFS_BLOCK_SIZE;
+	buf->f_namelen	= AFSNAMEMAX - 1;
+
+	if (as->dyn_root) {
+		buf->f_blocks	= 1;
+		buf->f_bavail	= 0;
+		buf->f_bfree	= 0;
+		return 0;
+	}
+	
 	key = afs_request_key(vnode->volume->cell);
 	if (IS_ERR(key))
 		return PTR_ERR(key);
@@ -645,10 +697,6 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	key_put(key);
 
 	if (ret == 0) {
-		buf->f_type	= dentry->d_sb->s_magic;
-		buf->f_bsize	= AFS_BLOCK_SIZE;
-		buf->f_namelen	= AFSNAMEMAX - 1;
-
 		if (vs.max_quota == 0)
 			buf->f_blocks = vs.part_max_blocks;
 		else

fs/afs/vlclient.c

@@ -23,7 +23,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 	struct afs_uvldbentry__xdr *uvldb;
 	struct afs_vldb_entry *entry;
 	bool new_only = false;
-	u32 tmp;
+	u32 tmp, nr_servers;
 	int i, ret;
 
 	_enter("");
@@ -36,6 +36,10 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 	uvldb = call->buffer;
 	entry = call->reply[0];
 
+	nr_servers = ntohl(uvldb->nServers);
+	if (nr_servers > AFS_NMAXNSERVERS)
+		nr_servers = AFS_NMAXNSERVERS;
+
 	for (i = 0; i < ARRAY_SIZE(uvldb->name) - 1; i++)
 		entry->name[i] = (u8)ntohl(uvldb->name[i]);
 	entry->name[i] = 0;
@@ -44,14 +48,14 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 	/* If there is a new replication site that we can use, ignore all the
 	 * sites that aren't marked as new.
 	 */
-	for (i = 0; i < AFS_NMAXNSERVERS; i++) {
+	for (i = 0; i < nr_servers; i++) {
 		tmp = ntohl(uvldb->serverFlags[i]);
 		if (!(tmp & AFS_VLSF_DONTUSE) &&
 		    (tmp & AFS_VLSF_NEWREPSITE))
 			new_only = true;
 	}
 
-	for (i = 0; i < AFS_NMAXNSERVERS; i++) {
+	for (i = 0; i < nr_servers; i++) {
 		struct afs_uuid__xdr *xdr;
 		struct afs_uuid *uuid;
 		int j;

fs/afs/volume.c

@@ -26,9 +26,8 @@ static struct afs_volume *afs_alloc_volume(struct afs_mount_params *params,
 					   unsigned long type_mask)
 {
 	struct afs_server_list *slist;
-	struct afs_server *server;
 	struct afs_volume *volume;
-	int ret = -ENOMEM, nr_servers = 0, i, j;
+	int ret = -ENOMEM, nr_servers = 0, i;
 
 	for (i = 0; i < vldb->nr_servers; i++)
 		if (vldb->fs_mask[i] & type_mask)
@@ -58,50 +57,10 @@ static struct afs_volume *afs_alloc_volume(struct afs_mount_params *params,
 
 	refcount_set(&slist->usage, 1);
 	volume->servers = slist;
-
-	/* Make sure a records exists for each server this volume occupies. */
-	for (i = 0; i < nr_servers; i++) {
-		if (!(vldb->fs_mask[i] & type_mask))
-			continue;
-
-		server = afs_lookup_server(params->cell, params->key,
-					   &vldb->fs_server[i]);
-		if (IS_ERR(server)) {
-			ret = PTR_ERR(server);
-			if (ret == -ENOENT)
-				continue;
-			goto error_2;
-		}
-
-		/* Insertion-sort by server pointer */
-		for (j = 0; j < slist->nr_servers; j++)
-			if (slist->servers[j].server >= server)
-				break;
-		if (j < slist->nr_servers) {
-			if (slist->servers[j].server == server) {
-				afs_put_server(params->net, server);
-				continue;
-			}
-
-			memmove(slist->servers + j + 1,
-				slist->servers + j,
-				(slist->nr_servers - j) * sizeof(struct afs_server_entry));
-		}
-
-		slist->servers[j].server = server;
-		slist->nr_servers++;
-	}
-
-	if (slist->nr_servers == 0) {
-		ret = -EDESTADDRREQ;
-		goto error_2;
-	}
-
 	return volume;
 
-error_2:
-	afs_put_serverlist(params->net, slist);
 error_1:
+	afs_put_cell(params->net, volume->cell);
 	kfree(volume);
 error_0:
 	return ERR_PTR(ret);
@@ -327,7 +286,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
 
 	/* See if the volume's server list got updated. */
 	new = afs_alloc_server_list(volume->cell, key,
-				      vldb, (1 << volume->type));
+				    vldb, (1 << volume->type));
 	if (IS_ERR(new)) {
 		ret = PTR_ERR(new);
 		goto error_vldb;

net/dns_resolver/dns_query.c

@@ -52,11 +52,11 @@
  * @name: Name to look up
  * @namelen: Length of name
  * @options: Request options (or NULL if no options)
- * @_result: Where to place the returned data.
+ * @_result: Where to place the returned data (or NULL)
  * @_expiry: Where to store the result expiry time (or NULL)
  *
- * The data will be returned in the pointer at *result, and the caller is
- * responsible for freeing it.
+ * The data will be returned in the pointer at *result, if provided, and the
+ * caller is responsible for freeing it.
  *
  * The description should be of the form "[<query_type>:]<domain_name>", and
  * the options need to be appropriate for the query type requested.  If no
@@ -81,7 +81,7 @@ int dns_query(const char *type, const char *name, size_t namelen,
 	kenter("%s,%*.*s,%zu,%s",
 	       type, (int)namelen, (int)namelen, name, namelen, options);
 
-	if (!name || namelen == 0 || !_result)
+	if (!name || namelen == 0)
 		return -EINVAL;
 
 	/* construct the query key description as "[<type>:]<name>" */
@@ -146,13 +146,15 @@ int dns_query(const char *type, const char *name, size_t namelen,
 	upayload = user_key_payload_locked(rkey);
 	len = upayload->datalen;
 
-	ret = -ENOMEM;
-	*_result = kmalloc(len + 1, GFP_KERNEL);
-	if (!*_result)
-		goto put;
+	if (_result) {
+		ret = -ENOMEM;
+		*_result = kmalloc(len + 1, GFP_KERNEL);
+		if (!*_result)
+			goto put;
 
-	memcpy(*_result, upayload->data, len);
-	(*_result)[len] = '\0';
+		memcpy(*_result, upayload->data, len);
+		(*_result)[len] = '\0';
+	}
 
 	if (_expiry)
 		*_expiry = rkey->expiry;