Re: [PATCH 24/38] union-mount: Copy up directory entries on first readdir()

[Ian Kent <raven@themaw.net>]

On Tue, Jun 15, 2010 at 11:39:54AM -0700, Valerie Aurora wrote:
> readdir() in union mounts is implemented by copying up all visible
> directory entries from the lower level directories to the topmost
> directory.  Directory entries that refer to lower level file system
> objects are marked as "fallthru" in the topmost directory.
> 
> Thanks to Felix Fietkau <nbd@openwrt.org> for a bug fix.
> 
> XXX - How to deal with fallthrus in lower layers?
> 
> Signed-off-by: Valerie Aurora <vaurora@redhat.com>
> Signed-off-by: Felix Fietkau <nbd@openwrt.org>
> ---
>  fs/readdir.c |    9 +++
>  fs/union.c   |  157 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  fs/union.h   |    2 +
>  3 files changed, 168 insertions(+), 0 deletions(-)
> 
> diff --git a/fs/readdir.c b/fs/readdir.c
> index 3a48491..dd3eae1 100644
> --- a/fs/readdir.c
> +++ b/fs/readdir.c
> @@ -19,6 +19,8 @@
>  
>  #include <asm/uaccess.h>
>  
> +#include "union.h"
> +
>  int vfs_readdir(struct file *file, filldir_t filler, void *buf)
>  {
>  	struct inode *inode = file->f_path.dentry->d_inode;
> @@ -36,9 +38,16 @@ int vfs_readdir(struct file *file, filldir_t filler, void *buf)
>  
>  	res = -ENOENT;
>  	if (!IS_DEADDIR(inode)) {
> +		if (IS_DIR_UNIONED(file->f_path.dentry) && !IS_OPAQUE(inode)) {
> +			res = union_copyup_dir(&file->f_path);
> +			if (res)
> +				goto out_unlock;
> +		}
> +
>  		res = file->f_op->readdir(file, buf, filler);
>  		file_accessed(file);
>  	}
> +out_unlock:
>  	mutex_unlock(&inode->i_mutex);
>  out:
>  	return res;
> diff --git a/fs/union.c b/fs/union.c
> index c089c02..76a6c34 100644
> --- a/fs/union.c
> +++ b/fs/union.c
> @@ -22,6 +22,8 @@
>  #include <linux/fs_struct.h>
>  #include <linux/slab.h>
>  #include <linux/namei.h>
> +#include <linux/file.h>
> +#include <linux/security.h>
>  
>  #include "union.h"
>  
> @@ -211,3 +213,158 @@ int union_create_topmost_dir(struct path *parent, struct qstr *name,
>  
>  	return res;
>  }
> +
> +/**
> + * union_copyup_dir_one - copy up a single directory entry
> + *
> + * Individual directory entry copyup function for union_copyup_dir.
> + * We get the entries from higher level layers first.
> + */
> +
> +static int union_copyup_dir_one(void *buf, const char *name, int namlen,
> +				loff_t offset, u64 ino, unsigned int d_type)
> +{
> +	struct dentry *topmost_dentry = (struct dentry *) buf;
> +	struct dentry *dentry;
> +	int err = 0;
> +
> +	switch (namlen) {
> +	case 2:
> +		if (name[1] != '.')
> +			break;
> +	case 1:
> +		if (name[0] != '.')
> +			break;
> +		return 0;
> +	}
> +
> +	/* Lookup this entry in the topmost directory */
> +	dentry = lookup_one_len(name, topmost_dentry, namlen);
> +
> +	if (IS_ERR(dentry)) {
> +		printk(KERN_WARNING "%s: error looking up %s\n", __func__,
> +		       dentry->d_name.name);
> +		err = PTR_ERR(dentry);
> +		goto out;
> +	}
> +
> +	/*
> +	 * If the entry already exists, one of the following is true:
> +	 * it was already copied up (due to an earlier lookup), an
> +	 * entry with the same name already exists on the topmost file
> +	 * system, it is a whiteout, or it is a fallthru.  In each
> +	 * case, the top level entry masks any entries from lower file
> +	 * systems, so don't copy up this entry.
> +	 */
> +	if (dentry->d_inode || d_is_whiteout(dentry) || d_is_fallthru(dentry))
> +		goto out_dput;
> +
> +	/*
> +	 * If the entry doesn't exist, create a fallthru entry in the
> +	 * topmost file system.  All possible directory types are
> +	 * used, so each file system must implement its own way of
> +	 * storing a fallthru entry.
> +	 */
> +	err = topmost_dentry->d_inode->i_op->fallthru(topmost_dentry->d_inode,
> +						      dentry);

There's a bit of indirection going on here so it isn't clear to me if
it is possible for i_op->fallthru() to ever be NULL?

> +out_dput:
> +	dput(dentry);
> +out:
> +	return err;
> +}
> +
> +/**
> + * union_copyup_dir - copy up low-level directory entries to topmost dir
> + *
> + * readdir() is difficult to support on union file systems for two
> + * reasons: We must eliminate duplicates and apply whiteouts, and we
> + * must return something in f_pos that lets us restart in the same
> + * place when we return.  Our solution is to, on first readdir() of
> + * the directory, copy up all visible entries from the low-level file
> + * systems and mark the entries that refer to low-level file system
> + * objects as "fallthru" entries.
> + *
> + * Locking strategy: We hold the topmost dir's i_mutex on entry.  We
> + * grab the i_mutex on lower directories one by one.  So the locking
> + * order is:
> + *
> + * Writable/topmost layers > Read-only/lower layers
> + *
> + * So there is no problem with lock ordering for union stacks with
> + * multiple lower layers.  E.g.:
> + *
> + * (topmost) A->B->C (bottom)
> + * (topmost) D->C->B (bottom)
> + *
> + * (Not that we support more than two layers at the moment.)
> + */
> +
> +int union_copyup_dir(struct path *topmost_path)
> +{
> +	struct dentry *topmost_dentry = topmost_path->dentry;
> +	struct union_dir *ud;
> +	int res = 0;
> +
> +	BUG_ON(IS_OPAQUE(topmost_dentry->d_inode));
> +
> +	res = mnt_want_write(topmost_path->mnt);
> +	if (res)
> +		return res;
> +	/*
> +	 * Mark this dir opaque to show that we have already copied up
> +	 * the lower entries.  Only fallthru entries pass through to
> +	 * the underlying file system.
> +	 */
> +	topmost_dentry->d_inode->i_flags |= S_OPAQUE;
> +	mark_inode_dirty(topmost_dentry->d_inode);
> +
> +	for (ud = topmost_path->dentry->d_union_dir; ud != NULL; ud = ud->u_lower) {
> +		struct file * ftmp;
> +		struct inode * inode;
> +		struct path path;
> +
> +		BUG_ON(ud->u_this.dentry->d_count.counter == 0);
> +		path = ud->u_this;
> +		/* dentry_open() doesn't get a path reference itself */
> +		path_get(&path);
> +		ftmp = dentry_open(path.dentry, path.mnt,
> +				   O_RDONLY | O_DIRECTORY | O_NOATIME,
> +				   current_cred());
> +		if (IS_ERR(ftmp)) {
> +			printk (KERN_ERR "unable to open dir %s for "
> +				"directory copyup: %ld\n",
> +				path.dentry->d_name.name, PTR_ERR(ftmp));
> +			path_put(&path);
> +			continue;
> +		}
> +
> +		inode = path.dentry->d_inode;
> +		mutex_lock(&inode->i_mutex);
> +
> +		res = -ENOENT;
> +		if (IS_DEADDIR(inode))
> +			goto out_fput;
> +		/*
> +		 * Read the whole directory, calling our directory
> +		 * entry copyup function on each entry.  Pass in the
> +		 * topmost dentry as our private data so we can create
> +		 * new entries in the topmost directory.
> +		 */
> +		res = ftmp->f_op->readdir(ftmp, topmost_dentry,
> +					  union_copyup_dir_one);
> +out_fput:
> +		mutex_unlock(&inode->i_mutex);
> +		fput(ftmp);
> +
> +		if (res)
> +			break;
> +
> +		/* XXX Should process directories below an opaque
> +		 * directory in case there are fallthrus in it */
> +		if (IS_OPAQUE(path.dentry->d_inode))
> +			break;
> +
> +	}
> +	mnt_drop_write(topmost_path->mnt);
> +	return res;
> +}
> diff --git a/fs/union.h b/fs/union.h
> index 505f132..80c2421 100644
> --- a/fs/union.h
> +++ b/fs/union.h
> @@ -58,6 +58,7 @@ extern void d_free_unions(struct dentry *);
>  int needs_lookup_union(struct path *, struct path *);
>  int union_create_topmost_dir(struct path *, struct qstr *, struct path *,
>  			     struct path *);
> +extern int union_copyup_dir(struct path *);
>  
>  #else /* CONFIG_UNION_MOUNT */
>  
> @@ -67,6 +68,7 @@ int union_create_topmost_dir(struct path *, struct qstr *, struct path *,
>  #define d_free_unions(x)		do { } while (0)
>  #define needs_lookup_union(x, y)	({ (0); })
>  #define union_create_topmost_dir(w, x, y, z)	({ BUG(); (NULL); })
> +#define union_copyup_dir(x)		({ BUG(); (0); })
>  
>  #endif	/* CONFIG_UNION_MOUNT */
>  #endif	/* __KERNEL__ */
> -- 
> 1.6.3.3
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/