aufs: directory op

This is very similar to file operations, including re-open after branch
management. The major part of readdir(3) is split into another object
called VDIR (in previous commit).
Signed-off-by: J. R. Okajima <hooanon05g@gmail.com>

fs/aufs/dir.c

@@ -7,6 +7,8 @@
  * directory operations
  */
 
+#include <linux/fs_stack.h>
+#include <linux/iversion.h>
 #include "aufs.h"
 
 void au_add_nlink(struct inode *dir, struct inode *h_dir)
@@ -188,6 +190,325 @@ out:
 
 /* ---------------------------------------------------------------------- */
 
+static int reopen_dir(struct file *file)
+{
+	int err;
+	unsigned int flags;
+	aufs_bindex_t bindex, btail, btop;
+	struct dentry *dentry, *h_dentry;
+	struct file *h_file;
+
+	/* open all lower dirs */
+	dentry = file->f_path.dentry;
+	btop = au_dbtop(dentry);
+	for (bindex = au_fbtop(file); bindex < btop; bindex++)
+		au_set_h_fptr(file, bindex, NULL);
+	au_set_fbtop(file, btop);
+
+	btail = au_dbtaildir(dentry);
+	for (bindex = au_fbbot_dir(file); btail < bindex; bindex--)
+		au_set_h_fptr(file, bindex, NULL);
+	au_set_fbbot_dir(file, btail);
+
+	flags = vfsub_file_flags(file);
+	for (bindex = btop; bindex <= btail; bindex++) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (!h_dentry)
+			continue;
+		h_file = au_hf_dir(file, bindex);
+		if (h_file)
+			continue;
+
+		h_file = au_h_open(dentry, bindex, flags, file);
+		err = PTR_ERR(h_file);
+		if (IS_ERR(h_file))
+			goto out; /* close all? */
+		au_set_h_fptr(file, bindex, h_file);
+	}
+	au_update_figen(file);
+	/* todo: necessary? */
+	/* file->f_ra = h_file->f_ra; */
+	err = 0;
+
+out:
+	return err;
+}
+
+static int do_open_dir(struct file *file, int flags, struct file *h_file)
+{
+	int err;
+	aufs_bindex_t bindex, btail;
+	struct dentry *dentry, *h_dentry;
+	struct vfsmount *mnt;
+
+	FiMustWriteLock(file);
+	AuDebugOn(h_file);
+
+	err = 0;
+	mnt = file->f_path.mnt;
+	dentry = file->f_path.dentry;
+	file->f_version = inode_query_iversion(d_inode(dentry));
+	bindex = au_dbtop(dentry);
+	au_set_fbtop(file, bindex);
+	btail = au_dbtaildir(dentry);
+	au_set_fbbot_dir(file, btail);
+	for (; !err && bindex <= btail; bindex++) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (!h_dentry)
+			continue;
+
+		h_file = au_h_open(dentry, bindex, flags, file);
+		if (IS_ERR(h_file)) {
+			err = PTR_ERR(h_file);
+			break;
+		}
+		au_set_h_fptr(file, bindex, h_file);
+	}
+	au_update_figen(file);
+	/* todo: necessary? */
+	/* file->f_ra = h_file->f_ra; */
+	if (!err)
+		return 0; /* success */
+
+	/* close all */
+	for (bindex = au_fbtop(file); bindex <= btail; bindex++)
+		au_set_h_fptr(file, bindex, NULL);
+	au_set_fbtop(file, -1);
+	au_set_fbbot_dir(file, -1);
+
+	return err;
+}
+
+static int aufs_open_dir(struct inode *inode __maybe_unused,
+			 struct file *file)
+{
+	int err;
+	struct super_block *sb;
+	struct au_fidir *fidir;
+
+	err = -ENOMEM;
+	sb = file->f_path.dentry->d_sb;
+	si_read_lock(sb, AuLock_FLUSH);
+	fidir = au_fidir_alloc(sb);
+	if (fidir) {
+		struct au_do_open_args args = {
+			.open	= do_open_dir,
+			.fidir	= fidir
+		};
+		err = au_do_open(file, &args);
+		if (unlikely(err))
+			au_kfree_rcu(fidir);
+	}
+	si_read_unlock(sb);
+	return err;
+}
+
+static int aufs_release_dir(struct inode *inode __maybe_unused,
+			    struct file *file)
+{
+	struct au_vdir *vdir_cache;
+	struct au_finfo *finfo;
+	struct au_fidir *fidir;
+	struct au_hfile *hf;
+	aufs_bindex_t bindex, bbot;
+
+	finfo = au_fi(file);
+	fidir = finfo->fi_hdir;
+	if (fidir) {
+		vdir_cache = fidir->fd_vdir_cache; /* lock-free */
+		if (vdir_cache)
+			au_vdir_free(vdir_cache);
+
+		bindex = finfo->fi_btop;
+		if (bindex >= 0) {
+			hf = fidir->fd_hfile + bindex;
+			/*
+			 * calls fput() instead of filp_close(),
+			 * since no dnotify or lock for the lower file.
+			 */
+			bbot = fidir->fd_bbot;
+			for (; bindex <= bbot; bindex++, hf++)
+				if (hf->hf_file)
+					au_hfput(hf, /*execed*/0);
+		}
+		au_kfree_rcu(fidir);
+		finfo->fi_hdir = NULL;
+	}
+	au_finfo_fin(file);
+	return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_do_flush_dir(struct file *file, fl_owner_t id)
+{
+	int err;
+	aufs_bindex_t bindex, bbot;
+	struct file *h_file;
+
+	err = 0;
+	bbot = au_fbbot_dir(file);
+	for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) {
+		h_file = au_hf_dir(file, bindex);
+		if (h_file)
+			err = vfsub_flush(h_file, id);
+	}
+	return err;
+}
+
+static int aufs_flush_dir(struct file *file, fl_owner_t id)
+{
+	return au_do_flush(file, id, au_do_flush_dir);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync)
+{
+	int err;
+	aufs_bindex_t bbot, bindex;
+	struct inode *inode;
+	struct super_block *sb;
+
+	err = 0;
+	sb = dentry->d_sb;
+	inode = d_inode(dentry);
+	IMustLock(inode);
+	bbot = au_dbbot(dentry);
+	for (bindex = au_dbtop(dentry); !err && bindex <= bbot; bindex++) {
+		struct path h_path;
+
+		if (au_test_ro(sb, bindex, inode))
+			continue;
+		h_path.dentry = au_h_dptr(dentry, bindex);
+		if (!h_path.dentry)
+			continue;
+
+		h_path.mnt = au_sbr_mnt(sb, bindex);
+		err = vfsub_fsync(NULL, &h_path, datasync);
+	}
+
+	return err;
+}
+
+static int au_do_fsync_dir(struct file *file, int datasync)
+{
+	int err;
+	aufs_bindex_t bbot, bindex;
+	struct file *h_file;
+	struct super_block *sb;
+	struct inode *inode;
+
+	err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0);
+	if (unlikely(err))
+		goto out;
+
+	inode = file_inode(file);
+	sb = inode->i_sb;
+	bbot = au_fbbot_dir(file);
+	for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) {
+		h_file = au_hf_dir(file, bindex);
+		if (!h_file || au_test_ro(sb, bindex, inode))
+			continue;
+
+		err = vfsub_fsync(h_file, &h_file->f_path, datasync);
+	}
+
+out:
+	return err;
+}
+
+/*
+ * @file may be NULL
+ */
+static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end,
+			  int datasync)
+{
+	int err;
+	struct dentry *dentry;
+	struct inode *inode;
+	struct super_block *sb;
+
+	err = 0;
+	dentry = file->f_path.dentry;
+	inode = d_inode(dentry);
+	inode_lock(inode);
+	sb = dentry->d_sb;
+	si_noflush_read_lock(sb);
+	if (file)
+		err = au_do_fsync_dir(file, datasync);
+	else {
+		di_write_lock_child(dentry);
+		err = au_do_fsync_dir_no_file(dentry, datasync);
+	}
+	au_cpup_attr_timesizes(inode);
+	di_write_unlock(dentry);
+	if (file)
+		fi_write_unlock(file);
+
+	si_read_unlock(sb);
+	inode_unlock(inode);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int aufs_iterate_shared(struct file *file, struct dir_context *ctx)
+{
+	int err;
+	struct dentry *dentry;
+	struct inode *inode, *h_inode;
+	struct super_block *sb;
+
+	AuDbg("%pD, ctx{%ps, %llu}\n", file, ctx->actor, ctx->pos);
+
+	dentry = file->f_path.dentry;
+	inode = d_inode(dentry);
+	IMustLock(inode);
+
+	sb = dentry->d_sb;
+	si_read_lock(sb, AuLock_FLUSH);
+	err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0);
+	if (unlikely(err))
+		goto out;
+	err = au_alive_dir(dentry);
+	if (!err)
+		err = au_vdir_init(file);
+	di_downgrade_lock(dentry, AuLock_IR);
+	if (unlikely(err))
+		goto out_unlock;
+
+	h_inode = au_h_iptr(inode, au_ibtop(inode));
+	if (!au_test_nfsd()) {
+		err = au_vdir_fill_de(file, ctx);
+		fsstack_copy_attr_atime(inode, h_inode);
+	} else {
+		/*
+		 * nfsd filldir may call lookup_one_len(), vfs_getattr(),
+		 * encode_fh() and others.
+		 */
+		atomic_inc(&h_inode->i_count);
+		di_read_unlock(dentry, AuLock_IR);
+		si_read_unlock(sb);
+		err = au_vdir_fill_de(file, ctx);
+		fsstack_copy_attr_atime(inode, h_inode);
+		fi_write_unlock(file);
+		iput(h_inode);
+
+		AuTraceErr(err);
+		return err;
+	}
+
+out_unlock:
+	di_read_unlock(dentry, AuLock_IR);
+	fi_write_unlock(file);
+out:
+	si_read_unlock(sb);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
 #define AuTestEmpty_WHONLY	1
 #define AuTestEmpty_CALLED	(1 << 1)
 #define au_ftest_testempty(flags, name)	((flags) & AuTestEmpty_##name)
@@ -392,3 +713,16 @@ int au_test_empty(struct dentry *dentry, struct au_nhash *whlist)
 
 	return err;
 }
+
+/* ---------------------------------------------------------------------- */
+
+const struct file_operations aufs_dir_fop = {
+	.owner		= THIS_MODULE,
+	.llseek		= default_llseek,
+	.read		= generic_read_dir,
+	.iterate_shared	= aufs_iterate_shared,
+	.open		= aufs_open_dir,
+	.release	= aufs_release_dir,
+	.flush		= aufs_flush_dir,
+	.fsync		= aufs_fsync_dir
+};

fs/aufs/dir.h

@@ -70,6 +70,7 @@ struct au_vdir {
 /* ---------------------------------------------------------------------- */
 
 /* dir.c */
+extern const struct file_operations aufs_dir_fop;
 void au_add_nlink(struct inode *dir, struct inode *h_dir);
 void au_sub_nlink(struct inode *dir, struct inode *h_dir);
 loff_t au_dir_size(struct file *file, struct dentry *dentry);

fs/aufs/inode.c

@@ -223,7 +223,7 @@ static int set_inode(struct inode *inode, struct dentry *dentry)
 		isdir = 1;
 		btail = au_dbtaildir(dentry);
 		inode->i_op = iop + AuIop_DIR;
-		inode->i_fop = &simple_dir_operations; /* re-commit later */
+		inode->i_fop = &aufs_dir_fop;
 		break;
 	case S_IFLNK:
 		btail = au_dbtail(dentry);

fs/aufs/super.c

@@ -751,8 +751,8 @@ static int alloc_root(struct super_block *sb)
 	if (IS_ERR(inode))
 		goto out;
 
-	inode->i_op = aufs_iop + AuIop_DIR;
-	inode->i_fop = &simple_dir_operations; /* replace later */
+	inode->i_op = aufs_iop + AuIop_DIR; /* with getattr by default */
+	inode->i_fop = &aufs_dir_fop;
 	inode->i_mode = S_IFDIR;
 	set_nlink(inode, 2);
 	unlock_new_inode(inode);