aufs: copy-up 2/7, internal lookup for the target

Basically copy-up is done by these steps using au_pin (in another
commit).
- lock the target parent mutex
- lookup a negative dentry with a whiteout-ed temporary unique name
- create it
- unlock the target parent mutex
- copy filedata
- copy metadata (inode attributes)
- lock the target parent mutex
- rename the temporary name to the target name
- unlock the target parent mutex

This commit contains step2 mainly.
I hope someday aufs uses O_TMPFILE for this.
Signed-off-by: J. R. Okajima <hooanon05g@gmail.com>

fs/aufs/dentry.c

@@ -11,6 +11,241 @@
 #include <linux/namei.h>
 #include "aufs.h"
 
+/*
+ * returns positive/negative dentry, NULL or an error.
+ * NULL means whiteout-ed or not-found.
+ */
+static struct dentry*
+au_do_lookup(struct dentry *h_parent, struct dentry *dentry,
+	     aufs_bindex_t bindex, struct au_do_lookup_args *args)
+{
+	struct dentry *h_dentry;
+	struct inode *h_inode;
+	struct au_branch *br;
+	int wh_found, opq;
+	unsigned char wh_able;
+	const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG);
+	const unsigned char ignore_perm = !!au_ftest_lkup(args->flags,
+							  IGNORE_PERM);
+
+	wh_found = 0;
+	br = au_sbr(dentry->d_sb, bindex);
+	wh_able = !!au_br_whable(br->br_perm);
+	if (wh_able)
+		wh_found = au_wh_test(h_parent, &args->whname, ignore_perm);
+	h_dentry = ERR_PTR(wh_found);
+	if (!wh_found)
+		goto real_lookup;
+	if (unlikely(wh_found < 0))
+		goto out;
+
+	/* We found a whiteout */
+	/* au_set_dbbot(dentry, bindex); */
+	au_set_dbwh(dentry, bindex);
+	if (!allow_neg)
+		return NULL; /* success */
+
+real_lookup:
+	if (!ignore_perm)
+		h_dentry = vfsub_lkup_one(args->name, h_parent);
+	else
+		h_dentry = au_sio_lkup_one(args->name, h_parent);
+	if (IS_ERR(h_dentry)) {
+		if (PTR_ERR(h_dentry) == -ENAMETOOLONG
+		    && !allow_neg)
+			h_dentry = NULL;
+		goto out;
+	}
+
+	h_inode = d_inode(h_dentry);
+	if (d_is_negative(h_dentry)) {
+		if (!allow_neg)
+			goto out_neg;
+	} else if (wh_found
+		   || (args->type && args->type != (h_inode->i_mode & S_IFMT)))
+		goto out_neg;
+
+	if (au_dbbot(dentry) <= bindex)
+		au_set_dbbot(dentry, bindex);
+	if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry))
+		au_set_dbtop(dentry, bindex);
+	au_set_h_dptr(dentry, bindex, h_dentry);
+
+	if (!d_is_dir(h_dentry)
+	    || !wh_able
+	    || (d_really_is_positive(dentry) && !d_is_dir(dentry)))
+		goto out; /* success */
+
+	inode_lock_shared_nested(h_inode, AuLsc_I_CHILD);
+	opq = au_diropq_test(h_dentry);
+	inode_unlock_shared(h_inode);
+	if (opq > 0)
+		au_set_dbdiropq(dentry, bindex);
+	else if (unlikely(opq < 0)) {
+		au_set_h_dptr(dentry, bindex, NULL);
+		h_dentry = ERR_PTR(opq);
+	}
+	goto out;
+
+out_neg:
+	dput(h_dentry);
+	h_dentry = NULL;
+out:
+	return h_dentry;
+}
+
+/*
+ * returns the number of lower positive dentries,
+ * otherwise an error.
+ * can be called at unlinking with @type is zero.
+ */
+int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop,
+		   unsigned int flags)
+{
+	int npositive, err;
+	aufs_bindex_t bindex, btail, bdiropq;
+	unsigned char isdir;
+	struct au_do_lookup_args args = {
+		.flags		= flags,
+		.name		= &dentry->d_name
+	};
+	struct dentry *parent;
+	struct super_block *sb;
+
+	sb = dentry->d_sb;
+	err = au_wh_name_alloc(&args.whname, args.name);
+	if (unlikely(err))
+		goto out;
+
+	isdir = !!d_is_dir(dentry);
+
+	npositive = 0;
+	parent = dget_parent(dentry);
+	btail = au_dbtaildir(parent);
+	for (bindex = btop; bindex <= btail; bindex++) {
+		struct dentry *h_parent, *h_dentry;
+		struct inode *h_inode, *h_dir;
+
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (h_dentry) {
+			if (d_is_positive(h_dentry))
+				npositive++;
+			break;
+		}
+		h_parent = au_h_dptr(parent, bindex);
+		if (!h_parent || !d_is_dir(h_parent))
+			continue;
+
+		h_dir = d_inode(h_parent);
+		inode_lock_shared_nested(h_dir, AuLsc_I_PARENT);
+		h_dentry = au_do_lookup(h_parent, dentry, bindex, &args);
+		inode_unlock_shared(h_dir);
+		err = PTR_ERR(h_dentry);
+		if (IS_ERR(h_dentry))
+			goto out_parent;
+		if (h_dentry)
+			au_fclr_lkup(args.flags, ALLOW_NEG);
+
+		if (au_dbwh(dentry) == bindex)
+			break;
+		if (!h_dentry)
+			continue;
+		if (d_is_negative(h_dentry))
+			continue;
+		h_inode = d_inode(h_dentry);
+		npositive++;
+		if (!args.type)
+			args.type = h_inode->i_mode & S_IFMT;
+		if (args.type != S_IFDIR)
+			break;
+		else if (isdir) {
+			/* the type of lower may be different */
+			bdiropq = au_dbdiropq(dentry);
+			if (bdiropq >= 0 && bdiropq <= bindex)
+				break;
+		}
+	}
+
+	if (npositive) {
+		AuLabel(positive);
+		au_update_dbtop(dentry);
+	}
+	err = npositive;
+	if (unlikely(au_dbtop(dentry) < 0)) {
+		err = -EIO;
+		AuIOErr("both of real entry and whiteout found, %pd, err %d\n",
+			dentry, err);
+	}
+
+out_parent:
+	dput(parent);
+	au_kfree_try_rcu(args.whname.name);
+out:
+	return err;
+}
+
+struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+	int wkq_err;
+
+	if (!au_test_h_perm_sio(d_inode(parent), MAY_EXEC))
+		dentry = vfsub_lkup_one(name, parent);
+	else {
+		struct vfsub_lkup_one_args args = {
+			.errp	= &dentry,
+			.name	= name,
+			.parent	= parent
+		};
+
+		wkq_err = au_wkq_wait(vfsub_call_lkup_one, &args);
+		if (unlikely(wkq_err))
+			dentry = ERR_PTR(wkq_err);
+	}
+
+	return dentry;
+}
+
+/*
+ * lookup @dentry on @bindex which should be negative.
+ */
+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh)
+{
+	int err;
+	struct dentry *parent, *h_parent, *h_dentry;
+	struct au_branch *br;
+
+	parent = dget_parent(dentry);
+	h_parent = au_h_dptr(parent, bindex);
+	br = au_sbr(dentry->d_sb, bindex);
+	if (wh)
+		h_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name);
+	else
+		h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent);
+	err = PTR_ERR(h_dentry);
+	if (IS_ERR(h_dentry))
+		goto out;
+	if (unlikely(d_is_positive(h_dentry))) {
+		err = -EIO;
+		AuIOErr("%pd should be negative on b%d.\n", h_dentry, bindex);
+		dput(h_dentry);
+		goto out;
+	}
+
+	err = 0;
+	if (bindex < au_dbtop(dentry))
+		au_set_dbtop(dentry, bindex);
+	if (au_dbbot(dentry) < bindex)
+		au_set_dbbot(dentry, bindex);
+	au_set_h_dptr(dentry, bindex, h_dentry);
+
+out:
+	dput(parent);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
 /* subset of struct inode */
 struct au_iattr {
 	unsigned long		i_ino;

fs/aufs/dentry.h

@@ -31,11 +31,33 @@ struct au_dinfo {
 
 /* ---------------------------------------------------------------------- */
 
+/* flags for au_lkup_dentry() */
+#define AuLkup_ALLOW_NEG	1
+#define AuLkup_IGNORE_PERM	(1 << 1)
+#define au_ftest_lkup(flags, name)	((flags) & AuLkup_##name)
+#define au_fset_lkup(flags, name) \
+	do { (flags) |= AuLkup_##name; } while (0)
+#define au_fclr_lkup(flags, name) \
+	do { (flags) &= ~AuLkup_##name; } while (0)
+
+struct au_do_lookup_args {
+	unsigned int		flags;
+	mode_t			type;
+	struct qstr		whname, *name;
+};
+
+/* ---------------------------------------------------------------------- */
+
 /* dentry.c */
 struct au_branch;
+struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent);
 int au_h_verify(struct dentry *h_dentry, struct inode *h_dir,
 		struct dentry *h_parent, struct au_branch *br);
 
+int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop,
+		   unsigned int flags);
+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh);
+
 /* dinfo.c */
 void au_di_init_once(void *_di);
 struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc);

fs/aufs/whout.c

@@ -57,14 +57,10 @@ int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, int try_sio)
 	int err;
 	struct dentry *wh_dentry;
 
-#if 0 /* re-commit later */
 	if (!try_sio)
 		wh_dentry = vfsub_lkup_one(wh_name, h_parent);
 	else
 		wh_dentry = au_sio_lkup_one(wh_name, h_parent);
-#else
-	wh_dentry = ERR_PTR(-ENOENT);
-#endif
 	err = PTR_ERR(wh_dentry);
 	if (IS_ERR(wh_dentry)) {
 		if (err == -ENAMETOOLONG)
@@ -104,6 +100,63 @@ int au_diropq_test(struct dentry *h_dentry)
 	return err;
 }
 
+/*
+ * returns a negative dentry whose name is unique and temporary.
+ */
+struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br,
+			     struct qstr *prefix)
+{
+	struct dentry *dentry;
+	int i;
+	char defname[NAME_MAX - AUFS_MAX_NAMELEN + DNAME_INLINE_LEN + 1],
+		*name, *p;
+	/* strict atomic_t is unnecessary here */
+	static unsigned short cnt;
+	struct qstr qs;
+
+	BUILD_BUG_ON(sizeof(cnt) * 2 > AUFS_WH_TMP_LEN);
+
+	name = defname;
+	qs.len = sizeof(defname) - DNAME_INLINE_LEN + prefix->len - 1;
+	if (unlikely(prefix->len > DNAME_INLINE_LEN)) {
+		dentry = ERR_PTR(-ENAMETOOLONG);
+		if (unlikely(qs.len > NAME_MAX))
+			goto out;
+		dentry = ERR_PTR(-ENOMEM);
+		name = kmalloc(qs.len + 1, GFP_NOFS);
+		if (unlikely(!name))
+			goto out;
+	}
+
+	/* doubly whiteout-ed */
+	memcpy(name, AUFS_WH_PFX AUFS_WH_PFX, AUFS_WH_PFX_LEN * 2);
+	p = name + AUFS_WH_PFX_LEN * 2;
+	memcpy(p, prefix->name, prefix->len);
+	p += prefix->len;
+	*p++ = '.';
+	AuDebugOn(name + qs.len + 1 - p <= AUFS_WH_TMP_LEN);
+
+	qs.name = name;
+	for (i = 0; i < 3; i++) {
+		sprintf(p, "%.*x", AUFS_WH_TMP_LEN, cnt++);
+		dentry = au_sio_lkup_one(&qs, h_parent);
+		if (IS_ERR(dentry) || d_is_negative(dentry))
+			goto out_name;
+		dput(dentry);
+	}
+	/* pr_warn("could not get random name\n"); */
+	dentry = ERR_PTR(-EEXIST);
+	AuDbg("%.*s\n", AuLNPair(&qs));
+	BUG();
+
+out_name:
+	if (name != defname)
+		au_kfree_try_rcu(name);
+out:
+	AuTraceErrPtr(dentry);
+	return dentry;
+}
+
 /* ---------------------------------------------------------------------- */
 /*
  * functions for removing a whiteout

fs/aufs/whout.h

@@ -18,11 +18,13 @@ int au_wh_name_alloc(struct qstr *wh, const struct qstr *name);
 struct dentry;
 int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, int try_sio);
 int au_diropq_test(struct dentry *h_dentry);
+struct au_branch;
+struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br,
+			     struct qstr *prefix);
 struct inode;
 struct path;
 int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path,
 			struct dentry *dentry);
-struct au_branch;
 struct super_block;
 int au_wh_init(struct au_branch *br, struct super_block *sb);