[RFC Aufs2 #2 05/28] aufs branch directory/filesystem

[J. R. Okajima]

initial commit
branch management

Signed-off-by: J. R. Okajima <hooanon05@xxxxxxxxxxx>
---
 fs/aufs/branch.c |  944 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/aufs/branch.h |  200 ++++++++++++
 2 files changed, 1144 insertions(+), 0 deletions(-)
 create mode 100644 fs/aufs/branch.c
 create mode 100644 fs/aufs/branch.h

diff --git a/fs/aufs/branch.c b/fs/aufs/branch.c
new file mode 100644
index 0000000..232f5b3
--- /dev/null
+++ b/fs/aufs/branch.c
@@ -0,0 +1,944 @@
+/*
+ * Copyright (C) 2005-2009 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+/*
+ * branch management
+ */
+
+#include "aufs.h"
+
+/*
+ * free a single branch
+ */
+static void au_br_do_free(struct au_branch *br)
+{
+	int i;
+	struct au_wbr *wbr;
+
+	if (br->br_xino.xi_file)
+		fput(br->br_xino.xi_file);
+	mutex_destroy(&br->br_xino.xi_nondir_mtx);
+
+	AuDebugOn(atomic_read(&br->br_count));
+
+	wbr = br->br_wbr;
+	if (wbr) {
+		for (i = 0; i < AuBrWh_Last; i++)
+			dput(wbr->wbr_wh[i]);
+		AuDebugOn(atomic_read(&wbr->wbr_wh_running));
+		au_rwsem_destroy(&wbr->wbr_wh_rwsem);
+	}
+
+	/* some filesystems acquire extra lock */
+	lockdep_off();
+	mntput(br->br_mnt);
+	lockdep_on();
+
+	kfree(wbr);
+	kfree(br);
+}
+
+/*
+ * frees all branches
+ */
+void au_br_free(struct au_sbinfo *sbinfo)
+{
+	aufs_bindex_t bmax;
+	struct au_branch **br;
+
+	bmax = sbinfo->si_bend + 1;
+	br = sbinfo->si_branch;
+	while (bmax--)
+		au_br_do_free(*br++);
+}
+
+/*
+ * find the index of a branch which is specified by @br_id.
+ */
+int au_br_index(struct super_block *sb, aufs_bindex_t br_id)
+{
+	aufs_bindex_t bindex, bend;
+
+	bend = au_sbend(sb);
+	for (bindex = 0; bindex <= bend; bindex++)
+		if (au_sbr_id(sb, bindex) == br_id)
+			return bindex;
+	return -1;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * add a branch
+ */
+
+static int test_overlap(struct super_block *sb, struct dentry *h_d1,
+			struct dentry *h_d2)
+{
+	if (unlikely(h_d1 == h_d2))
+		return 1;
+	return !!au_test_subdir(h_d1, h_d2)
+		|| !!au_test_subdir(h_d2, h_d1)
+		|| au_test_loopback_overlap(sb, h_d1, h_d2)
+		|| au_test_loopback_overlap(sb, h_d2, h_d1);
+}
+
+/*
+ * returns a newly allocated branch. @new_nbranch is a number of branches
+ * after adding a branch.
+ */
+static struct au_branch *au_br_alloc(struct super_block *sb, int new_nbranch,
+				     int perm)
+{
+	struct au_branch *add_branch;
+	struct dentry *root;
+
+	root = sb->s_root;
+	add_branch = kmalloc(sizeof(*add_branch), GFP_NOFS);
+	if (unlikely(!add_branch))
+		goto out;
+
+	add_branch->br_wbr = NULL;
+	if (au_br_writable(perm)) {
+		/* may be freed separately at changing the branch permission */
+		add_branch->br_wbr = kmalloc(sizeof(*add_branch->br_wbr),
+					     GFP_NOFS);
+		if (unlikely(!add_branch->br_wbr))
+			goto out_br;
+	}
+
+	if (unlikely(au_sbr_realloc(au_sbi(sb), new_nbranch)
+		     || au_di_realloc(au_di(root), new_nbranch)
+		     || au_ii_realloc(au_ii(root->d_inode), new_nbranch)))
+		goto out_wbr;
+	return add_branch; /* success */
+
+ out_wbr:
+	kfree(add_branch->br_wbr);
+ out_br:
+	kfree(add_branch);
+ out:
+	return ERR_PTR(-ENOMEM);
+}
+
+/*
+ * test if the branch permission is legal or not.
+ */
+static int test_br(struct inode *inode, int brperm, char *path)
+{
+	int err;
+
+	err = 0;
+	if (unlikely(au_br_writable(brperm) && IS_RDONLY(inode))) {
+		AuErr("write permission for readonly mount or inode, %s\n",
+		      path);
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+/*
+ * returns:
+ * 0: success, the caller will add it
+ * plus: success, it is already unified, the caller should ignore it
+ * minus: error
+ */
+static int test_add(struct super_block *sb, struct au_opt_add *add, int remount)
+{
+	int err;
+	aufs_bindex_t bend, bindex;
+	struct dentry *root;
+	struct inode *inode, *h_inode;
+
+	root = sb->s_root;
+	bend = au_sbend(sb);
+	if (unlikely(bend >= 0
+		     && au_find_dbindex(root, add->path.dentry) >= 0)) {
+		err = 1;
+		if (!remount) {
+			err = -EINVAL;
+			AuErr("%s duplicated\n", add->pathname);
+		}
+		goto out;
+	}
+
+	err = -ENOSPC; /* -E2BIG; */
+	if (unlikely(AUFS_BRANCH_MAX <= add->bindex
+		     || AUFS_BRANCH_MAX - 1 <= bend)) {
+		AuErr("number of branches exceeded %s\n", add->pathname);
+		goto out;
+	}
+
+	err = -EDOM;
+	if (unlikely(add->bindex < 0 || bend + 1 < add->bindex)) {
+		AuErr("bad index %d\n", add->bindex);
+		goto out;
+	}
+
+	inode = add->path.dentry->d_inode;
+	err = -ENOENT;
+	if (unlikely(!inode->i_nlink)) {
+		AuErr("no existence %s\n", add->pathname);
+		goto out;
+	}
+
+	err = -EINVAL;
+	if (unlikely(inode->i_sb == sb)) {
+		AuErr("%s must be outside\n", add->pathname);
+		goto out;
+	}
+
+	if (unlikely(au_test_fs_unsuppoted(inode->i_sb))) {
+		AuErr("unsupported filesystem, %s (%s)\n",
+		      add->pathname, au_sbtype(inode->i_sb));
+		goto out;
+	}
+
+	err = test_br(add->path.dentry->d_inode, add->perm, add->pathname);
+	if (unlikely(err))
+		goto out;
+
+	if (bend < 0)
+		return 0; /* success */
+
+	err = -EINVAL;
+	for (bindex = 0; bindex <= bend; bindex++)
+		if (unlikely(test_overlap(sb, add->path.dentry,
+					  au_h_dptr(root, bindex)))) {
+			AuErr("%s is overlapped\n", add->pathname);
+			goto out;
+		}
+
+	err = 0;
+	if (au_opt_test(au_mntflags(sb), WARN_PERM)) {
+		h_inode = au_h_dptr(root, 0)->d_inode;
+		if ((h_inode->i_mode & S_IALLUGO) != (inode->i_mode & S_IALLUGO)
+		    || h_inode->i_uid != inode->i_uid
+		    || h_inode->i_gid != inode->i_gid)
+			AuWarn("uid/gid/perm %s %u/%u/0%o, %u/%u/0%o\n",
+			       add->pathname,
+			       inode->i_uid, inode->i_gid,
+			       (inode->i_mode & S_IALLUGO),
+			       h_inode->i_uid, h_inode->i_gid,
+			       (h_inode->i_mode & S_IALLUGO));
+	}
+
+ out:
+	return err;
+}
+
+/*
+ * initialize or clean the whiteouts for an adding branch
+ */
+static int au_br_init_wh(struct super_block *sb, struct au_branch *br,
+			 int new_perm, struct dentry *h_root)
+{
+	int err, old_perm;
+	aufs_bindex_t bindex;
+	struct mutex *h_mtx;
+	struct au_wbr *wbr;
+	struct au_hinode *hdir;
+
+	wbr = br->br_wbr;
+	old_perm = br->br_perm;
+	br->br_perm = new_perm;
+	hdir = NULL;
+	h_mtx = NULL;
+	bindex = au_br_index(sb, br->br_id);
+	if (0 <= bindex) {
+		hdir = au_hi(sb->s_root->d_inode, bindex);
+		au_hin_imtx_lock_nested(hdir, AuLsc_I_PARENT);
+	} else {
+		h_mtx = &h_root->d_inode->i_mutex;
+		mutex_lock_nested(h_mtx, AuLsc_I_PARENT);
+	}
+	if (!wbr)
+		err = au_wh_init(h_root, br, sb);
+	else {
+		wbr_wh_write_lock(wbr);
+		err = au_wh_init(h_root, br, sb);
+		wbr_wh_write_unlock(wbr);
+	}
+	if (hdir)
+		au_hin_imtx_unlock(hdir);
+	else
+		mutex_unlock(h_mtx);
+	br->br_perm = old_perm;
+
+	if (!err && wbr && !au_br_writable(new_perm)) {
+		kfree(wbr);
+		br->br_wbr = NULL;
+	}
+
+	return err;
+}
+
+static int au_wbr_init(struct au_branch *br, struct super_block *sb,
+		       int perm, struct path *path)
+{
+	int err;
+	struct au_wbr *wbr;
+
+	wbr = br->br_wbr;
+	init_rwsem(&wbr->wbr_wh_rwsem);
+	memset(wbr->wbr_wh, 0, sizeof(wbr->wbr_wh));
+	atomic_set(&wbr->wbr_wh_running, 0);
+	wbr->wbr_bytes = 0;
+
+	err = au_br_init_wh(sb, br, perm, path->dentry);
+
+	return err;
+}
+
+/* intialize a new branch */
+static int au_br_init(struct au_branch *br, struct super_block *sb,
+		      struct au_opt_add *add)
+{
+	int err;
+
+	err = 0;
+	br->br_xino.xi_file = NULL;
+	mutex_init(&br->br_xino.xi_nondir_mtx);
+	br->br_perm = add->perm;
+	br->br_mnt = add->path.mnt; /* set first, mntget() later */
+	atomic_set(&br->br_count, 0);
+	br->br_xino_upper = AUFS_XINO_TRUNC_INIT;
+	atomic_set(&br->br_xino_running, 0);
+	br->br_id = au_new_br_id(sb);
+
+	if (au_br_writable(add->perm)) {
+		err = au_wbr_init(br, sb, add->perm, &add->path);
+		if (unlikely(err))
+			goto out;
+	}
+
+	if (au_opt_test(au_mntflags(sb), XINO)) {
+		err = au_xino_br(sb, br, add->path.dentry->d_inode->i_ino,
+				 au_sbr(sb, 0)->br_xino.xi_file, /*do_test*/1);
+		if (unlikely(err)) {
+			AuDebugOn(br->br_xino.xi_file);
+			goto out;
+		}
+	}
+
+	sysaufs_br_init(br);
+	mntget(add->path.mnt);
+
+ out:
+	return err;
+}
+
+static void au_br_do_add_brp(struct au_sbinfo *sbinfo, aufs_bindex_t bindex,
+			     struct au_branch *br, aufs_bindex_t bend,
+			     aufs_bindex_t amount)
+{
+	struct au_branch **brp;
+
+	brp = sbinfo->si_branch + bindex;
+	memmove(brp + 1, brp, sizeof(*brp) * amount);
+	*brp = br;
+	sbinfo->si_bend++;
+	if (unlikely(bend < 0))
+		sbinfo->si_bend = 0;
+}
+
+static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex,
+			     aufs_bindex_t bend, aufs_bindex_t amount)
+{
+	struct au_hdentry *hdp;
+
+	hdp = dinfo->di_hdentry + bindex;
+	memmove(hdp + 1, hdp, sizeof(*hdp) * amount);
+	au_h_dentry_init(hdp);
+	dinfo->di_bend++;
+	if (unlikely(bend < 0))
+		dinfo->di_bstart = 0;
+}
+
+static void au_br_do_add_hip(struct au_iinfo *iinfo, aufs_bindex_t bindex,
+			     aufs_bindex_t bend, aufs_bindex_t amount)
+{
+	struct au_hinode *hip;
+
+	hip = iinfo->ii_hinode + bindex;
+	memmove(hip + 1, hip, sizeof(*hip) * amount);
+	hip->hi_inode = NULL;
+	au_hin_init(hip, NULL);
+	iinfo->ii_bend++;
+	if (unlikely(bend < 0))
+		iinfo->ii_bstart = 0;
+}
+
+static void au_br_do_add(struct super_block *sb, struct dentry *h_dentry,
+			 struct au_branch *br, aufs_bindex_t bindex)
+{
+	struct dentry *root;
+	struct inode *root_inode;
+	aufs_bindex_t bend, amount;
+
+	root = sb->s_root;
+	root_inode = root->d_inode;
+	au_plink_block_maintain(sb);
+	bend = au_sbend(sb);
+	amount = bend + 1 - bindex;
+	au_br_do_add_brp(au_sbi(sb), bindex, br, bend, amount);
+	au_br_do_add_hdp(au_di(root), bindex, bend, amount);
+	au_br_do_add_hip(au_ii(root_inode), bindex, bend, amount);
+	au_set_h_dptr(root, bindex, dget(h_dentry));
+	au_set_h_iptr(root_inode, bindex, au_igrab(h_dentry->d_inode),
+		      /*flags*/0);
+}
+
+int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount)
+{
+	int err;
+	unsigned long long maxb;
+	aufs_bindex_t bend, add_bindex;
+	struct dentry *root, *h_dentry;
+	struct inode *root_inode;
+	struct au_branch *add_branch;
+
+	root = sb->s_root;
+	root_inode = root->d_inode;
+	IMustLock(root_inode);
+	err = test_add(sb, add, remount);
+	if (unlikely(err < 0))
+		goto out;
+	if (err) {
+		err = 0;
+		goto out; /* success */
+	}
+
+	bend = au_sbend(sb);
+	add_branch = au_br_alloc(sb, bend + 2, add->perm);
+	err = PTR_ERR(add_branch);
+	if (IS_ERR(add_branch))
+		goto out;
+
+	err = au_br_init(add_branch, sb, add);
+	if (unlikely(err)) {
+		au_br_do_free(add_branch);
+		goto out;
+	}
+
+	add_bindex = add->bindex;
+	h_dentry = add->path.dentry;
+	if (!remount)
+		au_br_do_add(sb, h_dentry, add_branch, add_bindex);
+	else {
+		sysaufs_brs_del(sb, add_bindex);
+		au_br_do_add(sb, h_dentry, add_branch, add_bindex);
+		sysaufs_brs_add(sb, add_bindex);
+	}
+
+	if (!add_bindex)
+		au_cpup_attr_all(root_inode, /*force*/1);
+	else
+		au_add_nlink(root_inode, h_dentry->d_inode);
+	maxb = h_dentry->d_sb->s_maxbytes;
+	if (sb->s_maxbytes < maxb)
+		sb->s_maxbytes = maxb;
+
+	/*
+	 * this test/set prevents aufs from handling unnecesary inotify events
+	 * of xino files, in a case of re-adding a writable branch which was
+	 * once detached from aufs.
+	 */
+	if (au_xino_brid(sb) < 0
+	    && au_br_writable(add_branch->br_perm)
+	    && !au_test_fs_bad_xino(h_dentry->d_sb)
+	    && add_branch->br_xino.xi_file
+	    && add_branch->br_xino.xi_file->f_dentry->d_parent == h_dentry)
+		au_xino_brid_set(sb, add_branch->br_id);
+
+ out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * delete a branch
+ */
+
+/* to show the line number, do not make it inlined function */
+#define AuVerbose(do_info, fmt, args...) do { \
+	if (do_info) \
+		AuInfo(fmt, ##args); \
+} while (0)
+
+/*
+ * test if the branch is deletable or not.
+ */
+static int test_dentry_busy(struct dentry *root, aufs_bindex_t bindex,
+			    unsigned int sigen)
+{
+	int err, i, j, ndentry;
+	aufs_bindex_t bstart, bend;
+	unsigned char verbose;
+	struct au_dcsub_pages dpages;
+	struct au_dpage *dpage;
+	struct dentry *d;
+	struct inode *inode;
+
+	err = au_dpages_init(&dpages, GFP_NOFS);
+	if (unlikely(err))
+		goto out;
+	err = au_dcsub_pages(&dpages, root, NULL, NULL);
+	if (unlikely(err))
+		goto out_dpages;
+
+	verbose = !!au_opt_test(au_mntflags(root->d_sb), VERBOSE);
+	for (i = 0; !err && i < dpages.ndpage; i++) {
+		dpage = dpages.dpages + i;
+		ndentry = dpage->ndentry;
+		for (j = 0; !err && j < ndentry; j++) {
+			d = dpage->dentries[j];
+			AuDebugOn(!atomic_read(&d->d_count));
+			inode = d->d_inode;
+			if (au_digen(d) == sigen && au_iigen(inode) == sigen)
+				di_read_lock_child(d, AuLock_IR);
+			else {
+				di_write_lock_child(d);
+				err = au_reval_dpath(d, sigen);
+				if (!err)
+					di_downgrade_lock(d, AuLock_IR);
+				else {
+					di_write_unlock(d);
+					break;
+				}
+			}
+
+			bstart = au_dbstart(d);
+			bend = au_dbend(d);
+			if (bstart <= bindex
+			    && bindex <= bend
+			    && au_h_dptr(d, bindex)
+			    && (!S_ISDIR(inode->i_mode) || bstart == bend)) {
+				err = -EBUSY;
+				AuVerbose(verbose, "busy %.*s\n", AuDLNPair(d));
+			}
+			di_read_unlock(d, AuLock_IR);
+		}
+	}
+
+ out_dpages:
+	au_dpages_free(&dpages);
+ out:
+	return err;
+}
+
+static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex,
+			   unsigned int sigen)
+{
+	int err;
+	struct inode *i;
+	aufs_bindex_t bstart, bend;
+	unsigned char verbose;
+
+	err = 0;
+	verbose = !!au_opt_test(au_mntflags(sb), VERBOSE);
+	list_for_each_entry(i, &sb->s_inodes, i_sb_list) {
+		AuDebugOn(!atomic_read(&i->i_count));
+		if (!list_empty(&i->i_dentry))
+			continue;
+
+		if (au_iigen(i) == sigen)
+			ii_read_lock_child(i);
+		else {
+			ii_write_lock_child(i);
+			err = au_refresh_hinode_self(i, /*do_attr*/1);
+			if (!err)
+				ii_downgrade_lock(i);
+			else {
+				ii_write_unlock(i);
+				break;
+			}
+		}
+
+		bstart = au_ibstart(i);
+		bend = au_ibend(i);
+		if (bstart <= bindex
+		    && bindex <= bend
+		    && au_h_iptr(i, bindex)
+		    && (!S_ISDIR(i->i_mode) || bstart == bend)) {
+			err = -EBUSY;
+			AuVerbose(verbose, "busy i%lu\n", i->i_ino);
+			ii_read_unlock(i);
+			break;
+		}
+		ii_read_unlock(i);
+	}
+
+	return err;
+}
+
+static int test_children_busy(struct dentry *root, aufs_bindex_t bindex)
+{
+	int err;
+	unsigned int sigen;
+
+	sigen = au_sigen(root->d_sb);
+	DiMustNoWaiters(root);
+	IiMustNoWaiters(root->d_inode);
+	di_write_unlock(root);
+	err = test_dentry_busy(root, bindex, sigen);
+	if (!err)
+		err = test_inode_busy(root->d_sb, bindex, sigen);
+	di_write_lock_child(root); /* aufs_write_lock() calls ..._child() */
+
+	return err;
+}
+
+static void au_br_do_del_brp(struct au_sbinfo *sbinfo,
+			     const aufs_bindex_t bindex,
+			     const aufs_bindex_t bend)
+{
+	struct au_branch **brp, **p;
+
+	brp = sbinfo->si_branch + bindex;
+	if (bindex < bend)
+		memmove(brp, brp + 1, sizeof(*brp) * (bend - bindex));
+	sbinfo->si_branch[0 + bend] = NULL;
+	sbinfo->si_bend--;
+
+	p = krealloc(sbinfo->si_branch, sizeof(*p) * bend, GFP_NOFS);
+	if (p)
+		sbinfo->si_branch = p;
+}
+
+static void au_br_do_del_hdp(struct au_dinfo *dinfo, const aufs_bindex_t bindex,
+			     const aufs_bindex_t bend)
+{
+	struct au_hdentry *hdp, *p;
+
+	hdp = dinfo->di_hdentry + bindex;
+	if (bindex < bend)
+		memmove(hdp, hdp + 1, sizeof(*hdp) * (bend - bindex));
+	dinfo->di_hdentry[0 + bend].hd_dentry = NULL;
+	dinfo->di_bend--;
+
+	p = krealloc(dinfo->di_hdentry, sizeof(*p) * bend, GFP_NOFS);
+	if (p)
+		dinfo->di_hdentry = p;
+}
+
+static void au_br_do_del_hip(struct au_iinfo *iinfo, const aufs_bindex_t bindex,
+			     const aufs_bindex_t bend)
+{
+	struct au_hinode *hip, *p;
+
+	hip = iinfo->ii_hinode + bindex;
+	if (bindex < bend)
+		memmove(hip, hip + 1, sizeof(*hip) * (bend - bindex));
+	iinfo->ii_hinode[0 + bend].hi_inode = NULL;
+	au_hin_init(iinfo->ii_hinode + bend, NULL);
+	iinfo->ii_bend--;
+
+	p = krealloc(iinfo->ii_hinode, sizeof(*p) * bend, GFP_NOFS);
+	if (p)
+		iinfo->ii_hinode = p;
+}
+
+static void au_br_do_del(struct super_block *sb, aufs_bindex_t bindex,
+			 struct au_branch *br)
+{
+	aufs_bindex_t bend;
+	struct au_sbinfo *sbinfo;
+	struct dentry *root;
+	struct inode *inode;
+
+	root = sb->s_root;
+	inode = root->d_inode;
+	au_plink_block_maintain(sb);
+	sbinfo = au_sbi(sb);
+	bend = sbinfo->si_bend;
+
+	dput(au_h_dptr(root, bindex));
+	au_hiput(au_hi(inode, bindex));
+	au_br_do_free(br);
+
+	au_br_do_del_brp(sbinfo, bindex, bend);
+	au_br_do_del_hdp(au_di(root), bindex, bend);
+	au_br_do_del_hip(au_ii(inode), bindex, bend);
+}
+
+int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount)
+{
+	int err, rerr, i;
+	unsigned int mnt_flags;
+	aufs_bindex_t bindex, bend, br_id;
+	unsigned char do_wh, verbose;
+	struct au_branch *br;
+	struct au_wbr *wbr;
+
+	err = 0;
+	bindex = au_find_dbindex(sb->s_root, del->h_path.dentry);
+	if (bindex < 0) {
+		if (remount)
+			goto out; /* success */
+		err = -ENOENT;
+		AuErr("%s no such branch\n", del->pathname);
+		goto out;
+	}
+	AuDbg("bindex b%d\n", bindex);
+
+	err = -EBUSY;
+	mnt_flags = au_mntflags(sb);
+	verbose = !!au_opt_test(mnt_flags, VERBOSE);
+	bend = au_sbend(sb);
+	if (unlikely(!bend)) {
+		AuVerbose(verbose, "no more branches left\n");
+		goto out;
+	}
+	br = au_sbr(sb, bindex);
+	i = atomic_read(&br->br_count);
+	if (unlikely(i)) {
+		AuVerbose(verbose, "%d file(s) opened\n", i);
+		goto out;
+	}
+
+	wbr = br->br_wbr;
+	do_wh = wbr && (wbr->wbr_whbase || wbr->wbr_plink || wbr->wbr_orph);
+	if (do_wh) {
+		for (i = 0; i < AuBrWh_Last; i++) {
+			dput(wbr->wbr_wh[i]);
+			wbr->wbr_wh[i] = NULL;
+		}
+	}
+
+	err = test_children_busy(sb->s_root, bindex);
+	if (unlikely(err)) {
+		if (do_wh)
+			goto out_wh;
+		goto out;
+	}
+
+	err = 0;
+	br_id = br->br_id;
+	if (!remount)
+		au_br_do_del(sb, bindex, br);
+	else {
+		sysaufs_brs_del(sb, bindex);
+		au_br_do_del(sb, bindex, br);
+		sysaufs_brs_add(sb, bindex);
+	}
+
+	if (!bindex)
+		au_cpup_attr_all(sb->s_root->d_inode, /*force*/1);
+	else
+		au_sub_nlink(sb->s_root->d_inode, del->h_path.dentry->d_inode);
+	if (au_opt_test(mnt_flags, PLINK))
+		au_plink_half_refresh(sb, br_id);
+
+	if (sb->s_maxbytes == del->h_path.dentry->d_sb->s_maxbytes) {
+		bend--;
+		sb->s_maxbytes = 0;
+		for (bindex = 0; bindex <= bend; bindex++) {
+			unsigned long long maxb;
+
+			maxb = au_sbr_sb(sb, bindex)->s_maxbytes;
+			if (sb->s_maxbytes < maxb)
+				sb->s_maxbytes = maxb;
+		}
+	}
+
+	if (au_xino_brid(sb) == br->br_id)
+		au_xino_brid_set(sb, -1);
+	goto out; /* success */
+
+ out_wh:
+	/* revert */
+	rerr = au_br_init_wh(sb, br, br->br_perm, del->h_path.dentry);
+	if (rerr)
+		AuWarn("failed re-creating base whiteout, %s. (%d)\n",
+		       del->pathname, rerr);
+ out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * change a branch permission
+ */
+
+static int do_need_sigen_inc(int a, int b)
+{
+	return au_br_whable(a) && !au_br_whable(b);
+}
+
+static int need_sigen_inc(int old, int new)
+{
+	return do_need_sigen_inc(old, new)
+		|| do_need_sigen_inc(new, old);
+}
+
+static int au_br_mod_files_ro(struct super_block *sb, aufs_bindex_t bindex)
+{
+	int err;
+	unsigned long n, ul, bytes, files;
+	aufs_bindex_t bstart;
+	struct file *file, *hf, **a;
+	const int step_bytes = 1024, /* memory allocation unit */
+		step_files = step_bytes / sizeof(*a);
+
+	err = -ENOMEM;
+	n = 0;
+	bytes = step_bytes;
+	files = step_files;
+	a = kmalloc(bytes, GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+
+	/* no need file_list_lock() since sbinfo is locked? defered? */
+	list_for_each_entry(file, &sb->s_files, f_u.fu_list) {
+		if (special_file(file->f_dentry->d_inode->i_mode))
+			continue;
+
+		AuDbg("%.*s\n", AuDLNPair(file->f_dentry));
+		fi_read_lock(file);
+		if (unlikely(au_test_mmapped(file))) {
+			err = -EBUSY;
+			FiMustNoWaiters(file);
+			fi_read_unlock(file);
+			goto out_free;
+		}
+
+		bstart = au_fbstart(file);
+		if (!S_ISREG(file->f_dentry->d_inode->i_mode)
+		    || !(file->f_mode & FMODE_WRITE)
+		    || bstart != bindex) {
+			FiMustNoWaiters(file);
+			fi_read_unlock(file);
+			continue;
+		}
+
+		hf = au_h_fptr(file, bstart);
+		FiMustNoWaiters(file);
+		fi_read_unlock(file);
+
+		if (n < files)
+			a[n++] = hf;
+		else {
+			void *p;
+
+			err = -ENOMEM;
+			bytes += step_bytes;
+			files += step_files;
+			p = krealloc(a, bytes, GFP_NOFS);
+			if (p) {
+				a = p;
+				a[n++] = hf;
+			} else
+				goto out_free;
+		}
+	}
+
+	err = 0;
+	for (ul = 0; ul < n; ul++) {
+		/* todo: already flushed? */
+		hf = a[ul];
+		hf->f_flags = au_file_roflags(hf->f_flags);
+		hf->f_mode &= ~FMODE_WRITE;
+		file_release_write(hf);
+		mnt_drop_write(hf->f_vfsmnt);
+	}
+
+ out_free:
+	kfree(a);
+ out:
+	return err;
+}
+
+int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount,
+	      int *do_update)
+{
+	int err, rerr;
+	aufs_bindex_t bindex;
+	struct dentry *root;
+	struct au_branch *br;
+
+	root = sb->s_root;
+	au_plink_block_maintain(sb);
+	bindex = au_find_dbindex(root, mod->h_root);
+	if (bindex < 0) {
+		if (remount)
+			return 0; /* success */
+		err = -ENOENT;
+		AuErr("%s no such branch\n", mod->path);
+		goto out;
+	}
+	AuDbg("bindex b%d\n", bindex);
+
+	err = test_br(mod->h_root->d_inode, mod->perm, mod->path);
+	if (unlikely(err))
+		goto out;
+
+	br = au_sbr(sb, bindex);
+	if (br->br_perm == mod->perm)
+		return 0; /* success */
+
+	if (au_br_writable(br->br_perm)) {
+		/* remove whiteout base */
+		err = au_br_init_wh(sb, br, mod->perm, mod->h_root);
+		if (unlikely(err))
+			goto out;
+
+		if (!au_br_writable(mod->perm)) {
+			/* rw --> ro, file might be mmapped */
+			DiMustNoWaiters(root);
+			IiMustNoWaiters(root->d_inode);
+			di_write_unlock(root);
+			err = au_br_mod_files_ro(sb, bindex);
+			/* aufs_write_lock() calls ..._child() */
+			di_write_lock_child(root);
+
+			if (unlikely(err)) {
+				rerr = -ENOMEM;
+				br->br_wbr = kmalloc(sizeof(*br->br_wbr),
+						     GFP_NOFS);
+				if (br->br_wbr)
+					rerr = au_br_init_wh
+						(sb, br, br->br_perm,
+						 mod->h_root);
+				if (unlikely(rerr)) {
+					AuIOErr("nested error %d (%d)\n",
+						rerr, err);
+					br->br_perm = mod->perm;
+				}
+			}
+		}
+	} else if (au_br_writable(mod->perm)) {
+		/* ro --> rw */
+		err = -ENOMEM;
+		br->br_wbr = kmalloc(sizeof(*br->br_wbr), GFP_NOFS);
+		if (br->br_wbr) {
+			struct path path = {
+				.mnt	= br->br_mnt,
+				.dentry	= mod->h_root
+			};
+
+			err = au_wbr_init(br, sb, mod->perm, &path);
+			if (unlikely(err)) {
+				kfree(br->br_wbr);
+				br->br_wbr = NULL;
+			}
+		}
+	}
+
+	if (!err) {
+		*do_update |= need_sigen_inc(br->br_perm, mod->perm);
+		br->br_perm = mod->perm;
+	}
+
+ out:
+	return err;
+}
diff --git a/fs/aufs/branch.h b/fs/aufs/branch.h
new file mode 100644
index 0000000..5a7fed4
--- /dev/null
+++ b/fs/aufs/branch.h
@@ -0,0 +1,200 @@
+/*
+ * Copyright (C) 2005-2009 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+/*
+ * branch filesystems and xino for them
+ */
+
+#ifndef __AUFS_BRANCH_H__
+#define __AUFS_BRANCH_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/sysfs.h>
+#include <linux/aufs_type.h>
+#include "rwsem.h"
+#include "super.h"
+
+/* ---------------------------------------------------------------------- */
+
+/* a xino file */
+struct au_xino_file {
+	struct file		*xi_file;
+	struct mutex		xi_nondir_mtx;
+
+	/* todo: make xino files an array to support huge inode number */
+};
+
+/* members for writable branch only */
+enum {AuBrWh_BASE, AuBrWh_PLINK, AuBrWh_ORPH, AuBrWh_Last};
+struct au_wbr {
+	struct rw_semaphore	wbr_wh_rwsem;
+	struct dentry		*wbr_wh[AuBrWh_Last];
+	atomic_t 		wbr_wh_running;
+#define wbr_whbase		wbr_wh[AuBrWh_BASE]	/* whiteout base */
+#define wbr_plink		wbr_wh[AuBrWh_PLINK]	/* pseudo-link dir */
+#define wbr_orph		wbr_wh[AuBrWh_ORPH]	/* dir for orphans */
+
+	/* mfs mode */
+	unsigned long long	wbr_bytes;
+};
+
+/* protected by superblock rwsem */
+struct au_branch {
+	struct au_xino_file	br_xino;
+
+	aufs_bindex_t		br_id;
+
+	int			br_perm;
+	struct vfsmount		*br_mnt;
+	atomic_t		br_count;
+
+	struct au_wbr		*br_wbr;
+
+	/* xino truncation */
+	blkcnt_t		br_xino_upper;	/* watermark in blocks */
+	atomic_t		br_xino_running;
+
+#ifdef CONFIG_SYSFS
+	/* an entry under sysfs per mount-point */
+	char			br_name[8];
+	struct attribute	br_attr;
+#endif
+};
+
+/* ---------------------------------------------------------------------- */
+
+/* branch permission and attribute */
+enum {
+	AuBrPerm_RW,		/* writable, linkable wh */
+	AuBrPerm_RO,		/* readonly, no wh */
+	AuBrPerm_RR,		/* natively readonly, no wh */
+
+	AuBrPerm_RWNoLinkWH,	/* un-linkable whiteouts */
+
+	AuBrPerm_ROWH,		/* whiteout-able */
+	AuBrPerm_RRWH,		/* whiteout-able */
+
+	AuBrPerm_Last
+};
+
+static inline int au_br_writable(int brperm)
+{
+	return brperm == AuBrPerm_RW || brperm == AuBrPerm_RWNoLinkWH;
+}
+
+static inline int au_br_whable(int brperm)
+{
+	return brperm == AuBrPerm_RW
+		|| brperm == AuBrPerm_ROWH
+		|| brperm == AuBrPerm_RRWH;
+}
+
+static inline int au_br_rdonly(struct au_branch *br)
+{
+	return ((br->br_mnt->mnt_sb->s_flags & MS_RDONLY)
+		|| !au_br_writable(br->br_perm))
+		? -EROFS : 0;
+}
+
+static inline int au_br_hinotifyable(int brperm __maybe_unused)
+{
+#ifdef CONFIG_AUFS_HINOTIFY
+	return brperm != AuBrPerm_RR && brperm != AuBrPerm_RRWH;
+#else
+	return 0;
+#endif
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* branch.c */
+struct au_sbinfo;
+void au_br_free(struct au_sbinfo *sinfo);
+int au_br_index(struct super_block *sb, aufs_bindex_t br_id);
+struct au_opt_add;
+int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount);
+struct au_opt_del;
+int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount);
+struct au_opt_mod;
+int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount,
+	      int *do_update);
+
+/* xino.c */
+int au_xib_trunc(struct super_block *sb);
+ssize_t xino_fread(au_readf_t func, struct file *file, void *buf, size_t size,
+		   loff_t *pos);
+ssize_t xino_fwrite(au_writef_t func, struct file *file, void *buf, size_t size,
+		    loff_t *pos);
+struct file *au_xino_create(struct super_block *sb, char *fname, int silent);
+ino_t au_xino_new_ino(struct super_block *sb);
+int au_xino_write0(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+		   ino_t ino);
+int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+		  ino_t ino);
+int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+		 ino_t *ino);
+int au_xino_br(struct super_block *sb, struct au_branch *br, ino_t hino,
+	       struct file *base_file, int do_test);
+int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex);
+
+struct au_opt_xino;
+int au_xino_set(struct super_block *sb, struct au_opt_xino *xino, int remount);
+void au_xino_clr(struct super_block *sb);
+struct file *au_xino_def(struct super_block *sb);
+int au_xino_path(struct seq_file *seq, struct file *file);
+
+/* ---------------------------------------------------------------------- */
+
+/* Superblock to branch */
+static inline
+aufs_bindex_t au_sbr_id(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_sbr(sb, bindex)->br_id;
+}
+
+static inline
+struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_sbr(sb, bindex)->br_mnt;
+}
+
+static inline
+struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_sbr_mnt(sb, bindex)->mnt_sb;
+}
+
+static inline void au_sbr_put(struct super_block *sb, aufs_bindex_t bindex)
+{
+	atomic_dec(&au_sbr(sb, bindex)->br_count);
+}
+
+static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_sbr(sb, bindex)->br_perm;
+}
+
+static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_br_whable(au_sbr_perm(sb, bindex));
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * wbr_wh_read_lock, wbr_wh_write_lock
+ * wbr_wh_read_unlock, wbr_wh_write_unlock, wbr_wh_downgrade_lock
+ */
+AuSimpleRwsemFuncs(wbr_wh, struct au_wbr *wbr, &wbr->wbr_wh_rwsem);
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_BRANCH_H__ */
-- 
1.6.1.284.g5dc13

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/