diff -Nur linux-2.6.31.5.orig/Documentation/ABI/testing/debugfs-aufs linux-2.6.31.5/Documentation/ABI/testing/debugfs-aufs
--- linux-2.6.31.5.orig/Documentation/ABI/testing/debugfs-aufs 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.31.5/Documentation/ABI/testing/debugfs-aufs 2009-11-15 22:02:37.000000000 +0100
@@ -0,0 +1,40 @@
+What: /debug/aufs/si_<id>/
+Date: March 2009
+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
+Description:
+ Under /debug/aufs, a directory named si_<id> is created
+ per aufs mount, where <id> is a unique id generated
+ internally.
+
+What: /debug/aufs/si_<id>/xib
+Date: March 2009
+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
+Description:
+ It shows the consumed blocks by xib (External Inode Number
+ Bitmap), its block size and file size.
+ When the aufs mount option 'noxino' is specified, it
+ will be empty. About XINO files, see
+ Documentation/filesystems/aufs/aufs.5 in detail.
+
+What: /debug/aufs/si_<id>/xino0, xino1 ... xinoN
+Date: March 2009
+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
+Description:
+ It shows the consumed blocks by xino (External Inode Number
+ Translation Table), its link count, block size and file
+ size.
+ When the aufs mount option 'noxino' is specified, it
+ will be empty. About XINO files, see
+ Documentation/filesystems/aufs/aufs.5 in detail.
+
+What: /debug/aufs/si_<id>/xigen
+Date: March 2009
+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
+Description:
+ It shows the consumed blocks by xigen (External Inode
+ Generation Table), its block size and file size.
+ If CONFIG_AUFS_EXPORT is disabled, this entry will not
+ be created.
+ When the aufs mount option 'noxino' is specified, it
+ will be empty. About XINO files, see
+ Documentation/filesystems/aufs/aufs.5 in detail.
diff -Nur linux-2.6.31.5.orig/Documentation/ABI/testing/sysfs-aufs linux-2.6.31.5/Documentation/ABI/testing/sysfs-aufs
--- linux-2.6.31.5.orig/Documentation/ABI/testing/sysfs-aufs 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.31.5/Documentation/ABI/testing/sysfs-aufs 2009-11-15 22:02:37.000000000 +0100
@@ -0,0 +1,25 @@
+What: /sys/fs/aufs/si_<id>/
+Date: March 2009
+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
+Description:
+ Under /sys/fs/aufs, a directory named si_<id> is created
+ per aufs mount, where <id> is a unique id generated
+ internally.
+
+What: /sys/fs/aufs/si_<id>/br0, br1 ... brN
+Date: March 2009
+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
+Description:
+ It shows the abolute path of a member directory (which
+ is called branch) in aufs, and its permission.
+
+What: /sys/fs/aufs/si_<id>/xi_path
+Date: March 2009
+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
+Description:
+ It shows the abolute path of XINO (External Inode Number
+ Bitmap, Translation Table and Generation Table) file
+ even if it is the default path.
+ When the aufs mount option 'noxino' is specified, it
+ will be empty. About XINO files, see
+ Documentation/filesystems/aufs/aufs.5 in detail.
diff -Nur linux-2.6.31.5.orig/fs/aufs/aufs.h linux-2.6.31.5/fs/aufs/aufs.h
--- linux-2.6.31.5.orig/fs/aufs/aufs.h 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.31.5/fs/aufs/aufs.h 2009-11-15 22:02:37.000000000 +0100
@@ -0,0 +1,51 @@
+/*
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+/*
+ * all header files
+ */
+
+#ifndef __AUFS_H__
+#define __AUFS_H__
+
+#ifdef __KERNEL__
+
+#include "debug.h"
+
+#include "branch.h"
+#include "cpup.h"
+#include "dcsub.h"
+#include "dbgaufs.h"
+#include "dentry.h"
+#include "dir.h"
+#include "file.h"
+#include "fstype.h"
+#include "inode.h"
+#include "loop.h"
+#include "module.h"
+#include "opts.h"
+#include "rwsem.h"
+#include "spl.h"
+#include "super.h"
+#include "sysaufs.h"
+#include "vfsub.h"
+#include "whout.h"
+#include "wkq.h"
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_H__ */
diff -Nur linux-2.6.31.5.orig/fs/aufs/branch.c linux-2.6.31.5/fs/aufs/branch.c
--- linux-2.6.31.5.orig/fs/aufs/branch.c 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.31.5/fs/aufs/branch.c 2009-11-15 22:02:37.000000000 +0100
@@ -0,0 +1,974 @@
+/*
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+/*
+ * branch management
+ */
+
+#include <linux/file.h>
+#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));
+ AuRwDestroy(&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;
+
+ AuRwMustWriteLock(&sbinfo->si_rwsem);
+
+ 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;
+ au_rw_init(&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;
+ memset(&br->br_xino, 0, sizeof(br->br_xino));
+ 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;
+
+ AuRwMustWriteLock(&sbinfo->si_rwsem);
+
+ 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;
+
+ AuRwMustWriteLock(&dinfo->di_rwsem);
+
+ 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;
+
+ AuRwMustWriteLock(&iinfo->ii_rwsem);
+
+ 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;
+
+ AuRwMustWriteLock(&sbinfo->si_rwsem);
+
+ 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;
+
+ AuRwMustWriteLock(&dinfo->di_rwsem);
+
+ 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;
+
+ AuRwMustWriteLock(&iinfo->ii_rwsem);
+
+ 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;
+
+ SiMustWriteLock(sb);
+
+ 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) {
+ /* instead of WbrWhMustWriteLock(wbr) */
+ SiMustWriteLock(sb);
+ 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? */
+ /* cf. fs/super.c:mark_files_ro() */
+ hf = a[ul];
+ hf->f_mode &= ~FMODE_WRITE;
+ if (!file_check_writeable(hf)) {
+ 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 -Nur linux-2.6.31.5.orig/fs/aufs/branch.h linux-2.6.31.5/fs/aufs/branch.h
--- linux-2.6.31.5.orig/fs/aufs/branch.h 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.31.5/fs/aufs/branch.h 2009-11-15 22:02:37.000000000 +0100
@@ -0,0 +1,219 @@
+/*
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+/*
+ * 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/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 */
+
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *xi_dbgaufs;
+#endif
+};
+
+/* members for writable branch only */
+enum {AuBrWh_BASE, AuBrWh_PLINK, AuBrWh_ORPH, AuBrWh_Last};
+struct au_wbr {
+ struct au_rwsem 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 */
+static const loff_t au_loff_max = LLONG_MAX;
+
+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_create2(struct file *base_file, struct file *copy_src);
+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_return(&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);
+
+#define WbrWhMustNoWaiters(wbr) AuRwMustNoWaiters(&wbr->wbr_wh_rwsem)
+#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&wbr->wbr_wh_rwsem)
+#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&wbr->wbr_wh_rwsem)
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_BRANCH_H__ */
diff -Nur linux-2.6.31.5.orig/fs/aufs/cpup.c linux-2.6.31.5/fs/aufs/cpup.c
--- linux-2.6.31.5.orig/fs/aufs/cpup.c 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.31.5/fs/aufs/cpup.c 2009-11-15 22:02:37.000000000 +0100
@@ -0,0 +1,1048 @@
+/*
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+/*
+ * copy-up functions, see wbr_policy.c for copy-down
+ */
+
+#include <linux/file.h>
+#include <linux/fs_stack.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include "aufs.h"
+
+void au_cpup_attr_flags(struct inode *dst, struct inode *src)
+{
+ const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE
+ | S_NOATIME | S_NOCMTIME;
+
+ dst->i_flags |= src->i_flags & ~mask;
+ if (au_test_fs_notime(dst->i_sb))
+ dst->i_flags |= S_NOATIME | S_NOCMTIME;
+}
+
+void au_cpup_attr_timesizes(struct inode *inode)
+{
+ struct inode *h_inode;
+
+ h_inode = au_h_iptr(inode, au_ibstart(inode));
+ fsstack_copy_attr_times(inode, h_inode);
+ vfsub_copy_inode_size(inode, h_inode);
+}
+
+void au_cpup_attr_nlink(struct inode *inode, int force)
+{
+ struct inode *h_inode;
+ struct super_block *sb;
+ aufs_bindex_t bindex, bend;
+
+ sb = inode->i_sb;
+ bindex = au_ibstart(inode);
+ h_inode = au_h_iptr(inode, bindex);
+ if (!force
+ && !S_ISDIR(h_inode->i_mode)
+ && au_opt_test(au_mntflags(sb), PLINK)
+ && au_plink_test(inode))
+ return;
+
+ inode->i_nlink = h_inode->i_nlink;
+
+ /*
+ * fewer nlink makes find(1) noisy, but larger nlink doesn't.
+ * it may includes whplink directory.
+ */
+ if (S_ISDIR(h_inode->i_mode)) {
+ bend = au_ibend(inode);
+ for (bindex++; bindex <= bend; bindex++) {
+ h_inode = au_h_iptr(inode, bindex);
+ if (h_inode)
+ au_add_nlink(inode, h_inode);
+ }
+ }
+}
+
+void au_cpup_attr_changeable(struct inode *inode)
+{
+ struct inode *h_inode;
+
+ h_inode = au_h_iptr(inode, au_ibstart(inode));
+ inode->i_mode = h_inode->i_mode;
+ inode->i_uid = h_inode->i_uid;
+ inode->i_gid = h_inode->i_gid;
+ au_cpup_attr_timesizes(inode);
+ au_cpup_attr_flags(inode, h_inode);
+}
+
+void au_cpup_igen(struct inode *inode, struct inode *h_inode)
+{
+ struct au_iinfo *iinfo = au_ii(inode);
+
+ IiMustWriteLock(inode);
+
+ iinfo->ii_higen = h_inode->i_generation;
+ iinfo->ii_hsb1 = h_inode->i_sb;
+}
+
+void au_cpup_attr_all(struct inode *inode, int force)
+{
+ struct inode *h_inode;
+
+ h_inode = au_h_iptr(inode, au_ibstart(inode));
+ au_cpup_attr_changeable(inode);
+ if (inode->i_nlink > 0)
+ au_cpup_attr_nlink(inode, force);
+ inode->i_rdev = h_inode->i_rdev;
+ inode->i_blkbits = h_inode->i_blkbits;
+ au_cpup_igen(inode, h_inode);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */
+
+/* keep the timestamps of the parent dir when cpup */
+void au_dtime_store(struct au_dtime *dt, struct dentry *dentry,
+ struct path *h_path)
+{
+ struct inode *h_inode;
+
+ dt->dt_dentry = dentry;
+ dt->dt_h_path = *h_path;
+ h_inode = h_path->dentry->d_inode;
+ dt->dt_atime = h_inode->i_atime;
+ dt->dt_mtime = h_inode->i_mtime;
+ /* smp_mb(); */
+}
+
+void au_dtime_revert(struct au_dtime *dt)
+{
+ struct iattr attr;
+ int err;
+
+ attr.ia_atime = dt->dt_atime;
+ attr.ia_mtime = dt->dt_mtime;
+ attr.ia_valid = ATTR_FORCE | ATTR_MTIME | ATTR_MTIME_SET
+ | ATTR_ATIME | ATTR_ATIME_SET;
+
+ err = vfsub_notify_change(&dt->dt_h_path, &attr);
+ if (unlikely(err))
+ AuWarn("restoring timestamps failed(%d). ignored\n", err);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static noinline_for_stack
+int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src)
+{
+ int err, sbits;
+ struct iattr ia;
+ struct path h_path;
+ struct inode *h_isrc, *h_idst;
+
+ h_path.dentry = au_h_dptr(dst, bindex);
+ h_idst = h_path.dentry->d_inode;
+ h_path.mnt = au_sbr_mnt(dst->d_sb, bindex);
+ h_isrc = h_src->d_inode;
+ ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID
+ | ATTR_ATIME | ATTR_MTIME
+ | ATTR_ATIME_SET | ATTR_MTIME_SET;
+ ia.ia_uid = h_isrc->i_uid;
+ ia.ia_gid = h_isrc->i_gid;
+ ia.ia_atime = h_isrc->i_atime;
+ ia.ia_mtime = h_isrc->i_mtime;
+ if (h_idst->i_mode != h_isrc->i_mode
+ && !S_ISLNK(h_idst->i_mode)) {
+ ia.ia_valid |= ATTR_MODE;
+ ia.ia_mode = h_isrc->i_mode;
+ }
+ sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID));
+ au_cpup_attr_flags(h_idst, h_isrc);
+ err = vfsub_notify_change(&h_path, &ia);
+
+ /* is this nfs only? */
+ if (!err && sbits && au_test_nfs(h_path.dentry->d_sb)) {
+ ia.ia_valid = ATTR_FORCE | ATTR_MODE;
+ ia.ia_mode = h_isrc->i_mode;
+ err = vfsub_notify_change(&h_path, &ia);
+ }
+
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_do_copy_file(struct file *dst, struct file *src, loff_t len,
+ char *buf, unsigned long blksize)
+{
+ int err;
+ size_t sz, rbytes, wbytes;
+ unsigned char all_zero;
+ char *p, *zp;
+ struct mutex *h_mtx;
+ /* reduce stack usage */
+ struct iattr *ia;
+
+ zp = page_address(ZERO_PAGE(0));
+ if (unlikely(!zp))
+ return -ENOMEM; /* possible? */
+
+ err = 0;
+ all_zero = 0;
+ while (len) {
+ AuDbg("len %lld\n", len);
+ sz = blksize;
+ if (len < blksize)
+ sz = len;
+
+ rbytes = 0;
+ /* todo: signal_pending? */
+ while (!rbytes || err == -EAGAIN || err == -EINTR) {
+ rbytes = vfsub_read_k(src, buf, sz, &src->f_pos);
+ err = rbytes;
+ }
+ if (unlikely(err < 0))
+ break;
+
+ all_zero = 0;
+ if (len >= rbytes && rbytes == blksize)
+ all_zero = !memcmp(buf, zp, rbytes);
+ if (!all_zero) {
+ wbytes = rbytes;
+ p = buf;
+ while (wbytes) {
+ size_t b;
+
+ b = vfsub_write_k(dst, p, wbytes, &dst->f_pos);
+ err = b;
+ /* todo: signal_pending? */
+ if (unlikely(err == -EAGAIN || err == -EINTR))
+ continue;
+ if (unlikely(err < 0))
+ break;
+ wbytes -= b;
+ p += b;
+ }
+ } else {
+ loff_t res;
+
+ AuLabel(hole);
+ res = vfsub_llseek(dst, rbytes, SEEK_CUR);
+ err = res;
+ if (unlikely(res < 0))
+ break;
+ }
+ len -= rbytes;
+ err = 0;
+ }
+
+ /* the last block may be a hole */
+ if (!err && all_zero) {
+ AuLabel(last hole);
+
+ err = 1;
+ if (au_test_nfs(dst->f_dentry->d_sb)) {
+ /* nfs requires this step to make last hole */
+ /* is this only nfs? */
+ do {
+ /* todo: signal_pending? */
+ err = vfsub_write_k(dst, "\0", 1, &dst->f_pos);
+ } while (err == -EAGAIN || err == -EINTR);
+ if (err == 1)
+ dst->f_pos--;
+ }
+
+ if (err == 1) {
+ ia = (void *)buf;
+ ia->ia_size = dst->f_pos;
+ ia->ia_valid = ATTR_SIZE | ATTR_FILE;
+ ia->ia_file = dst;
+ h_mtx = &dst->f_dentry->d_inode->i_mutex;
+ mutex_lock_nested(h_mtx, AuLsc_I_CHILD2);
+ err = vfsub_notify_change(&dst->f_path, ia);
+ mutex_unlock(h_mtx);
+ }
+ }
+
+ return err;
+}
+
+int au_copy_file(struct file *dst, struct file *src, loff_t len)
+{
+ int err;
+ unsigned long blksize;
+ unsigned char do_kfree;
+ char *buf;
+
+ err = -ENOMEM;
+ blksize = dst->f_dentry->d_sb->s_blocksize;
+ if (!blksize || PAGE_SIZE < blksize)
+ blksize = PAGE_SIZE;
+ AuDbg("blksize %lu\n", blksize);
+ do_kfree = (blksize != PAGE_SIZE && blksize >= sizeof(struct iattr *));
+ if (do_kfree)
+ buf = kmalloc(blksize, GFP_NOFS);
+ else
+ buf = (void *)__get_free_page(GFP_NOFS);
+ if (unlikely(!buf))
+ goto out;
+
+ if (len > (1 << 22))
+ AuDbg("copying a large file %lld\n", (long long)len);
+
+ src->f_pos = 0;
+ dst->f_pos = 0;
+ err = au_do_copy_file(dst, src, len, buf, blksize);
+ if (do_kfree)
+ kfree(buf);
+ else
+ free_page((unsigned long)buf);
+
+ out:
+ return err;
+}
+
+/*
+ * to support a sparse file which is opened with O_APPEND,
+ * we need to close the file.
+ */
+static int au_cp_regular(struct dentry *dentry, aufs_bindex_t bdst,
+ aufs_bindex_t bsrc, loff_t len)
+{
+ int err, i;
+ enum { SRC, DST };
+ struct {
+ aufs_bindex_t bindex;
+ unsigned int flags;
+ struct dentry *dentry;
+ struct file *file;
+ void *label, *label_file;
+ } *f, file[] = {
+ {
+ .bindex = bsrc,
+ .flags = O_RDONLY | O_NOATIME | O_LARGEFILE,
+ .file = NULL,
+ .label = &&out,
+ .label_file = &&out_src
+ },
+ {
+ .bindex = bdst,
+ .flags = O_WRONLY | O_NOATIME | O_LARGEFILE,
+ .file = NULL,
+ .label = &&out_src,
+ .label_file = &&out_dst
+ }
+ };
+ struct super_block *sb;
+
+ /* bsrc branch can be ro/rw. */
+ sb = dentry->d_sb;
+ f = file;
+ for (i = 0; i < 2; i++, f++) {
+ f->dentry = au_h_dptr(dentry, f->bindex);
+ f->file = au_h_open(dentry, f->bindex, f->flags, /*file*/NULL);
+ err = PTR_ERR(f->file);
+ if (IS_ERR(f->file))
+ goto *f->label;
+ err = -EINVAL;
+ if (unlikely(!f->file->f_op))
+ goto *f->label_file;
+ }
+
+ /* try stopping to update while we copyup */
+ IMustLock(file[SRC].dentry->d_inode);
+ err = au_copy_file(file[DST].file, file[SRC].file, len);
+
+ out_dst:
+ fput(file[DST].file);
+ au_sbr_put(sb, file[DST].bindex);
+ out_src:
+ fput(file[SRC].file);
+ au_sbr_put(sb, file[SRC].bindex);
+ out:
+ return err;
+}
+
+static int au_do_cpup_regular(struct dentry *dentry, aufs_bindex_t bdst,
+ aufs_bindex_t bsrc, loff_t len,
+ struct inode *h_dir, struct path *h_path)
+{
+ int err, rerr;
+ loff_t l;
+
+ err = 0;
+ l = i_size_read(au_h_iptr(dentry->d_inode, bsrc));
+ if (len == -1 || l < len)
+ len = l;
+ if (len)
+ err = au_cp_regular(dentry, bdst, bsrc, len);
+ if (!err)
+ goto out; /* success */
+
+ rerr = vfsub_unlink(h_dir, h_path, /*force*/0);
+ if (rerr) {
+ AuIOErr("failed unlinking cpup-ed %.*s(%d, %d)\n",
+ AuDLNPair(h_path->dentry), err, rerr);
+ err = -EIO;
+ }
+
+ out:
+ return err;
+}
+
+static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src,
+ struct inode *h_dir)
+{
+ int err, symlen;
+ mm_segment_t old_fs;
+ char *sym;
+
+ err = -ENOSYS;
+ if (unlikely(!h_src->d_inode->i_op->readlink))
+ goto out;
+
+ err = -ENOMEM;
+ sym = __getname();
+ if (unlikely(!sym))
+ goto out;
+
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ symlen = h_src->d_inode->i_op->readlink(h_src, (char __user *)sym,
+ PATH_MAX);
+ err = symlen;
+ set_fs(old_fs);
+
+ if (symlen > 0) {
+ sym[symlen] = 0;
+ err = vfsub_symlink(h_dir, h_path, sym);
+ }
+ __putname(sym);
+
+ out:
+ return err;
+}
+
+/* return with the lower dst inode is locked */
+static noinline_for_stack
+int cpup_entry(struct dentry *dentry, aufs_bindex_t bdst,
+ aufs_bindex_t bsrc, loff_t len, unsigned int flags,
+ struct dentry *dst_parent)
+{
+ int err;
+ umode_t mode;
+ unsigned int mnt_flags;
+ unsigned char isdir;
+ const unsigned char do_dt = !!au_ftest_cpup(flags, DTIME);
+ struct au_dtime dt;
+ struct path h_path;
+ struct dentry *h_src, *h_dst, *h_parent;
+ struct inode *h_inode, *h_dir;
+ struct super_block *sb;
+
+ /* bsrc branch can be ro/rw. */
+ h_src = au_h_dptr(dentry, bsrc);
+ h_inode = h_src->d_inode;
+ AuDebugOn(h_inode != au_h_iptr(dentry->d_inode, bsrc));
+
+ /* try stopping to be referenced while we are creating */
+ h_dst = au_h_dptr(dentry, bdst);
+ h_parent = h_dst->d_parent; /* dir inode is locked */
+ h_dir = h_parent->d_inode;
+ IMustLock(h_dir);
+ AuDebugOn(h_parent != h_dst->d_parent);
+
+ sb = dentry->d_sb;
+ h_path.mnt = au_sbr_mnt(sb, bdst);
+ if (do_dt) {
+ h_path.dentry = h_parent;
+ au_dtime_store(&dt, dst_parent, &h_path);
+ }
+ h_path.dentry = h_dst;
+
+ isdir = 0;
+ mode = h_inode->i_mode;
+ switch (mode & S_IFMT) {
+ case S_IFREG:
+ /* try stopping to update while we are referencing */
+ IMustLock(h_inode);
+ err = vfsub_create(h_dir, &h_path, mode | S_IWUSR);
+ if (!err)
+ err = au_do_cpup_regular
+ (dentry, bdst, bsrc, len,
+ au_h_iptr(dst_parent->d_inode, bdst), &h_path);
+ break;
+ case S_IFDIR:
+ isdir = 1;
+ err = vfsub_mkdir(h_dir, &h_path, mode);
+ if (!err) {
+ /*
+ * strange behaviour from the users view,
+ * particularry setattr case
+ */
+ if (au_ibstart(dst_parent->d_inode) == bdst)
+ au_cpup_attr_nlink(dst_parent->d_inode,
+ /*force*/1);
+ au_cpup_attr_nlink(dentry->d_inode, /*force*/1);
+ }
+ break;
+ case S_IFLNK:
+ err = au_do_cpup_symlink(&h_path, h_src, h_dir);
+ break;
+ case S_IFCHR:
+ case S_IFBLK:
+ AuDebugOn(!capable(CAP_MKNOD));
+ /*FALLTHROUGH*/
+ case S_IFIFO:
+ case S_IFSOCK:
+ err = vfsub_mknod(h_dir, &h_path, mode, h_inode->i_rdev);
+ break;
+ default:
+ AuIOErr("Unknown inode type 0%o\n", mode);
+ err = -EIO;
+ }
+
+ mnt_flags = au_mntflags(sb);
+ if (!au_opt_test(mnt_flags, UDBA_NONE)
+ && !isdir
+ && au_opt_test(mnt_flags, XINO)
+ && h_inode->i_nlink == 1
+ /* todo: unnecessary? */
+ /* && dentry->d_inode->i_nlink == 1 */
+ && bdst < bsrc
+ && !au_ftest_cpup(flags, KEEPLINO))
+ au_xino_write(sb, bsrc, h_inode->i_ino, /*ino*/0);
+ /* ignore this error */
+
+ if (do_dt)
+ au_dtime_revert(&dt);
+ return err;
+}
+
+/*
+ * copyup the @dentry from @bsrc to @bdst.
+ * the caller must set the both of lower dentries.
+ * @len is for truncating when it is -1 copyup the entire file.
+ * in link/rename cases, @dst_parent may be different from the real one.
+ */
+static int au_cpup_single(struct dentry *dentry, aufs_bindex_t bdst,
+ aufs_bindex_t bsrc, loff_t len, unsigned int flags,
+ struct dentry *dst_parent)
+{
+ int err, rerr;
+ aufs_bindex_t old_ibstart;
+ unsigned char isdir, plink;
+ struct au_dtime dt;
+ struct path h_path;
+ struct dentry *h_src, *h_dst, *h_parent;
+ struct inode *dst_inode, *h_dir, *inode;
+ struct super_block *sb;
+
+ AuDebugOn(bsrc <= bdst);
+
+ sb = dentry->d_sb;
+ h_path.mnt = au_sbr_mnt(sb, bdst);
+ h_dst = au_h_dptr(dentry, bdst);
+ h_parent = h_dst->d_parent; /* dir inode is locked */
+ h_dir = h_parent->d_inode;
+ IMustLock(h_dir);
+
+ h_src = au_h_dptr(dentry, bsrc);
+ inode = dentry->d_inode;
+
+ if (!dst_parent)
+ dst_parent = dget_parent(dentry);
+ else
+ dget(dst_parent);
+
+ plink = !!au_opt_test(au_mntflags(sb), PLINK);
+ dst_inode = au_h_iptr(inode, bdst);
+ if (dst_inode) {
+ if (unlikely(!plink)) {
+ err = -EIO;
+ AuIOErr("i%lu exists on a upper branch "
+ "but plink is disabled\n", inode->i_ino);
+ goto out;
+ }
+
+ if (dst_inode->i_nlink) {
+ const int do_dt = au_ftest_cpup(flags, DTIME);
+
+ h_src = au_plink_lkup(inode, bdst);
+ err = PTR_ERR(h_src);
+ if (IS_ERR(h_src))
+ goto out;
+ if (unlikely(!h_src->d_inode)) {
+ err = -EIO;
+ AuIOErr("i%lu exists on a upper branch "
+ "but plink is broken\n", inode->i_ino);
+ dput(h_src);
+ goto out;
+ }
+
+ if (do_dt) {
+ h_path.dentry = h_parent;
+ au_dtime_store(&dt, dst_parent, &h_path);
+ }
+ h_path.dentry = h_dst;
+ err = vfsub_link(h_src, h_dir, &h_path);
+ if (do_dt)
+ au_dtime_revert(&dt);
+ dput(h_src);
+ goto out;
+ } else
+ /* todo: cpup_wh_file? */
+ /* udba work */
+ au_update_brange(inode, 1);
+ }
+
+ old_ibstart = au_ibstart(inode);
+ err = cpup_entry(dentry, bdst, bsrc, len, flags, dst_parent);
+ if (unlikely(err))
+ goto out;
+ dst_inode = h_dst->d_inode;
+ mutex_lock_nested(&dst_inode->i_mutex, AuLsc_I_CHILD2);
+
+ err = cpup_iattr(dentry, bdst, h_src);
+ isdir = S_ISDIR(dst_inode->i_mode);
+ if (!err) {
+ if (bdst < old_ibstart)
+ au_set_ibstart(inode, bdst);
+ au_set_h_iptr(inode, bdst, au_igrab(dst_inode),
+ au_hi_flags(inode, isdir));
+ mutex_unlock(&dst_inode->i_mutex);
+ if (!isdir
+ && h_src->d_inode->i_nlink > 1
+ && plink)
+ au_plink_append(inode, bdst, h_dst);
+ goto out; /* success */
+ }
+
+ /* revert */
+ h_path.dentry = h_parent;
+ mutex_unlock(&dst_inode->i_mutex);
+ au_dtime_store(&dt, dst_parent, &h_path);
+ h_path.dentry = h_dst;
+ if (!isdir)
+ rerr = vfsub_unlink(h_dir, &h_path, /*force*/0);
+ else
+ rerr = vfsub_rmdir(h_dir, &h_path);
+ au_dtime_revert(&dt);
+ if (rerr) {
+ AuIOErr("failed removing broken entry(%d, %d)\n", err, rerr);
+ err = -EIO;
+ }
+
+ out:
+ dput(dst_parent);
+ return err;
+}
+
+struct au_cpup_single_args {
+ int *errp;
+ struct dentry *dentry;
+ aufs_bindex_t bdst, bsrc;
+ loff_t len;
+ unsigned int flags;
+ struct dentry *dst_parent;
+};
+
+static void au_call_cpup_single(void *args)
+{
+ struct au_cpup_single_args *a = args;
+ *a->errp = au_cpup_single(a->dentry, a->bdst, a->bsrc, a->len,
+ a->flags, a->dst_parent);
+}
+
+int au_sio_cpup_single(struct dentry *dentry, aufs_bindex_t bdst,
+ aufs_bindex_t bsrc, loff_t len, unsigned int flags,
+ struct dentry *dst_parent)
+{
+ int err, wkq_err;
+ umode_t mode;
+ struct dentry *h_dentry;
+
+ h_dentry = au_h_dptr(dentry, bsrc);
+ mode = h_dentry->d_inode->i_mode & S_IFMT;
+ if ((mode != S_IFCHR && mode != S_IFBLK)
+ || capable(CAP_MKNOD))
+ err = au_cpup_single(dentry, bdst, bsrc, len, flags,
+ dst_parent);
+ else {
+ struct au_cpup_single_args args = {
+ .errp = &err,
+ .dentry = dentry,
+ .bdst = bdst,
+ .bsrc = bsrc,
+ .len = len,
+ .flags = flags,
+ .dst_parent = dst_parent
+ };
+ wkq_err = au_wkq_wait(au_call_cpup_single, &args);
+ if (unlikely(wkq_err))
+ err = wkq_err;
+ }
+
+ return err;
+}
+
+/*
+ * copyup the @dentry from the first active lower branch to @bdst,
+ * using au_cpup_single().
+ */
+static int au_cpup_simple(struct dentry *dentry, aufs_bindex_t bdst, loff_t len,
+ unsigned int flags)
+{
+ int err;
+ aufs_bindex_t bsrc, bend;
+
+ bend = au_dbend(dentry);
+ for (bsrc = bdst + 1; bsrc <= bend; bsrc++)
+ if (au_h_dptr(dentry, bsrc))
+ break;
+
+ err = au_lkup_neg(dentry, bdst);
+ if (!err) {
+ err = au_cpup_single(dentry, bdst, bsrc, len, flags, NULL);
+ if (!err)
+ return 0; /* success */
+
+ /* revert */
+ au_set_h_dptr(dentry, bdst, NULL);
+ au_set_dbstart(dentry, bsrc);
+ }
+
+ return err;
+}
+
+struct au_cpup_simple_args {
+ int *errp;
+ struct dentry *dentry;
+ aufs_bindex_t bdst;
+ loff_t len;
+ unsigned int flags;
+};
+
+static void au_call_cpup_simple(void *args)
+{
+ struct au_cpup_simple_args *a = args;
+ *a->errp = au_cpup_simple(a->dentry, a->bdst, a->len, a->flags);
+}
+
+int au_sio_cpup_simple(struct dentry *dentry, aufs_bindex_t bdst, loff_t len,
+ unsigned int flags)
+{
+ int err, wkq_err;
+ unsigned char do_sio;
+ struct dentry *parent;
+ struct inode *h_dir;
+
+ parent = dget_parent(dentry);
+ h_dir = au_h_iptr(parent->d_inode, bdst);
+ do_sio = !!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE);
+ if (!do_sio) {
+ /*
+ * testing CAP_MKNOD is for generic fs,
+ * but CAP_FSETID is for xfs only, currently.
+ */
+ umode_t mode = dentry->d_inode->i_mode;
+ do_sio = (((mode & (S_IFCHR | S_IFBLK))
+ && !capable(CAP_MKNOD))
+ || ((mode & (S_ISUID | S_ISGID))
+ && !capable(CAP_FSETID)));
+ }
+ if (!do_sio)
+ err = au_cpup_simple(dentry, bdst, len, flags);
+ else {
+ struct au_cpup_simple_args args = {
+ .errp = &err,
+ .dentry = dentry,
+ .bdst = bdst,
+ .len = len,
+ .flags = flags
+ };
+ wkq_err = au_wkq_wait(au_call_cpup_simple, &args);
+ if (unlikely(wkq_err))
+ err = wkq_err;
+ }
+
+ dput(parent);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * copyup the deleted file for writing.
+ */
+static int au_do_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst,
+ struct dentry *wh_dentry, struct file *file,
+ loff_t len)
+{
+ int err;
+ aufs_bindex_t bstart;
+ struct au_dinfo *dinfo;
+ struct dentry *h_d_dst, *h_d_start;
+
+ dinfo = au_di(dentry);
+ AuRwMustWriteLock(&dinfo->di_rwsem);
+
+ bstart = dinfo->di_bstart;
+ h_d_dst = dinfo->di_hdentry[0 + bdst].hd_dentry;
+ dinfo->di_bstart = bdst;
+ dinfo->di_hdentry[0 + bdst].hd_dentry = wh_dentry;
+ h_d_start = dinfo->di_hdentry[0 + bstart].hd_dentry;
+ if (file)
+ dinfo->di_hdentry[0 + bstart].hd_dentry
+ = au_h_fptr(file, au_fbstart(file))->f_dentry;
+ err = au_cpup_single(dentry, bdst, bstart, len, !AuCpup_DTIME,
+ /*h_parent*/NULL);
+ if (!err && file) {
+ err = au_reopen_nondir(file);
+ dinfo->di_hdentry[0 + bstart].hd_dentry = h_d_start;
+ }
+ dinfo->di_hdentry[0 + bdst].hd_dentry = h_d_dst;
+ dinfo->di_bstart = bstart;
+
+ return err;
+}
+
+static int au_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len,
+ struct file *file)
+{
+ int err;
+ struct au_dtime dt;
+ struct dentry *parent, *h_parent, *wh_dentry;
+ struct au_branch *br;
+ struct path h_path;
+
+ br = au_sbr(dentry->d_sb, bdst);
+ parent = dget_parent(dentry);
+ h_parent = au_h_dptr(parent, bdst);
+ wh_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name);
+ err = PTR_ERR(wh_dentry);
+ if (IS_ERR(wh_dentry))
+ goto out;
+
+ h_path.dentry = h_parent;
+ h_path.mnt = br->br_mnt;
+ au_dtime_store(&dt, parent, &h_path);
+ err = au_do_cpup_wh(dentry, bdst, wh_dentry, file, len);
+ if (unlikely(err))
+ goto out_wh;
+
+ dget(wh_dentry);
+ h_path.dentry = wh_dentry;
+ err = vfsub_unlink(h_parent->d_inode, &h_path, /*force*/0);
+ if (unlikely(err)) {
+ AuIOErr("failed remove copied-up tmp file %.*s(%d)\n",
+ AuDLNPair(wh_dentry), err);
+ err = -EIO;
+ }
+ au_dtime_revert(&dt);
+ au_set_hi_wh(dentry->d_inode, bdst, wh_dentry);
+
+ out_wh:
+ dput(wh_dentry);
+ out:
+ dput(parent);
+ return err;
+}
+
+struct au_cpup_wh_args {
+ int *errp;
+ struct dentry *dentry;
+ aufs_bindex_t bdst;
+ loff_t len;
+ struct file *file;
+};
+
+static void au_call_cpup_wh(void *args)
+{
+ struct au_cpup_wh_args *a = args;
+ *a->errp = au_cpup_wh(a->dentry, a->bdst, a->len, a->file);
+}
+
+int au_sio_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len,
+ struct file *file)
+{
+ int err, wkq_err;
+ struct dentry *parent, *h_orph, *h_parent, *h_dentry;
+ struct inode *dir, *h_dir, *h_tmpdir, *h_inode;
+ struct au_wbr *wbr;
+
+ parent = dget_parent(dentry);
+ dir = parent->d_inode;
+ h_orph = NULL;
+ h_parent = NULL;
+ h_dir = au_igrab(au_h_iptr(dir, bdst));
+ h_tmpdir = h_dir;
+ if (!h_dir->i_nlink) {
+ wbr = au_sbr(dentry->d_sb, bdst)->br_wbr;
+ h_orph = wbr->wbr_orph;
+
+ h_parent = dget(au_h_dptr(parent, bdst));
+ au_set_h_dptr(parent, bdst, NULL);
+ au_set_h_dptr(parent, bdst, dget(h_orph));
+ h_tmpdir = h_orph->d_inode;
+ au_set_h_iptr(dir, bdst, NULL, 0);
+ au_set_h_iptr(dir, bdst, au_igrab(h_tmpdir), /*flags*/0);
+
+ /* this temporary unlock is safe */
+ if (file)
+ h_dentry = au_h_fptr(file, au_fbstart(file))->f_dentry;
+ else
+ h_dentry = au_h_dptr(dentry, au_dbstart(dentry));
+ h_inode = h_dentry->d_inode;
+ IMustLock(h_inode);
+ mutex_unlock(&h_inode->i_mutex);
+ mutex_lock_nested(&h_tmpdir->i_mutex, AuLsc_I_PARENT3);
+ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
+ }
+
+ if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE))
+ err = au_cpup_wh(dentry, bdst, len, file);
+ else {
+ struct au_cpup_wh_args args = {
+ .errp = &err,
+ .dentry = dentry,
+ .bdst = bdst,
+ .len = len,
+ .file = file
+ };
+ wkq_err = au_wkq_wait(au_call_cpup_wh, &args);
+ if (unlikely(wkq_err))
+ err = wkq_err;
+ }
+
+ if (h_orph) {
+ mutex_unlock(&h_tmpdir->i_mutex);
+ au_set_h_iptr(dir, bdst, NULL, 0);
+ au_set_h_iptr(dir, bdst, au_igrab(h_dir), /*flags*/0);
+ au_set_h_dptr(parent, bdst, NULL);
+ au_set_h_dptr(parent, bdst, h_parent);
+ }
+ iput(h_dir);
+ dput(parent);
+
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * generic routine for both of copy-up and copy-down.
+ */
+/* cf. revalidate function in file.c */
+int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst,
+ int (*cp)(struct dentry *dentry, aufs_bindex_t bdst,
+ struct dentry *h_parent, void *arg),
+ void *arg)
+{
+ int err;
+ struct au_pin pin;
+ struct dentry *d, *parent, *h_parent, *real_parent;
+
+ err = 0;
+ parent = dget_parent(dentry);
+ if (IS_ROOT(parent))
+ goto out;
+
+ au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2,
+ au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE);
+
+ /* do not use au_dpage */
+ real_parent = parent;
+ while (1) {
+ dput(parent);
+ parent = dget_parent(dentry);
+ h_parent = au_h_dptr(parent, bdst);
+ if (h_parent)
+ goto out; /* success */
+
+ /* find top dir which is necessary to cpup */
+ do {
+ d = parent;
+ dput(parent);
+ parent = dget_parent(d);
+ di_read_lock_parent3(parent, !AuLock_IR);
+ h_parent = au_h_dptr(parent, bdst);
+ di_read_unlock(parent, !AuLock_IR);
+ } while (!h_parent);
+
+ if (d != real_parent)
+ di_write_lock_child3(d);
+
+ /* somebody else might create while we were sleeping */
+ if (!au_h_dptr(d, bdst) || !au_h_dptr(d, bdst)->d_inode) {
+ if (au_h_dptr(d, bdst))
+ au_update_dbstart(d);
+
+ au_pin_set_dentry(&pin, d);
+ err = au_do_pin(&pin);
+ if (!err) {
+ err = cp(d, bdst, h_parent, arg);
+ au_unpin(&pin);
+ }
+ }
+
+ if (d != real_parent)
+ di_write_unlock(d);
+ if (unlikely(err))
+ break;
+ }
+
+ out:
+ dput(parent);
+ return err;
+}
+
+static int au_cpup_dir(struct dentry *dentry, aufs_bindex_t bdst,
+ struct dentry *h_parent __maybe_unused ,
+ void *arg __maybe_unused)
+{
+ return au_sio_cpup_simple(dentry, bdst, -1, AuCpup_DTIME);
+}
+
+int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst)
+{
+ return au_cp_dirs(dentry, bdst, au_cpup_dir, NULL);
+}
+
+int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst)
+{
+ int err;
+ struct dentry *parent;
+ struct inode *dir;
+
+ parent = dget_parent(dentry);
+ dir = parent->d_inode;
+ err = 0;
+ if (au_h_iptr(dir, bdst))
+ goto out;
+
+ di_read_unlock(parent, AuLock_IR);
+ di_write_lock_parent(parent);
+ /* someone else might change our inode while we were sleeping */
+ if (!au_h_iptr(dir, bdst))
+ err = au_cpup_dirs(dentry, bdst);
+ di_downgrade_lock(parent, AuLock_IR);
+
+ out:
+ dput(parent);
+ return err;
+}
diff -Nur linux-2.6.31.5.orig/fs/aufs/cpup.h linux-2.6.31.5/fs/aufs/cpup.h
--- linux-2.6.31.5.orig/fs/aufs/cpup.h 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.31.5/fs/aufs/cpup.h 2009-11-15 22:02:37.000000000 +0100
@@ -0,0 +1,81 @@
+/*
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+/*
+ * copy-up/down functions
+ */
+
+#ifndef __AUFS_CPUP_H__
+#define __AUFS_CPUP_H__
+
+#ifdef __KERNEL__
+
+#include <linux/path.h>
+#include <linux/time.h>
+#include <linux/aufs_type.h>
+
+struct inode;
+struct file;
+
+void au_cpup_attr_flags(struct inode *dst, struct inode *src);
+void au_cpup_attr_timesizes(struct inode *inode);
+void au_cpup_attr_nlink(struct inode *inode, int force);
+void au_cpup_attr_changeable(struct inode *inode);
+void au_cpup_igen(struct inode *inode, struct inode *h_inode);
+void au_cpup_attr_all(struct inode *inode, int force);
+
+/* ---------------------------------------------------------------------- */
+
+/* cpup flags */
+#define AuCpup_DTIME 1 /* do dtime_store/revert */
+#define AuCpup_KEEPLINO (1 << 1) /* do not clear the lower xino,
+ for link(2) */
+#define au_ftest_cpup(flags, name) ((flags) & AuCpup_##name)
+#define au_fset_cpup(flags, name) { (flags) |= AuCpup_##name; }
+#define au_fclr_cpup(flags, name) { (flags) &= ~AuCpup_##name; }
+
+int au_copy_file(struct file *dst, struct file *src, loff_t len);
+int au_sio_cpup_single(struct dentry *dentry, aufs_bindex_t bdst,
+ aufs_bindex_t bsrc, loff_t len, unsigned int flags,
+ struct dentry *dst_parent);
+int au_sio_cpup_simple(struct dentry *dentry, aufs_bindex_t bdst, loff_t len,
+ unsigned int flags);
+int au_sio_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len,
+ struct file *file);
+
+int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst,
+ int (*cp)(struct dentry *dentry, aufs_bindex_t bdst,
+ struct dentry *h_parent, void *arg),
+ void *arg);
+int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst);
+int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst);
+
+/* ---------------------------------------------------------------------- */
+
+/* keep timestamps when copyup */
+struct au_dtime {
+ struct dentry *dt_dentry;
+ struct path dt_h_path;
+ struct timespec dt_atime, dt_mtime;
+};
+void au_dtime_store(struct au_dtime *dt, struct dentry *dentry,
+ struct path *h_path);
+void au_dtime_revert(struct au_dtime *dt);
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_CPUP_H__ */
diff -Nur linux-2.6.31.5.orig/fs/aufs/dbgaufs.c linux-2.6.31.5/fs/aufs/dbgaufs.c
--- linux-2.6.31.5.orig/fs/aufs/dbgaufs.c 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.31.5/fs/aufs/dbgaufs.c 2009-11-15 22:02:37.000000000 +0100
@@ -0,0 +1,331 @@
+/*
+ * Copyright (C) 2005-2009 Junjiro R. Oka