2009-03-09 03:40:43

by J. R. Okajima

Subject: [Aufs 00/25] source files

A few weeks ago, I posted the design of aufs.
And here are source files.

I have another version which dropped many features and the size became
about half because such suggestion was posted LKML. But I got no
response for it. Additionally I am afraid it is useless in real world
since the dropped features are so essential.
This version here I am posting is full aufs2 against the mainline
(linux-2.6.git).

Kindly review and let me know your comments.
And please consider incorporating into mainline.

J. R. Okajima (25):
aufs documents
aufs public header file
aufs module global
aufs super_block
aufs branch directory/filesystem
aufs xino
aufs object lifetime management via sysfs
aufs mount options/flags
aufs workqueue
aufs sub-VFS
aufs sub-dcache
aufs copy-up
aufs whiteout
aufs pseudo-link
aufs policies to select one among multiple writable branches
aufs dentry and lookup
aufs file
aufs direcotry
aufs inode
aufs ioctl
aufs sysfs entries
aufs branch for loopback block device
aufs internal inotify
aufs test for fstype
aufs debug

Documentation/filesystems/aufs/README | 251 ++++
Documentation/filesystems/aufs/aufs.5 | 1514 ++++++++++++++++++++
Documentation/filesystems/aufs/design/01intro.txt | 128 ++
Documentation/filesystems/aufs/design/02struct.txt | 205 +++
Documentation/filesystems/aufs/design/03lookup.txt | 95 ++
Documentation/filesystems/aufs/design/04branch.txt | 67 +
.../filesystems/aufs/design/05wbr_policy.txt | 57 +
.../filesystems/aufs/design/06fmode_exec.txt | 24 +
Documentation/filesystems/aufs/design/07mmap.txt | 44 +
Documentation/filesystems/aufs/design/08plan.txt | 169 +++
fs/Kconfig | 1 +
fs/Makefile | 1 +
fs/aufs/Kconfig | 78 +
fs/aufs/Makefile | 20 +
fs/aufs/aufs.h | 43 +
fs/aufs/branch.c | 944 ++++++++++++
fs/aufs/branch.h | 200 +++
fs/aufs/cpup.c | 1028 +++++++++++++
fs/aufs/cpup.h | 68 +
fs/aufs/dcsub.c | 214 +++
fs/aufs/dcsub.h | 43 +
fs/aufs/debug.c | 406 ++++++
fs/aufs/debug.h | 245 ++++
fs/aufs/dentry.c | 857 +++++++++++
fs/aufs/dentry.h | 213 +++
fs/aufs/dinfo.c | 351 +++++
fs/aufs/dir.c | 493 +++++++
fs/aufs/dir.h | 104 ++
fs/aufs/f_op.c | 551 +++++++
fs/aufs/file.c | 552 +++++++
fs/aufs/file.h | 148 ++
fs/aufs/finfo.c | 126 ++
fs/aufs/fstype.h | 434 ++++++
fs/aufs/hinotify.c | 746 ++++++++++
fs/aufs/i_op.c | 855 +++++++++++
fs/aufs/i_op_add.c | 625 ++++++++
fs/aufs/i_op_del.c | 471 ++++++
fs/aufs/i_op_ren.c | 929 ++++++++++++
fs/aufs/iinfo.c | 257 ++++
fs/aufs/inode.c | 356 +++++
fs/aufs/inode.h | 471 ++++++
fs/aufs/ioctl.c | 54 +
fs/aufs/loop.c | 46 +
fs/aufs/loop.h | 41 +
fs/aufs/magic.mk | 52 +
fs/aufs/module.c | 164 +++
fs/aufs/module.h | 66 +
fs/aufs/opts.c | 1438 +++++++++++++++++++
fs/aufs/opts.h | 180 +++
fs/aufs/plink.c | 335 +++++
fs/aufs/rwsem.h | 52 +
fs/aufs/sbinfo.c | 192 +++
fs/aufs/spl.h | 47 +
fs/aufs/super.c | 846 +++++++++++
fs/aufs/super.h | 266 ++++
fs/aufs/sysaufs.c | 79 +
fs/aufs/sysaufs.h | 102 ++
fs/aufs/sysfs.c | 308 ++++
fs/aufs/sysrq.c | 105 ++
fs/aufs/vdir.c | 776 ++++++++++
fs/aufs/vfsub.c | 716 +++++++++
fs/aufs/vfsub.h | 137 ++
fs/aufs/wbr_policy.c | 628 ++++++++
fs/aufs/whout.c | 1010 +++++++++++++
fs/aufs/whout.h | 78 +
fs/aufs/wkq.c | 249 ++++
fs/aufs/wkq.h | 72 +
fs/aufs/xino.c | 1181 +++++++++++++++
fs/namei.c | 4 +-
fs/splice.c | 10 +-
include/linux/aufs_type.h | 98 ++
include/linux/namei.h | 3 +
include/linux/splice.h | 6 +
73 files changed, 23718 insertions(+), 7 deletions(-)
create mode 100644 Documentation/filesystems/aufs/README
create mode 100644 Documentation/filesystems/aufs/aufs.5
create mode 100644 Documentation/filesystems/aufs/design/01intro.txt
create mode 100644 Documentation/filesystems/aufs/design/02struct.txt
create mode 100644 Documentation/filesystems/aufs/design/03lookup.txt
create mode 100644 Documentation/filesystems/aufs/design/04branch.txt
create mode 100644 Documentation/filesystems/aufs/design/05wbr_policy.txt
create mode 100644 Documentation/filesystems/aufs/design/06fmode_exec.txt
create mode 100644 Documentation/filesystems/aufs/design/07mmap.txt
create mode 100644 Documentation/filesystems/aufs/design/08plan.txt
create mode 100644 fs/aufs/Kconfig
create mode 100644 fs/aufs/Makefile
create mode 100644 fs/aufs/aufs.h
create mode 100644 fs/aufs/branch.c
create mode 100644 fs/aufs/branch.h
create mode 100644 fs/aufs/cpup.c
create mode 100644 fs/aufs/cpup.h
create mode 100644 fs/aufs/dcsub.c
create mode 100644 fs/aufs/dcsub.h
create mode 100644 fs/aufs/debug.c
create mode 100644 fs/aufs/debug.h
create mode 100644 fs/aufs/dentry.c
create mode 100644 fs/aufs/dentry.h
create mode 100644 fs/aufs/dinfo.c
create mode 100644 fs/aufs/dir.c
create mode 100644 fs/aufs/dir.h
create mode 100644 fs/aufs/f_op.c
create mode 100644 fs/aufs/file.c
create mode 100644 fs/aufs/file.h
create mode 100644 fs/aufs/finfo.c
create mode 100644 fs/aufs/fstype.h
create mode 100644 fs/aufs/hinotify.c
create mode 100644 fs/aufs/i_op.c
create mode 100644 fs/aufs/i_op_add.c
create mode 100644 fs/aufs/i_op_del.c
create mode 100644 fs/aufs/i_op_ren.c
create mode 100644 fs/aufs/iinfo.c
create mode 100644 fs/aufs/inode.c
create mode 100644 fs/aufs/inode.h
create mode 100644 fs/aufs/ioctl.c
create mode 100644 fs/aufs/loop.c
create mode 100644 fs/aufs/loop.h
create mode 100644 fs/aufs/magic.mk
create mode 100644 fs/aufs/module.c
create mode 100644 fs/aufs/module.h
create mode 100644 fs/aufs/opts.c
create mode 100644 fs/aufs/opts.h
create mode 100644 fs/aufs/plink.c
create mode 100644 fs/aufs/rwsem.h
create mode 100644 fs/aufs/sbinfo.c
create mode 100644 fs/aufs/spl.h
create mode 100644 fs/aufs/super.c
create mode 100644 fs/aufs/super.h
create mode 100644 fs/aufs/sysaufs.c
create mode 100644 fs/aufs/sysaufs.h
create mode 100644 fs/aufs/sysfs.c
create mode 100644 fs/aufs/sysrq.c
create mode 100644 fs/aufs/vdir.c
create mode 100644 fs/aufs/vfsub.c
create mode 100644 fs/aufs/vfsub.h
create mode 100644 fs/aufs/wbr_policy.c
create mode 100644 fs/aufs/whout.c
create mode 100644 fs/aufs/whout.h
create mode 100644 fs/aufs/wkq.c
create mode 100644 fs/aufs/wkq.h
create mode 100644 fs/aufs/xino.c
create mode 100644 include/linux/aufs_type.h

2009-03-09 03:31:28

by J. R. Okajima

Subject: [Aufs 22/25] aufs branch for loopback block device

initial commit
support and test loopback block device as a branch

Signed-off-by: J. R. Okajima <[email protected]>
---
fs/aufs/loop.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
fs/aufs/loop.h | 41 +++++++++++++++++++++++++++++++++++++++++
2 files changed, 87 insertions(+), 0 deletions(-)
create mode 100644 fs/aufs/loop.c
create mode 100644 fs/aufs/loop.h

diff --git a/fs/aufs/loop.c b/fs/aufs/loop.c
new file mode 100644
index 0000000..84a940f
--- /dev/null
+++ b/fs/aufs/loop.c
@@ -0,0 +1,46 @@
+/*
+ * 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.
+ */
+
+/*
+ * support for loopback block device as a branch
+ */
+
+#include <linux/loop.h>
+#include "aufs.h"
+
+/*
+ * test if two lower dentries have overlapping branches.
+ */
+int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_d1,
+ struct dentry *h_d2)
+{
+ struct inode *h_inode;
+ struct loop_device *l;
+
+ h_inode = h_d1->d_inode;
+ if (MAJOR(h_inode->i_sb->s_dev) != LOOP_MAJOR)
+ return 0;
+
+ l = h_inode->i_sb->s_bdev->bd_disk->private_data;
+ h_d1 = l->lo_backing_file->f_dentry;
+ /* h_d1 can be local NFS. in this case aufs cannot detect the loop */
+ if (unlikely(h_d1->d_sb == sb))
+ return 1;
+ return !!au_test_subdir(h_d1, h_d2);
+}
+
+/* true if a kernel thread named 'loop[0-9].*' accesses a file */
+int au_test_loopback_kthread(void)
+{
+ const char c = current->comm[4];
+
+ return current->mm == NULL
+ && '0' <= c && c <= '9'
+ && strncmp(current->comm, "loop", 4) == 0;
+}
diff --git a/fs/aufs/loop.h b/fs/aufs/loop.h
new file mode 100644
index 0000000..1c0ee40
--- /dev/null
+++ b/fs/aufs/loop.h
@@ -0,0 +1,41 @@
+/*
+ * 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.
+ */
+
+/*
+ * support for loopback mount as a branch
+ */
+
+#ifndef __AUFS_LOOP_H__
+#define __AUFS_LOOP_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+
+#ifdef CONFIG_AUFS_BDEV_LOOP
+/* loop.c */
+int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_d1,
+ struct dentry *h_d2);
+int au_test_loopback_kthread(void);
+#else
+static inline
+int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_d1,
+ struct dentry *h_d2)
+{
+ return 0;
+}
+
+static inline int au_test_loopback_kthread(void)
+{
+ return 0;
+}
+#endif /* BLK_DEV_LOOP */
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_LOOP_H__ */
--
1.6.1.284.g5dc13

2009-03-09 03:32:05

by J. R. Okajima

Subject: [Aufs 25/25] aufs debug

initial commit
debug print

Signed-off-by: J. R. Okajima <[email protected]>
---
fs/aufs/debug.c | 406 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/aufs/debug.h | 245 +++++++++++++++++++++++++++++++++
fs/aufs/sysrq.c | 105 ++++++++++++++
3 files changed, 756 insertions(+), 0 deletions(-)
create mode 100644 fs/aufs/debug.c
create mode 100644 fs/aufs/debug.h
create mode 100644 fs/aufs/sysrq.c

diff --git a/fs/aufs/debug.c b/fs/aufs/debug.c
new file mode 100644
index 0000000..e8bc59c
--- /dev/null
+++ b/fs/aufs/debug.c
@@ -0,0 +1,406 @@
+/*
+ * 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.
+ */
+
+/*
+ * debug print functions
+ */
+
+#include "aufs.h"
+
+atomic_t au_cond = ATOMIC_INIT(0);
+
+char *au_plevel = KERN_DEBUG;
+#define dpri(fmt, arg...) do { \
+ if (au_debug_test()) \
+ printk("%s" fmt, au_plevel, ##arg); \
+} while (0)
+
+/* ---------------------------------------------------------------------- */
+
+void au_dpri_whlist(struct au_nhash *whlist)
+{
+ int i;
+ struct hlist_head *head;
+ struct au_vdir_wh *tpos;
+ struct hlist_node *pos;
+
+ for (i = 0; i < AuSize_NHASH; i++) {
+ head = whlist->heads + i;
+ hlist_for_each_entry(tpos, pos, head, wh_hash)
+ dpri("b%d, %.*s, %d\n",
+ tpos->wh_bindex,
+ tpos->wh_str.len, tpos->wh_str.name,
+ tpos->wh_str.len);
+ }
+}
+
+void au_dpri_vdir(struct au_vdir *vdir)
+{
+ int i;
+ union au_vdir_deblk_p p;
+ unsigned char *o;
+
+ if (!vdir || IS_ERR(vdir)) {
+ dpri("err %ld\n", PTR_ERR(vdir));
+ return;
+ }
+
+ dpri("nblk %d, deblk %p, last{%d, %p}, ver %lu\n",
+ vdir->vd_nblk, vdir->vd_deblk,
+ vdir->vd_last.i, vdir->vd_last.p.p, vdir->vd_version);
+ for (i = 0; i < vdir->vd_nblk; i++) {
+ p.deblk = vdir->vd_deblk[i];
+ o = p.p;
+ dpri("[%d]: %p\n", i, o);
+ }
+}
+
+static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode,
+ struct dentry *wh)
+{
+ char *n = NULL;
+ int l = 0;
+
+ if (!inode || IS_ERR(inode)) {
+ dpri("i%d: err %ld\n", bindex, PTR_ERR(inode));
+ return -1;
+ }
+
+ /* the type of i_blocks depends upon CONFIG_LSF */
+ BUILD_BUG_ON(sizeof(inode->i_blocks) != sizeof(unsigned long)
+ && sizeof(inode->i_blocks) != sizeof(u64));
+ if (wh) {
+ n = (void *)wh->d_name.name;
+ l = wh->d_name.len;
+ }
+
+ dpri("i%d: i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu,"
+ " ct %lld, np %lu, st 0x%lx, f 0x%x, g %x%s%.*s\n",
+ bindex,
+ inode->i_ino, inode->i_sb ? au_sbtype(inode->i_sb) : "??",
+ atomic_read(&inode->i_count), inode->i_nlink, inode->i_mode,
+ i_size_read(inode), (unsigned long long)inode->i_blocks,
+ (long long)timespec_to_ns(&inode->i_ctime) & 0x0ffff,
+ inode->i_mapping ? inode->i_mapping->nrpages : 0,
+ inode->i_state, inode->i_flags, inode->i_generation,
+ l ? ", wh " : "", l, n);
+ return 0;
+}
+
+void au_dpri_inode(struct inode *inode)
+{
+ struct au_iinfo *iinfo;
+ aufs_bindex_t bindex;
+ int err;
+
+ err = do_pri_inode(-1, inode, NULL);
+ if (err || !au_test_aufs(inode->i_sb))
+ return;
+
+ iinfo = au_ii(inode);
+ if (!iinfo)
+ return;
+ dpri("i-1: bstart %d, bend %d, gen %d\n",
+ iinfo->ii_bstart, iinfo->ii_bend, au_iigen(inode));
+ if (iinfo->ii_bstart < 0)
+ return;
+ for (bindex = iinfo->ii_bstart; bindex <= iinfo->ii_bend; bindex++)
+ do_pri_inode(bindex, iinfo->ii_hinode[0 + bindex].hi_inode,
+ iinfo->ii_hinode[0 + bindex].hi_whdentry);
+}
+
+static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry)
+{
+ struct dentry *wh = NULL;
+
+ if (!dentry || IS_ERR(dentry)) {
+ dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry));
+ return -1;
+ }
+ /* do not call dget_parent() here */
+ dpri("d%d: %.*s?/%.*s, %s, cnt %d, flags 0x%x\n",
+ bindex,
+ AuDLNPair(dentry->d_parent), AuDLNPair(dentry),
+ dentry->d_sb ? au_sbtype(dentry->d_sb) : "??",
+ atomic_read(&dentry->d_count), dentry->d_flags);
+ if (bindex >= 0 && dentry->d_inode && au_test_aufs(dentry->d_sb)) {
+ struct au_iinfo *iinfo = au_ii(dentry->d_inode);
+ if (iinfo)
+ wh = iinfo->ii_hinode[0 + bindex].hi_whdentry;
+ }
+ do_pri_inode(bindex, dentry->d_inode, wh);
+ return 0;
+}
+
+void au_dpri_dentry(struct dentry *dentry)
+{
+ struct au_dinfo *dinfo;
+ aufs_bindex_t bindex;
+ int err;
+
+ err = do_pri_dentry(-1, dentry);
+ if (err || !au_test_aufs(dentry->d_sb))
+ return;
+
+ dinfo = au_di(dentry);
+ if (!dinfo)
+ return;
+ dpri("d-1: bstart %d, bend %d, bwh %d, bdiropq %d, gen %d\n",
+ dinfo->di_bstart, dinfo->di_bend,
+ dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry));
+ if (dinfo->di_bstart < 0)
+ return;
+ for (bindex = dinfo->di_bstart; bindex <= dinfo->di_bend; bindex++)
+ do_pri_dentry(bindex, dinfo->di_hdentry[0 + bindex].hd_dentry);
+}
+
+static int do_pri_file(aufs_bindex_t bindex, struct file *file)
+{
+ char a[32];
+
+ if (!file || IS_ERR(file)) {
+ dpri("f%d: err %ld\n", bindex, PTR_ERR(file));
+ return -1;
+ }
+ a[0] = 0;
+ if (bindex < 0
+ && file->f_dentry
+ && au_test_aufs(file->f_dentry->d_sb)
+ && au_fi(file))
+ snprintf(a, sizeof(a), ", mmapped %d", au_test_mmapped(file));
+ dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, pos %llu%s\n",
+ bindex, file->f_mode, file->f_flags, (long)file_count(file),
+ file->f_pos, a);
+ if (file->f_dentry)
+ do_pri_dentry(bindex, file->f_dentry);
+ return 0;
+}
+
+void au_dpri_file(struct file *file)
+{
+ struct au_finfo *finfo;
+ aufs_bindex_t bindex;
+ int err;
+
+ err = do_pri_file(-1, file);
+ if (err || !file->f_dentry || !au_test_aufs(file->f_dentry->d_sb))
+ return;
+
+ finfo = au_fi(file);
+ if (!finfo)
+ return;
+ if (finfo->fi_bstart < 0)
+ return;
+ for (bindex = finfo->fi_bstart; bindex <= finfo->fi_bend; bindex++) {
+ struct au_hfile *hf;
+
+ hf = finfo->fi_hfile + bindex;
+ do_pri_file(bindex, hf ? hf->hf_file : NULL);
+ }
+}
+
+static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br)
+{
+ struct vfsmount *mnt;
+ struct super_block *sb;
+
+ if (!br || IS_ERR(br)
+ || !(mnt = br->br_mnt) || IS_ERR(mnt)
+ || !(sb = mnt->mnt_sb) || IS_ERR(sb)) {
+ dpri("s%d: err %ld\n", bindex, PTR_ERR(br));
+ return -1;
+ }
+
+ dpri("s%d: {perm 0x%x, cnt %d, wbr %p}, "
+ "%s, dev 0x%02x%02x, flags 0x%lx, cnt(BIAS) %d, active %d, "
+ "xino %d\n",
+ bindex, br->br_perm, atomic_read(&br->br_count), br->br_wbr,
+ au_sbtype(sb), MAJOR(sb->s_dev), MINOR(sb->s_dev),
+ sb->s_flags, sb->s_count - S_BIAS,
+ atomic_read(&sb->s_active), !!br->br_xino.xi_file);
+ return 0;
+}
+
+void au_dpri_sb(struct super_block *sb)
+{
+ struct au_sbinfo *sbinfo;
+ aufs_bindex_t bindex;
+ int err;
+ /* to reuduce stack size */
+ struct {
+ struct vfsmount mnt;
+ struct au_branch fake;
+ } *a;
+
+ /* this function can be called from magic sysrq */
+ a = kzalloc(sizeof(*a), GFP_ATOMIC);
+ if (unlikely(!a)) {
+ dpri("no memory\n");
+ return;
+ }
+
+ a->mnt.mnt_sb = sb;
+ a->fake.br_perm = 0;
+ a->fake.br_mnt = &a->mnt;
+ a->fake.br_xino.xi_file = NULL;
+ atomic_set(&a->fake.br_count, 0);
+ smp_mb(); /* atomic_set */
+ err = do_pri_br(-1, &a->fake);
+ kfree(a);
+ dpri("dev 0x%x\n", sb->s_dev);
+ if (err || !au_test_aufs(sb))
+ return;
+
+ sbinfo = au_sbi(sb);
+ if (!sbinfo)
+ return;
+ dpri("nw %d, gen %u, kobj %d\n",
+ atomic_read(&sbinfo->si_nowait.nw_len), sbinfo->si_generation,
+ atomic_read(&sbinfo->si_kobj.kref.refcount));
+ for (bindex = 0; bindex <= sbinfo->si_bend; bindex++)
+ do_pri_br(bindex, sbinfo->si_branch[0 + bindex]);
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_dbg_sleep_jiffy(int jiffy)
+{
+ while (jiffy)
+ jiffy = schedule_timeout_uninterruptible(jiffy);
+}
+
+void au_dbg_iattr(struct iattr *ia)
+{
+#define AuBit(name) if (ia->ia_valid & ATTR_ ## name) \
+ dpri(#name "\n")
+ AuBit(MODE);
+ AuBit(UID);
+ AuBit(GID);
+ AuBit(SIZE);
+ AuBit(ATIME);
+ AuBit(MTIME);
+ AuBit(CTIME);
+ AuBit(ATIME_SET);
+ AuBit(MTIME_SET);
+ AuBit(FORCE);
+ AuBit(ATTR_FLAG);
+ AuBit(KILL_SUID);
+ AuBit(KILL_SGID);
+ AuBit(FILE);
+ AuBit(KILL_PRIV);
+ AuBit(OPEN);
+ AuBit(TIMES_SET);
+#undef AuBit
+ dpri("ia_file %p\n", ia->ia_file);
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_dbg_verify_dir_parent(struct dentry *dentry, unsigned int sigen)
+{
+ struct dentry *parent;
+
+ parent = dget_parent(dentry);
+ AuDebugOn(!S_ISDIR(dentry->d_inode->i_mode)
+ || IS_ROOT(dentry)
+ || au_digen(parent) != sigen);
+ dput(parent);
+}
+
+void au_dbg_verify_nondir_parent(struct dentry *dentry, unsigned int sigen)
+{
+ struct dentry *parent;
+
+ parent = dget_parent(dentry);
+ AuDebugOn(S_ISDIR(dentry->d_inode->i_mode)
+ || au_digen(parent) != sigen);
+ dput(parent);
+}
+
+void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen)
+{
+ int err, i, j;
+ struct au_dcsub_pages dpages;
+ struct au_dpage *dpage;
+ struct dentry **dentries;
+
+ err = au_dpages_init(&dpages, GFP_NOFS);
+ AuDebugOn(err);
+ err = au_dcsub_pages_rev(&dpages, parent, /*do_include*/1, NULL, NULL);
+ AuDebugOn(err);
+ for (i = dpages.ndpage - 1; !err && i >= 0; i--) {
+ dpage = dpages.dpages + i;
+ dentries = dpage->dentries;
+ for (j = dpage->ndentry - 1; !err && j >= 0; j--)
+ AuDebugOn(au_digen(dentries[j]) != sigen);
+ }
+ au_dpages_free(&dpages);
+}
+
+void au_dbg_verify_hf(struct au_finfo *finfo)
+{
+ struct au_hfile *hf;
+ aufs_bindex_t bend, bindex;
+
+ if (finfo->fi_bstart >= 0) {
+ bend = finfo->fi_bend;
+ for (bindex = finfo->fi_bstart; bindex <= bend; bindex++) {
+ hf = finfo->fi_hfile + bindex;
+ AuDebugOn(hf->hf_file || hf->hf_br);
+ }
+ }
+}
+
+void au_dbg_verify_kthread(void)
+{
+ if (au_test_wkq(current)) {
+ au_dbg_blocked();
+ BUG();
+ }
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_debug_sbinfo_init(struct au_sbinfo *sbinfo __maybe_unused)
+{
+#ifdef AuForceNoPlink
+ au_opt_clr(sbinfo->si_mntflags, PLINK);
+#endif
+#ifdef AuForceNoXino
+ au_opt_clr(sbinfo->si_mntflags, XINO);
+#endif
+#ifdef AuForceNoRefrof
+ au_opt_clr(sbinfo->si_mntflags, REFROF);
+#endif
+#ifdef AuForceHinotify
+ au_opt_set_udba(sbinfo->si_mntflags, UDBA_HINOTIFY);
+#endif
+}
+
+int __init au_debug_init(void)
+{
+ aufs_bindex_t bindex;
+ struct au_vdir_destr destr;
+
+ bindex = -1;
+ AuDebugOn(bindex >= 0);
+
+ destr.len = -1;
+ AuDebugOn(destr.len < NAME_MAX);
+
+#ifdef CONFIG_4KSTACKS
+ AuWarn("CONFIG_4KSTACKS is defined.\n");
+#endif
+
+#ifdef AuForceNoBrs
+ sysaufs_brs = 0;
+#endif
+
+ return 0;
+}
diff --git a/fs/aufs/debug.h b/fs/aufs/debug.h
new file mode 100644
index 0000000..0b377a8
--- /dev/null
+++ b/fs/aufs/debug.h
@@ -0,0 +1,245 @@
+/*
+ * 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.
+ */
+
+/*
+ * debug print functions
+ */
+
+#ifndef __AUFS_DEBUG_H__
+#define __AUFS_DEBUG_H__
+
+#ifdef __KERNEL__
+
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/kd.h>
+#include <linux/vt_kern.h>
+#include <linux/sysrq.h>
+#include <linux/aufs_type.h>
+
+#ifdef CONFIG_AUFS_DEBUG
+#define AuDebugOn(a) BUG_ON(a)
+extern atomic_t au_cond;
+static inline void au_debug(int n)
+{
+ atomic_set(&au_cond, n);
+ smp_mb();
+}
+
+static inline int au_debug_test(void)
+{
+ int ret;
+
+ ret = atomic_read(&au_cond);
+ smp_mb();
+ return ret;
+}
+#else
+#define AuDebugOn(a) do {} while (0)
+#define au_debug() do {} while (0)
+static inline int au_debug_test(void)
+{
+ return 0;
+}
+#endif /* CONFIG_AUFS_DEBUG */
+
+/* ---------------------------------------------------------------------- */
+
+/* debug print */
+
+#define AuDpri(lvl, fmt, arg...) \
+ printk(lvl AUFS_NAME " %s:%d:%s[%d]: " fmt, \
+ __func__, __LINE__, current->comm, current->pid, ##arg)
+#define AuDbg(fmt, arg...) do { \
+ if (au_debug_test()) \
+ AuDpri(KERN_DEBUG, fmt, ##arg); \
+} while (0)
+#define AuLabel(l) AuDbg(#l "\n")
+#define AuInfo(fmt, arg...) AuDpri(KERN_INFO, fmt, ##arg)
+#define AuWarn(fmt, arg...) AuDpri(KERN_WARNING, fmt, ##arg)
+#define AuErr(fmt, arg...) AuDpri(KERN_ERR, fmt, ##arg)
+#define AuIOErr(fmt, arg...) AuErr("I/O Error, " fmt, ##arg)
+#define AuWarn1(fmt, arg...) do { \
+ static unsigned char _c; \
+ if (!_c++) \
+ AuWarn(fmt, ##arg); \
+} while (0)
+
+#define AuErr1(fmt, arg...) do { \
+ static unsigned char _c; \
+ if (!_c++) \
+ AuErr(fmt, ##arg); \
+} while (0)
+
+#define AuIOErr1(fmt, arg...) do { \
+ static unsigned char _c; \
+ if (!_c++) \
+ AuIOErr(fmt, ##arg); \
+} while (0)
+
+#define AuUnsupportMsg "This operation is not supported." \
+ " Please report this application to aufs-users ML."
+#define AuUnsupport(fmt, args...) do { \
+ AuErr(AuUnsupportMsg "\n" fmt, ##args); \
+ dump_stack(); \
+} while (0)
+
+#define AuTraceErr(e) do { \
+ if (unlikely((e) < 0)) \
+ AuDbg("err %d\n", (int)(e)); \
+} while (0)
+
+#define AuTraceErrPtr(p) do { \
+ if (IS_ERR(p)) \
+ AuDbg("err %ld\n", PTR_ERR(p)); \
+} while (0)
+
+/* dirty macros for debug print, use with "%.*s" and caution */
+#define AuLNPair(qstr) (qstr)->len, (qstr)->name
+#define AuDLNPair(d) AuLNPair(&(d)->d_name)
+
+/* ---------------------------------------------------------------------- */
+
+struct au_sbinfo;
+struct au_finfo;
+#ifdef CONFIG_AUFS_DEBUG
+extern char *au_plevel;
+struct au_nhash;
+void au_dpri_whlist(struct au_nhash *whlist);
+struct au_vdir;
+void au_dpri_vdir(struct au_vdir *vdir);
+void au_dpri_inode(struct inode *inode);
+void au_dpri_dentry(struct dentry *dentry);
+void au_dpri_file(struct file *filp);
+void au_dpri_sb(struct super_block *sb);
+
+void au_dbg_sleep_jiffy(int jiffy);
+void au_dbg_iattr(struct iattr *ia);
+
+void au_dbg_verify_dir_parent(struct dentry *dentry, unsigned int sigen);
+void au_dbg_verify_nondir_parent(struct dentry *dentry, unsigned int sigen);
+void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen);
+void au_dbg_verify_hf(struct au_finfo *finfo);
+void au_dbg_verify_kthread(void);
+
+int __init au_debug_init(void);
+void au_debug_sbinfo_init(struct au_sbinfo *sbinfo);
+#define AuDbgWhlist(w) do { \
+ AuDbg(#w "\n"); \
+ au_dpri_whlist(w); \
+} while (0)
+
+#define AuDbgVdir(v) do { \
+ AuDbg(#v "\n"); \
+ au_dpri_vdir(v); \
+} while (0)
+
+#define AuDbgInode(i) do { \
+ AuDbg(#i "\n"); \
+ au_dpri_inode(i); \
+} while (0)
+
+#define AuDbgDentry(d) do { \
+ AuDbg(#d "\n"); \
+ au_dpri_dentry(d); \
+} while (0)
+
+#define AuDbgFile(f) do { \
+ AuDbg(#f "\n"); \
+ au_dpri_file(f); \
+} while (0)
+
+#define AuDbgSb(sb) do { \
+ AuDbg(#sb "\n"); \
+ au_dpri_sb(sb); \
+} while (0)
+
+#define AuDbgSleep(sec) do { \
+ AuDbg("sleep %d sec\n", sec); \
+ ssleep(sec); \
+} while (0)
+
+#define AuDbgSleepJiffy(jiffy) do { \
+ AuDbg("sleep %d jiffies\n", jiffy); \
+ au_dbg_sleep_jiffy(jiffy); \
+} while (0)
+
+#define AuDbgIAttr(ia) do { \
+ AuDbg("ia_valid 0x%x\n", (ia)->ia_valid); \
+ au_dbg_iattr(ia); \
+} while (0)
+#else
+static inline void au_dbg_verify_dir_parent(struct dentry *dentry,
+ unsigned int sigen)
+{
+ /* empty */
+}
+static inline void au_dbg_verify_nondir_parent(struct dentry *dentry,
+ unsigned int sigen)
+{
+ /* empty */
+}
+static inline void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen)
+{
+ /* empty */
+}
+static inline void au_dbg_verify_hf(struct au_finfo *finfo)
+{
+ /* empty */
+}
+static inline void au_dbg_verify_kthread(void)
+{
+ /* empty */
+}
+
+static inline int au_debug_init(void)
+{
+ return 0;
+}
+static inline void au_debug_sbinfo_init(struct au_sbinfo *sbinfo)
+{
+ /* empty */
+}
+#define AuDbgWhlist(w) do {} while (0)
+#define AuDbgVdir(v) do {} while (0)
+#define AuDbgInode(i) do {} while (0)
+#define AuDbgDentry(d) do {} while (0)
+#define AuDbgFile(f) do {} while (0)
+#define AuDbgSb(sb) do {} while (0)
+#define AuDbgSleep(sec) do {} while (0)
+#define AuDbgSleepJiffy(jiffy) do {} while (0)
+#define AuDbgIAttr(ia) do {} while (0)
+#endif /* CONFIG_AUFS_DEBUG */
+
+/* ---------------------------------------------------------------------- */
+
+#ifdef CONFIG_AUFS_MAGIC_SYSRQ
+int __init au_sysrq_init(void);
+void au_sysrq_fin(void);
+
+#ifdef CONFIG_HW_CONSOLE
+#define au_dbg_blocked() do { \
+ WARN_ON(1); \
+ handle_sysrq('w', vc_cons[fg_console].d->vc_tty); \
+} while (0)
+#else
+#define au_dbg_blocked() do {} while (0)
+#endif
+
+#else
+static inline int au_sysrq_init(void)
+{
+ return 0;
+}
+#define au_sysrq_fin() do {} while (0)
+#define au_dbg_blocked() do {} while (0)
+#endif /* CONFIG_AUFS_MAGIC_SYSRQ */
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DEBUG_H__ */
diff --git a/fs/aufs/sysrq.c b/fs/aufs/sysrq.c
new file mode 100644
index 0000000..afec3af
--- /dev/null
+++ b/fs/aufs/sysrq.c
@@ -0,0 +1,105 @@
+/*
+ * 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.
+ */
+
+/*
+ * magic sysrq hanlder
+ */
+
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+/* #include <linux/sysrq.h> */
+#include "aufs.h"
+
+/* ---------------------------------------------------------------------- */
+
+static void sysrq_sb(struct super_block *sb)
+{
+ char *plevel;
+ struct au_sbinfo *sbinfo;
+ struct file *file;
+
+ plevel = au_plevel;
+ au_plevel = KERN_WARNING;
+ au_debug(1);
+
+ sbinfo = au_sbi(sb);
+ pr_warning("si=%lx\n", sysaufs_si_id(sbinfo));
+ pr_warning(AUFS_NAME ": superblock\n");
+ au_dpri_sb(sb);
+ pr_warning(AUFS_NAME ": root dentry\n");
+ au_dpri_dentry(sb->s_root);
+ pr_warning(AUFS_NAME ": root inode\n");
+ au_dpri_inode(sb->s_root->d_inode);
+#if 0
+ struct inode *i;
+ pr_warning(AUFS_NAME ": isolated inode\n");
+ list_for_each_entry(i, &sb->s_inodes, i_sb_list)
+ if (list_empty(&i->i_dentry))
+ au_dpri_inode(i);
+#endif
+ pr_warning(AUFS_NAME ": files\n");
+ list_for_each_entry(file, &sb->s_files, f_u.fu_list)
+ if (!special_file(file->f_dentry->d_inode->i_mode))
+ au_dpri_file(file);
+
+ au_plevel = plevel;
+ au_debug(0);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* module parameter */
+static char *aufs_sysrq_key = "a";
+module_param_named(sysrq, aufs_sysrq_key, charp, S_IRUGO);
+MODULE_PARM_DESC(sysrq, "MagicSysRq key for " AUFS_NAME);
+
+static void au_sysrq(int key, struct tty_struct *tty)
+{
+ struct kobject *kobj;
+ struct au_sbinfo *sbinfo;
+
+ /* spin_lock(&sysaufs_ket->list_lock); */
+ list_for_each_entry(kobj, &sysaufs_ket->list, entry) {
+ sbinfo = container_of(kobj, struct au_sbinfo, si_kobj);
+ sysrq_sb(sbinfo->si_sb);
+ }
+ /* spin_unlock(&sysaufs_ket->list_lock); */
+}
+
+static struct sysrq_key_op au_sysrq_op = {
+ .handler = au_sysrq,
+ .help_msg = "Aufs",
+ .action_msg = "Aufs",
+ .enable_mask = SYSRQ_ENABLE_DUMP
+};
+
+/* ---------------------------------------------------------------------- */
+
+int __init au_sysrq_init(void)
+{
+ int err;
+ char key;
+
+ err = -1;
+ key = *aufs_sysrq_key;
+ if ('a' <= key && key <= 'z')
+ err = register_sysrq_key(key, &au_sysrq_op);
+ if (unlikely(err))
+ AuErr("err %d, sysrq=%c\n", err, key);
+ return err;
+}
+
+void au_sysrq_fin(void)
+{
+ int err;
+ err = unregister_sysrq_key(*aufs_sysrq_key, &au_sysrq_op);
+ if (unlikely(err))
+ AuErr("err %d (ignored)\n", err);
+}
--
1.6.1.284.g5dc13

2009-03-09 03:32:42

by J. R. Okajima

Subject: [Aufs 24/25] aufs test for fstype

initial commit
judge the type of filesystem of branch

Signed-off-by: J. R. Okajima <[email protected]>
---
fs/aufs/fstype.h | 434 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/aufs/magic.mk | 52 +++++++
2 files changed, 486 insertions(+), 0 deletions(-)
create mode 100644 fs/aufs/fstype.h
create mode 100644 fs/aufs/magic.mk

diff --git a/fs/aufs/fstype.h b/fs/aufs/fstype.h
new file mode 100644
index 0000000..eac06aa
--- /dev/null
+++ b/fs/aufs/fstype.h
@@ -0,0 +1,434 @@
+/*
+ * 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.
+ */
+
+/*
+ * judging filesystem type
+ */
+
+#ifndef __AUFS_FSTYPE_H__
+#define __AUFS_FSTYPE_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/cramfs_fs.h>
+#include <linux/magic.h>
+#include <linux/romfs_fs.h>
+#include <linux/aufs_type.h>
+
+static inline int au_test_aufs(struct super_block *sb)
+{
+ return sb->s_magic == AUFS_SUPER_MAGIC;
+}
+
+static inline const char *au_sbtype(struct super_block *sb)
+{
+ return sb->s_type->name;
+}
+
+static inline int au_test_iso9660(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_ROMFS_FS) || defined(CONFIG_ROMFS_FS_MODULE)
+ return sb->s_magic == ROMFS_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_romfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_ISO9660_FS) || defined(CONFIG_ISO9660_FS_MODULE)
+ return sb->s_magic == ISOFS_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_cramfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_CRAMFS) || defined(CONFIG_CRAMFS_MODULE)
+ return sb->s_magic == CRAMFS_MAGIC;
+#endif
+ return 0;
+}
+
+static inline int au_test_nfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_NFS_FS) || defined(CONFIG_NFS_FS_MODULE)
+ return sb->s_magic == NFS_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_fuse(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_FUSE_FS) || defined(CONFIG_FUSE_FS_MODULE)
+ return sb->s_magic == FUSE_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_xfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_XFS_FS) || defined(CONFIG_XFS_FS_MODULE)
+ return sb->s_magic == XFS_SB_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_tmpfs(struct super_block *sb __maybe_unused)
+{
+#ifdef CONFIG_TMPFS
+ return sb->s_magic == TMPFS_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_ecryptfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_ECRYPT_FS) || defined(CONFIG_ECRYPT_FS_MODULE)
+ return !strcmp(au_sbtype(sb), "ecryptfs");
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_smbfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_SMB_FS) || defined(CONFIG_SMB_FS_MODULE)
+ return sb->s_magic == SMB_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_ocfs2(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_OCFS2_FS) || defined(CONFIG_OCFS2_FS_MODULE)
+ return sb->s_magic == OCFS2_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_ocfs2_dlmfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_OCFS2_FS_O2CB) || defined(CONFIG_OCFS2_FS_O2CB_MODULE)
+ return sb->s_magic == DLMFS_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_coda(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_CODA_FS) || defined(CONFIG_CODA_FS_MODULE)
+ return sb->s_magic == CODA_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_v9fs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_9P_FS) || defined(CONFIG_9P_FS_MODULE)
+ return sb->s_magic == V9FS_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_ext4(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_EXT4DEV_FS) || defined(CONFIG_EXT4DEV_FS_MODULE)
+ return sb->s_magic == EXT4_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_sysv(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_SYSV_FS) || defined(CONFIG_SYSV_FS_MODULE)
+ return !strcmp(au_sbtype(sb), "sysv");
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_ramfs(struct super_block *sb)
+{
+ return sb->s_magic == RAMFS_MAGIC;
+}
+
+static inline int au_test_ubifs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_UBIFS_FS) || defined(CONFIG_UBIFS_FS_MODULE)
+ return sb->s_magic == UBIFS_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_procfs(struct super_block *sb __maybe_unused)
+{
+#ifdef CONFIG_PROC_FS
+ return sb->s_magic == PROC_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_sysfs(struct super_block *sb __maybe_unused)
+{
+#ifdef CONFIG_SYSFS
+ return sb->s_magic == SYSFS_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_configfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_CONFIGFS_FS) || defined(CONFIG_CONFIGFS_FS_MODULE)
+ return sb->s_magic == CONFIGFS_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_minix(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_MINIX_FS) || defined(CONFIG_MINIX_FS_MODULE)
+ return sb->s_magic == MINIX3_SUPER_MAGIC
+ || sb->s_magic == MINIX2_SUPER_MAGIC
+ || sb->s_magic == MINIX2_SUPER_MAGIC2
+ || sb->s_magic == MINIX_SUPER_MAGIC
+ || sb->s_magic == MINIX_SUPER_MAGIC2;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_cifs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_CIFS_FS) || defined(CONFIGCIFS_FS_MODULE)
+ return sb->s_magic == CIFS_MAGIC_NUMBER;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_fat(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_FAT_FS) || defined(CONFIG_FAT_FS_MODULE)
+ return sb->s_magic == MSDOS_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_msdos(struct super_block *sb)
+{
+ return au_test_fat(sb);
+}
+
+static inline int au_test_vfat(struct super_block *sb)
+{
+ return au_test_fat(sb);
+}
+
+static inline int au_test_securityfs(struct super_block *sb __maybe_unused)
+{
+#ifdef CONFIG_SECURITYFS
+ return sb->s_magic == SECURITYFS_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_squashfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_SQUASHFS) || defined(CONFIG_SQUASHFS_MODULE)
+ return sb->s_magic == SQUASHFS_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_btrfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_BTRFS_FS) || defined(CONFIG_BTRFS_FS_MODULE)
+ return sb->s_magic == BTRFS_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+static inline int au_test_xenfs(struct super_block *sb __maybe_unused)
+{
+#if defined(CONFIG_XENFS) || defined(CONFIG_XENFS_MODULE)
+ return sb->s_magic == XENFS_SUPER_MAGIC;
+#else
+ return 0;
+#endif
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * they can't be an aufs branch.
+ */
+static inline int au_test_fs_unsuppoted(struct super_block *sb)
+{
+ return au_test_procfs(sb)
+ || au_test_sysfs(sb)
+ || au_test_configfs(sb)
+ || au_test_securityfs(sb)
+ || au_test_xenfs(sb)
+ || au_test_ramfs(sb)
+ /* || !strcmp(au_sbtype(sb), "unionfs") */
+ || au_test_aufs(sb); /* will be supported in next version */
+}
+
+/*
+ * If the filesystem supports NFS-export, then it has to support NULL as
+ * a nameidata parameter for ->create(), ->lookup() and ->d_revalidate().
+ * We can apply this principle when we handle a lower filesystem.
+ */
+static inline int au_test_fs_null_nd(struct super_block *sb)
+{
+ return !!sb->s_export_op;
+}
+
+static inline int au_test_fs_remote(struct super_block *sb)
+{
+ return !au_test_tmpfs(sb)
+ && !(sb->s_type->fs_flags & FS_REQUIRES_DEV);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * Note: these functions (below) are created after reading ->getattr() in all
+ * filesystems under linux/fs. it means we have to do so in every update...
+ */
+
+/*
+ * some filesystems require getattr to refresh the inode attributes before
+ * referencing.
+ * in most cases, we can rely on the inode attribute in NFS (or every remote fs)
+ * and leave the work for d_revalidate()
+ */
+static inline int au_test_fs_refresh_iattr(struct super_block *sb)
+{
+ return au_test_nfs(sb)
+ || au_test_fuse(sb)
+ /* || au_test_smbfs(sb) */ /* untested */
+ /* || au_test_ocfs2(sb) */ /* untested */
+ /* || au_test_btrfs(sb) */ /* untested */
+ /* || au_test_coda(sb) */ /* untested */
+ /* || au_test_v9fs(sb) */ /* untested */
+ ;
+}
+
+/*
+ * filesystems which don't maintain i_size or i_blocks.
+ */
+static inline int au_test_fs_bad_iattr_size(struct super_block *sb)
+{
+ return au_test_xfs(sb)
+ /* || au_test_ext4(sb) */ /* untested */
+ /* || au_test_ocfs2(sb) */ /* untested */
+ /* || au_test_ocfs2_dlmfs(sb) */ /* untested */
+ /* || au_test_sysv(sb) */ /* untested */
+ /* || au_test_ramfs(sb)*/ /* unsupported */
+ /* || au_test_ubifs(sb) */ /* untested */
+ /* || au_test_minix(sb) */ /* untested */
+ ;
+}
+
+/*
+ * filesystems which don't store the correct value in some of their inode
+ * attributes.
+ */
+static inline int au_test_fs_bad_iattr(struct super_block *sb)
+{
+ return au_test_fs_bad_iattr_size(sb)
+ /* || au_test_cifs(sb) */ /* untested */
+ || au_test_fat(sb)
+ || au_test_msdos(sb)
+ || au_test_vfat(sb);
+}
+
+/*
+ * filesystems which sets S_NOATIME and S_NOCMTIME.
+ */
+static inline int au_test_fs_notime(struct super_block *sb)
+{
+ return au_test_nfs(sb)
+ || au_test_fuse(sb)
+ /* || au_test_cifs(sb) */ /* untested */
+ /* || au_test_ubifs(sb) */ /* untested */
+ ;
+}
+
+/*
+ * filesystems which requires replacing i_mapping.
+ */
+static inline int au_test_fs_bad_mapping(struct super_block *sb)
+{
+ return au_test_fuse(sb);
+}
+
+/* temporary support for i#1 in cramfs */
+static inline int au_test_fs_unique_ino(struct inode *inode)
+{
+ if (au_test_cramfs(inode->i_sb))
+ return inode->i_ino != 1;
+ return 1;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * the filesystem where the xino files placed must support i/o after unlink and
+ * maintain i_size and i_blocks.
+ */
+static inline int au_test_fs_bad_xino(struct super_block *sb)
+{
+ return au_test_fs_remote(sb)
+ || au_test_fs_bad_iattr_size(sb)
+ || !au_test_fs_null_nd(sb) /* to keep xino code simple */
+ /* don't want unnecessary work for xino */
+ || au_test_aufs(sb)
+ || au_test_ecryptfs(sb);
+}
+
+static inline int au_test_fs_trunc_xino(struct super_block *sb)
+{
+ return au_test_tmpfs(sb);
+}
+
+/*
+ * test if the @sb is real-readonly.
+ */
+static inline int au_test_fs_rr(struct super_block *sb)
+{
+ return au_test_squashfs(sb)
+ || au_test_iso9660(sb)
+ || au_test_cramfs(sb)
+ || au_test_romfs(sb);
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_FSTYPE_H__ */
diff --git a/fs/aufs/magic.mk b/fs/aufs/magic.mk
new file mode 100644
index 0000000..83d613c
--- /dev/null
+++ b/fs/aufs/magic.mk
@@ -0,0 +1,52 @@
+
+# defined in ${srctree}/fs/fuse/inode.c
+# tristate
+ifdef CONFIG_FUSE_FS
+ccflags-y += -DFUSE_SUPER_MAGIC=0x65735546
+endif
+
+# defined in ${srctree}/fs/ocfs2/ocfs2_fs.h
+# tristate
+ifdef CONFIG_OCFS2_FS
+ccflags-y += -DOCFS2_SUPER_MAGIC=0x7461636f
+endif
+
+# defined in ${srctree}/fs/ocfs2/dlm/userdlm.h
+# tristate
+ifdef CONFIG_OCFS2_FS_O2CB
+ccflags-y += -DDLMFS_MAGIC=0x76a9f425
+endif
+
+# defined in ${srctree}/fs/ramfs/inode.c
+# always true
+ccflags-y += -DRAMFS_MAGIC=0x858458f6
+
+# defined in ${srctree}/fs/cifs/cifsfs.c
+# tristate
+ifdef CONFIG_CIFS_FS
+ccflags-y += -DCIFS_MAGIC_NUMBER=0xFF534D42
+endif
+
+# defined in ${srctree}/fs/xfs/xfs_sb.h
+# tristate
+ifdef CONFIG_XFS_FS
+ccflags-y += -DXFS_SB_MAGIC=0x58465342
+endif
+
+# defined in ${srctree}/fs/configfs/mount.c
+# tristate
+ifdef CONFIG_CONFIGFS_FS
+ccflags-y += -DCONFIGFS_MAGIC=0x62656570
+endif
+
+# defined in ${srctree}/fs/9p/v9fs.h
+# tristate
+ifdef CONFIG_9P_FS
+ccflags-y += -DV9FS_MAGIC=0x01021997
+endif
+
+# defined in ${srctree}/fs/ubifs/ubifs.h
+# tristate
+ifdef CONFIG_UBIFS_FS
+ccflags-y += -DUBIFS_SUPER_MAGIC=0x24051905
+endif
--
1.6.1.284.g5dc13

2009-03-09 03:33:00

by J. R. Okajima

Subject: [Aufs 21/25] aufs sysfs entries

initial commit
sysfs entries, compiled only when CONFIG_SYSFS is enabled

Signed-off-by: J. R. Okajima <[email protected]>
---
fs/aufs/sysfs.c | 308 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 308 insertions(+), 0 deletions(-)
create mode 100644 fs/aufs/sysfs.c

diff --git a/fs/aufs/sysfs.c b/fs/aufs/sysfs.c
new file mode 100644
index 0000000..b03c2f7
--- /dev/null
+++ b/fs/aufs/sysfs.c
@@ -0,0 +1,308 @@
+/*
+ * 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.
+ */
+
+/*
+ * sysfs interface
+ */
+
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/sysfs.h>
+#include "aufs.h"
+
+#ifdef CONFIG_AUFS_DEBUG
+static ssize_t debug_show(struct kobject *kobj __maybe_unused,
+ struct kobj_attribute *attr __maybe_unused,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", au_debug_test());
+}
+
+static ssize_t debug_store(struct kobject *kobj __maybe_unused,
+ struct kobj_attribute *attr __maybe_unused,
+ const char *buf, size_t sz)
+{
+ if (unlikely(!sz || (*buf != '0' && *buf != '1')))
+ return -EOPNOTSUPP;
+
+ if (*buf == '0')
+ au_debug(0);
+ else if (*buf == '1')
+ au_debug(1);
+ return sz;
+}
+
+static struct kobj_attribute au_debug_attr = __ATTR(debug, S_IRUGO | S_IWUSR,
+ debug_show, debug_store);
+#endif
+
+static struct attribute *au_attr[] = {
+#ifdef CONFIG_AUFS_DEBUG
+ &au_debug_attr.attr,
+#endif
+ NULL, /* need to NULL terminate the list of attributes */
+};
+
+static struct attribute_group sysaufs_attr_group_body = {
+ .attrs = au_attr
+};
+
+struct attribute_group *sysaufs_attr_group = &sysaufs_attr_group_body;
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * they are copied from linux/lib/kobject.c,
+ * and will be exported in the future.
+ */
+static ssize_t au_attr_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ struct kobj_attribute *kattr;
+ ssize_t ret = -EIO;
+
+ kattr = container_of(attr, struct kobj_attribute, attr);
+ if (kattr->show)
+ ret = kattr->show(kobj, kattr, buf);
+ return ret;
+}
+
+#ifdef CONFIG_AUFS_DEBUG
+static ssize_t au_attr_store(struct kobject *kobj, struct attribute *attr,
+ const char *buf, size_t count)
+{
+ struct kobj_attribute *kattr;
+ ssize_t ret = -EIO;
+
+ kattr = container_of(attr, struct kobj_attribute, attr);
+ if (kattr->store)
+ ret = kattr->store(kobj, kattr, buf, count);
+ return ret;
+}
+#endif
+
+static struct sysfs_ops sysaufs_ops = {
+ .show = au_attr_show,
+#ifdef CONFIG_AUFS_DEBUG
+ .store = au_attr_store
+#endif
+};
+
+static struct kobj_type sysaufs_ktype_body = {
+ .sysfs_ops = &sysaufs_ops
+};
+struct kobj_type *sysaufs_ktype = &sysaufs_ktype_body;
+
+/* ---------------------------------------------------------------------- */
+
+static int sysaufs_sbi_xi(struct seq_file *seq, struct file *xf,
+ struct kstat *st)
+{
+ int err;
+
+ err = vfs_getattr(xf->f_vfsmnt, xf->f_dentry, st);
+ if (!err) {
+ seq_printf(seq, "%llux%lu %lld",
+ st->blocks, st->blksize, (long long)st->size);
+ seq_putc(seq, '\n');
+ } else
+ seq_printf(seq, "err %d\n", err);
+
+ return err;
+}
+
+int sysaufs_si_xino(struct seq_file *seq, struct super_block *sb)
+{
+ int err;
+ aufs_bindex_t bend, bindex;
+ struct kstat st;
+ struct au_sbinfo *sbinfo;
+ struct file *xf;
+
+ err = 0;
+ sbinfo = au_sbi(sb);
+ if (!au_opt_test(au_mntflags(sb), XINO))
+ goto out; /* success */
+
+ xf = sbinfo->si_xib;
+ err = au_xino_path(seq, xf);
+ seq_putc(seq, '\n');
+ if (!err)
+ err = sysaufs_sbi_xi(seq, xf, &st);
+
+ bend = au_sbend(sb);
+ for (bindex = 0; !err && bindex <= bend; bindex++) {
+ xf = au_sbr(sb, bindex)->br_xino.xi_file;
+ if (!xf)
+ continue;
+
+ seq_printf(seq, "%d: ", bindex);
+ err = vfs_getattr(xf->f_vfsmnt, xf->f_dentry, &st);
+ if (!err) {
+ seq_printf(seq, "%ld, %llux%lu %lld",
+ (long)file_count(xf), st.blocks, st.blksize,
+ (long long)st.size);
+ seq_putc(seq, '\n');
+ } else
+ seq_printf(seq, "err %d\n", err);
+ }
+
+ out:
+ return err;
+}
+
+/*
+ * the lifetime of branch is independent from the entry under sysfs.
+ * sysfs handles the lifetime of the entry, and never call ->show() after it is
+ * unlinked.
+ */
+#define SysaufsBr_PREFIX "br"
+static int sysaufs_sbi_br(struct seq_file *seq, struct super_block *sb,
+ aufs_bindex_t bindex)
+{
+ int err;
+ struct path path;
+ struct dentry *root;
+ struct au_branch *br;
+
+ err = -ENOENT;
+ if (unlikely(au_sbend(sb) < bindex))
+ goto out;
+
+ err = 0;
+ root = sb->s_root;
+ di_read_lock_parent(root, !AuLock_IR);
+ br = au_sbr(sb, bindex);
+ path.mnt = br->br_mnt;
+ path.dentry = au_h_dptr(root, bindex);
+ au_seq_path(seq, &path);
+ di_read_unlock(root, !AuLock_IR);
+ seq_printf(seq, "=%s\n", au_optstr_br_perm(br->br_perm));
+
+ out:
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static struct seq_file *au_seq(char *p, ssize_t len)
+{
+ struct seq_file *seq;
+
+ seq = kzalloc(sizeof(*seq), GFP_NOFS);
+ if (seq) {
+ /* mutex_init(&seq.lock); */
+ seq->buf = p;
+ seq->size = len;
+ return seq; /* success */
+ }
+
+ seq = ERR_PTR(-ENOMEM);
+ return seq;
+}
+
+/* todo: file size may exceed PAGE_SIZE */
+ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ ssize_t err;
+ long l;
+ struct au_sbinfo *sbinfo;
+ struct super_block *sb;
+ struct seq_file *seq;
+ char *name;
+ struct attribute **cattr;
+
+ sbinfo = container_of(kobj, struct au_sbinfo, si_kobj);
+ sb = sbinfo->si_sb;
+ si_noflush_read_lock(sb);
+
+ seq = au_seq(buf, PAGE_SIZE);
+ err = PTR_ERR(seq);
+ if (IS_ERR(seq))
+ goto out;
+
+ name = (void *)attr->name;
+ cattr = sysaufs_si_attrs;
+ while (*cattr) {
+ if (!strcmp(name, (*cattr)->name)) {
+ err = container_of(*cattr, struct sysaufs_si_attr, attr)
+ ->show(seq, sb);
+ goto out_seq;
+ }
+ cattr++;
+ }
+
+ if (!strncmp(name, SysaufsBr_PREFIX, sizeof(SysaufsBr_PREFIX) - 1)) {
+ name += sizeof(SysaufsBr_PREFIX) - 1;
+ err = strict_strtol(name, 10, &l);
+ if (!err)
+ err = sysaufs_sbi_br(seq, sb, (aufs_bindex_t)l);
+ goto out_seq;
+ }
+ BUG();
+
+ out_seq:
+ if (!err) {
+ err = seq->count;
+ /* sysfs limit */
+ if (unlikely(err == PAGE_SIZE))
+ err = -EFBIG;
+ }
+ kfree(seq);
+ out:
+ si_read_unlock(sb);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void sysaufs_br_init(struct au_branch *br)
+{
+ br->br_attr.name = br->br_name;
+ br->br_attr.mode = S_IRUGO;
+ br->br_attr.owner = THIS_MODULE;
+}
+
+void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex)
+{
+ struct au_sbinfo *sbinfo;
+ aufs_bindex_t bend;
+
+ if (!sysaufs_brs)
+ return;
+
+ sbinfo = au_sbi(sb);
+ bend = au_sbend(sb);
+ for (; bindex <= bend; bindex++)
+ sysfs_remove_file(&sbinfo->si_kobj,
+ &au_sbr(sb, bindex)->br_attr);
+}
+
+void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex)
+{
+ int err;
+ aufs_bindex_t bend;
+ struct kobject *kobj;
+ struct au_branch *br;
+
+ if (!sysaufs_brs)
+ return;
+
+ kobj = &au_sbi(sb)->si_kobj;
+ bend = au_sbend(sb);
+ for (; bindex <= bend; bindex++) {
+ br = au_sbr(sb, bindex);
+ snprintf(br->br_name, sizeof(br->br_name),
+ SysaufsBr_PREFIX "%d", bindex);
+ err = sysfs_create_file(kobj, &br->br_attr);
+ if (unlikely(err))
+ AuWarn("failed %s under sysfs(%d)\n", br->br_name, err);
+ }
+}
--
1.6.1.284.g5dc13

2009-03-09 03:33:23

by J. R. Okajima

Subject: [Aufs 18/25] aufs direcotry

initial commit
directory operations
virtual or vertical(stacked) directory

Signed-off-by: J. R. Okajima <[email protected]>
---
fs/aufs/dir.c | 493 +++++++++++++++++++++++++++++++++++
fs/aufs/dir.h | 104 ++++++++
fs/aufs/vdir.c | 776 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 1373 insertions(+), 0 deletions(-)
create mode 100644 fs/aufs/dir.c
create mode 100644 fs/aufs/dir.h
create mode 100644 fs/aufs/vdir.c

diff --git a/fs/aufs/dir.c b/fs/aufs/dir.c
new file mode 100644
index 0000000..44c78c9
--- /dev/null
+++ b/fs/aufs/dir.c
@@ -0,0 +1,493 @@
+/*
+ * 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.
+ */
+
+/*
+ * directory operations
+ */
+
+#include <linux/fs_stack.h>
+#include "aufs.h"
+
+void au_add_nlink(struct inode *dir, struct inode *h_dir)
+{
+ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode));
+
+ dir->i_nlink += h_dir->i_nlink - 2;
+ if (h_dir->i_nlink < 2)
+ dir->i_nlink += 2;
+}
+
+void au_sub_nlink(struct inode *dir, struct inode *h_dir)
+{
+ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode));
+
+ dir->i_nlink -= h_dir->i_nlink - 2;
+ if (h_dir->i_nlink < 2)
+ dir->i_nlink -= 2;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int reopen_dir(struct file *file)
+{
+ int err;
+ unsigned int flags;
+ aufs_bindex_t bindex, btail, bstart;
+ struct dentry *dentry, *h_dentry;
+ struct file *h_file;
+
+ /* open all lower dirs */
+ dentry = file->f_dentry;
+ bstart = au_dbstart(dentry);
+ for (bindex = au_fbstart(file); bindex < bstart; bindex++)
+ au_set_h_fptr(file, bindex, NULL);
+ au_set_fbstart(file, bstart);
+
+ btail = au_dbtaildir(dentry);
+ for (bindex = au_fbend(file); btail < bindex; bindex--)
+ au_set_h_fptr(file, bindex, NULL);
+ au_set_fbend(file, btail);
+
+ flags = file->f_flags;
+ for (bindex = bstart; bindex <= btail; bindex++) {
+ h_dentry = au_h_dptr(dentry, bindex);
+ if (!h_dentry)
+ continue;
+ h_file = au_h_fptr(file, bindex);
+ if (h_file)
+ continue;
+
+ h_file = au_h_open(dentry, bindex, flags, file);
+ err = PTR_ERR(h_file);
+ if (IS_ERR(h_file))
+ goto out; /* close all? */
+ au_set_h_fptr(file, bindex, h_file);
+ }
+ au_update_figen(file);
+ /* todo: necessary? */
+ /* file->f_ra = h_file->f_ra; */
+ err = 0;
+
+ out:
+ return err;
+}
+
+static int do_open_dir(struct file *file, int flags)
+{
+ int err;
+ aufs_bindex_t bindex, btail;
+ struct dentry *dentry, *h_dentry;
+ struct file *h_file;
+
+ err = 0;
+ dentry = file->f_dentry;
+ au_set_fvdir_cache(file, NULL);
+ au_fi(file)->fi_maintain_plink = 0;
+ file->f_version = dentry->d_inode->i_version;
+ bindex = au_dbstart(dentry);
+ au_set_fbstart(file, bindex);
+ btail = au_dbtaildir(dentry);
+ au_set_fbend(file, btail);
+ for (; !err && bindex <= btail; bindex++) {
+ h_dentry = au_h_dptr(dentry, bindex);
+ if (!h_dentry)
+ continue;
+
+ h_file = au_h_open(dentry, bindex, flags, file);
+ if (IS_ERR(h_file)) {
+ err = PTR_ERR(h_file);
+ break;
+ }
+ au_set_h_fptr(file, bindex, h_file);
+ }
+ au_update_figen(file);
+ /* todo: necessary? */
+ /* file->f_ra = h_file->f_ra; */
+ if (!err)
+ return 0; /* success */
+
+ /* close all */
+ for (bindex = au_fbstart(file); bindex <= btail; bindex++)
+ au_set_h_fptr(file, bindex, NULL);
+ au_set_fbstart(file, -1);
+ au_set_fbend(file, -1);
+ return err;
+}
+
+static int aufs_open_dir(struct inode *inode __maybe_unused,
+ struct file *file)
+{
+ return au_do_open(file, do_open_dir);
+}
+
+static int aufs_release_dir(struct inode *inode __maybe_unused,
+ struct file *file)
+{
+ struct au_vdir *vdir_cache;
+ struct super_block *sb;
+ struct au_sbinfo *sbinfo;
+
+ sb = file->f_dentry->d_sb;
+ si_noflush_read_lock(sb);
+ fi_write_lock(file);
+ vdir_cache = au_fvdir_cache(file);
+ if (vdir_cache)
+ au_vdir_free(vdir_cache);
+ if (au_fi(file)->fi_maintain_plink) {
+ sbinfo = au_sbi(sb);
+ au_fclr_si(sbinfo, MAINTAIN_PLINK);
+ wake_up_all(&sbinfo->si_plink_wq);
+ }
+ fi_write_unlock(file);
+ au_finfo_fin(file);
+ si_read_unlock(sb);
+ return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync)
+{
+ int err;
+ aufs_bindex_t bend, bindex;
+ struct inode *inode;
+ struct super_block *sb;
+
+ err = 0;
+ sb = dentry->d_sb;
+ inode = dentry->d_inode;
+ IMustLock(inode);
+ bend = au_dbend(dentry);
+ for (bindex = au_dbstart(dentry); !err && bindex <= bend; bindex++) {
+ struct path h_path;
+ struct inode *h_inode;
+ struct file_operations *fop;
+
+ if (au_test_ro(sb, bindex, inode))
+ continue;
+ h_path.dentry = au_h_dptr(dentry, bindex);
+ if (!h_path.dentry)
+ continue;
+ h_inode = h_path.dentry->d_inode;
+ if (!h_inode)
+ continue;
+
+ /* no mnt_want_write() */
+ /* cf. fs/nsfd/vfs.c and fs/nfsd/nfs4recover.c */
+ /* todo: inotiry fired? */
+ h_path.mnt = au_sbr_mnt(sb, bindex);
+ mutex_lock(&h_inode->i_mutex);
+ fop = (void *)h_inode->i_fop;
+ err = filemap_fdatawrite(h_inode->i_mapping);
+ if (!err && fop && fop->fsync)
+ err = fop->fsync(NULL, h_path.dentry, datasync);
+ if (!err)
+ err = filemap_fdatawrite(h_inode->i_mapping);
+ if (!err)
+ vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/
+ mutex_unlock(&h_inode->i_mutex);
+ }
+
+ return err;
+}
+
+static int au_do_fsync_dir(struct file *file, int datasync)
+{
+ int err;
+ aufs_bindex_t bend, bindex;
+ struct file *h_file;
+ struct super_block *sb;
+ struct inode *inode;
+ struct mutex *h_mtx;
+
+ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1);
+ if (unlikely(err))
+ goto out;
+
+ sb = file->f_dentry->d_sb;
+ inode = file->f_dentry->d_inode;
+ bend = au_fbend(file);
+ for (bindex = au_fbstart(file); !err && bindex <= bend; bindex++) {
+ h_file = au_h_fptr(file, bindex);
+ if (!h_file || au_test_ro(sb, bindex, inode))
+ continue;
+
+ err = vfs_fsync(h_file, h_file->f_dentry, datasync);
+ if (!err) {
+ h_mtx = &h_file->f_dentry->d_inode->i_mutex;
+ mutex_lock(h_mtx);
+ vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL);
+ /*ignore*/
+ mutex_unlock(h_mtx);
+ }
+ }
+
+ out:
+ return err;
+}
+
+/*
+ * @file may be NULL
+ */
+static int aufs_fsync_dir(struct file *file, struct dentry *dentry,
+ int datasync)
+{
+ int err;
+ struct super_block *sb;
+
+ IMustLock(dentry->d_inode);
+
+ err = 0;
+ sb = dentry->d_sb;
+ si_noflush_read_lock(sb);
+ if (file)
+ err = au_do_fsync_dir(file, datasync);
+ else {
+ di_write_lock_child(dentry);
+ err = au_do_fsync_dir_no_file(dentry, datasync);
+ }
+ au_cpup_attr_timesizes(dentry->d_inode);
+ di_write_unlock(dentry);
+ if (file)
+ fi_write_unlock(file);
+
+ si_read_unlock(sb);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int aufs_readdir(struct file *file, void *dirent, filldir_t filldir)
+{
+ int err;
+ struct dentry *dentry;
+ struct inode *inode;
+ struct super_block *sb;
+
+ dentry = file->f_dentry;
+ inode = dentry->d_inode;
+ IMustLock(inode);
+
+ sb = dentry->d_sb;
+ si_read_lock(sb, AuLock_FLUSH);
+ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1);
+ if (unlikely(err))
+ goto out;
+ err = au_vdir_init(file);
+ di_downgrade_lock(dentry, AuLock_IR);
+ if (unlikely(err))
+ goto out_unlock;
+
+ err = au_vdir_fill_de(file, dirent, filldir);
+ fsstack_copy_attr_atime(inode, au_h_iptr(inode, au_ibstart(inode)));
+
+ out_unlock:
+ di_read_unlock(dentry, AuLock_IR);
+ fi_write_unlock(file);
+ out:
+ si_read_unlock(sb);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+#define AuTestEmpty_WHONLY 1
+#define AuTestEmpty_CALLED (1 << 2)
+#define au_ftest_testempty(flags, name) ((flags) & AuTestEmpty_##name)
+#define au_fset_testempty(flags, name) { (flags) |= AuTestEmpty_##name; }
+#define au_fclr_testempty(flags, name) { (flags) &= ~AuTestEmpty_##name; }
+
+struct test_empty_arg {
+ struct au_nhash *whlist;
+ unsigned int flags;
+ int err;
+ aufs_bindex_t bindex;
+};
+
+static int test_empty_cb(void *__arg, const char *__name, int namelen,
+ loff_t offset __maybe_unused, u64 ino __maybe_unused,
+ unsigned int d_type __maybe_unused)
+{
+ struct test_empty_arg *arg = __arg;
+ char *name = (void *)__name;
+
+ arg->err = 0;
+ au_fset_testempty(arg->flags, CALLED);
+ /* smp_mb(); */
+ if (name[0] == '.'
+ && (namelen == 1 || (name[1] == '.' && namelen == 2)))
+ goto out; /* success */
+
+ if (namelen <= AUFS_WH_PFX_LEN
+ || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) {
+ if (au_ftest_testempty(arg->flags, WHONLY)
+ && !au_nhash_test_known_wh(arg->whlist, name, namelen))
+ arg->err = -ENOTEMPTY;
+ goto out;
+ }
+
+ name += AUFS_WH_PFX_LEN;
+ namelen -= AUFS_WH_PFX_LEN;
+ if (!au_nhash_test_known_wh(arg->whlist, name, namelen))
+ arg->err = au_nhash_append_wh
+ (arg->whlist, name, namelen, arg->bindex);
+
+ out:
+ /* smp_mb(); */
+ AuTraceErr(arg->err);
+ return arg->err;
+}
+
+static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg)
+{
+ int err;
+ struct file *h_file;
+
+ h_file = au_h_open(dentry, arg->bindex,
+ O_RDONLY | O_NONBLOCK | O_DIRECTORY | O_LARGEFILE,
+ /*file*/NULL);
+ err = PTR_ERR(h_file);
+ if (IS_ERR(h_file))
+ goto out;
+
+ err = 0;
+ if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE)
+ && !h_file->f_dentry->d_inode->i_nlink)
+ goto out_put;
+
+ do {
+ arg->err = 0;
+ au_fclr_testempty(arg->flags, CALLED);
+ /* smp_mb(); */
+ err = vfsub_readdir(h_file, test_empty_cb, arg);
+ if (err >= 0)
+ err = arg->err;
+ } while (!err && au_ftest_testempty(arg->flags, CALLED));
+
+ out_put:
+ fput(h_file);
+ au_sbr_put(dentry->d_sb, arg->bindex);
+ out:
+ return err;
+}
+
+struct do_test_empty_args {
+ int *errp;
+ struct dentry *dentry;
+ struct test_empty_arg *arg;
+};
+
+static void call_do_test_empty(void *args)
+{
+ struct do_test_empty_args *a = args;
+ *a->errp = do_test_empty(a->dentry, a->arg);
+}
+
+static int sio_test_empty(struct dentry *dentry, struct test_empty_arg *arg)
+{
+ int err, wkq_err;
+ struct dentry *h_dentry;
+ struct inode *h_inode;
+
+ h_dentry = au_h_dptr(dentry, arg->bindex);
+ h_inode = h_dentry->d_inode;
+ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
+ err = au_test_h_perm_sio(h_inode, MAY_EXEC | MAY_READ);
+ mutex_unlock(&h_inode->i_mutex);
+ if (!err)
+ err = do_test_empty(dentry, arg);
+ else {
+ struct do_test_empty_args args = {
+ .errp = &err,
+ .dentry = dentry,
+ .arg = arg
+ };
+ unsigned int flags = arg->flags;
+
+ wkq_err = au_wkq_wait(call_do_test_empty, &args);
+ if (unlikely(wkq_err))
+ err = wkq_err;
+ arg->flags = flags;
+ }
+
+ return err;
+}
+
+int au_test_empty_lower(struct dentry *dentry)
+{
+ int err;
+ aufs_bindex_t bindex, bstart, btail;
+ struct test_empty_arg arg;
+ struct au_nhash *whlist;
+
+ whlist = au_nhash_new(GFP_NOFS);
+ err = PTR_ERR(whlist);
+ if (IS_ERR(whlist))
+ goto out;
+
+ bstart = au_dbstart(dentry);
+ arg.whlist = whlist;
+ arg.flags = 0;
+ arg.bindex = bstart;
+ err = do_test_empty(dentry, &arg);
+ if (unlikely(err))
+ goto out_whlist;
+
+ au_fset_testempty(arg.flags, WHONLY);
+ btail = au_dbtaildir(dentry);
+ for (bindex = bstart + 1; !err && bindex <= btail; bindex++) {
+ struct dentry *h_dentry;
+
+ h_dentry = au_h_dptr(dentry, bindex);
+ if (h_dentry && h_dentry->d_inode) {
+ arg.bindex = bindex;
+ err = do_test_empty(dentry, &arg);
+ }
+ }
+
+ out_whlist:
+ au_nhash_del(whlist);
+ out:
+ return err;
+}
+
+int au_test_empty(struct dentry *dentry, struct au_nhash *whlist)
+{
+ int err;
+ struct test_empty_arg arg;
+ aufs_bindex_t bindex, btail;
+
+ err = 0;
+ arg.whlist = whlist;
+ arg.flags = AuTestEmpty_WHONLY;
+ btail = au_dbtaildir(dentry);
+ for (bindex = au_dbstart(dentry); !err && bindex <= btail; bindex++) {
+ struct dentry *h_dentry;
+
+ h_dentry = au_h_dptr(dentry, bindex);
+ if (h_dentry && h_dentry->d_inode) {
+ arg.bindex = bindex;
+ err = sio_test_empty(dentry, &arg);
+ }
+ }
+
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct file_operations aufs_dir_fop = {
+ .read = generic_read_dir,
+ .readdir = aufs_readdir,
+ .unlocked_ioctl = aufs_ioctl_dir,
+ .open = aufs_open_dir,
+ .release = aufs_release_dir,
+ .flush = aufs_flush,
+ .fsync = aufs_fsync_dir
+};
diff --git a/fs/aufs/dir.h b/fs/aufs/dir.h
new file mode 100644
index 0000000..1e20ca3
--- /dev/null
+++ b/fs/aufs/dir.h
@@ -0,0 +1,104 @@
+/*
+ * 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.
+ */
+
+/*
+ * directory operations
+ */
+
+#ifndef __AUFS_DIR_H__
+#define __AUFS_DIR_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/aufs_type.h>
+
+/* ---------------------------------------------------------------------- */
+
+/* need to be faster and smaller */
+
+#define AuSize_DEBLK 512
+#define AuSize_NHASH 32
+
+typedef char au_vdir_deblk_t[AuSize_DEBLK];
+
+struct au_nhash {
+ struct hlist_head heads[AuSize_NHASH];
+};
+
+struct au_vdir_destr {
+ unsigned char len;
+ char name[0];
+} __packed;
+
+struct au_vdir_dehstr {
+ struct hlist_node hash;
+ struct au_vdir_destr *str;
+};
+
+struct au_vdir_de {
+ ino_t de_ino;
+ unsigned char de_type;
+ /* caution: packed */
+ struct au_vdir_destr de_str;
+} __packed;
+
+struct au_vdir_wh {
+ struct hlist_node wh_hash;
+ aufs_bindex_t wh_bindex;
+ struct au_vdir_destr wh_str;
+} __packed;
+
+union au_vdir_deblk_p {
+ unsigned char *p;
+ au_vdir_deblk_t *deblk;
+ struct au_vdir_de *de;
+};
+
+struct au_vdir {
+ au_vdir_deblk_t **vd_deblk;
+ int vd_nblk;
+ struct {
+ int i;
+ union au_vdir_deblk_p p;
+ } vd_last;
+
+ unsigned long vd_version;
+ unsigned long vd_jiffy;
+};
+
+/* ---------------------------------------------------------------------- */
+
+/* dir.c */
+extern struct file_operations aufs_dir_fop;
+void au_add_nlink(struct inode *dir, struct inode *h_dir);
+void au_sub_nlink(struct inode *dir, struct inode *h_dir);
+int au_test_empty_lower(struct dentry *dentry);
+int au_test_empty(struct dentry *dentry, struct au_nhash *whlist);
+
+/* vdir.c */
+struct au_nhash *au_nhash_new(gfp_t gfp);
+void au_nhash_del(struct au_nhash *nhash);
+void au_nhash_init(struct au_nhash *nhash);
+void au_nhash_move(struct au_nhash *dst, struct au_nhash *src);
+void au_nhash_fin(struct au_nhash *nhash);
+int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt,
+ int limit);
+int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int namelen);
+int au_nhash_append_wh(struct au_nhash *whlist, char *name, int namelen,
+ aufs_bindex_t bindex);
+void au_vdir_free(struct au_vdir *vdir);
+int au_vdir_init(struct file *file);
+int au_vdir_fill_de(struct file *file, void *dirent, filldir_t filldir);
+
+/* ioctl.c */
+long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg);
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DIR_H__ */
diff --git a/fs/aufs/vdir.c b/fs/aufs/vdir.c
new file mode 100644
index 0000000..b0580c2
--- /dev/null
+++ b/fs/aufs/vdir.c
@@ -0,0 +1,776 @@
+/*
+ * 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.
+ */
+
+/*
+ * virtual or vertical directory
+ */
+
+#include "aufs.h"
+
+static int calc_size(int namelen)
+{
+ int sz;
+ const int mask = sizeof(ino_t) - 1;
+
+ BUILD_BUG_ON(sizeof(ino_t) != sizeof(long));
+
+ sz = sizeof(struct au_vdir_de) + namelen;
+ if (sz & mask) {
+ sz += sizeof(ino_t);
+ sz &= ~mask;
+ }
+
+ AuDebugOn(sz % sizeof(ino_t));
+ return sz;
+}
+
+static int set_deblk_end(union au_vdir_deblk_p *p,
+ union au_vdir_deblk_p *deblk_end)
+{
+ if (calc_size(0) <= deblk_end->p - p->p) {
+ p->de->de_str.len = 0;
+ /* smp_mb(); */
+ return 0;
+ }
+ return -1; /* error */
+}
+
+/* returns true or false */
+static int is_deblk_end(union au_vdir_deblk_p *p,
+ union au_vdir_deblk_p *deblk_end)
+{
+ if (calc_size(0) <= deblk_end->p - p->p)
+ return !p->de->de_str.len;
+ return 1;
+}
+
+static au_vdir_deblk_t *last_deblk(struct au_vdir *vdir)
+{
+ return vdir->vd_deblk[vdir->vd_nblk - 1];
+}
+
+void au_nhash_init(struct au_nhash *nhash)
+{
+ int i;
+ struct hlist_head *heads;
+
+ heads = nhash->heads;
+ for (i = 0; i < AuSize_NHASH; i++)
+ INIT_HLIST_HEAD(heads++);
+}
+
+struct au_nhash *au_nhash_new(gfp_t gfp)
+{
+ struct au_nhash *nhash;
+
+ nhash = kmalloc(sizeof(*nhash), gfp);
+ if (nhash) {
+ au_nhash_init(nhash);
+ return nhash;
+ }
+ return ERR_PTR(-ENOMEM);
+}
+
+void au_nhash_del(struct au_nhash *nhash)
+{
+ au_nhash_fin(nhash);
+ kfree(nhash);
+}
+
+void au_nhash_move(struct au_nhash *dst, struct au_nhash *src)
+{
+ int i;
+ struct hlist_head *dsth, *srch;
+
+ *dst = *src;
+ srch = src->heads;
+ dsth = dst->heads;
+ for (i = 0; i < AuSize_NHASH; i++) {
+ if (dsth->first)
+ dsth->first->pprev = &dsth->first;
+ dsth++;
+ INIT_HLIST_HEAD(srch++);
+ }
+ /* smp_mb(); */
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_nhash_fin(struct au_nhash *whlist)
+{
+ int i;
+ struct hlist_head *head;
+ struct au_vdir_wh *tpos;
+ struct hlist_node *pos, *n;
+
+ head = whlist->heads;
+ for (i = 0; i < AuSize_NHASH; i++) {
+ hlist_for_each_entry_safe(tpos, pos, n, head, wh_hash) {
+ /* hlist_del(pos); */
+ kfree(tpos);
+ }
+ head++;
+ }
+}
+
+int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt,
+ int limit)
+{
+ int n, i;
+ struct hlist_head *head;
+ struct au_vdir_wh *tpos;
+ struct hlist_node *pos;
+
+ n = 0;
+ head = whlist->heads;
+ for (i = 0; i < AuSize_NHASH; i++) {
+ hlist_for_each_entry(tpos, pos, head, wh_hash)
+ if (tpos->wh_bindex == btgt && ++n > limit)
+ return 1;
+ head++;
+ }
+ return 0;
+}
+
+static unsigned int au_name_hash(const unsigned char *name, unsigned int len)
+{
+ return full_name_hash(name, len) % AuSize_NHASH;
+}
+
+/* returns found or not */
+int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int namelen)
+{
+ struct hlist_head *head;
+ struct au_vdir_wh *tpos;
+ struct hlist_node *pos;
+ struct au_vdir_destr *str;
+
+ head = whlist->heads + au_name_hash(name, namelen);
+ hlist_for_each_entry(tpos, pos, head, wh_hash) {
+ str = &tpos->wh_str;
+ AuDbg("%.*s\n", str->len, str->name);
+ if (str->len == namelen && !memcmp(str->name, name, namelen))
+ return 1;
+ }
+ return 0;
+}
+
+int au_nhash_append_wh(struct au_nhash *whlist, char *name, int namelen,
+ aufs_bindex_t bindex)
+{
+ int err;
+ struct au_vdir_destr *str;
+ struct au_vdir_wh *wh;
+
+ err = -ENOMEM;
+ wh = kmalloc(sizeof(*wh) + namelen, GFP_NOFS);
+ if (unlikely(!wh))
+ goto out;
+
+ err = 0;
+ wh->wh_bindex = bindex;
+ str = &wh->wh_str;
+ str->len = namelen;
+ memcpy(str->name, name, namelen);
+ hlist_add_head(&wh->wh_hash,
+ whlist->heads + au_name_hash(name, namelen));
+ /* smp_mb(); */
+
+ out:
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_vdir_free(struct au_vdir *vdir)
+{
+ au_vdir_deblk_t **deblk;
+
+ deblk = vdir->vd_deblk;
+ while (vdir->vd_nblk--)
+ kfree(*deblk++);
+ kfree(vdir->vd_deblk);
+ au_cache_free_vdir(vdir);
+}
+
+static int append_deblk(struct au_vdir *vdir)
+{
+ int err, sz, i;
+ au_vdir_deblk_t **o;
+ union au_vdir_deblk_p p, deblk_end;
+
+ err = -ENOMEM;
+ sz = sizeof(*o) * vdir->vd_nblk;
+ o = au_kzrealloc(vdir->vd_deblk, sz, sz + sizeof(*o), GFP_NOFS);
+ if (unlikely(!o))
+ goto out;
+
+ vdir->vd_deblk = o;
+ p.deblk = kmalloc(sizeof(*p.deblk), GFP_NOFS);
+ if (p.deblk) {
+ i = vdir->vd_nblk++;
+ vdir->vd_deblk[i] = p.deblk;
+ vdir->vd_last.i = i;
+ vdir->vd_last.p.p = p.p;
+ deblk_end.deblk = p.deblk + 1;
+ err = set_deblk_end(&p, &deblk_end);
+ }
+
+ out:
+ return err;
+}
+
+static struct au_vdir *alloc_vdir(void)
+{
+ struct au_vdir *vdir;
+ int err;
+
+ err = -ENOMEM;
+ vdir = au_cache_alloc_vdir();
+ if (unlikely(!vdir))
+ goto out;
+
+ vdir->vd_deblk = kzalloc(sizeof(*vdir->vd_deblk), GFP_NOFS);
+ if (unlikely(!vdir->vd_deblk))
+ goto out_free;
+
+ vdir->vd_nblk = 0;
+ vdir->vd_version = 0;
+ vdir->vd_jiffy = 0;
+ err = append_deblk(vdir);
+ if (!err)
+ return vdir; /* success */
+
+ kfree(vdir->vd_deblk);
+
+ out_free:
+ au_cache_free_vdir(vdir);
+ out:
+ vdir = ERR_PTR(err);
+ return vdir;
+}
+
+static int reinit_vdir(struct au_vdir *vdir)
+{
+ int err;
+ union au_vdir_deblk_p p, deblk_end;
+
+ while (vdir->vd_nblk > 1) {
+ kfree(vdir->vd_deblk[vdir->vd_nblk - 1]);
+ vdir->vd_deblk[vdir->vd_nblk - 1] = NULL;
+ vdir->vd_nblk--;
+ }
+ p.deblk = vdir->vd_deblk[0];
+ deblk_end.deblk = p.deblk + 1;
+ err = set_deblk_end(&p, &deblk_end);
+ vdir->vd_version = 0;
+ vdir->vd_jiffy = 0;
+ vdir->vd_last.i = 0;
+ vdir->vd_last.p.deblk = vdir->vd_deblk[0];
+ /* smp_mb(); */
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void free_dehlist(struct au_nhash *dehlist)
+{
+ int i;
+ struct hlist_head *head;
+ struct au_vdir_dehstr *tpos;
+ struct hlist_node *pos, *n;
+
+ head = dehlist->heads;
+ for (i = 0; i < AuSize_NHASH; i++) {
+ hlist_for_each_entry_safe(tpos, pos, n, head, hash) {
+ /* hlist_del(pos); */
+ au_cache_free_dehstr(tpos);
+ }
+ head++;
+ }
+}
+
+/* returns found(true) or not */
+static int test_known(struct au_nhash *delist, char *name, int namelen)
+{
+ struct hlist_head *head;
+ struct au_vdir_dehstr *tpos;
+ struct hlist_node *pos;
+ struct au_vdir_destr *str;
+
+ head = delist->heads + au_name_hash(name, namelen);
+ hlist_for_each_entry(tpos, pos, head, hash) {
+ str = tpos->str;
+ AuDbg("%.*s\n", str->len, str->name);
+ if (str->len == namelen && !memcmp(str->name, name, namelen))
+ return 1;
+ }
+ return 0;
+
+}
+
+static int append_de(struct au_vdir *vdir, char *name, int namelen, ino_t ino,
+ unsigned int d_type, struct au_nhash *delist)
+{
+ int err, sz;
+ union au_vdir_deblk_p p, *room, deblk_end;
+ struct au_vdir_dehstr *dehstr;
+
+ p.deblk = last_deblk(vdir);
+ deblk_end.deblk = p.deblk + 1;
+ room = &vdir->vd_last.p;
+ AuDebugOn(room->p < p.p || deblk_end.p <= room->p
+ || !is_deblk_end(room, &deblk_end));
+
+ sz = calc_size(namelen);
+ if (unlikely(sz > deblk_end.p - room->p)) {
+ err = append_deblk(vdir);
+ if (unlikely(err))
+ goto out;
+
+ p.deblk = last_deblk(vdir);
+ deblk_end.deblk = p.deblk + 1;
+ /* smp_mb(); */
+ AuDebugOn(room->p != p.p);
+ }
+
+ err = -ENOMEM;
+ dehstr = au_cache_alloc_dehstr();
+ if (unlikely(!dehstr))
+ goto out;
+
+ dehstr->str = &room->de->de_str;
+ hlist_add_head(&dehstr->hash,
+ delist->heads + au_name_hash(name, namelen));
+ room->de->de_ino = ino;
+ room->de->de_type = d_type;
+ room->de->de_str.len = namelen;
+ memcpy(room->de->de_str.name, name, namelen);
+
+ err = 0;
+ room->p += sz;
+ if (unlikely(set_deblk_end(room, &deblk_end)))
+ err = append_deblk(vdir);
+ /* smp_mb(); */
+
+ out:
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+ unsigned int d_type, ino_t *ino)
+{
+ int err;
+ struct mutex *mtx;
+ const int isdir = (d_type == DT_DIR);
+
+ /* prevent hardlinks from race condition */
+ mtx = NULL;
+ if (!isdir) {
+ mtx = &au_sbr(sb, bindex)->br_xino.xi_nondir_mtx;
+ mutex_lock(mtx);
+ }
+ err = au_xino_read(sb, bindex, h_ino, ino);
+ if (unlikely(err))
+ goto out;
+
+ if (!*ino) {
+ err = -EIO;
+ *ino = au_xino_new_ino(sb);
+ if (unlikely(!*ino))
+ goto out;
+ err = au_xino_write(sb, bindex, h_ino, *ino);
+ if (unlikely(err))
+ goto out;
+ }
+
+ out:
+ if (!isdir)
+ mutex_unlock(mtx);
+ return err;
+}
+
+#define AuFillVdir_CALLED 1
+#define au_ftest_fillvdir(flags, name) ((flags) & AuFillVdir_##name)
+#define au_fset_fillvdir(flags, name) { (flags) |= AuFillVdir_##name; }
+#define au_fclr_fillvdir(flags, name) { (flags) &= ~AuFillVdir_##name; }
+
+struct fillvdir_arg {
+ struct file *file;
+ struct au_vdir *vdir;
+ struct au_nhash *delist;
+ struct au_nhash *whlist;
+ aufs_bindex_t bindex;
+ unsigned int flags;
+ int err;
+};
+
+static int fillvdir(void *__arg, const char *__name, int namelen,
+ loff_t offset __maybe_unused, u64 h_ino,
+ unsigned int d_type)
+{
+ struct fillvdir_arg *arg = __arg;
+ char *name = (void *)__name;
+ struct super_block *sb;
+ struct au_nhash *delist, *whlist;
+ ino_t ino;
+ aufs_bindex_t bindex, bend;
+
+ bend = arg->bindex;
+ arg->err = 0;
+ au_fset_fillvdir(arg->flags, CALLED);
+ /* smp_mb(); */
+ if (namelen <= AUFS_WH_PFX_LEN
+ || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) {
+ delist = arg->delist;
+ for (bindex = 0; bindex < bend; bindex++)
+ if (test_known(delist++, name, namelen)
+ || au_nhash_test_known_wh(arg->whlist + bindex,
+ name, namelen))
+ goto out; /* already exists or whiteouted */
+
+ ino = 1; /* why does gcc warn? */
+ sb = arg->file->f_dentry->d_sb;
+ arg->err = au_ino(sb, bend, h_ino, d_type, &ino);
+ if (!arg->err)
+ arg->err = append_de(arg->vdir, name, namelen, ino,
+ d_type, arg->delist + bend);
+ } else {
+ name += AUFS_WH_PFX_LEN;
+ namelen -= AUFS_WH_PFX_LEN;
+ whlist = arg->whlist;
+ for (bindex = 0; bindex < bend; bindex++)
+ if (au_nhash_test_known_wh(whlist++, name, namelen))
+ goto out; /* already whiteouted */
+
+ ino = 1; /* dummy */
+ if (!arg->err)
+ arg->err = au_nhash_append_wh
+ (arg->whlist + bend, name, namelen, bend);
+ }
+
+ out:
+ if (!arg->err)
+ arg->vdir->vd_jiffy = jiffies;
+ /* smp_mb(); */
+ AuTraceErr(arg->err);
+ return arg->err;
+}
+
+static int au_do_read_vdir(struct fillvdir_arg *arg)
+{
+ int err;
+ loff_t offset;
+ aufs_bindex_t bend, bindex, bstart;
+ struct file *hf, *file;
+ struct au_nhash *delist, *whlist;
+
+ err = -ENOMEM;
+ bend = au_fbend(arg->file);
+ arg->delist = kmalloc(sizeof(*arg->delist) * (bend + 1), GFP_NOFS);
+ if (unlikely(!arg->delist))
+ goto out;
+ arg->whlist = kmalloc(sizeof(*arg->whlist) * (bend + 1), GFP_NOFS);
+ if (unlikely(!arg->whlist))
+ goto out_delist;
+
+ err = 0;
+ delist = arg->delist;
+ whlist = arg->whlist;
+ for (bindex = 0; bindex <= bend; bindex++) {
+ au_nhash_init(delist++);
+ au_nhash_init(whlist++);
+ }
+
+ arg->flags = 0;
+ file = arg->file;
+ bstart = au_fbstart(file);
+ for (bindex = bstart; !err && bindex <= bend; bindex++) {
+ hf = au_h_fptr(file, bindex);
+ if (!hf)
+ continue;
+
+ offset = vfsub_llseek(hf, 0, SEEK_SET);
+ err = offset;
+ if (unlikely(offset))
+ break;
+
+ arg->bindex = bindex;
+ do {
+ arg->err = 0;
+ au_fclr_fillvdir(arg->flags, CALLED);
+ /* smp_mb(); */
+ err = vfsub_readdir(hf, fillvdir, arg);
+ if (err >= 0)
+ err = arg->err;
+ } while (!err && au_ftest_fillvdir(arg->flags, CALLED));
+ }
+
+ delist = arg->delist + bstart;
+ whlist = arg->whlist + bstart;
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ free_dehlist(delist++);
+ au_nhash_fin(whlist++);
+ }
+ kfree(arg->whlist);
+
+ out_delist:
+ kfree(arg->delist);
+ out:
+ return err;
+}
+
+static int read_vdir(struct file *file, int may_read)
+{
+ int err;
+ unsigned long expire;
+ unsigned char do_read;
+ struct fillvdir_arg arg;
+ struct inode *inode;
+ struct au_vdir *vdir, *allocated;
+
+ err = 0;
+ inode = file->f_dentry->d_inode;
+ IMustLock(inode);
+ allocated = NULL;
+ do_read = 0;
+ expire = au_sbi(inode->i_sb)->si_rdcache;
+ vdir = au_ivdir(inode);
+ if (!vdir) {
+ do_read = 1;
+ vdir = alloc_vdir();
+ err = PTR_ERR(vdir);
+ if (IS_ERR(vdir))
+ goto out;
+ err = 0;
+ allocated = vdir;
+ } else if (may_read
+ && (inode->i_version != vdir->vd_version
+ || time_after(jiffies, vdir->vd_jiffy + expire))) {
+ do_read = 1;
+ err = reinit_vdir(vdir);
+ if (unlikely(err))
+ goto out;
+ }
+
+ if (!do_read)
+ return 0; /* success */
+
+ arg.file = file;
+ arg.vdir = vdir;
+ err = au_do_read_vdir(&arg);
+ if (!err) {
+ /* file->f_pos = 0; */
+ vdir->vd_version = inode->i_version;
+ vdir->vd_last.i = 0;
+ vdir->vd_last.p.deblk = vdir->vd_deblk[0];
+ if (allocated)
+ au_set_ivdir(inode, allocated);
+ } else if (allocated)
+ au_vdir_free(allocated);
+
+ out:
+ return err;
+}
+
+static int copy_vdir(struct au_vdir *tgt, struct au_vdir *src)
+{
+ int err, i, rerr, n;
+
+ AuDebugOn(tgt->vd_nblk != 1);
+
+ err = -ENOMEM;
+ if (tgt->vd_nblk < src->vd_nblk) {
+ au_vdir_deblk_t **p;
+
+ p = au_kzrealloc(tgt->vd_deblk, sizeof(*p) * tgt->vd_nblk,
+ sizeof(*p) * src->vd_nblk, GFP_NOFS);
+ if (unlikely(!p))
+ goto out;
+ tgt->vd_deblk = p;
+ }
+
+ tgt->vd_nblk = src->vd_nblk;
+ n = src->vd_nblk;
+ memcpy(tgt->vd_deblk[0], src->vd_deblk[0], AuSize_DEBLK);
+ /* tgt->vd_last.i = 0; */
+ /* tgt->vd_last.p.deblk = tgt->vd_deblk[0]; */
+ tgt->vd_version = src->vd_version;
+ tgt->vd_jiffy = src->vd_jiffy;
+
+ for (i = 1; i < n; i++) {
+ tgt->vd_deblk[i] = kmalloc(AuSize_DEBLK, GFP_NOFS);
+ if (tgt->vd_deblk[i])
+ memcpy(tgt->vd_deblk[i], src->vd_deblk[i],
+ AuSize_DEBLK);
+ else
+ goto out;
+ }
+ /* smp_mb(); */
+ return 0; /* success */
+
+ out:
+ rerr = reinit_vdir(tgt);
+ BUG_ON(rerr);
+ return err;
+}
+
+int au_vdir_init(struct file *file)
+{
+ int err;
+ struct inode *inode;
+ struct au_vdir *vdir_cache, *allocated;
+
+ err = read_vdir(file, !file->f_pos);
+ if (unlikely(err))
+ goto out;
+
+ allocated = NULL;
+ vdir_cache = au_fvdir_cache(file);
+ if (!vdir_cache) {
+ vdir_cache = alloc_vdir();
+ err = PTR_ERR(vdir_cache);
+ if (IS_ERR(vdir_cache))
+ goto out;
+ allocated = vdir_cache;
+ } else if (!file->f_pos && vdir_cache->vd_version != file->f_version) {
+ err = reinit_vdir(vdir_cache);
+ if (unlikely(err))
+ goto out;
+ } else
+ return 0; /* success */
+
+ inode = file->f_dentry->d_inode;
+ err = copy_vdir(vdir_cache, au_ivdir(inode));
+ if (!err) {
+ file->f_version = inode->i_version;
+ if (allocated)
+ au_set_fvdir_cache(file, allocated);
+ } else if (allocated)
+ au_vdir_free(allocated);
+
+ out:
+ return err;
+}
+
+static loff_t calc_offset(struct au_vdir *vdir)
+{
+ loff_t offset;
+ union au_vdir_deblk_p p;
+
+ p.deblk = vdir->vd_deblk[vdir->vd_last.i];
+ offset = vdir->vd_last.p.p - p.p;
+ offset += sizeof(*p.deblk) * vdir->vd_last.i;
+ return offset;
+}
+
+/* returns true or false */
+static int seek_vdir(struct file *file)
+{
+ int valid, i, n;
+ loff_t offset;
+ union au_vdir_deblk_p p, deblk_end;
+ struct au_vdir *vdir_cache;
+
+ valid = 1;
+ vdir_cache = au_fvdir_cache(file);
+ offset = calc_offset(vdir_cache);
+ AuDbg("offset %lld\n", offset);
+ if (file->f_pos == offset)
+ goto out;
+
+ vdir_cache->vd_last.i = 0;
+ vdir_cache->vd_last.p.deblk = vdir_cache->vd_deblk[0];
+ if (!file->f_pos)
+ goto out;
+
+ valid = 0;
+ i = file->f_pos / AuSize_DEBLK;
+ AuDbg("i %d\n", i);
+ if (i >= vdir_cache->vd_nblk)
+ goto out;
+
+ n = vdir_cache->vd_nblk;
+ for (; i < n; i++) {
+ p.deblk = vdir_cache->vd_deblk[i];
+ deblk_end.deblk = p.deblk + 1;
+ offset = i;
+ offset *= AuSize_DEBLK;
+ while (!is_deblk_end(&p, &deblk_end) && offset < file->f_pos) {
+ int l;
+
+ l = calc_size(p.de->de_str.len);
+ offset += l;
+ p.p += l;
+ }
+ if (!is_deblk_end(&p, &deblk_end)) {
+ valid = 1;
+ vdir_cache->vd_last.i = i;
+ vdir_cache->vd_last.p = p;
+ break;
+ }
+ }
+
+ out:
+ /* smp_mb(); */
+ AuTraceErr(!valid);
+ return valid;
+}
+
+int au_vdir_fill_de(struct file *file, void *dirent, filldir_t filldir)
+{
+ int err, l;
+ union au_vdir_deblk_p deblk_end;
+ struct au_vdir *vdir_cache;
+ struct au_vdir_de *de;
+
+ BUILD_BUG_ON(AuSize_DEBLK < NAME_MAX || PAGE_SIZE < AuSize_DEBLK);
+
+ vdir_cache = au_fvdir_cache(file);
+ if (!seek_vdir(file))
+ return 0;
+
+ while (1) {
+ deblk_end.deblk
+ = vdir_cache->vd_deblk[vdir_cache->vd_last.i] + 1;
+ while (!is_deblk_end(&vdir_cache->vd_last.p, &deblk_end)) {
+ de = vdir_cache->vd_last.p.de;
+ AuDbg("%.*s, off%lld, i%lu, dt%d\n",
+ de->de_str.len, de->de_str.name,
+ file->f_pos, (unsigned long)de->de_ino,
+ de->de_type);
+ err = filldir(dirent, de->de_str.name, de->de_str.len,
+ file->f_pos, de->de_ino, de->de_type);
+ if (unlikely(err)) {
+ AuTraceErr(err);
+ /* todo: ignore the error caused by udba? */
+ /* return err; */
+ return 0;
+ }
+
+ l = calc_size(de->de_str.len);
+ vdir_cache->vd_last.p.p += l;
+ file->f_pos += l;
+ }
+ if (vdir_cache->vd_last.i < vdir_cache->vd_nblk - 1) {
+ vdir_cache->vd_last.i++;
+ vdir_cache->vd_last.p.deblk
+ = vdir_cache->vd_deblk[vdir_cache->vd_last.i];
+ file->f_pos = sizeof(*vdir_cache->vd_last.p.deblk)
+ * vdir_cache->vd_last.i;
+ continue;
+ }
+ break;
+ }
+
+ /* smp_mb(); */
+ return 0;
+}
--
1.6.1.284.g5dc13

2009-03-09 03:33:54

by J. R. Okajima

Subject: [Aufs 13/25] aufs whiteout

initial commit
whiteout for logical deletion and opaque directory

Signed-off-by: J. R. Okajima <[email protected]>
---
fs/aufs/whout.c | 1010 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/aufs/whout.h | 78 +++++
2 files changed, 1088 insertions(+), 0 deletions(-)
create mode 100644 fs/aufs/whout.c
create mode 100644 fs/aufs/whout.h

diff --git a/fs/aufs/whout.c b/fs/aufs/whout.c
new file mode 100644
index 0000000..f2343d2
--- /dev/null
+++ b/fs/aufs/whout.c
@@ -0,0 +1,1010 @@
+/*
+ * 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.
+ */
+
+/*
+ * whiteout for logical deletion and opaque directory
+ */
+
+#include <linux/fs.h>
+#include "aufs.h"
+
+#define WH_MASK S_IRUGO
+
+/*
+ * If a directory contains this file, then it is opaque. We start with the
+ * .wh. flag so that it is blocked by lookup.
+ */
+static struct qstr diropq_name = {
+ .name = AUFS_WH_DIROPQ,
+ .len = sizeof(AUFS_WH_DIROPQ) - 1
+};
+
+/*
+ * generate whiteout name, which is NOT terminated by NULL.
+ * @name: original d_name.name
+ * @len: original d_name.len
+ * @wh: whiteout qstr
+ * returns zero when succeeds, otherwise error.
+ * succeeded value as wh->name should be freed by kfree().
+ */
+int au_wh_name_alloc(struct qstr *wh, const struct qstr *name)
+{
+ char *p;
+
+ if (unlikely(name->len > PATH_MAX - AUFS_WH_PFX_LEN))
+ return -ENAMETOOLONG;
+
+ wh->len = name->len + AUFS_WH_PFX_LEN;
+ p = kmalloc(wh->len, GFP_NOFS);
+ wh->name = p;
+ if (p) {
+ memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN);
+ memcpy(p + AUFS_WH_PFX_LEN, name->name, name->len);
+ /* smp_mb(); */
+ return 0;
+ }
+ return -ENOMEM;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * test if the @wh_name exists under @h_parent.
+ * @try_sio specifies the necessary of super-io.
+ */
+int au_wh_test(struct dentry *h_parent, struct qstr *wh_name,
+ struct au_branch *br, int try_sio)
+{
+ int err;
+ struct dentry *wh_dentry;
+ struct inode *h_dir;
+
+ h_dir = h_parent->d_inode;
+ if (!try_sio)
+ wh_dentry = au_lkup_one(wh_name, h_parent, br, /*nd*/NULL);
+ else
+ wh_dentry = au_sio_lkup_one(wh_name, h_parent, br);
+ err = PTR_ERR(wh_dentry);
+ if (IS_ERR(wh_dentry))
+ goto out;
+
+ err = 0;
+ if (!wh_dentry->d_inode)
+ goto out_wh; /* success */
+
+ err = 1;
+ if (S_ISREG(wh_dentry->d_inode->i_mode))
+ goto out_wh; /* success */
+
+ err = -EIO;
+ AuIOErr("%.*s Invalid whiteout entry type 0%o.\n",
+ AuDLNPair(wh_dentry), wh_dentry->d_inode->i_mode);
+
+ out_wh:
+ dput(wh_dentry);
+ out:
+ return err;
+}
+
+/*
+ * test if the @h_dentry sets opaque or not.
+ */
+int au_diropq_test(struct dentry *h_dentry, struct au_branch *br)
+{
+ int err;
+ struct inode *h_dir;
+
+ h_dir = h_dentry->d_inode;
+ err = au_wh_test(h_dentry, &diropq_name, br,
+ au_test_h_perm_sio(h_dir, MAY_EXEC));
+ return err;
+}
+
+/*
+ * returns a negative dentry whose name is unique and temporary.
+ */
+struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br,
+ struct qstr *prefix)
+{
+#define HEX_LEN 4
+ struct dentry *dentry;
+ int i;
+ char defname[AUFS_WH_PFX_LEN * 2 + DNAME_INLINE_LEN_MIN + 1
+ + HEX_LEN + 1], *name, *p;
+ static unsigned short cnt;
+ struct qstr qs;
+
+ name = defname;
+ qs.len = sizeof(defname) - DNAME_INLINE_LEN_MIN + prefix->len - 1;
+ if (unlikely(prefix->len > DNAME_INLINE_LEN_MIN)) {
+ dentry = ERR_PTR(-ENAMETOOLONG);
+ if (unlikely(qs.len >= PATH_MAX))
+ goto out;
+ dentry = ERR_PTR(-ENOMEM);
+ name = kmalloc(qs.len + 1, GFP_NOFS);
+ if (unlikely(!name))
+ goto out;
+ }
+
+ /* doubly whiteout-ed */
+ memcpy(name, AUFS_WH_PFX AUFS_WH_PFX, AUFS_WH_PFX_LEN * 2);
+ p = name + AUFS_WH_PFX_LEN * 2;
+ memcpy(p, prefix->name, prefix->len);
+ p += prefix->len;
+ *p++ = '.';
+ AuDebugOn(name + qs.len + 1 - p <= HEX_LEN);
+
+ qs.name = name;
+ for (i = 0; i < 3; i++) {
+ sprintf(p, "%.*d", HEX_LEN, cnt++);
+ dentry = au_sio_lkup_one(&qs, h_parent, br);
+ if (IS_ERR(dentry) || !dentry->d_inode)
+ goto out_name;
+ dput(dentry);
+ }
+ /* AuWarn("could not get random name\n"); */
+ dentry = ERR_PTR(-EEXIST);
+ AuDbg("%.*s\n", AuLNPair(&qs));
+ BUG();
+
+ out_name:
+ if (name != defname)
+ kfree(name);
+ out:
+ return dentry;
+#undef HEX_LEN
+}
+
+/*
+ * rename the @h_dentry on @br to the whiteouted temporary name.
+ */
+int au_whtmp_ren(struct dentry *h_dentry, struct au_branch *br)
+{
+ int err;
+ struct path h_path = {
+ .mnt = br->br_mnt
+ };
+ struct inode *h_dir;
+ struct dentry *h_parent;
+
+ h_parent = h_dentry->d_parent; /* dir inode is locked */
+ h_dir = h_parent->d_inode;
+ IMustLock(h_dir);
+
+ h_path.dentry = au_whtmp_lkup(h_parent, br, &h_dentry->d_name);
+ err = PTR_ERR(h_path.dentry);
+ if (IS_ERR(h_path.dentry))
+ goto out;
+
+ /* under the same dir, no need to lock_rename() */
+ err = vfsub_rename(h_dir, h_dentry, h_dir, &h_path);
+ AuTraceErr(err);
+ dput(h_path.dentry);
+
+ out:
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * functions for removing a whiteout
+ */
+
+static int do_unlink_wh(struct inode *h_dir, struct path *h_path)
+{
+ int force;
+
+ /*
+ * forces superio when the dir has a sticky bit.
+ * this may be a violation of unix fs semantics.
+ */
+ force = (h_dir->i_mode & S_ISVTX)
+ && h_path->dentry->d_inode->i_uid != current_fsuid();
+ return vfsub_unlink(h_dir, h_path, force);
+}
+
+int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path,
+ struct dentry *dentry)
+{
+ int err;
+
+ err = do_unlink_wh(h_dir, h_path);
+ if (!err && dentry)
+ au_set_dbwh(dentry, -1);
+
+ return err;
+}
+
+static int unlink_wh_name(struct dentry *h_parent, struct qstr *wh,
+ struct au_branch *br)
+{
+ int err;
+ struct path h_path = {
+ .mnt = br->br_mnt
+ };
+
+ err = 0;
+ h_path.dentry = au_lkup_one(wh, h_parent, br, /*nd*/NULL);
+ if (IS_ERR(h_path.dentry))
+ err = PTR_ERR(h_path.dentry);
+ else {
+ if (h_path.dentry->d_inode
+ && S_ISREG(h_path.dentry->d_inode->i_mode))
+ err = do_unlink_wh(h_parent->d_inode, &h_path);
+ dput(h_path.dentry);
+ }
+
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * initialize/clean whiteout for a branch
+ */
+
+static void au_wh_clean(struct inode *h_dir, struct path *whpath,
+ const int isdir)
+{
+ int err;
+
+ if (!whpath->dentry->d_inode)
+ return;
+
+ err = mnt_want_write(whpath->mnt);
+ if (!err) {
+ if (isdir)
+ err = vfsub_rmdir(h_dir, whpath);
+ else
+ err = vfsub_unlink(h_dir, whpath, /*force*/0);
+ mnt_drop_write(whpath->mnt);
+ }
+ if (unlikely(err))
+ AuWarn("failed removing %.*s (%d), ignored.\n",
+ AuDLNPair(whpath->dentry), err);
+}
+
+static int test_linkable(struct dentry *h_root)
+{
+ struct inode *h_dir = h_root->d_inode;
+
+ if (h_dir->i_op->link)
+ return 0;
+
+ AuErr("%.*s (%s) doesn't support link(2), use noplink and rw+nolwh\n",
+ AuDLNPair(h_root), au_sbtype(h_root->d_sb));
+ return -ENOSYS;
+}
+
+/* todo: should this mkdir be done in /sbin/mount.aufs helper? */
+static int au_whdir(struct inode *h_dir, struct path *path)
+{
+ int err;
+
+ err = -EEXIST;
+ if (!path->dentry->d_inode) {
+ int mode = S_IRWXU;
+
+ if (au_test_nfs(path->dentry->d_sb))
+ mode |= S_IXUGO;
+ err = mnt_want_write(path->mnt);
+ if (!err) {
+ err = vfsub_mkdir(h_dir, path, mode);
+ mnt_drop_write(path->mnt);
+ }
+ } else if (S_ISDIR(path->dentry->d_inode->i_mode))
+ err = 0;
+ else
+ AuErr("unknown %.*s exists\n", AuDLNPair(path->dentry));
+
+ return err;
+}
+
+struct au_wh_base {
+ const struct qstr *name;
+ struct dentry *dentry;
+};
+
+static void au_wh_init_ro(struct inode *h_dir, struct au_wh_base base[],
+ struct path *h_path)
+{
+ h_path->dentry = base[AuBrWh_BASE].dentry;
+ au_wh_clean(h_dir, h_path, /*isdir*/0);
+ h_path->dentry = base[AuBrWh_PLINK].dentry;
+ au_wh_clean(h_dir, h_path, /*isdir*/1);
+ h_path->dentry = base[AuBrWh_ORPH].dentry;
+ au_wh_clean(h_dir, h_path, /*isdir*/1);
+}
+
+/*
+ * returns tri-state,
+ * minus: error, caller should print the mesage
+ * zero: succuess
+ * plus: error, caller should NOT print the mesage
+ */
+static int au_wh_init_rw_nolink(struct dentry *h_root, struct au_wbr *wbr,
+ int do_plink, struct au_wh_base base[],
+ struct path *h_path)
+{
+ int err;
+ struct inode *h_dir;
+
+ h_dir = h_root->d_inode;
+ h_path->dentry = base[AuBrWh_BASE].dentry;
+ au_wh_clean(h_dir, h_path, /*isdir*/0);
+ h_path->dentry = base[AuBrWh_PLINK].dentry;
+ if (do_plink) {
+ err = test_linkable(h_root);
+ if (unlikely(err)) {
+ err = 1;
+ goto out;
+ }
+
+ err = au_whdir(h_dir, h_path);
+ if (unlikely(err))
+ goto out;
+ wbr->wbr_plink = dget(base[AuBrWh_PLINK].dentry);
+ } else
+ au_wh_clean(h_dir, h_path, /*isdir*/1);
+ h_path->dentry = base[AuBrWh_ORPH].dentry;
+ err = au_whdir(h_dir, h_path);
+ if (unlikely(err))
+ goto out;
+ wbr->wbr_orph = dget(base[AuBrWh_ORPH].dentry);
+
+ out:
+ return err;
+}
+
+/*
+ * for the moment, aufs supports the branch filesystem which does not support
+ * link(2). testing on FAT which does not support i_op->setattr() fully either,
+ * copyup failed. finally, such filesystem will not be used as the writable
+ * branch.
+ *
+ * returns tri-state, see above.
+ */
+static int au_wh_init_rw(struct dentry *h_root, struct au_wbr *wbr,
+ int do_plink, struct au_wh_base base[],
+ struct path *h_path)
+{
+ int err;
+ struct inode *h_dir;
+
+ err = test_linkable(h_root);
+ if (unlikely(err)) {
+ err = 1;
+ goto out;
+ }
+
+ /*
+ * todo: should this create be done in /sbin/mount.aufs helper?
+ */
+ err = -EEXIST;
+ h_dir = h_root->d_inode;
+ if (!base[AuBrWh_BASE].dentry->d_inode) {
+ err = mnt_want_write(h_path->mnt);
+ if (!err) {
+ h_path->dentry = base[AuBrWh_BASE].dentry;
+ err = vfsub_create(h_dir, h_path, WH_MASK);
+ mnt_drop_write(h_path->mnt);
+ }
+ } else if (S_ISREG(base[AuBrWh_BASE].dentry->d_inode->i_mode))
+ err = 0;
+ else
+ AuErr("unknown %.*s/%.*s exists\n",
+ AuDLNPair(h_root), AuDLNPair(base[AuBrWh_BASE].dentry));
+ if (unlikely(err))
+ goto out;
+
+ h_path->dentry = base[AuBrWh_PLINK].dentry;
+ if (do_plink) {
+ err = au_whdir(h_dir, h_path);
+ if (unlikely(err))
+ goto out;
+ wbr->wbr_plink = dget(base[AuBrWh_PLINK].dentry);
+ } else
+ au_wh_clean(h_dir, h_path, /*isdir*/1);
+ wbr->wbr_whbase = dget(base[AuBrWh_BASE].dentry);
+
+ h_path->dentry = base[AuBrWh_ORPH].dentry;
+ err = au_whdir(h_dir, h_path);
+ if (unlikely(err))
+ goto out;
+ wbr->wbr_orph = dget(base[AuBrWh_ORPH].dentry);
+
+ out:
+ return err;
+}
+
+/*
+ * initialize the whiteout base file/dir for @br.
+ */
+int au_wh_init(struct dentry *h_root, struct au_branch *br,
+ struct super_block *sb)
+{
+ int err, i;
+ const unsigned char do_plink
+ = !!au_opt_test(au_mntflags(sb), PLINK);
+ struct path path = {
+ .mnt = br->br_mnt
+ };
+ struct inode *h_dir;
+ struct au_wbr *wbr = br->br_wbr;
+ static const struct qstr base_name[] = {
+ [AuBrWh_BASE] = {
+ .name = AUFS_BASE_NAME,
+ .len = sizeof(AUFS_BASE_NAME) - 1
+ },
+ [AuBrWh_PLINK] = {
+ .name = AUFS_PLINKDIR_NAME,
+ .len = sizeof(AUFS_PLINKDIR_NAME) - 1
+ },
+ [AuBrWh_ORPH] = {
+ .name = AUFS_ORPHDIR_NAME,
+ .len = sizeof(AUFS_ORPHDIR_NAME) - 1
+ }
+ };
+ struct au_wh_base base[] = {
+ [AuBrWh_BASE] = {
+ .name = base_name + AuBrWh_BASE,
+ .dentry = NULL
+ },
+ [AuBrWh_PLINK] = {
+ .name = base_name + AuBrWh_PLINK,
+ .dentry = NULL
+ },
+ [AuBrWh_ORPH] = {
+ .name = base_name + AuBrWh_ORPH,
+ .dentry = NULL
+ }
+ };
+
+
+ h_dir = h_root->d_inode;
+ for (i = 0; i < AuBrWh_Last; i++) {
+ /* doubly whiteouted */
+ struct dentry *d;
+
+ d = au_wh_lkup(h_root, (void *)base[i].name, br);
+ err = PTR_ERR(d);
+ if (IS_ERR(d))
+ goto out;
+
+ base[i].dentry = d;
+ AuDebugOn(wbr
+ && wbr->wbr_wh[i]
+ && wbr->wbr_wh[i] != base[i].dentry);
+ }
+
+ if (wbr)
+ for (i = 0; i < AuBrWh_Last; i++) {
+ dput(wbr->wbr_wh[i]);
+ wbr->wbr_wh[i] = NULL;
+ }
+
+ err = 0;
+
+ switch (br->br_perm) {
+ case AuBrPerm_RO:
+ case AuBrPerm_ROWH:
+ case AuBrPerm_RR:
+ case AuBrPerm_RRWH:
+ au_wh_init_ro(h_dir, base, &path);
+ break;
+
+ case AuBrPerm_RWNoLinkWH:
+ err = au_wh_init_rw_nolink(h_root, wbr, do_plink, base, &path);
+ if (err > 0)
+ goto out;
+ else if (err)
+ goto out_err;
+ break;
+
+ case AuBrPerm_RW:
+ err = au_wh_init_rw(h_root, wbr, do_plink, base, &path);
+ if (err > 0)
+ goto out;
+ else if (err)
+ goto out_err;
+ break;
+
+ default:
+ BUG();
+ }
+ goto out; /* success */
+
+ out_err:
+ AuErr("an error(%d) on the writable branch %.*s(%s)\n",
+ err, AuDLNPair(h_root), au_sbtype(h_root->d_sb));
+ out:
+ for (i = 0; i < AuBrWh_Last; i++)
+ dput(base[i].dentry);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * whiteouts are all hard-linked usually.
+ * when its link count reaches a ceiling, we create a new whiteout base
+ * asynchronously.
+ */
+
+struct reinit_br_wh {
+ struct super_block *sb;
+ struct au_branch *br;
+};
+
+static void reinit_br_wh(void *arg)
+{
+ int err;
+ aufs_bindex_t bindex;
+ struct path h_path;
+ struct reinit_br_wh *a = arg;
+ struct au_wbr *wbr;
+ struct inode *dir;
+ struct dentry *h_root;
+ struct au_hinode *hdir;
+
+ err = 0;
+ wbr = a->br->br_wbr;
+ /* big aufs lock */
+ si_noflush_write_lock(a->sb);
+ if (!au_br_writable(a->br->br_perm))
+ goto out;
+ bindex = au_br_index(a->sb, a->br->br_id);
+ if (unlikely(bindex < 0))
+ goto out;
+
+ dir = a->sb->s_root->d_inode;
+ /* ii_read_lock_parent(dir); */
+ hdir = au_hi(dir, bindex);
+ h_root = au_h_dptr(a->sb->s_root, bindex);
+
+ au_hin_imtx_lock_nested(hdir, AuLsc_I_PARENT);
+ wbr_wh_write_lock(wbr);
+ err = au_h_verify(wbr->wbr_whbase, au_opt_udba(a->sb), hdir->hi_inode,
+ h_root, a->br);
+ if (!err) {
+ err = mnt_want_write(a->br->br_mnt);
+ if (!err) {
+ h_path.dentry = wbr->wbr_whbase;
+ h_path.mnt = a->br->br_mnt;
+ err = vfsub_unlink(hdir->hi_inode, &h_path, /*force*/0);
+ mnt_drop_write(a->br->br_mnt);
+ }
+ } else {
+ AuWarn("%.*s is moved, ignored\n", AuDLNPair(wbr->wbr_whbase));
+ err = 0;
+ }
+ dput(wbr->wbr_whbase);
+ wbr->wbr_whbase = NULL;
+ if (!err)
+ err = au_wh_init(h_root, a->br, a->sb);
+ wbr_wh_write_unlock(wbr);
+ au_hin_imtx_unlock(hdir);
+ /* ii_read_unlock(dir); */
+
+ out:
+ if (wbr)
+ atomic_dec(&wbr->wbr_wh_running);
+ atomic_dec(&a->br->br_count);
+ au_nwt_done(&au_sbi(a->sb)->si_nowait);
+ si_write_unlock(a->sb);
+ kfree(arg);
+ if (unlikely(err))
+ AuIOErr("err %d\n", err);
+}
+
+static void kick_reinit_br_wh(struct super_block *sb, struct au_branch *br)
+{
+ int do_dec, wkq_err;
+ struct reinit_br_wh *arg;
+
+ do_dec = 1;
+ if (atomic_inc_return(&br->br_wbr->wbr_wh_running) != 1)
+ goto out;
+
+ /* ignore ENOMEM */
+ arg = kmalloc(sizeof(*arg), GFP_NOFS);
+ if (arg) {
+ /*
+ * dec(wh_running), kfree(arg) and dec(br_count)
+ * in reinit function
+ */
+ arg->sb = sb;
+ arg->br = br;
+ atomic_inc(&br->br_count);
+ wkq_err = au_wkq_nowait(reinit_br_wh, arg, sb);
+ if (unlikely(wkq_err)) {
+ atomic_dec(&br->br_wbr->wbr_wh_running);
+ atomic_dec(&br->br_count);
+ kfree(arg);
+ }
+ do_dec = 0;
+ }
+
+ out:
+ if (do_dec)
+ atomic_dec(&br->br_wbr->wbr_wh_running);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * create the whiteout @wh.
+ */
+static int link_or_create_wh(struct super_block *sb, aufs_bindex_t bindex,
+ struct dentry *wh)
+{
+ int err;
+ struct path h_path = {
+ .dentry = wh
+ };
+ struct au_branch *br;
+ struct au_wbr *wbr;
+ struct dentry *h_parent;
+ struct inode *h_dir;
+
+ h_parent = wh->d_parent; /* dir inode is locked */
+ h_dir = h_parent->d_inode;
+ IMustLock(h_dir);
+
+ br = au_sbr(sb, bindex);
+ h_path.mnt = br->br_mnt;
+ wbr = br->br_wbr;
+ wbr_wh_read_lock(wbr);
+ if (wbr->wbr_whbase) {
+ err = vfsub_link(wbr->wbr_whbase, h_dir, &h_path);
+ if (!err || err != -EMLINK)
+ goto out;
+
+ /* link count full. re-initialize br_whbase. */
+ kick_reinit_br_wh(sb, br);
+ }
+
+ /* return this error in this context */
+ err = vfsub_create(h_dir, &h_path, WH_MASK);
+
+ out:
+ wbr_wh_read_unlock(wbr);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * create or remove the diropq.
+ */
+static struct dentry *do_diropq(struct dentry *dentry, aufs_bindex_t bindex,
+ unsigned int flags)
+{
+ struct dentry *opq_dentry, *h_dentry;
+ struct super_block *sb;
+ struct au_branch *br;
+ int err;
+
+ sb = dentry->d_sb;
+ br = au_sbr(sb, bindex);
+ h_dentry = au_h_dptr(dentry, bindex);
+ opq_dentry = au_lkup_one(&diropq_name, h_dentry, br, /*nd*/NULL);
+ if (IS_ERR(opq_dentry))
+ goto out;
+
+ if (au_ftest_diropq(flags, CREATE)) {
+ err = link_or_create_wh(sb, bindex, opq_dentry);
+ if (!err) {
+ au_set_dbdiropq(dentry, bindex);
+ goto out; /* success */
+ }
+ } else {
+ struct path tmp = {
+ .dentry = opq_dentry,
+ .mnt = br->br_mnt
+ };
+ err = do_unlink_wh(au_h_iptr(dentry->d_inode, bindex), &tmp);
+ if (!err)
+ au_set_dbdiropq(dentry, -1);
+ }
+ dput(opq_dentry);
+ opq_dentry = ERR_PTR(err);
+
+ out:
+ return opq_dentry;
+}
+
+struct do_diropq_args {
+ struct dentry **errp;
+ struct dentry *dentry;
+ aufs_bindex_t bindex;
+ unsigned int flags;
+};
+
+static void call_do_diropq(void *args)
+{
+ struct do_diropq_args *a = args;
+ *a->errp = do_diropq(a->dentry, a->bindex, a->flags);
+}
+
+struct dentry *au_diropq_sio(struct dentry *dentry, aufs_bindex_t bindex,
+ unsigned int flags)
+{
+ struct dentry *diropq, *h_dentry;
+
+ h_dentry = au_h_dptr(dentry, bindex);
+ if (!au_test_h_perm_sio(h_dentry->d_inode, MAY_EXEC | MAY_WRITE))
+ diropq = do_diropq(dentry, bindex, flags);
+ else {
+ int wkq_err;
+ struct do_diropq_args args = {
+ .errp = &diropq,
+ .dentry = dentry,
+ .bindex = bindex,
+ .flags = flags
+ };
+
+ wkq_err = au_wkq_wait(call_do_diropq, &args);
+ if (unlikely(wkq_err))
+ diropq = ERR_PTR(wkq_err);
+ }
+
+ return diropq;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * lookup whiteout dentry.
+ * @h_parent: lower parent dentry which must exist and be locked
+ * @base_name: name of dentry which will be whiteouted
+ * returns dentry for whiteout.
+ */
+struct dentry *au_wh_lkup(struct dentry *h_parent, struct qstr *base_name,
+ struct au_branch *br)
+{
+ int err;
+ struct qstr wh_name;
+ struct dentry *wh_dentry;
+
+ err = au_wh_name_alloc(&wh_name, base_name);
+ wh_dentry = ERR_PTR(err);
+ if (!err) {
+ wh_dentry = au_lkup_one(&wh_name, h_parent, br, /*nd*/NULL);
+ kfree(wh_name.name);
+ }
+ return wh_dentry;
+}
+
+/*
+ * link/create a whiteout for @dentry on @bindex.
+ */
+struct dentry *au_wh_create(struct dentry *dentry, aufs_bindex_t bindex,
+ struct dentry *h_parent)
+{
+ struct dentry *wh_dentry;
+ struct super_block *sb;
+ int err;
+
+ sb = dentry->d_sb;
+ wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, au_sbr(sb, bindex));
+ if (!IS_ERR(wh_dentry) && !wh_dentry->d_inode) {
+ err = link_or_create_wh(sb, bindex, wh_dentry);
+ if (!err)
+ au_set_dbwh(dentry, bindex);
+ else {
+ dput(wh_dentry);
+ wh_dentry = ERR_PTR(err);
+ }
+ }
+
+ return wh_dentry;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* Delete all whiteouts in this directory on branch bindex. */
+static int del_wh_children(struct dentry *h_dentry, struct au_nhash *whlist,
+ aufs_bindex_t bindex, struct au_branch *br)
+{
+ int err, i;
+ struct qstr wh_name;
+ char *p;
+ struct hlist_head *head;
+ struct au_vdir_wh *tpos;
+ struct hlist_node *pos;
+ struct au_vdir_destr *str;
+
+ err = -ENOMEM;
+ p = __getname();
+ wh_name.name = p;
+ if (unlikely(!wh_name.name))
+ goto out;
+
+ err = 0;
+ memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN);
+ p += AUFS_WH_PFX_LEN;
+ head = whlist->heads;
+ for (i = 0; !err && i < AuSize_NHASH; i++, head++) {
+ hlist_for_each_entry(tpos, pos, head, wh_hash) {
+ if (tpos->wh_bindex != bindex)
+ continue;
+
+ str = &tpos->wh_str;
+ if (str->len + AUFS_WH_PFX_LEN <= PATH_MAX) {
+ memcpy(p, str->name, str->len);
+ wh_name.len = AUFS_WH_PFX_LEN + str->len;
+ err = unlink_wh_name(h_dentry, &wh_name, br);
+ if (!err)
+ continue;
+ break;
+ }
+ AuIOErr("whiteout name too long %.*s\n",
+ str->len, str->name);
+ err = -EIO;
+ break;
+ }
+ }
+ __putname(wh_name.name);
+
+ out:
+ return err;
+}
+
+struct del_wh_children_args {
+ int *errp;
+ struct dentry *h_dentry;
+ struct au_nhash *whlist;
+ aufs_bindex_t bindex;
+ struct au_branch *br;
+};
+
+static void call_del_wh_children(void *args)
+{
+ struct del_wh_children_args *a = args;
+ *a->errp = del_wh_children(a->h_dentry, a->whlist, a->bindex, a->br);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * rmdir the whiteouted temporary named dir @h_dentry.
+ * @whlist: whiteouted children.
+ */
+int au_whtmp_rmdir(struct inode *dir, aufs_bindex_t bindex,
+ struct dentry *wh_dentry, struct au_nhash *whlist)
+{
+ int err;
+ struct path h_tmp;
+ struct inode *wh_inode, *h_dir;
+ struct au_branch *br;
+
+ h_dir = wh_dentry->d_parent->d_inode; /* dir inode is locked */
+ IMustLock(h_dir);
+
+ br = au_sbr(dir->i_sb, bindex);
+ wh_inode = wh_dentry->d_inode;
+ mutex_lock_nested(&wh_inode->i_mutex, AuLsc_I_CHILD);
+
+ /*
+ * someone else might change some whiteouts while we were sleeping.
+ * it means this whlist may have an obsoleted entry.
+ */
+ if (!au_test_h_perm_sio(wh_inode, MAY_EXEC | MAY_WRITE))
+ err = del_wh_children(wh_dentry, whlist, bindex, br);
+ else {
+ int wkq_err;
+ struct del_wh_children_args args = {
+ .errp = &err,
+ .h_dentry = wh_dentry,
+ .whlist = whlist,
+ .bindex = bindex,
+ .br = br
+ };
+
+ wkq_err = au_wkq_wait(call_del_wh_children, &args);
+ if (unlikely(wkq_err))
+ err = wkq_err;
+ }
+ mutex_unlock(&wh_inode->i_mutex);
+
+ if (!err) {
+ h_tmp.dentry = wh_dentry;
+ h_tmp.mnt = br->br_mnt;
+ err = vfsub_rmdir(h_dir, &h_tmp);
+ /* d_drop(h_dentry); */
+ }
+
+ if (!err) {
+ if (au_ibstart(dir) == bindex) {
+ au_cpup_attr_timesizes(dir);
+ drop_nlink(dir);
+ }
+ return 0; /* success */
+ }
+
+ AuWarn("failed removing %.*s(%d), ignored\n",
+ AuDLNPair(wh_dentry), err);
+ return err;
+}
+
+static void au_whtmp_rmdir_free_args(struct au_whtmp_rmdir_args *args)
+{
+ au_nhash_fin(&args->whlist);
+ dput(args->wh_dentry);
+ iput(args->dir);
+ kfree(args);
+}
+
+static void call_rmdir_whtmp(void *args)
+{
+ int err;
+ struct au_whtmp_rmdir_args *a = args;
+ struct super_block *sb;
+ struct dentry *h_parent;
+ struct inode *h_dir;
+ struct au_branch *br;
+ struct au_hinode *hdir;
+
+ /* rmdir by nfsd may cause deadlock with this i_mutex */
+ /* mutex_lock(&a->dir->i_mutex); */
+ sb = a->dir->i_sb;
+ si_noflush_read_lock(sb);
+ err = au_test_ro(sb, a->bindex, NULL);
+ if (unlikely(err))
+ goto out;
+
+ err = -EIO;
+ br = au_sbr(sb, a->bindex);
+ ii_write_lock_parent(a->dir);
+ h_parent = dget_parent(a->wh_dentry);
+ h_dir = h_parent->d_inode;
+ hdir = au_hi(a->dir, a->bindex);
+ au_hin_imtx_lock_nested(hdir, AuLsc_I_PARENT);
+ err = au_h_verify(a->wh_dentry, au_opt_udba(sb), h_dir, h_parent, br);
+ if (!err) {
+ err = mnt_want_write(br->br_mnt);
+ if (!err) {
+ err = au_whtmp_rmdir(a->dir, a->bindex, a->wh_dentry,
+ &a->whlist);
+ mnt_drop_write(br->br_mnt);
+ }
+ }
+ au_hin_imtx_unlock(hdir);
+ dput(h_parent);
+ ii_write_unlock(a->dir);
+
+ out:
+ /* mutex_unlock(&a->dir->i_mutex); */
+ au_nwt_done(&au_sbi(sb)->si_nowait);
+ si_read_unlock(sb);
+ au_whtmp_rmdir_free_args(a);
+ if (unlikely(err))
+ AuIOErr("err %d\n", err);
+}
+
+void au_whtmp_kick_rmdir(struct inode *dir, aufs_bindex_t bindex,
+ struct dentry *wh_dentry, struct au_nhash *whlist,
+ struct au_whtmp_rmdir_args *args)
+{
+ int wkq_err;
+
+ IMustLock(dir);
+
+ /* all post-process will be done in do_rmdir_whtmp(). */
+ args->dir = au_igrab(dir);
+ args->bindex = bindex;
+ args->wh_dentry = dget(wh_dentry);
+ au_nhash_init(&args->whlist);
+ au_nhash_move(&args->whlist, whlist);
+ wkq_err = au_wkq_nowait(call_rmdir_whtmp, args, dir->i_sb);
+ if (unlikely(wkq_err)) {
+ AuWarn("rmdir error %.*s (%d), ignored\n",
+ AuDLNPair(wh_dentry), wkq_err);
+ au_whtmp_rmdir_free_args(args);
+ }
+}
diff --git a/fs/aufs/whout.h b/fs/aufs/whout.h
new file mode 100644
index 0000000..084e34c
--- /dev/null
+++ b/fs/aufs/whout.h
@@ -0,0 +1,78 @@
+/*
+ * 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.
+ */
+
+/*
+ * whiteout for logical deletion and opaque directory
+ */
+
+#ifndef __AUFS_WHOUT_H__
+#define __AUFS_WHOUT_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/aufs_type.h>
+#include "dir.h"
+
+/* whout.c */
+int au_wh_name_alloc(struct qstr *wh, const struct qstr *name);
+struct au_branch;
+int au_wh_test(struct dentry *h_parent, struct qstr *wh_name,
+ struct au_branch *br, int try_sio);
+int au_diropq_test(struct dentry *h_dentry, struct au_branch *br);
+struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br,
+ struct qstr *prefix);
+int au_whtmp_ren(struct dentry *h_dentry, struct au_branch *br);
+int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path,
+ struct dentry *dentry);
+int au_wh_init(struct dentry *h_parent, struct au_branch *br,
+ struct super_block *sb);
+
+/* diropq flags */
+#define AuDiropq_CREATE 1
+#define au_ftest_diropq(flags, name) ((flags) & AuDiropq_##name)
+#define au_fset_diropq(flags, name) { (flags) |= AuDiropq_##name; }
+#define au_fclr_diropq(flags, name) { (flags) &= ~AuDiropq_##name; }
+
+struct dentry *au_diropq_sio(struct dentry *dentry, aufs_bindex_t bindex,
+ unsigned int flags);
+struct dentry *au_wh_lkup(struct dentry *h_parent, struct qstr *base_name,
+ struct au_branch *br);
+struct dentry *au_wh_create(struct dentry *dentry, aufs_bindex_t bindex,
+ struct dentry *h_parent);
+
+/* real rmdir for the whiteout-ed dir */
+struct au_whtmp_rmdir_args {
+ struct inode *dir;
+ aufs_bindex_t bindex;
+ struct dentry *wh_dentry;
+ struct au_nhash whlist;
+};
+
+int au_whtmp_rmdir(struct inode *dir, aufs_bindex_t bindex,
+ struct dentry *wh_dentry, struct au_nhash *whlist);
+void au_whtmp_kick_rmdir(struct inode *dir, aufs_bindex_t bindex,
+ struct dentry *wh_dentry, struct au_nhash *whlist,
+ struct au_whtmp_rmdir_args *args);
+
+/* ---------------------------------------------------------------------- */
+
+static inline struct dentry *au_diropq_create(struct dentry *dentry,
+ aufs_bindex_t bindex)
+{
+ return au_diropq_sio(dentry, bindex, AuDiropq_CREATE);
+}
+
+static inline int au_diropq_remove(struct dentry *dentry, aufs_bindex_t bindex)
+{
+ return PTR_ERR(au_diropq_sio(dentry, bindex, !AuDiropq_CREATE));
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_WHOUT_H__ */
--
1.6.1.284.g5dc13

2009-03-09 03:33:39

by J. R. Okajima

Subject: [Aufs 07/25] aufs object lifetime management via sysfs

initial commit
some aufs objects have a corresponding entry under sysfs, so the
lifetime will be managed by struct kref even if CONFIG_SYSFS is
disabled.
This file is compiled unconditionally.

Signed-off-by: J. R. Okajima <[email protected]>
---
fs/aufs/sysaufs.c | 79 +++++++++++++++++++++++++++++++++++++++++
fs/aufs/sysaufs.h | 102 +++++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 181 insertions(+), 0 deletions(-)
create mode 100644 fs/aufs/sysaufs.c
create mode 100644 fs/aufs/sysaufs.h

diff --git a/fs/aufs/sysaufs.c b/fs/aufs/sysaufs.c
new file mode 100644
index 0000000..47ffbfd
--- /dev/null
+++ b/fs/aufs/sysaufs.c
@@ -0,0 +1,79 @@
+/*
+ * 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.
+ */
+
+/*
+ * sysfs interface and lifetime management
+ * they are necessary regardless sysfs is disabled.
+ */
+
+#include <linux/fs.h>
+#include <linux/random.h>
+#include <linux/sysfs.h>
+#include "aufs.h"
+
+unsigned long sysaufs_si_mask;
+struct kset *sysaufs_ket;
+
+#define AuSiAttr(_name) { \
+ .attr = { .name = __stringify(_name), .mode = 0444 }, \
+ .show = sysaufs_si_##_name, \
+}
+
+static struct sysaufs_si_attr sysaufs_si_attr_xino = AuSiAttr(xino);
+struct attribute *sysaufs_si_attrs[] = {
+ &sysaufs_si_attr_xino.attr,
+ NULL,
+};
+
+static struct sysfs_ops au_sbi_ops = {
+ .show = sysaufs_si_show
+};
+
+static struct kobj_type au_sbi_ktype = {
+ .release = au_si_free,
+ .sysfs_ops = &au_sbi_ops,
+ .default_attrs = sysaufs_si_attrs
+};
+
+/* ---------------------------------------------------------------------- */
+
+int sysaufs_si_init(struct au_sbinfo *sbinfo)
+{
+ int err;
+
+ sbinfo->si_kobj.kset = sysaufs_ket;
+ err = kobject_init_and_add(&sbinfo->si_kobj, &au_sbi_ktype,
+ /*&sysaufs_ket->kobj*/NULL,
+ "si_%lx", sysaufs_si_id(sbinfo));
+ return err;
+}
+
+void sysaufs_fin(void)
+{
+ sysfs_remove_group(&sysaufs_ket->kobj, sysaufs_attr_group);
+ kset_unregister(sysaufs_ket);
+}
+
+int __init sysaufs_init(void)
+{
+ int err;
+
+ get_random_bytes(&sysaufs_si_mask, sizeof(sysaufs_si_mask));
+
+ sysaufs_ket = kset_create_and_add(AUFS_NAME, NULL, fs_kobj);
+ err = PTR_ERR(sysaufs_ket);
+ if (IS_ERR(sysaufs_ket))
+ goto out;
+ err = sysfs_create_group(&sysaufs_ket->kobj, sysaufs_attr_group);
+ if (unlikely(err))
+ kset_unregister(sysaufs_ket);
+
+ out:
+ return err;
+}
diff --git a/fs/aufs/sysaufs.h b/fs/aufs/sysaufs.h
new file mode 100644
index 0000000..04ffab2
--- /dev/null
+++ b/fs/aufs/sysaufs.h
@@ -0,0 +1,102 @@
+/*
+ * 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.
+ */
+
+/*
+ * sysfs interface and mount lifetime management
+ */
+
+#ifndef __SYSAUFS_H__
+#define __SYSAUFS_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/aufs_type.h>
+
+struct sysaufs_si_attr {
+ struct attribute attr;
+ int (*show)(struct seq_file *seq, struct super_block *sb);
+};
+
+/* ---------------------------------------------------------------------- */
+
+/* sysaufs.c */
+extern unsigned long sysaufs_si_mask;
+extern struct kset *sysaufs_ket;
+extern struct attribute *sysaufs_si_attrs[];
+int sysaufs_si_init(struct au_sbinfo *sbinfo);
+int __init sysaufs_init(void);
+void sysaufs_fin(void);
+
+/* ---------------------------------------------------------------------- */
+
+/* some people doesn't like to show a pointer in kernel */
+static inline unsigned long sysaufs_si_id(struct au_sbinfo *sbinfo)
+{
+ return sysaufs_si_mask ^ (unsigned long)sbinfo;
+}
+
+struct au_branch;
+#ifdef CONFIG_SYSFS
+/* sysfs.c */
+extern struct attribute_group *sysaufs_attr_group;
+extern struct kobj_type *sysaufs_ktype;
+
+int sysaufs_si_xino(struct seq_file *seq, struct super_block *sb);
+ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr,
+ char *buf);
+
+void sysaufs_br_init(struct au_branch *br);
+void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex);
+void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex);
+
+#define sysaufs_brs_init() do {} while (0)
+
+#else
+#define sysaufs_attr_group NULL
+#define sysaufs_ktype NULL
+
+static inline
+int sysaufs_si_xino(struct seq_file *seq, struct super_block *sb)
+{
+ return 0;
+}
+
+static inline
+ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ return 0;
+}
+
+static inline void sysaufs_br_init(struct au_branch *br)
+{
+ /* empty */
+}
+
+static inline void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex)
+{
+ /* nothing */
+}
+
+static inline void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex)
+{
+ /* nothing */
+}
+
+static inline void sysaufs_brs_init(void)
+{
+ sysaufs_brs = 0;
+}
+
+#endif /* CONFIG_SYSFS */
+
+#endif /* __KERNEL__ */
+#endif /* __SYSAUFS_H__ */
--
1.6.1.284.g5dc13

2009-03-09 03:34:19

by J. R. Okajima

Subject: [Aufs 12/25] aufs copy-up

initial commit
internal copy-up functions
see wbr_policy.c for copy-down

Signed-off-by: J. R. Okajima <[email protected]>
---
fs/aufs/cpup.c | 1028 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/aufs/cpup.h | 68 ++++
2 files changed, 1096 insertions(+), 0 deletions(-)
create mode 100644 fs/aufs/cpup.c
create mode 100644 fs/aufs/cpup.h

diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c
new file mode 100644
index 0000000..91808b1
--- /dev/null
+++ b/fs/aufs/cpup.c
@@ -0,0 +1,1028 @@
+/*
+ * 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.
+ */
+
+/*
+ * copy-up functions, see wbr_policy.c for copy-down
+ */
+
+#include <linux/fs_stack.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);
+
+ 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_path.dentry = au_h_dptr(dst, bindex);
+ h_path.mnt = au_sbr_mnt(dst->d_sb, bindex);
+ h_isrc = h_src->d_inode;
+ ia.ia_valid = ATTR_FORCE | ATTR_MODE | ATTR_UID | ATTR_GID
+ | ATTR_ATIME | ATTR_MTIME
+ | ATTR_ATIME_SET | ATTR_MTIME_SET;
+ ia.ia_mode = h_isrc->i_mode;
+ 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;
+ sbits = !!(ia.ia_mode & (S_ISUID | S_ISGID));
+ au_cpup_attr_flags(h_path.dentry->d_inode, 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_write0(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);
+ 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_PARENT2);
+ 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 --git a/fs/aufs/cpup.h b/fs/aufs/cpup.h
new file mode 100644
index 0000000..240014a
--- /dev/null
+++ b/fs/aufs/cpup.h
@@ -0,0 +1,68 @@
+/*
+ * 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.
+ */
+
+/*
+ * copy-up/down functions
+ */
+
+#ifndef __AUFS_CPUP_H__
+#define __AUFS_CPUP_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/aufs_type.h>
+
+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__ */
--
1.6.1.284.g5dc13

2009-03-09 03:34:37

by J. R. Okajima

Subject: [Aufs 05/25] aufs branch directory/filesystem

initial commit
branch management

Signed-off-by: J. R. Okajima <[email protected]>
---
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

2009-03-09 03:35:18

by J. R. Okajima

Subject: [Aufs 09/25] aufs workqueue

initial commit
workqueue for asynchronous and super-io operations.
they are used for:
- handling 'opaque' directory and whiteout
- lookup and copy-up/down with credential
- internal xino file i/o

Signed-off-by: J. R. Okajima <[email protected]>
---
fs/aufs/wkq.c | 249 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/aufs/wkq.h | 72 +++++++++++++++++
2 files changed, 321 insertions(+), 0 deletions(-)
create mode 100644 fs/aufs/wkq.c
create mode 100644 fs/aufs/wkq.h

diff --git a/fs/aufs/wkq.c b/fs/aufs/wkq.c
new file mode 100644
index 0000000..41e30be
--- /dev/null
+++ b/fs/aufs/wkq.c
@@ -0,0 +1,249 @@
+/*
+ * 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.
+ */
+
+/*
+ * workqueue for asynchronous/super-io operations
+ * todo: try new dredential scheme
+ */
+
+#include "aufs.h"
+
+/* internal workqueue named AUFS_WKQ_NAME */
+static struct au_wkq {
+ struct workqueue_struct *q;
+
+ /* balancing */
+ atomic_t busy;
+} *au_wkq;
+
+struct au_wkinfo {
+ struct work_struct wk;
+ struct super_block *sb;
+
+ unsigned int flags; /* see wkq.h */
+
+ au_wkq_func_t func;
+ void *args;
+
+ atomic_t *busyp;
+ struct completion *comp;
+};
+
+/* ---------------------------------------------------------------------- */
+
+static int enqueue(struct au_wkq *wkq, struct au_wkinfo *wkinfo)
+{
+ wkinfo->busyp = &wkq->busy;
+ if (au_ftest_wkq(wkinfo->flags, WAIT))
+ return !queue_work(wkq->q, &wkinfo->wk);
+ else
+ return !schedule_work(&wkinfo->wk);
+}
+
+static void do_wkq(struct au_wkinfo *wkinfo)
+{
+ unsigned int idle, n;
+ int i, idle_idx;
+
+ while (1) {
+ if (au_ftest_wkq(wkinfo->flags, WAIT)) {
+ idle_idx = 0;
+ idle = UINT_MAX;
+ for (i = 0; i < aufs_nwkq; i++) {
+ n = atomic_inc_return(&au_wkq[i].busy);
+ if (n == 1 && !enqueue(au_wkq + i, wkinfo))
+ return; /* success */
+
+ if (n < idle) {
+ idle_idx = i;
+ idle = n;
+ }
+ atomic_dec(&au_wkq[i].busy);
+ }
+ } else
+ idle_idx = aufs_nwkq;
+
+ atomic_inc(&au_wkq[idle_idx].busy);
+ if (!enqueue(au_wkq + idle_idx, wkinfo))
+ return; /* success */
+
+ /* impossible? */
+ AuWarn1("failed to queue_work()\n");
+ yield();
+ }
+}
+
+static void wkq_func(struct work_struct *wk)
+{
+ struct au_wkinfo *wkinfo = container_of(wk, struct au_wkinfo, wk);
+
+ wkinfo->func(wkinfo->args);
+ atomic_dec(wkinfo->busyp);
+ if (au_ftest_wkq(wkinfo->flags, WAIT))
+ complete(wkinfo->comp);
+ else {
+ kobject_put(&au_sbi(wkinfo->sb)->si_kobj);
+ module_put(THIS_MODULE);
+ kfree(wkinfo);
+ }
+}
+
+/*
+ * Since struct completion is large, try allocating it dynamically.
+ */
+#if defined(CONFIG_4KSTACKS) || defined(AuTest4KSTACKS)
+#define AuWkqCompDeclare(name) struct completion *comp = NULL
+
+static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp)
+{
+ *comp = kmalloc(sizeof(**comp), GFP_NOFS);
+ if (*comp) {
+ init_completion(*comp);
+ wkinfo->comp = *comp;
+ return 0;
+ }
+ return -ENOMEM;
+}
+
+static void au_wkq_comp_free(struct completion *comp)
+{
+ kfree(comp);
+}
+
+#else
+
+/* no braces */
+#define AuWkqCompDeclare(name) \
+ DECLARE_COMPLETION_ONSTACK(_ ## name); \
+ struct completion *comp = &_ ## name
+
+static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp)
+{
+ wkinfo->comp = *comp;
+ return 0;
+}
+
+static void au_wkq_comp_free(struct completion *comp __maybe_unused)
+{
+ /* empty */
+}
+#endif /* 4KSTACKS */
+
+static void au_wkq_run(struct au_wkinfo *wkinfo)
+{
+ au_dbg_verify_kthread();
+ INIT_WORK(&wkinfo->wk, wkq_func);
+ do_wkq(wkinfo);
+}
+
+int au_wkq_wait(au_wkq_func_t func, void *args)
+{
+ int err;
+ AuWkqCompDeclare(comp);
+ struct au_wkinfo wkinfo = {
+ .flags = AuWkq_WAIT,
+ .func = func,
+ .args = args
+ };
+
+ err = au_wkq_comp_alloc(&wkinfo, &comp);
+ if (!err) {
+ au_wkq_run(&wkinfo);
+ /* no timeout, no interrupt */
+ wait_for_completion(wkinfo.comp);
+ au_wkq_comp_free(comp);
+ }
+
+ return err;
+
+}
+
+int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb)
+{
+ int err;
+ struct au_wkinfo *wkinfo;
+
+ atomic_inc(&au_sbi(sb)->si_nowait.nw_len);
+
+ /*
+ * wkq_func() must free this wkinfo.
+ * it highly depends upon the implementation of workqueue.
+ */
+ err = 0;
+ wkinfo = kmalloc(sizeof(*wkinfo), GFP_NOFS);
+ if (wkinfo) {
+ wkinfo->sb = sb;
+ wkinfo->flags = !AuWkq_WAIT;
+ wkinfo->func = func;
+ wkinfo->args = args;
+ wkinfo->comp = NULL;
+ kobject_get(&au_sbi(sb)->si_kobj);
+ __module_get(THIS_MODULE);
+
+ au_wkq_run(wkinfo);
+ } else {
+ err = -ENOMEM;
+ atomic_dec(&au_sbi(sb)->si_nowait.nw_len);
+ }
+
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_nwt_init(struct au_nowait_tasks *nwt)
+{
+ atomic_set(&nwt->nw_len, 0);
+ /* smp_mb();*/ /* atomic_set */
+ init_waitqueue_head(&nwt->nw_wq);
+}
+
+void au_wkq_fin(void)
+{
+ int i;
+
+ for (i = 0; i < aufs_nwkq; i++)
+ if (au_wkq[i].q && !IS_ERR(au_wkq[i].q))
+ destroy_workqueue(au_wkq[i].q);
+ kfree(au_wkq);
+}
+
+int __init au_wkq_init(void)
+{
+ int err, i;
+ struct au_wkq *nowaitq;
+
+ /* '+1' is for accounting of nowait queue */
+ err = -ENOMEM;
+ au_wkq = kcalloc(aufs_nwkq + 1, sizeof(*au_wkq), GFP_NOFS);
+ if (unlikely(!au_wkq))
+ goto out;
+
+ err = 0;
+ for (i = 0; i < aufs_nwkq; i++) {
+ au_wkq[i].q = create_singlethread_workqueue(AUFS_WKQ_NAME);
+ if (au_wkq[i].q && !IS_ERR(au_wkq[i].q)) {
+ atomic_set(&au_wkq[i].busy, 0);
+ continue;
+ }
+
+ err = PTR_ERR(au_wkq[i].q);
+ au_wkq_fin();
+ goto out;
+ }
+
+ /* nowait accounting */
+ nowaitq = au_wkq + aufs_nwkq;
+ atomic_set(&nowaitq->busy, 0);
+ nowaitq->q = NULL;
+ /* smp_mb(); */ /* atomic_set */
+
+ out:
+ return err;
+}
diff --git a/fs/aufs/wkq.h b/fs/aufs/wkq.h
new file mode 100644
index 0000000..17d24d8
--- /dev/null
+++ b/fs/aufs/wkq.h
@@ -0,0 +1,72 @@
+/*
+ * 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.
+ */
+
+/*
+ * workqueue for asynchronous/super-io operations
+ * todo: try new credentials management scheme
+ */
+
+#ifndef __AUFS_WKQ_H__
+#define __AUFS_WKQ_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <linux/aufs_type.h>
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * in the next operation, wait for the 'nowait' tasks in system-wide workqueue
+ */
+struct au_nowait_tasks {
+ atomic_t nw_len;
+ wait_queue_head_t nw_wq;
+};
+
+/* ---------------------------------------------------------------------- */
+
+typedef void (*au_wkq_func_t)(void *args);
+
+/* wkq flags */
+#define AuWkq_WAIT 1
+#define au_ftest_wkq(flags, name) ((flags) & AuWkq_##name)
+#define au_fset_wkq(flags, name) { (flags) |= AuWkq_##name; }
+#define au_fclr_wkq(flags, name) { (flags) &= ~AuWkq_##name; }
+
+/* wkq.c */
+int au_wkq_wait(au_wkq_func_t func, void *args);
+int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb);
+void au_nwt_init(struct au_nowait_tasks *nwt);
+int __init au_wkq_init(void);
+void au_wkq_fin(void);
+
+/* ---------------------------------------------------------------------- */
+
+static inline int au_test_wkq(struct task_struct *tsk)
+{
+ return !tsk->mm && !strcmp(tsk->comm, AUFS_WKQ_NAME);
+}
+
+static inline void au_nwt_done(struct au_nowait_tasks *nwt)
+{
+ if (!atomic_dec_return(&nwt->nw_len))
+ wake_up_all(&nwt->nw_wq);
+}
+
+static inline int au_nwt_flush(struct au_nowait_tasks *nwt)
+{
+ wait_event(nwt->nw_wq, !atomic_read(&nwt->nw_len));
+ return 0;
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_WKQ_H__ */
--
1.6.1.284.g5dc13

2009-03-09 03:34:52

by J. R. Okajima

Subject: [Aufs 03/25] aufs module global

initial commit
common header file
module initialization and module global vars

Signed-off-by: J. R. Okajima <[email protected]>
---
fs/aufs/Kconfig | 78 ++++++++++++++++++++++++++
fs/aufs/Makefile | 20 +++++++
fs/aufs/aufs.h | 43 ++++++++++++++
fs/aufs/module.c | 164 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/aufs/module.h | 66 ++++++++++++++++++++++
fs/aufs/rwsem.h | 52 +++++++++++++++++
fs/aufs/spl.h | 47 +++++++++++++++
7 files changed, 470 insertions(+), 0 deletions(-)
create mode 100644 fs/aufs/Kconfig
create mode 100644 fs/aufs/Makefile
create mode 100644 fs/aufs/aufs.h
create mode 100644 fs/aufs/module.c
create mode 100644 fs/aufs/module.h
create mode 100644 fs/aufs/rwsem.h
create mode 100644 fs/aufs/spl.h

diff --git a/fs/aufs/Kconfig b/fs/aufs/Kconfig
new file mode 100644
index 0000000..065a0c6
--- /dev/null
+++ b/fs/aufs/Kconfig
@@ -0,0 +1,78 @@
+config AUFS_FS
+ bool "Advanced multi layered unification filesystem support"
+ depends on EXPERIMENTAL
+ help
+ Aufs is a stackable unification filesystem such as Unionfs,
+ which unifies several directories and provides a merged single
+ directory.
+ In the early days, aufs was entirely re-designed and
+ re-implemented Unionfs Version 1.x series. Introducing many
+ original ideas, approaches and improvements, it becomes totally
+ different from Unionfs while keeping the basic features.
+
+if AUFS_FS
+choice
+ prompt "Maximum number of branches"
+ default AUFS_BRANCH_MAX_127
+ help
+ Specifies the maximum number of branches (or member directories)
+ in a single aufs. The larger value consumes more system
+ resources and has a minor impact to performance.
+config AUFS_BRANCH_MAX_127
+ bool "127"
+ help
+ Specifies the maximum number of branches (or member directories)
+ in a single aufs. The larger value consumes more system
+ resources and has a minor impact to performance.
+config AUFS_BRANCH_MAX_511
+ bool "511"
+ help
+ Specifies the maximum number of branches (or member directories)
+ in a single aufs. The larger value consumes more system
+ resources and has a minor impact to performance.
+config AUFS_BRANCH_MAX_1023
+ bool "1023"
+ help
+ Specifies the maximum number of branches (or member directories)
+ in a single aufs. The larger value consumes more system
+ resources and has a minor impact to performance.
+config AUFS_BRANCH_MAX_32767
+ bool "32767"
+ help
+ Specifies the maximum number of branches (or member directories)
+ in a single aufs. The larger value consumes more system
+ resources and has a minor impact to performance.
+endchoice
+
+config AUFS_HINOTIFY
+ bool "Use inotify to detect actions on a branch"
+ depends on INOTIFY
+ help
+ If you want to modify files on branches directly, eg. bypassing aufs,
+ and want aufs to detect the changes of them fully, then enable this
+ option and use 'udba=inotify' mount option.
+ It will have a negative impact to the performance.
+ See detail in aufs.5.
+
+config AUFS_DEBUG
+ bool "Debug aufs"
+ help
+ Enable this to compile aufs internal debug code.
+ It will have a negative impact to the performance.
+
+config AUFS_MAGIC_SYSRQ
+ bool
+ depends on AUFS_DEBUG && MAGIC_SYSRQ
+ default y
+ help
+ Automatic configuration for internal use.
+ When aufs supports Magic SysRq, enabled automatically.
+
+config AUFS_BDEV_LOOP
+ bool
+ depends on BLK_DEV_LOOP
+ default y
+ help
+ Automatic configuration for internal use.
+ Convert =[ym] into =y.
+endif
diff --git a/fs/aufs/Makefile b/fs/aufs/Makefile
new file mode 100644
index 0000000..9952a46
--- /dev/null
+++ b/fs/aufs/Makefile
@@ -0,0 +1,20 @@
+
+include ${srctree}/${src}/magic.mk
+-include ${srctree}/${src}/priv_def.mk
+
+obj-$(CONFIG_AUFS_FS) += aufs.o
+aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \
+ wkq.o vfsub.o dcsub.o \
+ cpup.o whout.o plink.o wbr_policy.o \
+ dinfo.o dentry.o \
+ finfo.o file.o f_op.o \
+ dir.o vdir.o \
+ iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \
+ ioctl.o
+
+# all are boolean
+aufs-$(CONFIG_SYSFS) += sysfs.o
+aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o
+aufs-$(CONFIG_AUFS_HINOTIFY) += hinotify.o
+aufs-$(CONFIG_AUFS_DEBUG) += debug.o
+aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o
diff --git a/fs/aufs/aufs.h b/fs/aufs/aufs.h
new file mode 100644
index 0000000..a599aee
--- /dev/null
+++ b/fs/aufs/aufs.h
@@ -0,0 +1,43 @@
+/*
+ * 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.
+ */
+
+/*
+ * all header files
+ */
+
+#ifndef __AUFS_H__
+#define __AUFS_H__
+
+#ifdef __KERNEL__
+
+#include <linux/bug.h>
+
+#include "debug.h"
+
+#include "branch.h"
+#include "cpup.h"
+#include "dcsub.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 --git a/fs/aufs/module.c b/fs/aufs/module.c
new file mode 100644
index 0000000..c2219d3
--- /dev/null
+++ b/fs/aufs/module.c
@@ -0,0 +1,164 @@
+/*
+ * 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.
+ */
+
+/*
+ * module global variables and operations
+ */
+
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include "aufs.h"
+
+void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp)
+{
+ if (new_sz <= nused)
+ return p;
+
+ p = krealloc(p, new_sz, gfp);
+ if (p)
+ memset(p + nused, 0, new_sz - nused);
+ return p;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * aufs caches
+ */
+struct kmem_cache *au_cachep[AuCache_Last];
+static int __init au_cache_init(void)
+{
+ au_cachep[AuCache_DINFO] = AuCache(au_dinfo);
+ if (au_cachep[AuCache_DINFO])
+ au_cachep[AuCache_ICNTNR] = AuCache(au_icntnr);
+ if (au_cachep[AuCache_ICNTNR])
+ au_cachep[AuCache_FINFO] = AuCache(au_finfo);
+ if (au_cachep[AuCache_FINFO])
+ au_cachep[AuCache_VDIR] = AuCache(au_vdir);
+ if (au_cachep[AuCache_VDIR])
+ au_cachep[AuCache_DEHSTR] = AuCache(au_vdir_dehstr);
+ if (au_cachep[AuCache_DEHSTR])
+ return 0;
+
+ return -ENOMEM;
+}
+
+static void au_cache_fin(void)
+{
+ int i;
+ for (i = 0; i < AuCache_Last; i++)
+ if (au_cachep[i]) {
+ kmem_cache_destroy(au_cachep[i]);
+ au_cachep[i] = NULL;
+ }
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_dir_roflags;
+
+/*
+ * functions for module interface.
+ */
+MODULE_LICENSE("GPL");
+/* MODULE_LICENSE("GPL v2"); */
+MODULE_AUTHOR("Junjiro R. Okajima");
+MODULE_DESCRIPTION(AUFS_NAME
+ " -- Advanced multi layered unification filesystem");
+MODULE_VERSION(AUFS_VERSION);
+
+/* it should be 'byte', but param_set_byte() prints it by "%c" */
+short aufs_nwkq = AUFS_NWKQ_DEF;
+MODULE_PARM_DESC(nwkq, "the number of workqueue thread, " AUFS_WKQ_NAME);
+module_param_named(nwkq, aufs_nwkq, short, S_IRUGO);
+
+/* this module parameter has no meaning when SYSFS is disabled */
+int sysaufs_brs = 1;
+MODULE_PARM_DESC(brs, "use <sysfs>/fs/aufs/si_*/brN");
+module_param_named(brs, sysaufs_brs, int, S_IRUGO);
+
+/* ---------------------------------------------------------------------- */
+
+static char au_esc_chars[0x20 + 3]; /* 0x01-0x20, backslash, del, and NULL */
+
+int au_seq_path(struct seq_file *seq, struct path *path)
+{
+ return seq_path(seq, path, au_esc_chars);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int __init aufs_init(void)
+{
+ int err, i;
+ char *p;
+
+ p = au_esc_chars;
+ for (i = 1; i <= ' '; i++)
+ *p++ = i;
+ *p++ = '\\';
+ *p++ = '\x7f';
+ *p = 0;
+
+ au_dir_roflags = au_file_roflags(O_DIRECTORY | O_LARGEFILE);
+
+ sysaufs_brs_init();
+ au_debug_init();
+
+ err = -EINVAL;
+ if (unlikely(aufs_nwkq <= 0))
+ goto out;
+
+ err = sysaufs_init();
+ if (unlikely(err))
+ goto out;
+ err = au_wkq_init();
+ if (unlikely(err))
+ goto out_sysaufs;
+ err = au_hinotify_init();
+ if (unlikely(err))
+ goto out_wkq;
+ err = au_sysrq_init();
+ if (unlikely(err))
+ goto out_hin;
+ err = au_cache_init();
+ if (unlikely(err))
+ goto out_sysrq;
+ err = register_filesystem(&aufs_fs_type);
+ if (unlikely(err))
+ goto out_cache;
+ pr_info(AUFS_NAME " " AUFS_VERSION "\n");
+ goto out; /* success */
+
+ out_cache:
+ au_cache_fin();
+ out_sysrq:
+ au_sysrq_fin();
+ out_hin:
+ au_hinotify_fin();
+ out_wkq:
+ au_wkq_fin();
+ out_sysaufs:
+ sysaufs_fin();
+ out:
+ return err;
+}
+
+static void __exit aufs_exit(void)
+{
+ unregister_filesystem(&aufs_fs_type);
+ au_cache_fin();
+ au_sysrq_fin();
+ au_hinotify_fin();
+ au_wkq_fin();
+ sysaufs_fin();
+}
+
+module_init(aufs_init);
+module_exit(aufs_exit);
diff --git a/fs/aufs/module.h b/fs/aufs/module.h
new file mode 100644
index 0000000..85e397a
--- /dev/null
+++ b/fs/aufs/module.h
@@ -0,0 +1,66 @@
+/*
+ * 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.
+ */
+
+/*
+ * module initialization and module-global
+ */
+
+#ifndef __AUFS_MODULE_H__
+#define __AUFS_MODULE_H__
+
+#ifdef __KERNEL__
+
+#include <linux/slab.h>
+
+/* module parameters */
+extern short aufs_nwkq;
+extern int sysaufs_brs;
+
+/* ---------------------------------------------------------------------- */
+
+extern int au_dir_roflags;
+
+void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp);
+int au_seq_path(struct seq_file *seq, struct path *path);
+
+/* ---------------------------------------------------------------------- */
+
+/* kmem cache */
+enum {
+ AuCache_DINFO,
+ AuCache_ICNTNR,
+ AuCache_FINFO,
+ AuCache_VDIR,
+ AuCache_DEHSTR,
+#ifdef CONFIG_AUFS_HINOTIFY
+ AuCache_HINOTIFY,
+#endif
+ AuCache_Last
+};
+
+#define AuCache(type) KMEM_CACHE(type, SLAB_RECLAIM_ACCOUNT)
+
+extern struct kmem_cache *au_cachep[];
+
+#define AuCacheFuncs(name, index) \
+static inline void *au_cache_alloc_##name(void) \
+{ return kmem_cache_alloc(au_cachep[AuCache_##index], GFP_NOFS); } \
+static inline void au_cache_free_##name(void *p) \
+{ kmem_cache_free(au_cachep[AuCache_##index], p); }
+
+AuCacheFuncs(dinfo, DINFO);
+AuCacheFuncs(icntnr, ICNTNR);
+AuCacheFuncs(finfo, FINFO);
+AuCacheFuncs(vdir, VDIR);
+AuCacheFuncs(dehstr, DEHSTR);
+
+/* ---------------------------------------------------------------------- */
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_MODULE_H__ */
diff --git a/fs/aufs/rwsem.h b/fs/aufs/rwsem.h
new file mode 100644
index 0000000..d569243
--- /dev/null
+++ b/fs/aufs/rwsem.h
@@ -0,0 +1,52 @@
+/*
+ * 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.
+ */
+
+/*
+ * simple read-write semaphore wrappers
+ */
+
+#ifndef __AUFS_RWSEM_H__
+#define __AUFS_RWSEM_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+
+#define au_rwsem_destroy(rw) AuDebugOn(rwsem_is_locked(rw))
+#define AuRwMustNoWaiters(rw) AuDebugOn(!list_empty(&(rw)->wait_list))
+
+#define AuSimpleLockRwsemFuncs(prefix, param, rwsem) \
+static inline void prefix##_read_lock(param) \
+{ down_read(rwsem); } \
+static inline void prefix##_write_lock(param) \
+{ down_write(rwsem); } \
+static inline int prefix##_read_trylock(param) \
+{ return down_read_trylock(rwsem); } \
+static inline int prefix##_write_trylock(param) \
+{ return down_write_trylock(rwsem); }
+/* why is not _nested version defined */
+/* static inline void prefix##_read_trylock_nested(param, lsc)
+{ down_write_trylock_nested(rwsem, lsc)); }
+static inline void prefix##_write_trylock_nestd(param, lsc)
+{ down_write_trylock_nested(rwsem, lsc); } */
+
+#define AuSimpleUnlockRwsemFuncs(prefix, param, rwsem) \
+static inline void prefix##_read_unlock(param) \
+{ up_read(rwsem); } \
+static inline void prefix##_write_unlock(param) \
+{ up_write(rwsem); } \
+static inline void prefix##_downgrade_lock(param) \
+{ downgrade_write(rwsem); }
+
+#define AuSimpleRwsemFuncs(prefix, param, rwsem) \
+ AuSimpleLockRwsemFuncs(prefix, param, rwsem) \
+ AuSimpleUnlockRwsemFuncs(prefix, param, rwsem)
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_RWSEM_H__ */
diff --git a/fs/aufs/spl.h b/fs/aufs/spl.h
new file mode 100644
index 0000000..89ea7a2
--- /dev/null
+++ b/fs/aufs/spl.h
@@ -0,0 +1,47 @@
+/*
+ * 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.
+ */
+
+/*
+ * simple list protected by a spinlock
+ */
+
+#ifndef __AUFS_SPL_H__
+#define __AUFS_SPL_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+
+struct au_splhead {
+ spinlock_t spin;
+ struct list_head head;
+};
+
+static inline void au_spl_init(struct au_splhead *spl)
+{
+ spin_lock_init(&spl->spin);
+ INIT_LIST_HEAD(&spl->head);
+}
+
+static inline void au_spl_add(struct list_head *list, struct au_splhead *spl)
+{
+ spin_lock(&spl->spin);
+ list_add(list, &spl->head);
+ spin_unlock(&spl->spin);
+}
+
+static inline void au_spl_del(struct list_head *list, struct au_splhead *spl)
+{
+ spin_lock(&spl->spin);
+ list_del(list);
+ spin_unlock(&spl->spin);
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_SPL_H__ */
--
1.6.1.284.g5dc13

2009-03-09 03:35:42