-aufs3.8 kbuild patch
+aufs3.x-rcN kbuild patch
diff --git a/fs/Kconfig b/fs/Kconfig
-index 780725a..d460c05 100644
+index ec35851..a059d62 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
-@@ -211,6 +211,7 @@ source "fs/sysv/Kconfig"
+@@ -218,6 +218,7 @@ source "fs/sysv/Kconfig"
source "fs/ufs/Kconfig"
source "fs/exofs/Kconfig"
source "fs/f2fs/Kconfig"
endif # MISC_FILESYSTEMS
diff --git a/fs/Makefile b/fs/Makefile
-index 9d53192..e70f08f 100644
+index a88ac48..162500e 100644
--- a/fs/Makefile
+++ b/fs/Makefile
-@@ -127,3 +127,4 @@ obj-$(CONFIG_F2FS_FS) += f2fs/
- obj-y += exofs/ # Multiple modules
+@@ -126,3 +126,4 @@ obj-y += exofs/ # Multiple modules
obj-$(CONFIG_CEPH_FS) += ceph/
obj-$(CONFIG_PSTORE) += pstore/
+ obj-$(CONFIG_EFIVAR_FS) += efivarfs/
+obj-$(CONFIG_AUFS_FS) += aufs/
-aufs3.8 base patch
+diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
+index 68ceb97..0352fa4 100644
+--- a/include/uapi/linux/Kbuild
++++ b/include/uapi/linux/Kbuild
+@@ -58,6 +58,7 @@ header-y += atmsvc.h
+ header-y += atm_tcp.h
+ header-y += atm_zatm.h
+ header-y += audit.h
++header-y += aufs_type.h
+ header-y += auto_fs4.h
+ header-y += auto_fs.h
+ header-y += auxvec.h
+aufs3.x-rcN base patch
-diff --git a/fs/file_table.c b/fs/file_table.c
-index de9e965..e73287a 100644
---- a/fs/file_table.c
-+++ b/fs/file_table.c
-@@ -36,7 +36,7 @@ struct files_stat_struct files_stat = {
- .max_files = NR_FILE
- };
+diff --git a/MAINTAINERS b/MAINTAINERS
+index efbcb50..30a1654 100644
+--- a/MAINTAINERS
++++ b/MAINTAINERS
+@@ -1864,6 +1864,20 @@ F: include/linux/audit.h
+ F: include/uapi/linux/audit.h
+ F: kernel/audit*
--DEFINE_STATIC_LGLOCK(files_lglock);
-+DEFINE_LGLOCK(files_lglock);
++AUFS (advanced multi layered unification filesystem) FILESYSTEM
++M: "J. R. Okajima" <hooanon05g@gmail.com>
++L: linux-unionfs@vger.kernel.org
++L: aufs-users@lists.sourceforge.net (members only)
++W: http://aufs.sourceforge.net
++T: git://git.code.sf.net/p/aufs/aufs3-linux
++T: git://github.com/sfjro/aufs3-linux.git
++S: Supported
++F: Documentation/filesystems/aufs/
++F: Documentation/ABI/testing/debugfs-aufs
++F: Documentation/ABI/testing/sysfs-aufs
++F: fs/aufs/
++F: include/uapi/linux/aufs_type.h
++
+ AUXILIARY DISPLAY DRIVERS
+ M: Miguel Ojeda Sandonis <miguel.ojeda.sandonis@gmail.com>
+ W: http://miguelojeda.es/auxdisplay.htm
+diff --git a/drivers/block/loop.c b/drivers/block/loop.c
+index d1f168b..a0da519 100644
+--- a/drivers/block/loop.c
++++ b/drivers/block/loop.c
+@@ -592,6 +592,24 @@ static inline int is_loop_device(struct file *file)
+ return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
+ }
- /* SLAB cache for file structures */
- static struct kmem_cache *filp_cachep __read_mostly;
-diff --git a/fs/inode.c b/fs/inode.c
-index 14084b7..ece87ed 100644
---- a/fs/inode.c
-+++ b/fs/inode.c
-@@ -1503,7 +1503,7 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
- * This does the actual work of updating an inodes time or version. Must have
- * had called mnt_want_write() before calling this.
++/*
++ * for AUFS
++ * no get/put for file.
++ */
++struct file *loop_backing_file(struct super_block *sb)
++{
++ struct file *ret;
++ struct loop_device *l;
++
++ ret = NULL;
++ if (MAJOR(sb->s_dev) == LOOP_MAJOR) {
++ l = sb->s_bdev->bd_disk->private_data;
++ ret = l->lo_backing_file;
++ }
++ return ret;
++}
++EXPORT_SYMBOL(loop_backing_file);
++
+ /* loop sysfs attributes */
+
+ static ssize_t loop_attr_show(struct device *dev, char *page,
+diff --git a/fs/dcache.c b/fs/dcache.c
+index c71e373..b93a9f2 100644
+--- a/fs/dcache.c
++++ b/fs/dcache.c
+@@ -1130,7 +1130,7 @@ enum d_walk_ret {
+ *
+ * The @enter() and @finish() callbacks are called with d_lock held.
*/
--static int update_time(struct inode *inode, struct timespec *time, int flags)
-+int update_time(struct inode *inode, struct timespec *time, int flags)
+-static void d_walk(struct dentry *parent, void *data,
++void d_walk(struct dentry *parent, void *data,
+ enum d_walk_ret (*enter)(void *, struct dentry *),
+ void (*finish)(void *))
{
- if (inode->i_op->update_time)
- return inode->i_op->update_time(inode, time, flags);
diff --git a/fs/splice.c b/fs/splice.c
-index 6909d89..020c7bc 100644
+index 7968da9..beb9993 100644
--- a/fs/splice.c
+++ b/fs/splice.c
-@@ -1092,8 +1092,8 @@ EXPORT_SYMBOL(generic_splice_sendpage);
+@@ -1099,8 +1099,8 @@ EXPORT_SYMBOL(generic_splice_sendpage);
/*
* Attempt to initiate a splice from pipe to file.
*/
{
ssize_t (*splice_write)(struct pipe_inode_info *, struct file *,
loff_t *, size_t, unsigned int);
-@@ -1120,9 +1120,9 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
+@@ -1116,9 +1116,9 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
/*
* Attempt to initiate a splice from a file to a pipe.
*/
{
ssize_t (*splice_read)(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
-diff --git a/include/linux/fs.h b/include/linux/fs.h
-index 7617ee0..1a39c33 100644
---- a/include/linux/fs.h
-+++ b/include/linux/fs.h
-@@ -2551,6 +2551,7 @@ extern int inode_change_ok(const struct inode *, struct iattr *);
- extern int inode_newsize_ok(const struct inode *, loff_t offset);
- extern void setattr_copy(struct inode *inode, const struct iattr *attr);
-
-+extern int update_time(struct inode *, struct timespec *, int);
- extern int file_update_time(struct file *file);
+diff --git a/include/linux/file.h b/include/linux/file.h
+index f87d308..9a290b3 100644
+--- a/include/linux/file.h
++++ b/include/linux/file.h
+@@ -19,6 +19,7 @@ struct dentry;
+ struct path;
+ extern struct file *alloc_file(struct path *, fmode_t mode,
+ const struct file_operations *fop);
++extern struct file *get_empty_filp(void);
- extern int generic_show_options(struct seq_file *m, struct dentry *root);
+ static inline void fput_light(struct file *file, int fput_needed)
+ {
diff --git a/include/linux/splice.h b/include/linux/splice.h
-index 09a545a..1ac5727 100644
+index da2751d..2e0fca6 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
-@@ -91,4 +91,10 @@ extern void splice_shrink_spd(struct splice_pipe_desc *);
+@@ -83,4 +83,10 @@ extern void splice_shrink_spd(struct splice_pipe_desc *);
extern void spd_release_page(struct splice_pipe_desc *, unsigned int);
extern const struct pipe_buf_operations page_cache_pipe_buf_ops;
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags);
#endif
-aufs3.8 standalone patch
+aufs3.x-rcN mmap patch
-diff --git a/fs/file_table.c b/fs/file_table.c
-index e73287a..b33aebe 100644
---- a/fs/file_table.c
-+++ b/fs/file_table.c
-@@ -37,6 +37,7 @@ struct files_stat_struct files_stat = {
- };
+diff --git a/fs/buffer.c b/fs/buffer.c
+index 20805db..363569f 100644
+--- a/fs/buffer.c
++++ b/fs/buffer.c
+@@ -2450,7 +2450,7 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+ * Update file times before taking page lock. We may end up failing the
+ * fault so this update may be superfluous but who really cares...
+ */
+- file_update_time(vma->vm_file);
++ vma_file_update_time(vma);
- DEFINE_LGLOCK(files_lglock);
-+EXPORT_SYMBOL(files_lglock);
+ ret = __block_page_mkwrite(vma, vmf, get_block);
+ sb_end_pagefault(sb);
+diff --git a/fs/proc/base.c b/fs/proc/base.c
+index 3f3d7ae..426bcc7 100644
+--- a/fs/proc/base.c
++++ b/fs/proc/base.c
+@@ -1735,7 +1735,7 @@ static int proc_map_files_get_link(struct dentry *dentry, struct path *path)
+ down_read(&mm->mmap_sem);
+ vma = find_exact_vma(mm, vm_start, vm_end);
+ if (vma && vma->vm_file) {
+- *path = vma->vm_file->f_path;
++ *path = vma_pr_or_file(vma)->f_path;
+ path_get(path);
+ rc = 0;
+ }
+diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
+index d4a3574..1397181 100644
+--- a/fs/proc/nommu.c
++++ b/fs/proc/nommu.c
+@@ -45,7 +45,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
+ file = region->vm_file;
- /* SLAB cache for file structures */
- static struct kmem_cache *filp_cachep __read_mostly;
-@@ -403,6 +404,8 @@ void file_sb_list_del(struct file *file)
+ if (file) {
+- struct inode *inode = file_inode(region->vm_file);
++ struct inode *inode;
++
++ file = vmr_pr_or_file(region);
++ inode = file_inode(file);
+ dev = inode->i_sb->s_dev;
+ ino = inode->i_ino;
}
+diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
+index 6dee68d..9afa35d 100644
+--- a/fs/proc/task_mmu.c
++++ b/fs/proc/task_mmu.c
+@@ -279,7 +279,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
+ const char *name = NULL;
+
+ if (file) {
+- struct inode *inode = file_inode(vma->vm_file);
++ struct inode *inode;
++
++ file = vma_pr_or_file(vma);
++ inode = file_inode(file);
+ dev = inode->i_sb->s_dev;
+ ino = inode->i_ino;
+ pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
+@@ -1479,7 +1482,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
+ struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
+ struct vm_area_struct *vma = v;
+ struct numa_maps *md = &numa_priv->md;
+- struct file *file = vma->vm_file;
++ struct file *file = vma_pr_or_file(vma);
+ struct mm_struct *mm = vma->vm_mm;
+ struct mm_walk walk = {
+ .hugetlb_entry = gather_hugetlb_stats,
+diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
+index 599ec2e..1740207 100644
+--- a/fs/proc/task_nommu.c
++++ b/fs/proc/task_nommu.c
+@@ -160,7 +160,10 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
+ file = vma->vm_file;
+
+ if (file) {
+- struct inode *inode = file_inode(vma->vm_file);
++ struct inode *inode;
++
++ file = vma_pr_or_file(vma);
++ inode = file_inode(file);
+ dev = inode->i_sb->s_dev;
+ ino = inode->i_ino;
+ pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
+diff --git a/include/linux/mm.h b/include/linux/mm.h
+index 47a9392..c8f8b46 100644
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -1254,6 +1254,28 @@ static inline int fixup_user_fault(struct task_struct *tsk,
+ }
+ #endif
+
++extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int);
++extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[],
++ int);
++extern void vma_do_get_file(struct vm_area_struct *, const char[], int);
++extern void vma_do_fput(struct vm_area_struct *, const char[], int);
++
++#define vma_file_update_time(vma) vma_do_file_update_time(vma, __func__, \
++ __LINE__)
++#define vma_pr_or_file(vma) vma_do_pr_or_file(vma, __func__, \
++ __LINE__)
++#define vma_get_file(vma) vma_do_get_file(vma, __func__, __LINE__)
++#define vma_fput(vma) vma_do_fput(vma, __func__, __LINE__)
++
++#ifndef CONFIG_MMU
++extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int);
++extern void vmr_do_fput(struct vm_region *, const char[], int);
++
++#define vmr_pr_or_file(region) vmr_do_pr_or_file(region, __func__, \
++ __LINE__)
++#define vmr_fput(region) vmr_do_fput(region, __func__, __LINE__)
++#endif /* !CONFIG_MMU */
++
+ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
+ extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
+ void *buf, int len, int write);
+diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
+index 199a03a..ed38ea3 100644
+--- a/include/linux/mm_types.h
++++ b/include/linux/mm_types.h
+@@ -241,6 +241,7 @@ struct vm_region {
+ unsigned long vm_top; /* region allocated to here */
+ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */
+ struct file *vm_file; /* the backing file or NULL */
++ struct file *vm_prfile; /* the virtual backing file or NULL */
+
+ int vm_usage; /* region usage count (access under nommu_region_sem) */
+ bool vm_icache_flushed : 1; /* true if the icache has been flushed for
+@@ -305,6 +306,7 @@ struct vm_area_struct {
+ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
+ units, *not* PAGE_CACHE_SIZE */
+ struct file * vm_file; /* File we map to (can be NULL). */
++ struct file *vm_prfile; /* shadow of vm_file */
+ void * vm_private_data; /* was vm_pte (shared mem) */
+
+ #ifndef CONFIG_MMU
+diff --git a/kernel/fork.c b/kernel/fork.c
+index cf65139..f28a048 100644
+--- a/kernel/fork.c
++++ b/kernel/fork.c
+@@ -430,7 +430,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+ struct inode *inode = file_inode(file);
+ struct address_space *mapping = file->f_mapping;
+
+- get_file(file);
++ vma_get_file(tmp);
+ if (tmp->vm_flags & VM_DENYWRITE)
+ atomic_dec(&inode->i_writecount);
+ i_mmap_lock_write(mapping);
+diff --git a/mm/Makefile b/mm/Makefile
+index 15dbe99..88e25b5 100644
+--- a/mm/Makefile
++++ b/mm/Makefile
+@@ -21,7 +21,7 @@ obj-y := filemap.o mempool.o oom_kill.o \
+ mm_init.o mmu_context.o percpu.o slab_common.o \
+ compaction.o vmacache.o \
+ interval_tree.o list_lru.o workingset.o \
+- debug.o $(mmu-y)
++ prfile.o debug.o $(mmu-y)
+
+ obj-y += init-mm.o
+
+diff --git a/mm/filemap.c b/mm/filemap.c
+index ad72420..8885258 100644
+--- a/mm/filemap.c
++++ b/mm/filemap.c
+@@ -2064,7 +2064,7 @@ int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+ int ret = VM_FAULT_LOCKED;
+
+ sb_start_pagefault(inode->i_sb);
+- file_update_time(vma->vm_file);
++ vma_file_update_time(vma);
+ lock_page(page);
+ if (page->mapping != inode->i_mapping) {
+ unlock_page(page);
+diff --git a/mm/madvise.c b/mm/madvise.c
+index d551475..1ebf71b 100644
+--- a/mm/madvise.c
++++ b/mm/madvise.c
+@@ -320,12 +320,12 @@ static long madvise_remove(struct vm_area_struct *vma,
+ * vma's reference to the file) can go away as soon as we drop
+ * mmap_sem.
+ */
+- get_file(f);
++ vma_get_file(vma);
+ up_read(¤t->mm->mmap_sem);
+ error = vfs_fallocate(f,
+ FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+ offset, end - start);
+- fput(f);
++ vma_fput(vma);
+ down_read(¤t->mm->mmap_sem);
+ return error;
}
+diff --git a/mm/memory.c b/mm/memory.c
+index 97839f5..5e5d491 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -2034,7 +2034,7 @@ static inline int wp_page_reuse(struct m
+ }
+
+ if (!page_mkwrite)
+- file_update_time(vma->vm_file);
++ vma_file_update_time(vma);
+ }
+
+ return VM_FAULT_WRITE;
+diff --git a/mm/mmap.c b/mm/mmap.c
+index 9ec50a3..4a6a641 100644
+--- a/mm/mmap.c
++++ b/mm/mmap.c
+@@ -274,7 +274,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
+ if (vma->vm_ops && vma->vm_ops->close)
+ vma->vm_ops->close(vma);
+ if (vma->vm_file)
+- fput(vma->vm_file);
++ vma_fput(vma);
+ mpol_put(vma_policy(vma));
+ kmem_cache_free(vm_area_cachep, vma);
+ return next;
+@@ -886,7 +886,7 @@ again: remove_next = 1 + (end > next->vm_end);
+ if (remove_next) {
+ if (file) {
+ uprobe_munmap(next, next->vm_start, next->vm_end);
+- fput(file);
++ vma_fput(vma);
+ }
+ if (next->anon_vma)
+ anon_vma_merge(vma, next);
+@@ -1671,8 +1671,8 @@ out:
+ return addr;
+
+ unmap_and_free_vma:
++ vma_fput(vma);
+ vma->vm_file = NULL;
+- fput(file);
+
+ /* Undo any partial mapping done by a device driver. */
+ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
+@@ -2473,7 +2473,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
+ goto out_free_mpol;
+
+ if (new->vm_file)
+- get_file(new->vm_file);
++ vma_get_file(new);
-+EXPORT_SYMBOL(file_sb_list_del);
+ if (new->vm_ops && new->vm_ops->open)
+ new->vm_ops->open(new);
+@@ -2492,7 +2492,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
+ if (new->vm_ops && new->vm_ops->close)
+ new->vm_ops->close(new);
+ if (new->vm_file)
+- fput(new->vm_file);
++ vma_fput(new);
+ unlink_anon_vmas(new);
+ out_free_mpol:
+ mpol_put(vma_policy(new));
+@@ -2635,7 +2635,6 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+ struct vm_area_struct *vma;
+ unsigned long populate = 0;
+ unsigned long ret = -EINVAL;
+- struct file *file;
+
+ pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. "
+ "See Documentation/vm/remap_file_pages.txt.\n",
+@@ -2679,10 +2678,10 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+ munlock_vma_pages_range(vma, start, start + size);
+ }
+
+- file = get_file(vma->vm_file);
++ vma_get_file(vma);
+ ret = do_mmap_pgoff(vma->vm_file, start, size,
+ prot, flags, pgoff, &populate);
+- fput(file);
++ vma_fput(vma);
+ out:
+ up_write(&mm->mmap_sem);
+ if (populate)
+@@ -2950,7 +2949,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
+ if (anon_vma_clone(new_vma, vma))
+ goto out_free_mempol;
+ if (new_vma->vm_file)
+- get_file(new_vma->vm_file);
++ vma_get_file(new_vma);
+ if (new_vma->vm_ops && new_vma->vm_ops->open)
+ new_vma->vm_ops->open(new_vma);
+ vma_link(mm, new_vma, prev, rb_link, rb_parent);
+diff --git a/mm/msync.c b/mm/msync.c
+index bb04d53..5c24c54 100644
+--- a/mm/msync.c
++++ b/mm/msync.c
+@@ -84,10 +84,10 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
+ start = vma->vm_end;
+ if ((flags & MS_SYNC) && file &&
+ (vma->vm_flags & VM_SHARED)) {
+- get_file(file);
++ vma_get_file(vma);
+ up_read(&mm->mmap_sem);
+ error = vfs_fsync_range(file, fstart, fend, 1);
+- fput(file);
++ vma_fput(vma);
+ if (error || start >= end)
+ goto out;
+ down_read(&mm->mmap_sem);
+diff --git a/mm/nommu.c b/mm/nommu.c
+index 3fba2dc..870ce96 100644
+--- a/mm/nommu.c
++++ b/mm/nommu.c
+@@ -693,7 +693,7 @@ static void __put_nommu_region(struct vm_region *region)
+ up_write(&nommu_region_sem);
+
+ if (region->vm_file)
+- fput(region->vm_file);
++ vmr_fput(region);
+
+ /* IO memory and memory shared directly out of the pagecache
+ * from ramfs/tmpfs mustn't be released here */
+@@ -858,7 +858,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
+ if (vma->vm_ops && vma->vm_ops->close)
+ vma->vm_ops->close(vma);
+ if (vma->vm_file)
+- fput(vma->vm_file);
++ vma_fput(vma);
+ put_nommu_region(vma->vm_region);
+ kmem_cache_free(vm_area_cachep, vma);
+ }
+@@ -1398,7 +1398,7 @@ unsigned long do_mmap_pgoff(struct file *file,
+ goto error_just_free;
+ }
+ }
+- fput(region->vm_file);
++ vmr_fput(region);
+ kmem_cache_free(vm_region_jar, region);
+ region = pregion;
+ result = start;
+@@ -1474,10 +1474,10 @@ error_just_free:
+ up_write(&nommu_region_sem);
+ error:
+ if (region->vm_file)
+- fput(region->vm_file);
++ vmr_fput(region);
+ kmem_cache_free(vm_region_jar, region);
+ if (vma->vm_file)
+- fput(vma->vm_file);
++ vma_fput(vma);
+ kmem_cache_free(vm_area_cachep, vma);
+ kleave(" = %d", ret);
+ return ret;
+diff --git a/mm/prfile.c b/mm/prfile.c
+new file mode 100644
+index 0000000..6aa5ab5
+--- /dev/null
++++ b/mm/prfile.c
+@@ -0,0 +1,86 @@
++/*
++ * Mainly for aufs which mmap(2) diffrent file and wants to print different path
++ * in /proc/PID/maps.
++ * Call these functions via macros defined in linux/mm.h.
++ *
++ * See Documentation/filesystems/aufs/design/06mmap.txt
++ *
++ * Copyright (c) 2014 Junjro R. Okajima
++ * Copyright (c) 2014 Ian Campbell
++ */
++
++#include <linux/mm.h>
++#include <linux/file.h>
++#include <linux/fs.h>
++
++/* #define PRFILE_TRACE */
++static inline void prfile_trace(struct file *f, struct file *pr,
++ const char func[], int line, const char func2[])
++{
++#ifdef PRFILE_TRACE
++ if (pr)
++ pr_info("%s:%d: %s, %p\n", func, line, func2,
++ f ? (char *)f->f_path.dentry->d_name.name : "(null)");
++#endif
++}
++
++void vma_do_file_update_time(struct vm_area_struct *vma, const char func[],
++ int line)
++{
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++
++ prfile_trace(f, pr, func, line, __func__);
++ file_update_time(f);
++ if (f && pr)
++ file_update_time(pr);
++}
++
++struct file *vma_do_pr_or_file(struct vm_area_struct *vma, const char func[],
++ int line)
++{
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++
++ prfile_trace(f, pr, func, line, __func__);
++ return (f && pr) ? pr : f;
++}
++
++void vma_do_get_file(struct vm_area_struct *vma, const char func[], int line)
++{
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++
++ prfile_trace(f, pr, func, line, __func__);
++ get_file(f);
++ if (f && pr)
++ get_file(pr);
++}
++
++void vma_do_fput(struct vm_area_struct *vma, const char func[], int line)
++{
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
++
++ prfile_trace(f, pr, func, line, __func__);
++ fput(f);
++ if (f && pr)
++ fput(pr);
++}
++
++#ifndef CONFIG_MMU
++struct file *vmr_do_pr_or_file(struct vm_region *region, const char func[],
++ int line)
++{
++ struct file *f = region->vm_file, *pr = region->vm_prfile;
++
++ prfile_trace(f, pr, func, line, __func__);
++ return (f && pr) ? pr : f;
++}
++
++void vmr_do_fput(struct vm_region *region, const char func[], int line)
++{
++ struct file *f = region->vm_file, *pr = region->vm_prfile;
+
- #ifdef CONFIG_SMP
++ prfile_trace(f, pr, func, line, __func__);
++ fput(f);
++ if (f && pr)
++ fput(pr);
++}
++#endif /* !CONFIG_MMU */
+aufs3.x-rcN standalone patch
+
+diff --git a/fs/dcache.c b/fs/dcache.c
+index b93a9f2..5a010ee 100644
+--- a/fs/dcache.c
++++ b/fs/dcache.c
+@@ -1235,6 +1235,7 @@ rename_retry:
+ seq = 1;
+ goto again;
+ }
++EXPORT_SYMBOL(d_walk);
/*
+ * Search for at least 1 mount point in the dentry's subdirs.
+diff --git a/fs/file_table.c b/fs/file_table.c
+index 3f85411..00e9dcf 100644
+--- a/fs/file_table.c
++++ b/fs/file_table.c
+@@ -147,6 +147,7 @@ over:
+ }
+ return ERR_PTR(-ENFILE);
+ }
++EXPORT_SYMBOL(get_empty_filp);
+
+ /**
+ * alloc_file - allocate and initialize a 'struct file'
+@@ -308,6 +309,7 @@ void put_filp(struct file *file)
+ file_free(file);
+ }
+ }
++EXPORT_SYMBOL(put_filp);
+
+ void __init files_init(unsigned long mempages)
+ {
diff --git a/fs/inode.c b/fs/inode.c
-index ece87ed..38f7bc8 100644
+index f00b16f..eb7b8b5 100644
--- a/fs/inode.c
+++ b/fs/inode.c
-@@ -56,6 +56,7 @@ static struct hlist_head *inode_hashtable __read_mostly;
+@@ -58,6 +58,7 @@ static struct hlist_head *inode_hashtable __read_mostly;
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
/*
* Empty aops. Can be used for the cases where the user does not
-@@ -1519,6 +1520,7 @@ int update_time(struct inode *inode, struct timespec *time, int flags)
- mark_inode_dirty_sync(inode);
- return 0;
- }
-+EXPORT_SYMBOL(update_time);
-
- /**
- * touch_atime - update the access time
diff --git a/fs/namespace.c b/fs/namespace.c
-index 55605c5..aed7607 100644
+index 82ef140..a3aa4b9 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
-@@ -52,6 +52,7 @@ EXPORT_SYMBOL_GPL(fs_kobj);
- * tree or hash is modified or when a vfsmount structure is modified.
- */
- DEFINE_BRLOCK(vfsmount_lock);
-+EXPORT_SYMBOL(vfsmount_lock);
+@@ -463,6 +463,7 @@ void __mnt_drop_write(struct vfsmount *mnt)
+ mnt_dec_writers(real_mount(mnt));
+ preempt_enable();
+ }
++EXPORT_SYMBOL_GPL(__mnt_drop_write);
- static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
- {
-@@ -1424,6 +1425,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
+ /**
+ * mnt_drop_write - give up write access to a mount
+@@ -1718,6 +1719,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
}
return 0;
}
static void cleanup_group_ids(struct mount *mnt, struct mount *end)
{
diff --git a/fs/notify/group.c b/fs/notify/group.c
-index bd2625b..2ff2a0f 100644
+index d16b62c..06ca6bc 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -22,6 +22,7 @@
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
-@@ -65,6 +66,7 @@ void fsnotify_get_group(struct fsnotify_group *group)
+@@ -72,6 +73,7 @@ void fsnotify_get_group(struct fsnotify_group *group)
{
atomic_inc(&group->refcnt);
}
/*
* Drop a reference to a group. Free it if it's through.
-@@ -74,6 +76,7 @@ void fsnotify_put_group(struct fsnotify_group *group)
+@@ -81,6 +83,7 @@ void fsnotify_put_group(struct fsnotify_group *group)
if (atomic_dec_and_test(&group->refcnt))
fsnotify_final_destroy_group(group);
}
/*
* Create a new fsnotify_group and hold a reference for the group returned.
-@@ -102,6 +105,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
+@@ -109,6 +112,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
return group;
}
int fsnotify_fasync(int fd, struct file *file, int on)
{
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
-index fc6b49b..a6bb87d 100644
+index 92e48c7..d2c4b68 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
-@@ -115,6 +115,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
+@@ -109,6 +109,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
mark->free_mark(mark);
}
}
+EXPORT_SYMBOL(fsnotify_put_mark);
- /*
- * Any time a mark is getting freed we end up here.
-@@ -197,6 +198,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
+ /* Calculate mask of events for a list of marks */
+ u32 fsnotify_recalc_mask(struct hlist_head *head)
+@@ -202,6 +203,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
fsnotify_destroy_mark_locked(mark, group);
mutex_unlock(&group->mark_mutex);
}
+EXPORT_SYMBOL(fsnotify_destroy_mark);
- void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
- {
-@@ -281,6 +283,7 @@ err:
+ /*
+ * Destroy all marks in the given list. The marks must be already detached from
+@@ -376,6 +378,7 @@ err:
return ret;
}
int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
struct inode *inode, struct vfsmount *mnt, int allow_dups)
-@@ -342,6 +345,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
+@@ -455,6 +458,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
atomic_set(&mark->refcnt, 1);
mark->free_mark = free_mark;
}
static int fsnotify_mark_destroy(void *ignored)
{
diff --git a/fs/open.c b/fs/open.c
-index 9b33c0c..e3365035 100644
+index 33f9cbf..fcc7eb4 100644
--- a/fs/open.c
+++ b/fs/open.c
-@@ -60,6 +60,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
+@@ -62,6 +62,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
mutex_unlock(&dentry->d_inode->i_mutex);
return ret;
}
long vfs_truncate(struct path *path, loff_t length)
{
+@@ -672,6 +673,7 @@ int open_check_o_direct(struct file *f)
+ }
+ return 0;
+ }
++EXPORT_SYMBOL(open_check_o_direct);
+
+ static int do_dentry_open(struct file *f,
+ int (*open)(struct inode *, struct file *),
diff --git a/fs/splice.c b/fs/splice.c
-index 020c7bc..a622ade 100644
+index beb9993..813275a 100644
--- a/fs/splice.c
+++ b/fs/splice.c
-@@ -1116,6 +1116,7 @@ long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
+@@ -1112,6 +1112,7 @@ long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
return splice_write(pipe, out, ppos, len, flags);
}
/*
* Attempt to initiate a splice from a file to a pipe.
-@@ -1142,6 +1143,7 @@ long do_splice_to(struct file *in, loff_t *ppos,
+@@ -1138,6 +1139,7 @@ long do_splice_to(struct file *in, loff_t *ppos,
return splice_read(in, ppos, pipe, len, flags);
}
/**
* splice_direct_to_actor - splices data directly between two non-pipes
+diff --git a/fs/xattr.c b/fs/xattr.c
+index 4ef6985..6bb6303 100644
+--- a/fs/xattr.c
++++ b/fs/xattr.c
+@@ -207,6 +207,7 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value,
+ *xattr_value = value;
+ return error;
+ }
++EXPORT_SYMBOL(vfs_getxattr_alloc);
+
+ /* Compare an extended attribute value with the given value */
+ int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name,
diff --git a/security/commoncap.c b/security/commoncap.c
-index 7ee08c7..176edf1 100644
+index f66713b..fd4c4b8 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
-@@ -988,9 +988,11 @@ int cap_mmap_addr(unsigned long addr)
+@@ -975,9 +975,11 @@ int cap_mmap_addr(unsigned long addr)
}
return ret;
}
}
+EXPORT_SYMBOL(cap_mmap_file);
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
-index d794abc..a20f167 100644
+index 188c1d2..426d9af 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -7,6 +7,7 @@
#include <linux/list.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>
-@@ -631,6 +632,7 @@ int __devcgroup_inode_permission(struct inode *inode, int mask)
+@@ -849,6 +850,7 @@ int __devcgroup_inode_permission(struct inode *inode, int mask)
return __devcgroup_check_permission(type, imajor(inode), iminor(inode),
access);
}
int devcgroup_inode_mknod(int mode, dev_t dev)
{
diff --git a/security/security.c b/security/security.c
-index 7b88c6a..5d00a30 100644
+index e81d5bb..0b7b840 100644
--- a/security/security.c
+++ b/security/security.c
-@@ -396,6 +396,7 @@ int security_path_rmdir(struct path *dir, struct dentry *dentry)
+@@ -430,6 +430,7 @@ int security_path_rmdir(struct path *dir, struct dentry *dentry)
return 0;
return security_ops->path_rmdir(dir, dentry);
}
int security_path_unlink(struct path *dir, struct dentry *dentry)
{
-@@ -412,6 +413,7 @@ int security_path_symlink(struct path *dir, struct dentry *dentry,
+@@ -446,6 +447,7 @@ int security_path_symlink(struct path *dir, struct dentry *dentry,
return 0;
return security_ops->path_symlink(dir, dentry, old_name);
}
int security_path_link(struct dentry *old_dentry, struct path *new_dir,
struct dentry *new_dentry)
-@@ -420,6 +422,7 @@ int security_path_link(struct dentry *old_dentry, struct path *new_dir,
+@@ -454,6 +456,7 @@ int security_path_link(struct dentry *old_dentry, struct path *new_dir,
return 0;
return security_ops->path_link(old_dentry, new_dir, new_dentry);
}
+EXPORT_SYMBOL(security_path_link);
int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
- struct path *new_dir, struct dentry *new_dentry)
-@@ -438,6 +441,7 @@ int security_path_truncate(struct path *path)
+ struct path *new_dir, struct dentry *new_dentry,
+@@ -481,6 +484,7 @@ int security_path_truncate(struct path *path)
return 0;
return security_ops->path_truncate(path);
}
int security_path_chmod(struct path *path, umode_t mode)
{
-@@ -445,6 +449,7 @@ int security_path_chmod(struct path *path, umode_t mode)
+@@ -488,6 +492,7 @@ int security_path_chmod(struct path *path, umode_t mode)
return 0;
return security_ops->path_chmod(path, mode);
}
int security_path_chown(struct path *path, kuid_t uid, kgid_t gid)
{
-@@ -452,6 +457,7 @@ int security_path_chown(struct path *path, kuid_t uid, kgid_t gid)
+@@ -495,6 +500,7 @@ int security_path_chown(struct path *path, kuid_t uid, kgid_t gid)
return 0;
return security_ops->path_chown(path, uid, gid);
}
int security_path_chroot(struct path *path)
{
-@@ -528,6 +534,7 @@ int security_inode_readlink(struct dentry *dentry)
+@@ -580,6 +586,7 @@ int security_inode_readlink(struct dentry *dentry)
return 0;
return security_ops->inode_readlink(dentry);
}
int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd)
{
-@@ -542,6 +549,7 @@ int security_inode_permission(struct inode *inode, int mask)
+@@ -594,6 +601,7 @@ int security_inode_permission(struct inode *inode, int mask)
return 0;
return security_ops->inode_permission(inode, mask);
}
int security_inode_setattr(struct dentry *dentry, struct iattr *attr)
{
-@@ -663,6 +671,7 @@ int security_file_permission(struct file *file, int mask)
+@@ -716,6 +724,7 @@ int security_file_permission(struct file *file, int mask)
return fsnotify_perm(file, mask);
}
int security_file_alloc(struct file *file)
{
-@@ -723,6 +732,7 @@ int security_mmap_file(struct file *file, unsigned long prot,
+@@ -775,6 +784,7 @@ int security_mmap_file(struct file *file, unsigned long prot,
return ret;
return ima_file_mmap(file, prot);
}
{
diff -urN /usr/share/empty/Documentation/ABI/testing/debugfs-aufs linux/Documentation/ABI/testing/debugfs-aufs
--- /usr/share/empty/Documentation/ABI/testing/debugfs-aufs 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/ABI/testing/debugfs-aufs 2012-08-26 08:39:00.753841216 +0200
-@@ -0,0 +1,37 @@
++++ linux/Documentation/ABI/testing/debugfs-aufs 2014-01-30 21:10:02.794146538 +0100
+@@ -0,0 +1,50 @@
+What: /debug/aufs/si_<id>/
+Date: March 2009
-+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
++Contact: J. R. Okajima <hooanon05g@gmail.com>
+Description:
+ Under /debug/aufs, a directory named si_<id> is created
+ per aufs mount, where <id> is a unique id generated
+ internally.
+
++What: /debug/aufs/si_<id>/plink
++Date: Apr 2013
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ It has three lines and shows the information about the
++ pseudo-link. The first line is a single number
++ representing a number of buckets. The second line is a
++ number of pseudo-links per buckets (separated by a
++ blank). The last line is a single number representing a
++ total number of psedo-links.
++ When the aufs mount option 'noplink' is specified, it
++ will show "1\n0\n0\n".
++
+What: /debug/aufs/si_<id>/xib
+Date: March 2009
-+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
++Contact: J. R. Okajima <hooanon05g@gmail.com>
+Description:
+ It shows the consumed blocks by xib (External Inode Number
+ Bitmap), its block size and file size.
+
+What: /debug/aufs/si_<id>/xino0, xino1 ... xinoN
+Date: March 2009
-+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
++Contact: J. R. Okajima <hooanon05g@gmail.com>
+Description:
+ It shows the consumed blocks by xino (External Inode Number
+ Translation Table), its link count, block size and file
+
+What: /debug/aufs/si_<id>/xigen
+Date: March 2009
-+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
++Contact: J. R. Okajima <hooanon05g@gmail.com>
+Description:
+ It shows the consumed blocks by xigen (External Inode
+ Generation Table), its block size and file size.
+ will be empty. About XINO files, see the aufs manual.
diff -urN /usr/share/empty/Documentation/ABI/testing/sysfs-aufs linux/Documentation/ABI/testing/sysfs-aufs
--- /usr/share/empty/Documentation/ABI/testing/sysfs-aufs 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/ABI/testing/sysfs-aufs 2012-08-26 08:39:00.753841216 +0200
-@@ -0,0 +1,24 @@
++++ linux/Documentation/ABI/testing/sysfs-aufs 2014-01-30 21:10:02.794146538 +0100
+@@ -0,0 +1,31 @@
+What: /sys/fs/aufs/si_<id>/
+Date: March 2009
-+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
++Contact: J. R. Okajima <hooanon05g@gmail.com>
+Description:
+ Under /sys/fs/aufs, a directory named si_<id> is created
+ per aufs mount, where <id> is a unique id generated
+
+What: /sys/fs/aufs/si_<id>/br0, br1 ... brN
+Date: March 2009
-+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
++Contact: J. R. Okajima <hooanon05g@gmail.com>
+Description:
+ It shows the abolute path of a member directory (which
+ is called branch) in aufs, and its permission.
+
++What: /sys/fs/aufs/si_<id>/brid0, brid1 ... bridN
++Date: July 2013
++Contact: J. R. Okajima <hooanon05g@gmail.com>
++Description:
++ It shows the id of a member directory (which is called
++ branch) in aufs.
++
+What: /sys/fs/aufs/si_<id>/xi_path
+Date: March 2009
-+Contact: J. R. Okajima <hooanon05@yahoo.co.jp>
++Contact: J. R. Okajima <hooanon05g@gmail.com>
+Description:
+ It shows the abolute path of XINO (External Inode Number
+ Bitmap, Translation Table and Generation Table) file
+ will be empty. About XINO files, see the aufs manual.
diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/01intro.txt linux/Documentation/filesystems/aufs/design/01intro.txt
--- /usr/share/empty/Documentation/filesystems/aufs/design/01intro.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/01intro.txt 2013-02-19 08:40:03.943559493 +0100
-@@ -0,0 +1,162 @@
++++ linux/Documentation/filesystems/aufs/design/01intro.txt 2015-06-22 08:27:37.867501461 +0200
+@@ -0,0 +1,170 @@
+
-+# Copyright (C) 2005-2013 Junjiro R. Okajima
++# Copyright (C) 2005-2015 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Introduction
+----------------------------------------
+- multi layered stackable unification filesystem, the member directory
+ is called as a branch.
+- branch permission and attribute, 'readonly', 'real-readonly',
-+ 'readwrite', 'whiteout-able', 'link-able whiteout' and their
++ 'readwrite', 'whiteout-able', 'link-able whiteout', etc. and their
+ combination.
+- internal "file copy-on-write".
+- logical deletion, whiteout.
+- unnecessary copy-up may happen, for example mmap(MAP_PRIVATE) after
+ open(O_RDWR).
+
-+Unionfs has a longer history. When I started implementing a stacking filesystem
-+(Aug 2005), it already existed. It has virtual super_block, inode,
-+dentry and file objects and they have an array pointing lower same kind
-+objects. After contributing many patches for Unionfs, I re-started my
-+project AUFS (Jun 2006).
++In linux-3.18, "overlay" filesystem (formerly known as "overlayfs") was
++merged into mainline. This is another implementation of UnionMount as a
++separated filesystem. All the limitations and known problems which
++UnionMount are equally inherited to "overlay" filesystem.
++
++Unionfs has a longer history. When I started implementing a stackable
++filesystem (Aug 2005), it already existed. It has virtual super_block,
++inode, dentry and file objects and they have an array pointing lower
++same kind objects. After contributing many patches for Unionfs, I
++re-started my project AUFS (Jun 2006).
+
+In AUFS, the structure of filesystem resembles to Unionfs, but I
+implemented my own ideas, approaches and enhancements and it became
+- DM snapshot-merge may help a lot when users try merging. in the
+ fs-layer union, users will use rsync(1).
+
++You may want to read my old paper "Filesystems in LiveCD"
++(http://aufs.sourceforge.net/aufs2/report/sq/sq.pdf).
++
+
-+Several characters/aspects of aufs
++Several characters/aspects/persona of aufs
+----------------------------------------------------------------------
+
-+Aufs has several characters or aspects.
++Aufs has several characters, aspects or persona.
+1. a filesystem, callee of VFS helper
+2. sub-VFS, caller of VFS helper for branches
+3. a virtual filesystem which maintains persistent inode number
+numbers. This is particularly important to support exporting a
+filesystem via NFS. Aufs is a virtual filesystem which doesn't have a
+backend block device for its own. But some storage is necessary to
-+maintain inode number. It may be a large space and may not suit to keep
-+in memory. Aufs rents some space from its first writable branch
-+filesystem (by default) and creates file(s) on it. These files are
-+created by aufs internally and removed soon (currently) keeping opened.
++keep and maintain the inode numbers. It may be a large space and may not
++suit to keep in memory. Aufs rents some space from its first writable
++branch filesystem (by default) and creates file(s) on it. These files
++are created by aufs internally and removed soon (currently) keeping
++opened.
+Note: Because these files are removed, they are totally gone after
+ unmounting aufs. It means the inode numbers are not persistent
+ across unmount or reboot. I have a plan to make them really
+about it. But currently I have implemented it in kernel space.
diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/02struct.txt linux/Documentation/filesystems/aufs/design/02struct.txt
--- /usr/share/empty/Documentation/filesystems/aufs/design/02struct.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/02struct.txt 2013-02-19 08:40:03.943559493 +0100
-@@ -0,0 +1,226 @@
++++ linux/Documentation/filesystems/aufs/design/02struct.txt 2015-06-22 08:27:37.867501461 +0200
+@@ -0,0 +1,258 @@
+
-+# Copyright (C) 2005-2013 Junjiro R. Okajima
++# Copyright (C) 2005-2015 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Basic Aufs Internal Structure
+
+
+Aufs lookup operation finds /ro/fileA and gets dentry for that. These
+pointers are stored in a aufs dentry. The array in aufs dentry will be,
-+- [0] = NULL
++- [0] = NULL (because /rw/fileA doesn't exist)
+- [1] = /ro/fileA
+
+This style of an array is essentially same to the aufs
+superblock/inode/dentry/file objects.
+
+Because aufs supports manipulating branches, ie. add/delete/change
-+dynamically, these objects has its own generation. When branches are
-+changed, the generation in aufs superblock is incremented. And a
-+generation in other object are compared when it is accessed.
-+When a generation in other objects are obsoleted, aufs refreshes the
-+internal array.
++branches dynamically, these objects has its own generation. When
++branches are changed, the generation in aufs superblock is
++incremented. And a generation in other object are compared when it is
++accessed. When a generation in other objects are obsoleted, aufs
++refreshes the internal array.
+
+
+Superblock
+Additionally aufs superblock has some data for policies to select one
+among multiple writable branches, XIB files, pseudo-links and kobject.
+See below in detail.
-+About the policies which supports copy-down a directory, see policy.txt
-+too.
++About the policies which supports copy-down a directory, see
++wbr_policy.txt too.
+
+
+Branch and XINO(External Inode Number Translation Table)
+might appear. If your branch filesystem consumes disk space for such
+holes, then you should specify 'xino=' option at mounting aufs.
+
++Aufs has a mount option to free the disk blocks for such holes in XINO
++files on tmpfs or ramdisk. But it is not so effective actually. If you
++meet a problem of disk shortage due to XINO files, then you should try
++"tmpfs-ino.patch" (and "vfs-ino.patch" too) in aufs4-standalone.git.
++The patch localizes the assignment inumbers per tmpfs-mount and avoid
++the holes in XINO files.
++
+Also a writable branch has three kinds of "whiteout bases". All these
-+are existed when the branch is joined to aufs and the names are
++are existed when the branch is joined to aufs, and their names are
+whiteout-ed doubly, so that users will never see their names in aufs
+hierarchy.
-+1. a regular file which will be linked to all whiteouts.
++1. a regular file which will be hardlinked to all whiteouts.
+2. a directory to store a pseudo-link.
-+3. a directory to store an "orphan-ed" file temporary.
++3. a directory to store an "orphan"-ed file temporary.
+
+1. Whiteout Base
+ When you remove a file on a readonly branch, aufs handles it as a
+ creating a file under this dir, the file is unlinked.
+
+Because aufs supports manipulating branches, ie. add/delete/change
-+dynamically, a branch has its own id. When the branch order changes, aufs
-+finds the new index by searching the branch id.
++dynamically, a branch has its own id. When the branch order changes,
++aufs finds the new index by searching the branch id.
+
+
+Pseudo-link
+simple list. If fileB is read after unlinking fileA, aufs returns
+filedata from the pseudo-link instead of the lower readonly
+branch. Because the pseudo-link is based upon the inode, to keep the
-+inode number by xino (see above) is important.
++inode number by xino (see above) is essentially necessary.
+
+All the hardlinks under the Pseudo-link Directory of the writable branch
+should be restored in a proper location later. Aufs provides a utility
+XIB(external inode number bitmap)
+----------------------------------------------------------------------
+Addition to the xino file per a branch, aufs has an external inode number
-+bitmap in a superblock object. It is also a file such like a xino file.
++bitmap in a superblock object. It is also an internal file such like a
++xino file.
+It is a simple bitmap to mark whether the aufs inode number is in-use or
+not.
+To reduce the file I/O, aufs prepares a single memory page to cache xib.
+
-+Aufs implements a feature to truncate/refresh both of xino and xib to
++As well as XINO files, aufs has a feature to truncate/refresh XIB to
+reduce the number of consumed disk blocks for these files.
+
+
+with eliminating the whiteout-ed ones, and sets it to file (dir)
+object. So the file object has its entry list until it is closed. The
+entry list will be updated when the file position is zero and becomes
-+old. This decision is made in aufs automatically.
++obsoleted. This decision is made in aufs automatically.
+
+The dynamically allocated memory block for the name of entries has a
+unit of 512 bytes (by default) and stores the names contiguously (no
+its completion. This approach solves a problem of a signal handler
+simply.
+If aufs didn't adopt the workqueue and changed the privilege of the
-+process, and if the mkdir/write call arises SIGXFSZ or other signal,
-+then the user process might gain a privilege or the generated core file
-+was owned by a superuser.
++process, then the process may receive the unexpected SIGXFSZ or other
++signals.
+
+Also aufs uses the system global workqueue ("events" kernel thread) too
+for asynchronous tasks, such like handling inotify/fsnotify, re-creating a
+
+Basically the whiteout represents "logical deletion" which stops aufs to
+lookup further, but also it represents "dir is opaque" which also stop
-+lookup.
++further lookup.
+
+In aufs, rmdir(2) and rename(2) for dir uses whiteout alternatively.
+In order to make several functions in a single systemcall to be
+unique whiteouted name.
+For example, in rename(2) dir where the target dir already existed, aufs
+renames the target dir to a temporary unique whiteouted name before the
-+actual rename on a branch and then handles other actions (make it opaque,
++actual rename on a branch, and then handles other actions (make it opaque,
+update the attributes, etc). If an error happens in these actions, aufs
+simply renames the whiteouted name back and returns an error. If all are
+succeeded, aufs registers a function to remove the whiteouted unique
+internally and makes change to the new file on the upper writable branch.
+When the trigger systemcall does not update the timestamps of the parent
+dir, aufs reverts it after copy-up.
++
++
++Move-down (aufs3.9 and later)
++----------------------------------------------------------------------
++"Copy-up" is one of the essential feature in aufs. It copies a file from
++the lower readonly branch to the upper writable branch when a user
++changes something about the file.
++"Move-down" is an opposite action of copy-up. Basically this action is
++ran manually instead of automatically and internally.
++For desgin and implementation, aufs has to consider these issues.
++- whiteout for the file may exist on the lower branch.
++- ancestor directories may not exist on the lower branch.
++- diropq for the ancestor directories may exist on the upper branch.
++- free space on the lower branch will reduce.
++- another access to the file may happen during moving-down, including
++ UDBA (see "Revalidate Dentry and UDBA").
++- the file should not be hard-linked nor pseudo-linked. they should be
++ handled by auplink utility later.
++
++Sometimes users want to move-down a file from the upper writable branch
++to the lower readonly or writable branch. For instance,
++- the free space of the upper writable branch is going to run out.
++- create a new intermediate branch between the upper and lower branch.
++- etc.
++
++For this purpose, use "aumvdown" command in aufs-util.git.
+diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/03atomic_open.txt linux/Documentation/filesystems/aufs/design/03atomic_open.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/03atomic_open.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/03atomic_open.txt 2015-06-22 08:27:37.870834875 +0200
+@@ -0,0 +1,85 @@
++
++# Copyright (C) 2015 Junjiro R. Okajima
++#
++# This program is free software; you can redistribute it and/or modify
++# it under the terms of the GNU General Public License as published by
++# the Free Software Foundation; either version 2 of the License, or
++# (at your option) any later version.
++#
++# This program is distributed in the hope that it will be useful,
++# but WITHOUT ANY WARRANTY; without even the implied warranty of
++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++# GNU General Public License for more details.
++#
++# You should have received a copy of the GNU General Public License
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
++
++Support for a branch who has its ->atomic_open()
++----------------------------------------------------------------------
++The filesystems who implement its ->atomic_open() are not majority. For
++example NFSv4 does, and aufs should call NFSv4 ->atomic_open,
++particularly for open(O_CREAT|O_EXCL, 0400) case. Other than
++->atomic_open(), NFSv4 returns an error for this open(2). While I am not
++sure whether all filesystems who have ->atomic_open() behave like this,
++but NFSv4 surely returns the error.
++
++In order to support ->atomic_open() for aufs, there are a few
++approaches.
++
++A. Introduce aufs_atomic_open()
++ - calls one of VFS:do_last(), lookup_open() or atomic_open() for
++ branch fs.
++B. Introduce aufs_atomic_open() calling create, open and chmod. this is
++ an aufs user Pip Cet's approach
++ - calls aufs_create(), VFS finish_open() and notify_change().
++ - pass fake-mode to finish_open(), and then correct the mode by
++ notify_change().
++C. Extend aufs_open() to call branch fs's ->atomic_open()
++ - no aufs_atomic_open().
++ - aufs_lookup() registers the TID to an aufs internal object.
++ - aufs_create() does nothing when the matching TID is registered, but
++ registers the mode.
++ - aufs_open() calls branch fs's ->atomic_open() when the matching
++ TID is registered.
++D. Extend aufs_open() to re-try branch fs's ->open() with superuser's
++ credential
++ - no aufs_atomic_open().
++ - aufs_create() registers the TID to an internal object. this info
++ represents "this process created this file just now."
++ - when aufs gets EACCES from branch fs's ->open(), then confirm the
++ registered TID and re-try open() with superuser's credential.
++
++Pros and cons for each approach.
++
++A.
++ - straightforward but highly depends upon VFS internal.
++ - the atomic behavaiour is kept.
++ - some of parameters such as nameidata are hard to reproduce for
++ branch fs.
++ - large overhead.
++B.
++ - easy to implement.
++ - the atomic behavaiour is lost.
++C.
++ - the atomic behavaiour is kept.
++ - dirty and tricky.
++ - VFS checks whether the file is created correctly after calling
++ ->create(), which means this approach doesn't work.
++D.
++ - easy to implement.
++ - the atomic behavaiour is lost.
++ - to open a file with superuser's credential and give it to a user
++ process is a bad idea, since the file object keeps the credential
++ in it. It may affect LSM or something. This approach doesn't work
++ either.
++
++The approach A is ideal, but it hard to implement. So here is a
++variation of A, which is to be implemented.
++
++A-1. Introduce aufs_atomic_open()
++ - calls branch fs ->atomic_open() if exists. otherwise calls
++ vfs_create() and finish_open().
++ - the demerit is that the several checks after branch fs
++ ->atomic_open() are lost. in the ordinary case, the checks are
++ done by VFS:do_last(), lookup_open() and atomic_open(). some can
++ be implemented in aufs, but not all I am afraid.
diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/03lookup.txt linux/Documentation/filesystems/aufs/design/03lookup.txt
--- /usr/share/empty/Documentation/filesystems/aufs/design/03lookup.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/03lookup.txt 2013-02-19 08:40:03.943559493 +0100
-@@ -0,0 +1,106 @@
++++ linux/Documentation/filesystems/aufs/design/03lookup.txt 2015-06-22 08:27:37.870834875 +0200
+@@ -0,0 +1,113 @@
+
-+# Copyright (C) 2005-2013 Junjiro R. Okajima
++# Copyright (C) 2005-2015 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Lookup in a Branch
+----------------------------------------------------------------------
+Since aufs has a character of sub-VFS (see Introduction), it operates
-+lookup for branches as VFS does. It may be a heavy work. Generally
-+speaking struct nameidata is a bigger structure and includes many
-+information. But almost all lookup operation in aufs is the simplest
-+case, ie. lookup only an entry directly connected to its parent. Digging
-+down the directory hierarchy is unnecessary.
-+
-+VFS has a function lookup_one_len() for that use, but it is not usable
-+for a branch filesystem which requires struct nameidata. So aufs
-+implements a simple lookup wrapper function. When a branch filesystem
-+allows NULL as nameidata, it calls lookup_one_len(). Otherwise it builds
-+a simplest nameidata and calls lookup_hash().
-+Here aufs applies "a principle in NFSD", ie. if the filesystem supports
-+NFS-export, then it has to support NULL as a nameidata parameter for
-+->create(), ->lookup() and ->d_revalidate(). So the lookup wrapper in
-+aufs tests if ->s_export_op in the branch is NULL or not.
-+
-+When a branch is a remote filesystem, aufs basically trusts its
++lookup for branches as VFS does. It may be a heavy work. But almost all
++lookup operation in aufs is the simplest case, ie. lookup only an entry
++directly connected to its parent. Digging down the directory hierarchy
++is unnecessary. VFS has a function lookup_one_len() for that use, and
++aufs calls it.
++
++When a branch is a remote filesystem, aufs basically relies upon its
+->d_revalidate(), also aufs forces the hardest revalidate tests for
+them.
+For d_revalidate, aufs implements three levels of revalidate tests. See
+"Revalidate Dentry and UDBA" in detail.
+
+
-+Loopback Mount
++Test Only the Highest One for the Directory Permission (dirperm1 option)
+----------------------------------------------------------------------
-+Basically aufs supports any type of filesystem and block device for a
-+branch (actually there are some exceptions). But it is prohibited to add
-+a loopback mounted one whose backend file exists in a filesystem which is
-+already added to aufs. The reason is to protect aufs from a recursive
-+lookup. If it was allowed, the aufs lookup operation might re-enter a
-+lookup for the loopback mounted branch in the same context, and will
-+cause a deadlock.
++Let's try case study.
++- aufs has two branches, upper readwrite and lower readonly.
++ /au = /rw + /ro
++- "dirA" exists under /ro, but /rw. and its mode is 0700.
++- user invoked "chmod a+rx /au/dirA"
++- the internal copy-up is activated and "/rw/dirA" is created and its
++ permission bits are set to world readable.
++- then "/au/dirA" becomes world readable?
++
++In this case, /ro/dirA is still 0700 since it exists in readonly branch,
++or it may be a natively readonly filesystem. If aufs respects the lower
++branch, it should not respond readdir request from other users. But user
++allowed it by chmod. Should really aufs rejects showing the entries
++under /ro/dirA?
++
++To be honest, I don't have a good solution for this case. So aufs
++implements 'dirperm1' and 'nodirperm1' mount options, and leave it to
++users.
++When dirperm1 is specified, aufs checks only the highest one for the
++directory permission, and shows the entries. Otherwise, as usual, checks
++every dir existing on all branches and rejects the request.
++
++As a side effect, dirperm1 option improves the performance of aufs
++because the number of permission check is reduced when the number of
++branch is many.
+
+
+Revalidate Dentry and UDBA (User's Direct Branch Access)
+ itself.
+3. No Extra Validation
+ This is the simplest test and doesn't add any additional revalidation
-+ test, and skip therevalidatin in step 4. It is useful and improves
++ test, and skip the revalidation in step 4. It is useful and improves
+ aufs performance when system surely hide the aufs branches from user,
+ by over-mounting something (or another method).
diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/04branch.txt linux/Documentation/filesystems/aufs/design/04branch.txt
--- /usr/share/empty/Documentation/filesystems/aufs/design/04branch.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/04branch.txt 2013-02-19 08:40:03.943559493 +0100
-@@ -0,0 +1,76 @@
++++ linux/Documentation/filesystems/aufs/design/04branch.txt 2015-06-22 08:27:37.870834875 +0200
+@@ -0,0 +1,74 @@
+
-+# Copyright (C) 2005-2013 Junjiro R. Okajima
++# Copyright (C) 2005-2015 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Branch Manipulation
+
+Add a Branch
+----------------------------------------------------------------------
+o Confirm the adding dir exists outside of aufs, including loopback
-+ mount.
-+- and other various attributes...
++ mount, and its various attributes.
+o Initialize the xino file and whiteout bases if necessary.
+ See struct.txt.
+
+ writable branch, and the writable branch is world-writable, then a
+ malicious guy may create /etc/passwd on the writable branch directly
+ and the infected file will be valid in aufs.
-+ I am afraid it can be a security issue, but nothing to do except
++ I am afraid it can be a security issue, but aufs can do nothing except
+ producing a warning.
+
+
+ same named entry on the upper branch.
diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/05wbr_policy.txt linux/Documentation/filesystems/aufs/design/05wbr_policy.txt
--- /usr/share/empty/Documentation/filesystems/aufs/design/05wbr_policy.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/05wbr_policy.txt 2013-02-19 08:40:03.943559493 +0100
-@@ -0,0 +1,65 @@
++++ linux/Documentation/filesystems/aufs/design/05wbr_policy.txt 2015-06-22 08:27:37.870834875 +0200
+@@ -0,0 +1,64 @@
+
-+# Copyright (C) 2005-2013 Junjiro R. Okajima
++# Copyright (C) 2005-2015 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Policies to Select One among Multiple Writable Branches
+----------------------------------------------------------------------
+writable branch which has the parent (or ancestor) dir of the target
+file is chosen (top-down-parent policy).
+By user's request, aufs implements some other policies to select the
-+writable branch, for file creation two policies, round-robin and
-+most-free-space policies. For copy-up three policies, top-down-parent,
-+bottom-up-parent and bottom-up policies.
++writable branch, for file creation several policies, round-robin,
++most-free-space, and other policies. For copy-up, top-down-parent,
++bottom-up-parent, bottom-up and others.
+
+As expected, the round-robin policy selects the branch in circular. When
+you have two writable branches and creates 10 new files, 5 files will be
+ where the source and the target exists and selects the higher
+ one. If the selected branch is readonly, then aufs follows the
+ copyup policy.
-diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06mmap.txt linux/Documentation/filesystems/aufs/design/06mmap.txt
---- /usr/share/empty/Documentation/filesystems/aufs/design/06mmap.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/06mmap.txt 2013-02-19 08:40:03.943559493 +0100
-@@ -0,0 +1,47 @@
+diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06fhsm.txt linux/Documentation/filesystems/aufs/design/06fhsm.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/06fhsm.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/06fhsm.txt 2015-06-22 08:27:37.870834875 +0200
+@@ -0,0 +1,120 @@
+
-+# Copyright (C) 2005-2013 Junjiro R. Okajima
++# Copyright (C) 2011-2015 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+
++
++File-based Hierarchical Storage Management (FHSM)
++----------------------------------------------------------------------
++Hierarchical Storage Management (or HSM) is a well-known feature in the
++storage world. Aufs provides this feature as file-based with multiple
++writable branches, based upon the principle of "Colder, the Lower".
++Here the word "colder" means that the less used files, and "lower" means
++that the position in the order of the stacked branches vertically.
++These multiple writable branches are prioritized, ie. the topmost one
++should be the fastest drive and be used heavily.
++
++o Characters in aufs FHSM story
++- aufs itself and a new branch attribute.
++- a new ioctl interface to move-down and to establish a connection with
++ the daemon ("move-down" is a converse of "copy-up").
++- userspace tool and daemon.
++
++The userspace daemon establishes a connection with aufs and waits for
++the notification. The notified information is very similar to struct
++statfs containing the number of consumed blocks and inodes.
++When the consumed blocks/inodes of a branch exceeds the user-specified
++upper watermark, the daemon activates its move-down process until the
++consumed blocks/inodes reaches the user-specified lower watermark.
++
++The actual move-down is done by aufs based upon the request from
++user-space since we need to maintain the inode number and the internal
++pointer arrays in aufs.
++
++Currently aufs FHSM handles the regular files only. Additionally they
++must not be hard-linked nor pseudo-linked.
++
++
++o Cowork of aufs and the user-space daemon
++ During the userspace daemon established the connection, aufs sends a
++ small notification to it whenever aufs writes something into the
++ writable branch. But it may cost high since aufs issues statfs(2)
++ internally. So user can specify a new option to cache the
++ info. Actually the notification is controlled by these factors.
++ + the specified cache time.
++ + classified as "force" by aufs internally.
++ Until the specified time expires, aufs doesn't send the info
++ except the forced cases. When aufs decide forcing, the info is always
++ notified to userspace.
++ For example, the number of free inodes is generally large enough and
++ the shortage of it happens rarely. So aufs doesn't force the
++ notification when creating a new file, directory and others. This is
++ the typical case which aufs doesn't force.
++ When aufs writes the actual filedata and the files consumes any of new
++ blocks, the aufs forces notifying.
++
++
++o Interfaces in aufs
++- New branch attribute.
++ + fhsm
++ Specifies that the branch is managed by FHSM feature. In other word,
++ participant in the FHSM.
++ When nofhsm is set to the branch, it will not be the source/target
++ branch of the move-down operation. This attribute is set
++ independently from coo and moo attributes, and if you want full
++ FHSM, you should specify them as well.
++- New mount option.
++ + fhsm_sec
++ Specifies a second to suppress many less important info to be
++ notified.
++- New ioctl.
++ + AUFS_CTL_FHSM_FD
++ create a new file descriptor which userspace can read the notification
++ (a subset of struct statfs) from aufs.
++- Module parameter 'brs'
++ It has to be set to 1. Otherwise the new mount option 'fhsm' will not
++ be set.
++- mount helpers /sbin/mount.aufs and /sbin/umount.aufs
++ When there are two or more branches with fhsm attributes,
++ /sbin/mount.aufs invokes the user-space daemon and /sbin/umount.aufs
++ terminates it. As a result of remounting and branch-manipulation, the
++ number of branches with fhsm attribute can be one. In this case,
++ /sbin/mount.aufs will terminate the user-space daemon.
++
++
++Finally the operation is done as these steps in kernel-space.
++- make sure that,
++ + no one else is using the file.
++ + the file is not hard-linked.
++ + the file is not pseudo-linked.
++ + the file is a regular file.
++ + the parent dir is not opaqued.
++- find the target writable branch.
++- make sure the file is not whiteout-ed by the upper (than the target)
++ branch.
++- make the parent dir on the target branch.
++- mutex lock the inode on the branch.
++- unlink the whiteout on the target branch (if exists).
++- lookup and create the whiteout-ed temporary name on the target branch.
++- copy the file as the whiteout-ed temporary name on the target branch.
++- rename the whiteout-ed temporary name to the original name.
++- unlink the file on the source branch.
++- maintain the internal pointer array and the external inode number
++ table (XINO).
++- maintain the timestamps and other attributes of the parent dir and the
++ file.
++
++And of course, in every step, an error may happen. So the operation
++should restore the original file state after an error happens.
+diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06mmap.txt linux/Documentation/filesystems/aufs/design/06mmap.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/06mmap.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/06mmap.txt 2015-06-22 08:27:37.870834875 +0200
+@@ -0,0 +1,72 @@
++
++# Copyright (C) 2005-2015 Junjiro R. Okajima
++#
++# This program is free software; you can redistribute it and/or modify
++# it under the terms of the GNU General Public License as published by
++# the Free Software Foundation; either version 2 of the License, or
++# (at your option) any later version.
++#
++# This program is distributed in the hope that it will be useful,
++# but WITHOUT ANY WARRANTY; without even the implied warranty of
++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++# GNU General Public License for more details.
++#
++# You should have received a copy of the GNU General Public License
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
++
+mmap(2) -- File Memory Mapping
+----------------------------------------------------------------------
+In aufs, the file-mapped pages are handled by a branch fs directly, no
+interaction with aufs. It means aufs_mmap() calls the branch fs's
+->mmap().
+This approach is simple and good, but there is one problem.
-+Under /proc, several entries show the mmap-ped files by its path (with
++Under /proc, several entries show the mmapped files by its path (with
+device and inode number), and the printed path will be the path on the
+branch fs's instead of virtual aufs's.
+This is not a problem in most cases, but some utilities lsof(1) (and its
+ incremented.
+- merging vma maintains the ref count too.
+
-+This is not a good approach. It just faking the printed path. But it
++This is not a good approach. It just fakes the printed path. But it
+leaves all behaviour around f_mapping unchanged. This is surely an
+advantage.
+Actually aufs had adopted another complicated approach which calls
+generic_file_mmap() and handles struct vm_operations_struct. In this
+approach, aufs met a hard problem and I could not solve it without
+switching the approach.
++
++There may be one more another approach which is
++- bind-mount the branch-root onto the aufs-root internally
++- grab the new vfsmount (ie. struct mount)
++- lazy-umount the branch-root internally
++- in open(2) the aufs-file, open the branch-file with the hidden
++ vfsmount (instead of the original branch's vfsmount)
++- ideally this "bind-mount and lazy-umount" should be done atomically,
++ but it may be possible from userspace by the mount helper.
++
++Adding the internal hidden vfsmount and using it in opening a file, the
++file path under /proc will be printed correctly. This approach looks
++smarter, but is not possible I am afraid.
++- aufs-root may be bind-mount later. when it happens, another hidden
++ vfsmount will be required.
++- it is hard to get the chance to bind-mount and lazy-umount
++ + in kernel-space, FS can have vfsmount in open(2) via
++ file->f_path, and aufs can know its vfsmount. But several locks are
++ already acquired, and if aufs tries to bind-mount and lazy-umount
++ here, then it may cause a deadlock.
++ + in user-space, bind-mount doesn't invoke the mount helper.
++- since /proc shows dev and ino, aufs has to give vma these info. it
++ means a new member vm_prinode will be necessary. this is essentially
++ equivalent to vm_prfile described above.
++
++I have to give up this "looks-smater" approach.
+diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06xattr.txt linux/Documentation/filesystems/aufs/design/06xattr.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/06xattr.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/06xattr.txt 2015-06-22 08:27:37.870834875 +0200
+@@ -0,0 +1,96 @@
++
++# Copyright (C) 2014-2015 Junjiro R. Okajima
++#
++# This program is free software; you can redistribute it and/or modify
++# it under the terms of the GNU General Public License as published by
++# the Free Software Foundation; either version 2 of the License, or
++# (at your option) any later version.
++#
++# This program is distributed in the hope that it will be useful,
++# but WITHOUT ANY WARRANTY; without even the implied warranty of
++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++# GNU General Public License for more details.
++#
++# You should have received a copy of the GNU General Public License
++# along with this program; if not, write to the Free Software
++# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++
++
++Listing XATTR/EA and getting the value
++----------------------------------------------------------------------
++For the inode standard attributes (owner, group, timestamps, etc.), aufs
++shows the values from the topmost existing file. This behaviour is good
++for the non-dir entries since the bahaviour exactly matches the shown
++information. But for the directories, aufs considers all the same named
++entries on the lower branches. Which means, if one of the lower entry
++rejects readdir call, then aufs returns an error even if the topmost
++entry allows it. This behaviour is necessary to respect the branch fs's
++security, but can make users confused since the user-visible standard
++attributes don't match the behaviour.
++To address this issue, aufs has a mount option called dirperm1 which
++checks the permission for the topmost entry only, and ignores the lower
++entry's permission.
++
++A similar issue can happen around XATTR.
++getxattr(2) and listxattr(2) families behave as if dirperm1 option is
++always set. Otherwise these very unpleasant situation would happen.
++- listxattr(2) may return the duplicated entries.
++- users may not be able to remove or reset the XATTR forever,
++
++
++XATTR/EA support in the internal (copy,move)-(up,down)
++----------------------------------------------------------------------
++Generally the extended attributes of inode are categorized as these.
++- "security" for LSM and capability.
++- "system" for posix ACL, 'acl' mount option is required for the branch
++ fs generally.
++- "trusted" for userspace, CAP_SYS_ADMIN is required.
++- "user" for userspace, 'user_xattr' mount option is required for the
++ branch fs generally.
++
++Moreover there are some other categories. Aufs handles these rather
++unpopular categories as the ordinary ones, ie. there is no special
++condition nor exception.
++
++In copy-up, the support for XATTR on the dst branch may differ from the
++src branch. In this case, the copy-up operation will get an error and
++the original user operation which triggered the copy-up will fail. It
++can happen that even all copy-up will fail.
++When both of src and dst branches support XATTR and if an error occurs
++during copying XATTR, then the copy-up should fail obviously. That is a
++good reason and aufs should return an error to userspace. But when only
++the src branch support that XATTR, aufs should not return an error.
++For example, the src branch supports ACL but the dst branch doesn't
++because the dst branch may natively un-support it or temporary
++un-support it due to "noacl" mount option. Of course, the dst branch fs
++may NOT return an error even if the XATTR is not supported. It is
++totally up to the branch fs.
++
++Anyway when the aufs internal copy-up gets an error from the dst branch
++fs, then aufs tries removing the just copied entry and returns the error
++to the userspace. The worst case of this situation will be all copy-up
++will fail.
++
++For the copy-up operation, there two basic approaches.
++- copy the specified XATTR only (by category above), and return the
++ error unconditionally if it happens.
++- copy all XATTR, and ignore the error on the specified category only.
++
++In order to support XATTR and to implement the correct behaviour, aufs
++chooses the latter approach and introduces some new branch attributes,
++"icexsec", "icexsys", "icextr", "icexusr", and "icexoth".
++They correspond to the XATTR namespaces (see above). Additionally, to be
++convenient, "icex" is also provided which means all "icex*" attributes
++are set (here the word "icex" stands for "ignore copy-error on XATTR").
++
++The meaning of these attributes is to ignore the error from setting
++XATTR on that branch.
++Note that aufs tries copying all XATTR unconditionally, and ignores the
++error from the dst branch according to the specified attributes.
++
++Some XATTR may have its default value. The default value may come from
++the parent dir or the environment. If the default value is set at the
++file creating-time, it will be overwritten by copy-up.
++Some contradiction may happen I am afraid.
++Do we need another attribute to stop copying XATTR? I am unsure. For
++now, aufs implements the branch attributes to ignore the error.
diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/07export.txt linux/Documentation/filesystems/aufs/design/07export.txt
--- /usr/share/empty/Documentation/filesystems/aufs/design/07export.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/07export.txt 2013-02-19 08:40:03.943559493 +0100
-@@ -0,0 +1,59 @@
++++ linux/Documentation/filesystems/aufs/design/07export.txt 2015-06-22 08:27:37.870834875 +0200
+@@ -0,0 +1,58 @@
+
-+# Copyright (C) 2005-2013 Junjiro R. Okajima
++# Copyright (C) 2005-2015 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Export Aufs via NFS
+----------------------------------------------------------------------
+ + find the index of a branch from its id in handle, and check it is
+ still exist in aufs.
+ + 1st level: get the inode number from handle and search it in cache.
-+ + 2nd level: if not found, get the parent inode number from handle and
-+ search it in cache. and then open the parent dir, find the matching
-+ inode number by vfs_readdir() and get its name, and call
-+ lookup_one_len() for the target dentry.
++ + 2nd level: if not found in cache, get the parent inode number from
++ the handle and search it in cache. and then open the found parent
++ dir, find the matching inode number by vfs_readdir() and get its
++ name, and call lookup_one_len() for the target dentry.
+ + 3rd level: if the parent dir is not cached, call
+ exportfs_decode_fh() for a branch and get the parent on a branch,
+ build a pathname of it, convert it a pathname in aufs, call
+ lookup_one_len(), vfs_getattr(), encode_fh() and others.
diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/08shwh.txt linux/Documentation/filesystems/aufs/design/08shwh.txt
--- /usr/share/empty/Documentation/filesystems/aufs/design/08shwh.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/08shwh.txt 2013-02-19 08:40:03.943559493 +0100
-@@ -0,0 +1,53 @@
++++ linux/Documentation/filesystems/aufs/design/08shwh.txt 2015-06-22 08:27:37.870834875 +0200
+@@ -0,0 +1,52 @@
+
-+# Copyright (C) 2005-2013 Junjiro R. Okajima
++# Copyright (C) 2005-2015 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Show Whiteout Mode (shwh)
+----------------------------------------------------------------------
+initramfs will use it to replace the old one at the next boot.
diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/10dynop.txt linux/Documentation/filesystems/aufs/design/10dynop.txt
--- /usr/share/empty/Documentation/filesystems/aufs/design/10dynop.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/10dynop.txt 2013-02-19 08:40:03.943559493 +0100
++++ linux/Documentation/filesystems/aufs/design/10dynop.txt 2015-06-22 08:27:37.870834875 +0200
@@ -0,0 +1,47 @@
+
-+# Copyright (C) 2010-2013 Junjiro R. Okajima
++# Copyright (C) 2010-2015 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Dynamically customizable FS operations
+----------------------------------------------------------------------
+operation. Some FS have multiple sets of them. For instance, ext2 has
+three sets, one for XIP, for NOBH, and for normal.
+Since aufs overrides and redirects these operations, sometimes aufs has
-+to change its behaviour according to the branch FS type. More imporantly
++to change its behaviour according to the branch FS type. More importantly
+VFS acts differently if a function (member in the struct) is set or
+not. It means aufs should have several sets of operations and select one
+among them according to the branch FS definition.
+
-+In order to solve this problem and not to affect the behavour of VFS,
++In order to solve this problem and not to affect the behaviour of VFS,
+aufs defines these operations dynamically. For instance, aufs defines
-+aio_read function for struct file_operations, but it may not be set to
-+the file_operations. When the branch FS doesn't have it, aufs doesn't
-+set it to its file_operations while the function definition itself is
-+still alive. So the behaviour of io_submit(2) will not change, and it
-+will return an error when aio_read is not defined.
++dummy direct_IO function for struct address_space_operations, but it may
++not be set to the address_space_operations actually. When the branch FS
++doesn't have it, aufs doesn't set it to its address_space_operations
++while the function definition itself is still alive. So the behaviour
++itself will not change, and it will return an error when direct_IO is
++not set.
+
+The lifetime of these dynamically generated operation object is
+maintained by aufs branch object. When the branch is removed from aufs,
+the reference counter of the object is decremented. When it reaches
+zero, the dynamically generated operation object will be freed.
+
-+This approach is designed to support AIO (io_submit), Direcit I/O and
-+XIP mainly.
-+Currently this approach is applied to file_operations and
-+vm_operations_struct for regular files only.
++This approach is designed to support AIO (io_submit), Direct I/O and
++XIP (DAX) mainly.
++Currently this approach is applied to address_space_operations for
++regular files only.
diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/99plan.txt linux/Documentation/filesystems/aufs/design/99plan.txt
--- /usr/share/empty/Documentation/filesystems/aufs/design/99plan.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/design/99plan.txt 2013-02-19 08:40:03.943559493 +0100
-@@ -0,0 +1,96 @@
++++ linux/Documentation/filesystems/aufs/design/99plan.txt 2015-06-22 08:27:37.870834875 +0200
+@@ -0,0 +1,57 @@
+
-+# Copyright (C) 2005-2013 Junjiro R. Okajima
++# Copyright (C) 2005-2015 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Plan
+
+easier to be reviewed.
+
+
-+Test Only the Highest One for the Directory Permission (dirperm1 option)
-+----------------------------------------------------------------------
-+Let's try case study.
-+- aufs has two branches, upper readwrite and lower readonly.
-+ /au = /rw + /ro
-+- "dirA" exists under /ro, but /rw. and its mode is 0700.
-+- user invoked "chmod a+rx /au/dirA"
-+- then "dirA" becomes world readable?
-+
-+In this case, /ro/dirA is still 0700 since it exists in readonly branch,
-+or it may be a natively readonly filesystem. If aufs respects the lower
-+branch, it should not respond readdir request from other users. But user
-+allowed it by chmod. Should really aufs rejects showing the entries
-+under /ro/dirA?
-+
-+To be honest, I don't have a best solution for this case. So I
-+implemented 'dirperm1' and 'nodirperm1' option in aufs1, and leave it to
-+users.
-+When dirperm1 is specified, aufs checks only the highest one for the
-+directory permission, and shows the entries. Otherwise, as usual, checks
-+every dir existing on all branches and rejects the request.
-+
-+As a side effect, dirperm1 option improves the performance of aufs
-+because the number of permission check is reduced.
-+
-+
+Being Another Aufs's Readonly Branch (robr)
+----------------------------------------------------------------------
+Aufs1 allows aufs to be another aufs's readonly branch.
+This feature was developed by a user's request. But it may not be used
-+currecnly.
++currently.
+
+
-+Copy-up on Open (coo=)
++Refresh the Opened File (refrof)
+----------------------------------------------------------------------
-+By default the internal copy-up is executed when it is really necessary.
-+It is not done when a file is opened for writing, but when write(2) is
-+done. Users who have many (over 100) branches want to know and analyse
-+when and what file is copied-up. To insert a new upper branch which
-+contains such files only may improve the performance of aufs.
-+
-+Aufs1 implemented "coo=none | leaf | all" option.
-+
-+
-+Refresh the Opened File (refrof)
-+----------------------------------------------------------------------
-+This option is implemented in aufs1 but incomplete.
++This option is implemented in aufs1 but incomplete.
+
+When user reads from a file, he expects to get its latest filedata
+generally. If the file is removed and a new same named file is created,
+- user opened "/au/fileA".
+- he or someone else inserts a branch (/new) between /rw and /ro.
+ /au = /rw + /new + /ro
-+- the new branch has "fileA".
++- the new branch contains "fileA".
+- user reads from the opened "fileA"
+- which filedata should aufs return, from /ro or /new?
+
+Here again I don't have a best and final answer. I got an idea to
+implement 'refrof' and 'norefrof' option. When 'refrof' (REFResh the
+Opened File) is specified (by default), aufs returns the filedata from
-+/new.
-+Otherwise from /new.
++/new. Otherwise from /ro.
diff -urN /usr/share/empty/Documentation/filesystems/aufs/README linux/Documentation/filesystems/aufs/README
--- /usr/share/empty/Documentation/filesystems/aufs/README 1970-01-01 01:00:00.000000000 +0100
-+++ linux/Documentation/filesystems/aufs/README 2013-03-14 20:07:40.574775374 +0100
-@@ -0,0 +1,333 @@
++++ linux/Documentation/filesystems/aufs/README 2015-06-22 08:27:37.867501461 +0200
+@@ -0,0 +1,384 @@
+
+Aufs3 -- advanced multi layered unification filesystem version 3.x
+http://aufs.sf.net
+0. Introduction
+----------------------------------------
+In the early days, aufs was entirely re-designed and re-implemented
-+Unionfs Version 1.x series. After many original ideas, approaches,
++Unionfs Version 1.x series. Adding many original ideas, approaches,
+improvements and implementations, it becomes totally different from
+Unionfs while keeping the basic features.
+Recently, Unionfs Version 2.x series begin taking some of the same
+aufs2-standalone.git repository, aufs1 from CVS on SourceForge.
+
+Note: it becomes clear that "Aufs was rejected. Let's give it up."
-+According to Christoph Hellwig, linux rejects all union-type filesystems
-+but UnionMount.
++ According to Christoph Hellwig, linux rejects all union-type
++ filesystems but UnionMount.
+<http://marc.info/?l=linux-kernel&m=123938533724484&w=2>
+
++PS. Al Viro seems have a plan to merge aufs as well as overlayfs and
++ UnionMount, and he pointed out an issue around a directory mutex
++ lock and aufs addressed it. But it is still unsure whether aufs will
++ be merged (or any other union solution).
++<http://marc.info/?l=linux-kernel&m=136312705029295&w=1>
++
+
+1. Features
+----------------------------------------
+- dynamic branch manipulation, add, del.
+- etc...
+
-+Also there are many enhancements in aufs1, such as:
++Also there are many enhancements in aufs, such as:
++- test only the highest one for the directory permission (dirperm1)
++- copyup on open (coo=)
++- 'move' policy for copy-up between two writable branches, after
++ checking free space.
++- xattr, acl
+- readdir(3) in userspace.
+- keep inode number by external inode number table
+- keep the timestamps of file/dir in internal copyup operation
+
+Currently these features are dropped temporary from aufs3.
+See design/08plan.txt in detail.
-+- test only the highest one for the directory permission (dirperm1)
-+- copyup on open (coo=)
+- nested mount, i.e. aufs as readonly no-whiteout branch of another aufs
+ (robr)
+- statistics of aufs thread (/sys/fs/aufs/stat)
-+- delegation mode (dlgt)
-+ a delegation of the internal branch access to support task I/O
-+ accounting, which also supports Linux Security Modules (LSM) mainly
-+ for Suse AppArmor.
-+- intent.open/create (file open in a single lookup)
+
+Features or just an idea in the future (see also design/*.txt),
+- reorder the branch index without del/re-add.
+- permanent xino files for NFSD
+- an option for refreshing the opened files after add/del branches
-+- 'move' policy for copy-up between two writable branches, after
-+ checking free space.
+- light version, without branch manipulation. (unnecessary?)
+- copyup in userspace
+- inotify in userspace
+- readv/writev
-+- xattr, acl
+
+
+2. Download
+git://git.kernel.org/.../torvalds/linux.git.
+And you cannot select CONFIG_AUFS_FS=m for this version, eg. you cannot
+build aufs3 as an external kernel module.
++Several extra patches are not included in this tree. Only
++aufs3-standalong tree contains them. They are describe in the later
++section "Configuration and Compilation."
+
+On the other hand, the aufs3-standalone tree has only aufs source files
+and necessary patches, and you can select CONFIG_AUFS_FS=m.
++But you need to apply all aufs patches manually.
+
+You will find GIT branches whose name is in form of "aufs3.x" where "x"
+represents the linux kernel version, "linux-3.x". For instance,
+
+o aufs3-linux tree
+$ git clone --reference /your/linux/git/tree \
-+ git://aufs.git.sourceforge.net/gitroot/aufs/aufs3-linux.git \
-+ aufs3-linux.git
++ git://git.code.sf.net/p/aufs/aufs3-linux aufs3-linux.git
+- if you don't have linux GIT tree, then remove "--reference ..."
+$ cd aufs3-linux.git
+$ git checkout origin/aufs3.0
+
++Or You may want to directly git-pull aufs into your linux GIT tree, and
++leave the patch-work to GIT.
++$ cd /your/linux/git/tree
++$ git remote add aufs3 https://github.com/sfjro/aufs3-linux.git
++- aufs3-linux.git tree also exists on github.
++$ git fetch aufs3
++$ git checkout -b my3.14 v3.14
++$ (add your change...)
++$ git pull aufs3 aufs3.14
++- now you have v3.14 + your_changes + aufs3.14 in you my3.14 branch.
++- you may need to solve some conflicts between your_changes and
++ aufs3.14. in this case, git-rerere is recommended so that you can
++ solve the similar confilicts automatically when you upgrade to 3.15 or
++ later in the future.
++
+o aufs3-standalone tree
-+$ git clone git://aufs.git.sourceforge.net/gitroot/aufs/aufs3-standalone.git \
++$ git clone git://git.code.sf.net/p/aufs/aufs3-standalone \
+ aufs3-standalone.git
+$ cd aufs3-standalone.git
+$ git checkout origin/aufs3.0
+
+o aufs-util tree
-+$ git clone git://aufs.git.sourceforge.net/gitroot/aufs/aufs-util.git \
++$ git clone git://git.code.sf.net/p/aufs/aufs-util \
+ aufs-util.git
+$ cd aufs-util.git
+$ git checkout origin/aufs3.0
+Make sure you have git-checkout'ed the correct branch.
+
+For aufs3-linux tree,
-+- enable CONFIG_EXPERIMENTAL and CONFIG_AUFS_FS.
++- enable CONFIG_AUFS_FS.
+- set other aufs configurations if necessary.
+
+For aufs3-standalone tree,
+1.
+- apply ./aufs3-kbuild.patch to your kernel source files.
+- apply ./aufs3-base.patch too.
-+- apply ./aufs3-proc_map.patch too, if you want to make /proc/PID/maps (and
-+ others including lsof(1)) show the file path on aufs instead of the
-+ path on the branch fs.
++- apply ./aufs3-mmap.patch too.
+- apply ./aufs3-standalone.patch too, if you have a plan to set
+ CONFIG_AUFS_FS=m. otherwise you don't need ./aufs3-standalone.patch.
+- copy ./{Documentation,fs,include/uapi/linux/aufs_type.h} files to your
+ kernel source tree. Never copy $PWD/include/uapi/linux/Kbuild.
-+- enable CONFIG_EXPERIMENTAL and CONFIG_AUFS_FS, you can select either
++- enable CONFIG_AUFS_FS, you can select either
+ =m or =y.
+- and build your kernel as usual.
+- install the built kernel.
++ Note: Since linux-3.9, every filesystem module requires an alias
++ "fs-<fsname>". You should make sure that "fs-aufs" is listed in your
++ modules.aliases file if you set CONFIG_AUFS_FS=m.
+- install the header files too by "make headers_install" to the
+ directory where you specify. By default, it is $PWD/usr.
+ "make help" shows a brief note for headers_install.
+2.
+- module only (CONFIG_AUFS_FS=m).
+- apply ./aufs3-base.patch to your kernel source files.
-+- apply ./aufs3-proc_map.patch too to your kernel source files,
-+ if you want to make /proc/PID/maps (and others including lsof(1)) show
-+ the file path on aufs instead of the path on the branch fs.
++- apply ./aufs3-mmap.patch too.
+- apply ./aufs3-standalone.patch too.
+- build your kernel, don't forget "make headers_install", and reboot.
+- edit ./config.mk and set other aufs configurations if necessary.
+ Note: You should read $PWD/fs/aufs/Kconfig carefully which describes
+ every aufs configurations.
+- build the module by simple "make".
++ Note: Since linux-3.9, every filesystem module requires an alias
++ "fs-<fsname>". You should make sure that "fs-aufs" is listed in your
++ modules.aliases file.
+- you can specify ${KDIR} make variable which points to your kernel
+ source tree.
+- install the files
+ then run "make install_ulib" too. And refer to the aufs manual in
+ detail.
+
++There several other patches in aufs3-standalone.git. They are all
++optional. When you meet some problems, they will help you.
++- aufs3-loopback.patch
++ Supports a nested loopback mount in a branch-fs. This patch is
++ unnecessary until aufs produces a message like "you may want to try
++ another patch for loopback file".
++- vfs-ino.patch
++ Modifies a system global kernel internal function get_next_ino() in
++ order to stop assigning 0 for an inode-number. Not directly related to
++ aufs, but recommended generally.
++- tmpfs-idr.patch
++ Keeps the tmpfs inode number as the lowest value. Effective to reduce
++ the size of aufs XINO files for tmpfs branch. Also it prevents the
++ duplication of inode number, which is important for backup tools and
++ other utilities. When you find aufs XINO files for tmpfs branch
++ growing too much, try this patch.
++
+
+4. Usage
+----------------------------------------
+Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and
+11).
+Sam Liddicott made a donation (2011/9).
++Era Scarecrow made a donation (2013/4).
++Bor Ratajc made a donation (2013/4).
++Alessandro Gorreta made a donation (2013/4).
++POIRETTE Marc made a donation (2013/4).
++Alessandro Gorreta made a donation (2013/4).
++lauri kasvandik made a donation (2013/5).
++"pemasu from Finland" made a donation (2013/7).
++The Parted Magic Project made a donation (2013/9 and 11).
++Pavel Barta made a donation (2013/10).
++Nikolay Pertsev made a donation (2014/5).
++James B made a donation (2014/7).
++Stefano Di Biase made a donation (2014/8).
++Daniel Epellei made a donation (2015/1).
+
+Thank you very much.
+Donations are always, including future donations, very important and
+# End: ;
diff -urN /usr/share/empty/fs/aufs/aufs.h linux/fs/aufs/aufs.h
--- /usr/share/empty/fs/aufs/aufs.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/aufs.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,60 @@
++++ linux/fs/aufs/aufs.h 2015-06-22 08:27:37.874168290 +0200
+@@ -0,0 +1,59 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+#endif /* __AUFS_H__ */
diff -urN /usr/share/empty/fs/aufs/branch.c linux/fs/aufs/branch.c
--- /usr/share/empty/fs/aufs/branch.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/branch.c 2013-03-14 20:07:41.038119650 +0100
-@@ -0,0 +1,1172 @@
++++ linux/fs/aufs/branch.c 2015-06-22 08:29:23.703424266 +0200
+@@ -0,0 +1,1406 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ AuRwDestroy(&wbr->wbr_wh_rwsem);
+ }
+
++ if (br->br_fhsm) {
++ au_br_fhsm_fin(br->br_fhsm);
++ kfree(br->br_fhsm);
++ }
++
+ key = br->br_dykey;
+ for (i = 0; i < AuBrDynOp; i++, key++)
+ if (*key)
+
+ /* recursive lock, s_umount of branch's */
+ lockdep_off();
-+ mntput(br->br_mnt);
++ path_put(&br->br_path);
+ lockdep_on();
+ kfree(wbr);
+ kfree(br);
+ goto out_hnotify;
+ }
+
++ add_branch->br_fhsm = NULL;
++ if (au_br_fhsm(perm)) {
++ err = au_fhsm_br_alloc(add_branch);
++ if (unlikely(err))
++ goto out_wbr;
++ }
++
+ err = au_sbr_realloc(au_sbi(sb), new_nbranch);
+ if (!err)
+ err = au_di_realloc(au_di(root), new_nbranch);
+ if (!err)
+ return add_branch; /* success */
+
++out_wbr:
+ kfree(add_branch->br_wbr);
-+
+out_hnotify:
+ au_hnotify_fin_br(add_branch);
+out_br:
+ goto out;
+ }
+
++ if (unlikely(inode->i_sb->s_stack_depth)) {
++ pr_err("already stacked, %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;
+ * 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 new_perm)
+{
+ int err, old_perm;
+ aufs_bindex_t bindex;
+ struct au_wbr *wbr;
+ struct au_hinode *hdir;
+
++ err = vfsub_mnt_want_write(au_br_mnt(br));
++ if (unlikely(err))
++ goto out;
++
+ wbr = br->br_wbr;
+ old_perm = br->br_perm;
+ br->br_perm = new_perm;
+ hdir = au_hi(sb->s_root->d_inode, bindex);
+ au_hn_imtx_lock_nested(hdir, AuLsc_I_PARENT);
+ } else {
-+ h_mtx = &h_root->d_inode->i_mutex;
++ h_mtx = &au_br_dentry(br)->d_inode->i_mutex;
+ mutex_lock_nested(h_mtx, AuLsc_I_PARENT);
+ }
+ if (!wbr)
-+ err = au_wh_init(h_root, br, sb);
++ err = au_wh_init(br, sb);
+ else {
+ wbr_wh_write_lock(wbr);
-+ err = au_wh_init(h_root, br, sb);
++ err = au_wh_init(br, sb);
+ wbr_wh_write_unlock(wbr);
+ }
+ if (hdir)
+ au_hn_imtx_unlock(hdir);
+ else
+ mutex_unlock(h_mtx);
++ vfsub_mnt_drop_write(au_br_mnt(br));
+ br->br_perm = old_perm;
+
+ if (!err && wbr && !au_br_writable(new_perm)) {
+ br->br_wbr = NULL;
+ }
+
++out:
+ return err;
+}
+
+static int au_wbr_init(struct au_branch *br, struct super_block *sb,
-+ int perm, struct path *path)
++ int perm)
+{
+ int err;
+ struct kstatfs kst;
+ struct au_wbr *wbr;
-+ struct dentry *h_dentry;
+
+ wbr = br->br_wbr;
+ au_rw_init(&wbr->wbr_wh_rwsem);
+
+ /*
+ * a limit for rmdir/rename a dir
-+ * cf. AUFS_MAX_NAMELEN in include/linux/aufs_type.h
++ * cf. AUFS_MAX_NAMELEN in include/uapi/linux/aufs_type.h
+ */
-+ err = vfs_statfs(path, &kst);
++ err = vfs_statfs(&br->br_path, &kst);
+ if (unlikely(err))
+ goto out;
+ err = -EINVAL;
-+ h_dentry = path->dentry;
+ if (kst.f_namelen >= NAME_MAX)
-+ err = au_br_init_wh(sb, br, perm, h_dentry);
++ err = au_br_init_wh(sb, br, perm);
+ else
-+ pr_err("%.*s(%s), unsupported namelen %ld\n",
-+ AuDLNPair(h_dentry), au_sbtype(h_dentry->d_sb),
-+ kst.f_namelen);
++ pr_err("%pd(%s), unsupported namelen %ld\n",
++ au_br_dentry(br),
++ au_sbtype(au_br_dentry(br)->d_sb), kst.f_namelen);
+
+out:
+ return err;
+}
+
-+/* intialize a new branch */
++/* initialize a new branch */
+static int au_br_init(struct au_branch *br, struct super_block *sb,
+ struct au_opt_add *add)
+{
+ memset(&br->br_xino, 0, sizeof(br->br_xino));
+ mutex_init(&br->br_xino.xi_nondir_mtx);
+ br->br_perm = add->perm;
-+ br->br_mnt = add->path.mnt; /* set first, mntget() later */
++ br->br_path = add->path; /* set first, path_get() later */
+ spin_lock_init(&br->br_dykey_lock);
+ memset(br->br_dykey, 0, sizeof(br->br_dykey));
+ 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);
+ AuDebugOn(br->br_id < 0);
+
+ if (au_br_writable(add->perm)) {
-+ err = au_wbr_init(br, sb, add->perm, &add->path);
++ err = au_wbr_init(br, sb, add->perm);
+ if (unlikely(err))
+ goto out_err;
+ }
+ }
+
+ sysaufs_br_init(br);
-+ mntget(add->path.mnt);
++ path_get(&br->br_path);
+ goto out; /* success */
+
+out_err:
-+ br->br_mnt = NULL;
++ memset(&br->br_path, 0, sizeof(br->br_path));
+out:
+ return err;
+}
+ 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)
++static void au_br_do_add(struct super_block *sb, struct au_branch *br,
++ aufs_bindex_t bindex)
+{
-+ struct dentry *root;
++ struct dentry *root, *h_dentry;
+ struct inode *root_inode;
+ aufs_bindex_t bend, amount;
+
+ root_inode = root->d_inode;
+ bend = au_sbend(sb);
+ amount = bend + 1 - bindex;
++ h_dentry = au_br_dentry(br);
+ au_sbilist_lock();
+ au_br_do_add_brp(au_sbi(sb), bindex, br, bend, amount);
+ au_br_do_add_hdp(au_di(root), bindex, bend, amount);
+ }
+
+ add_bindex = add->bindex;
-+ h_dentry = add->path.dentry;
+ if (!remount)
-+ au_br_do_add(sb, h_dentry, add_branch, add_bindex);
++ au_br_do_add(sb, add_branch, add_bindex);
+ else {
+ sysaufs_brs_del(sb, add_bindex);
-+ au_br_do_add(sb, h_dentry, add_branch, add_bindex);
++ au_br_do_add(sb, add_branch, add_bindex);
+ sysaufs_brs_add(sb, add_bindex);
+ }
+
++ h_dentry = add->path.dentry;
+ if (!add_bindex) {
+ au_cpup_attr_all(root_inode, /*force*/1);
+ sb->s_maxbytes = h_dentry->d_sb->s_maxbytes;
+ && 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)
++ && add_branch->br_xino.xi_file->f_path.dentry->d_parent == h_dentry)
+ au_xino_brid_set(sb, add_branch->br_id);
+
+out:
+
+/* ---------------------------------------------------------------------- */
+
++static unsigned long long au_farray_cb(void *a,
++ unsigned long long max __maybe_unused,
++ void *arg)
++{
++ unsigned long long n;
++ struct file **p, *f;
++ struct au_sphlhead *files;
++ struct au_finfo *finfo;
++ struct super_block *sb = arg;
++
++ n = 0;
++ p = a;
++ files = &au_sbi(sb)->si_files;
++ spin_lock(&files->spin);
++ hlist_for_each_entry(finfo, &files->head, fi_hlist) {
++ f = finfo->fi_file;
++ if (file_count(f)
++ && !special_file(file_inode(f)->i_mode)) {
++ get_file(f);
++ *p++ = f;
++ n++;
++ AuDebugOn(n > max);
++ }
++ }
++ spin_unlock(&files->spin);
++
++ return n;
++}
++
++static struct file **au_farray_alloc(struct super_block *sb,
++ unsigned long long *max)
++{
++ *max = atomic_long_read(&au_sbi(sb)->si_nfiles);
++ return au_array_alloc(max, au_farray_cb, sb);
++}
++
++static void au_farray_free(struct file **a, unsigned long long max)
++{
++ unsigned long long ull;
++
++ for (ull = 0; ull < max; ull++)
++ if (a[ull])
++ fput(a[ull]);
++ au_array_free(a);
++}
++
++/* ---------------------------------------------------------------------- */
++
+/*
+ * delete a branch
+ */
+ ndentry = dpage->ndentry;
+ for (j = 0; !err && j < ndentry; j++) {
+ d = dpage->dentries[j];
-+ AuDebugOn(!d->d_count);
++ AuDebugOn(au_dcount(d) <= 0);
+ if (!au_digen_test(d, sigen)) {
+ di_read_lock_child(d, AuLock_IR);
+ if (unlikely(au_dbrange_test(d))) {
+ && au_h_dptr(d, bindex)
+ && au_test_dbusy(d, bstart, bend)) {
+ err = -EBUSY;
-+ AuVerbose(verbose, "busy %.*s\n", AuDLNPair(d));
++ AuVerbose(verbose, "busy %pd\n", d);
+ AuDbgDentry(d);
+ }
+ di_read_unlock(d, AuLock_IR);
+ AuDbg("b%d\n", bindex);
+ for (ull = 0; !err && ull < max; ull++) {
+ i = array[ull];
++ if (unlikely(!i))
++ break;
+ if (i->i_ino == AUFS_ROOT_INO)
+ continue;
+
+ return err;
+}
+
++static int test_dir_busy(struct file *file, aufs_bindex_t br_id,
++ struct file **to_free, int *idx)
++{
++ int err;
++ unsigned char matched, root;
++ aufs_bindex_t bindex, bend;
++ struct au_fidir *fidir;
++ struct au_hfile *hfile;
++
++ err = 0;
++ root = IS_ROOT(file->f_path.dentry);
++ if (root) {
++ get_file(file);
++ to_free[*idx] = file;
++ (*idx)++;
++ goto out;
++ }
++
++ matched = 0;
++ fidir = au_fi(file)->fi_hdir;
++ AuDebugOn(!fidir);
++ bend = au_fbend_dir(file);
++ for (bindex = au_fbstart(file); bindex <= bend; bindex++) {
++ hfile = fidir->fd_hfile + bindex;
++ if (!hfile->hf_file)
++ continue;
++
++ if (hfile->hf_br->br_id == br_id) {
++ matched = 1;
++ break;
++ }
++ }
++ if (matched)
++ err = -EBUSY;
++
++out:
++ return err;
++}
++
++static int test_file_busy(struct super_block *sb, aufs_bindex_t br_id,
++ struct file **to_free, int opened)
++{
++ int err, idx;
++ unsigned long long ull, max;
++ aufs_bindex_t bstart;
++ struct file *file, **array;
++ struct dentry *root;
++ struct au_hfile *hfile;
++
++ array = au_farray_alloc(sb, &max);
++ err = PTR_ERR(array);
++ if (IS_ERR(array))
++ goto out;
++
++ err = 0;
++ idx = 0;
++ root = sb->s_root;
++ di_write_unlock(root);
++ for (ull = 0; ull < max; ull++) {
++ file = array[ull];
++ if (unlikely(!file))
++ break;
++
++ /* AuDbg("%pD\n", file); */
++ fi_read_lock(file);
++ bstart = au_fbstart(file);
++ if (!d_is_dir(file->f_path.dentry)) {
++ hfile = &au_fi(file)->fi_htop;
++ if (hfile->hf_br->br_id == br_id)
++ err = -EBUSY;
++ } else
++ err = test_dir_busy(file, br_id, to_free, &idx);
++ fi_read_unlock(file);
++ if (unlikely(err))
++ break;
++ }
++ di_write_lock_child(root);
++ au_farray_free(array, max);
++ AuDebugOn(idx > opened);
++
++out:
++ return err;
++}
++
++static void br_del_file(struct file **to_free, unsigned long long opened,
++ aufs_bindex_t br_id)
++{
++ unsigned long long ull;
++ aufs_bindex_t bindex, bstart, bend, bfound;
++ struct file *file;
++ struct au_fidir *fidir;
++ struct au_hfile *hfile;
++
++ for (ull = 0; ull < opened; ull++) {
++ file = to_free[ull];
++ if (unlikely(!file))
++ break;
++
++ /* AuDbg("%pD\n", file); */
++ AuDebugOn(!d_is_dir(file->f_path.dentry));
++ bfound = -1;
++ fidir = au_fi(file)->fi_hdir;
++ AuDebugOn(!fidir);
++ fi_write_lock(file);
++ bstart = au_fbstart(file);
++ bend = au_fbend_dir(file);
++ for (bindex = bstart; bindex <= bend; bindex++) {
++ hfile = fidir->fd_hfile + bindex;
++ if (!hfile->hf_file)
++ continue;
++
++ if (hfile->hf_br->br_id == br_id) {
++ bfound = bindex;
++ break;
++ }
++ }
++ AuDebugOn(bfound < 0);
++ au_set_h_fptr(file, bfound, NULL);
++ if (bfound == bstart) {
++ for (bstart++; bstart <= bend; bstart++)
++ if (au_hf_dir(file, bstart)) {
++ au_set_fbstart(file, bstart);
++ break;
++ }
++ }
++ fi_write_unlock(file);
++ }
++}
++
+static void au_br_do_del_brp(struct au_sbinfo *sbinfo,
+ const aufs_bindex_t bindex,
+ const aufs_bindex_t bend)
+ au_br_do_free(br);
+}
+
++static unsigned long long empty_cb(void *array, unsigned long long max,
++ void *arg)
++{
++ return max;
++}
++
+int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount)
+{
+ int err, rerr, i;
++ unsigned long long opened;
+ unsigned int mnt_flags;
+ aufs_bindex_t bindex, bend, br_id;
+ unsigned char do_wh, verbose;
+ struct au_branch *br;
+ struct au_wbr *wbr;
++ struct dentry *root;
++ struct file **to_free;
+
+ err = 0;
-+ bindex = au_find_dbindex(sb->s_root, del->h_path.dentry);
++ opened = 0;
++ to_free = NULL;
++ root = sb->s_root;
++ bindex = au_find_dbindex(root, del->h_path.dentry);
+ if (bindex < 0) {
+ if (remount)
+ goto out; /* success */
+ 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;
++ AuDebugOn(!path_equal(&br->br_path, &del->h_path));
++
++ br_id = br->br_id;
++ opened = atomic_read(&br->br_count);
++ if (unlikely(opened)) {
++ to_free = au_array_alloc(&opened, empty_cb, NULL);
++ err = PTR_ERR(to_free);
++ if (IS_ERR(to_free))
++ goto out;
++
++ err = test_file_busy(sb, br_id, to_free, opened);
++ if (unlikely(err)) {
++ AuVerbose(verbose, "%llu file(s) opened\n", opened);
++ goto out;
++ }
+ }
+
+ wbr = br->br_wbr;
+ }
+ }
+
-+ err = test_children_busy(sb->s_root, bindex, verbose);
++ err = test_children_busy(root, bindex, verbose);
+ if (unlikely(err)) {
+ if (do_wh)
+ goto out_wh;
+ }
+
+ err = 0;
-+ br_id = br->br_id;
++ if (to_free) {
++ /*
++ * now we confirmed the branch is deletable.
++ * let's free the remaining opened dirs on the branch.
++ */
++ di_write_unlock(root);
++ br_del_file(to_free, opened, br_id);
++ di_write_lock_child(root);
++ }
++
+ if (!remount)
+ au_br_do_del(sb, bindex, br);
+ else {
+ }
+
+ if (!bindex) {
-+ au_cpup_attr_all(sb->s_root->d_inode, /*force*/1);
++ au_cpup_attr_all(root->d_inode, /*force*/1);
+ sb->s_maxbytes = au_sbr_sb(sb, 0)->s_maxbytes;
+ } else
-+ au_sub_nlink(sb->s_root->d_inode, del->h_path.dentry->d_inode);
++ au_sub_nlink(root->d_inode, del->h_path.dentry->d_inode);
+ if (au_opt_test(mnt_flags, PLINK))
+ au_plink_half_refresh(sb, br_id);
+
+
+out_wh:
+ /* revert */
-+ rerr = au_br_init_wh(sb, br, br->br_perm, del->h_path.dentry);
++ rerr = au_br_init_wh(sb, br, br->br_perm);
+ if (rerr)
+ pr_warn("failed re-creating base whiteout, %s. (%d)\n",
+ del->pathname, rerr);
+out:
++ if (to_free)
++ au_farray_free(to_free, opened);
+ return err;
+}
+
+
+long au_ibusy_ioctl(struct file *file, unsigned long arg)
+{
-+ return au_ibusy(file->f_dentry->d_sb, (void __user *)arg);
++ return au_ibusy(file->f_path.dentry->d_sb, (void __user *)arg);
+}
+
+#ifdef CONFIG_COMPAT
+long au_ibusy_compat_ioctl(struct file *file, unsigned long arg)
+{
-+ return au_ibusy(file->f_dentry->d_sb, compat_ptr(arg));
++ return au_ibusy(file->f_path.dentry->d_sb, compat_ptr(arg));
+}
+#endif
+
+ || do_need_sigen_inc(new, old);
+}
+
-+static unsigned long long au_farray_cb(void *a,
-+ unsigned long long max __maybe_unused,
-+ void *arg)
-+{
-+ unsigned long long n;
-+ struct file **p, *f;
-+ struct super_block *sb = arg;
-+
-+ n = 0;
-+ p = a;
-+ lg_global_lock(&files_lglock);
-+ do_file_list_for_each_entry(sb, f) {
-+ if (au_fi(f)
-+ && file_count(f)
-+ && !special_file(f->f_dentry->d_inode->i_mode)) {
-+ get_file(f);
-+ *p++ = f;
-+ n++;
-+ AuDebugOn(n > max);
-+ }
-+ } while_file_list_for_each_entry;
-+ lg_global_unlock(&files_lglock);
-+
-+ return n;
-+}
-+
-+static struct file **au_farray_alloc(struct super_block *sb,
-+ unsigned long long *max)
-+{
-+ *max = atomic_long_read(&au_sbi(sb)->si_nfiles);
-+ return au_array_alloc(max, au_farray_cb, sb);
-+}
-+
-+static void au_farray_free(struct file **a, unsigned long long max)
-+{
-+ unsigned long long ull;
-+
-+ for (ull = 0; ull < max; ull++)
-+ if (a[ull])
-+ fput(a[ull]);
-+ au_array_free(a);
-+}
-+
+static int au_br_mod_files_ro(struct super_block *sb, aufs_bindex_t bindex)
+{
+ int err, do_warn;
+ unsigned int mnt_flags;
+ unsigned long long ull, max;
+ aufs_bindex_t br_id;
-+ unsigned char verbose;
++ unsigned char verbose, writer;
+ struct file *file, *hf, **array;
-+ struct inode *inode;
+ struct au_hfile *hfile;
+
+ mnt_flags = au_mntflags(sb);
+ br_id = au_sbr_id(sb, bindex);
+ for (ull = 0; ull < max; ull++) {
+ file = array[ull];
++ if (unlikely(!file))
++ break;
+
-+ /* AuDbg("%.*s\n", AuDLNPair(file->f_dentry)); */
++ /* AuDbg("%pD\n", file); */
+ fi_read_lock(file);
+ if (unlikely(au_test_mmapped(file))) {
+ err = -EBUSY;
-+ AuVerbose(verbose, "mmapped %.*s\n",
-+ AuDLNPair(file->f_dentry));
++ AuVerbose(verbose, "mmapped %pD\n", file);
+ AuDbgFile(file);
+ FiMustNoWaiters(file);
+ fi_read_unlock(file);
+ goto out_array;
+ }
+
-+ inode = file->f_dentry->d_inode;
+ hfile = &au_fi(file)->fi_htop;
+ hf = hfile->hf_file;
-+ if (!S_ISREG(inode->i_mode)
++ if (!d_is_reg(file->f_path.dentry)
+ || !(file->f_mode & FMODE_WRITE)
+ || hfile->hf_br->br_id != br_id
+ || !(hf->f_mode & FMODE_WRITE))
+ continue;
+
+ /* todo: already flushed? */
-+ /* cf. fs/super.c:mark_files_ro() */
++ /*
++ * fs/super.c:mark_files_ro() is gone, but aufs keeps its
++ * approach which resets f_mode and calls mnt_drop_write() and
++ * file_release_write() for each file, because the branch
++ * attribute in aufs world is totally different from the native
++ * fs rw/ro mode.
++ */
+ /* fi_read_lock(file); */
+ hfile = &au_fi(file)->fi_htop;
+ hf = hfile->hf_file;
+ /* fi_read_unlock(file); */
+ spin_lock(&hf->f_lock);
-+ hf->f_mode &= ~FMODE_WRITE;
++ writer = !!(hf->f_mode & FMODE_WRITER);
++ hf->f_mode &= ~(FMODE_WRITE | FMODE_WRITER);
+ spin_unlock(&hf->f_lock);
-+ if (!file_check_writeable(hf)) {
-+ file_release_write(hf);
-+ vfsub_mnt_drop_write(hf->f_vfsmnt);
++ if (writer) {
++ put_write_access(file_inode(hf));
++ __mnt_drop_write(hf->f_path.mnt);
+ }
+ }
+
+{
+ int err, rerr;
+ aufs_bindex_t bindex;
-+ struct path path;
+ struct dentry *root;
+ struct au_branch *br;
++ struct au_br_fhsm *bf;
+
+ root = sb->s_root;
+ bindex = au_find_dbindex(root, mod->h_root);
+ goto out;
+
+ br = au_sbr(sb, bindex);
++ AuDebugOn(mod->h_root != au_br_dentry(br));
+ if (br->br_perm == mod->perm)
+ return 0; /* success */
+
++ /* pre-allocate for non-fhsm --> fhsm */
++ bf = NULL;
++ if (!au_br_fhsm(br->br_perm) && au_br_fhsm(mod->perm)) {
++ err = au_fhsm_br_alloc(br);
++ if (unlikely(err))
++ goto out;
++ bf = br->br_fhsm;
++ br->br_fhsm = NULL;
++ }
++
+ if (au_br_writable(br->br_perm)) {
+ /* remove whiteout base */
-+ err = au_br_init_wh(sb, br, mod->perm, mod->h_root);
++ err = au_br_init_wh(sb, br, mod->perm);
+ if (unlikely(err))
-+ goto out;
++ goto out_bf;
+
+ if (!au_br_writable(mod->perm)) {
+ /* rw --> ro, file might be mmapped */
+ rerr = -ENOMEM;
+ br->br_wbr = kmalloc(sizeof(*br->br_wbr),
+ GFP_NOFS);
-+ if (br->br_wbr) {
-+ path.mnt = br->br_mnt;
-+ path.dentry = mod->h_root;
-+ rerr = au_wbr_init(br, sb, br->br_perm,
-+ &path);
-+ }
++ if (br->br_wbr)
++ rerr = au_wbr_init(br, sb, br->br_perm);
+ if (unlikely(rerr)) {
+ AuIOErr("nested error %d (%d)\n",
+ rerr, err);
+ err = -ENOMEM;
+ br->br_wbr = kmalloc(sizeof(*br->br_wbr), GFP_NOFS);
+ if (br->br_wbr) {
-+ path.mnt = br->br_mnt;
-+ path.dentry = mod->h_root;
-+ err = au_wbr_init(br, sb, mod->perm, &path);
++ err = au_wbr_init(br, sb, mod->perm);
+ if (unlikely(err)) {
+ kfree(br->br_wbr);
+ br->br_wbr = NULL;
+ }
+ }
+ }
++ if (unlikely(err))
++ goto out_bf;
++
++ if (au_br_fhsm(br->br_perm)) {
++ if (!au_br_fhsm(mod->perm)) {
++ /* fhsm --> non-fhsm */
++ au_br_fhsm_fin(br->br_fhsm);
++ kfree(br->br_fhsm);
++ br->br_fhsm = NULL;
++ }
++ } else if (au_br_fhsm(mod->perm))
++ /* non-fhsm --> fhsm */
++ br->br_fhsm = bf;
+
-+ if (!err) {
-+ *do_refresh |= need_sigen_inc(br->br_perm, mod->perm);
-+ br->br_perm = mod->perm;
-+ }
++ *do_refresh |= need_sigen_inc(br->br_perm, mod->perm);
++ br->br_perm = mod->perm;
++ goto out; /* success */
+
++out_bf:
++ kfree(bf);
+out:
+ AuTraceErr(err);
+ return err;
+}
++
++/* ---------------------------------------------------------------------- */
++
++int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs)
++{
++ int err;
++ struct kstatfs kstfs;
++
++ err = vfs_statfs(&br->br_path, &kstfs);
++ if (!err) {
++ stfs->f_blocks = kstfs.f_blocks;
++ stfs->f_bavail = kstfs.f_bavail;
++ stfs->f_files = kstfs.f_files;
++ stfs->f_ffree = kstfs.f_ffree;
++ }
++
++ return err;
++}
diff -urN /usr/share/empty/fs/aufs/branch.h linux/fs/aufs/branch.h
--- /usr/share/empty/fs/aufs/branch.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/branch.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,236 @@
++++ linux/fs/aufs/branch.h 2015-06-22 08:29:23.703424266 +0200
+@@ -0,0 +1,279 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+#endif
+};
+
++/* File-based Hierarchical Storage Management */
++struct au_br_fhsm {
++#ifdef CONFIG_AUFS_FHSM
++ struct mutex bf_lock;
++ unsigned long bf_jiffy;
++ struct aufs_stfs bf_stfs;
++ int bf_readable;
++#endif
++};
++
+/* members for writable branch only */
+enum {AuBrWh_BASE, AuBrWh_PLINK, AuBrWh_ORPH, AuBrWh_Last};
+struct au_wbr {
+};
+#endif
+
++/* sysfs entries */
++struct au_brsysfs {
++ char name[16];
++ struct attribute attr;
++};
++
++enum {
++ AuBrSysfs_BR,
++ AuBrSysfs_BRID,
++ AuBrSysfs_Last
++};
++
+/* 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;
++ struct path br_path;
+ spinlock_t br_dykey_lock;
+ struct au_dykey *br_dykey[AuBrDynOp];
+ atomic_t br_count;
+
+ struct au_wbr *br_wbr;
++ struct au_br_fhsm *br_fhsm;
+
+ /* xino truncation */
-+ blkcnt_t br_xino_upper; /* watermark in blocks */
+ atomic_t br_xino_running;
+
+#ifdef CONFIG_AUFS_HFSNOTIFY
+#endif
+
+#ifdef CONFIG_SYSFS
-+ /* an entry under sysfs per mount-point */
-+ char br_name[8];
-+ struct attribute br_attr;
++ /* entries under sysfs per mount-point */
++ struct au_brsysfs br_sysfs[AuBrSysfs_Last];
+#endif
+};
+
+/* ---------------------------------------------------------------------- */
+
-+/* branch permissions and attributes */
-+#define AuBrPerm_RW 1 /* writable, hardlinkable wh */
-+#define AuBrPerm_RO (1 << 1) /* readonly */
-+#define AuBrPerm_RR (1 << 2) /* natively readonly */
-+#define AuBrPerm_Mask (AuBrPerm_RW | AuBrPerm_RO | AuBrPerm_RR)
-+
-+#define AuBrRAttr_WH (1 << 3) /* whiteout-able */
-+
-+#define AuBrWAttr_NoLinkWH (1 << 4) /* un-hardlinkable whiteouts */
-+
-+static inline int au_br_writable(int brperm)
++static inline struct vfsmount *au_br_mnt(struct au_branch *br)
+{
-+ return brperm & AuBrPerm_RW;
++ return br->br_path.mnt;
+}
+
-+static inline int au_br_whable(int brperm)
++static inline struct dentry *au_br_dentry(struct au_branch *br)
+{
-+ return brperm & (AuBrPerm_RW | AuBrRAttr_WH);
++ return br->br_path.dentry;
+}
+
-+static inline int au_br_wh_linkable(int brperm)
++static inline struct super_block *au_br_sb(struct au_branch *br)
+{
-+ return !(brperm & AuBrWAttr_NoLinkWH);
++ return au_br_mnt(br)->mnt_sb;
+}
+
+static inline int au_br_rdonly(struct au_branch *br)
+{
-+ return ((br->br_mnt->mnt_sb->s_flags & MS_RDONLY)
++ return ((au_br_sb(br)->s_flags & MS_RDONLY)
+ || !au_br_writable(br->br_perm))
+ ? -EROFS : 0;
+}
+#endif
+}
+
++static inline int au_br_test_oflag(int oflag, struct au_branch *br)
++{
++ int err, exec_flag;
++
++ err = 0;
++ exec_flag = oflag & __FMODE_EXEC;
++ if (unlikely(exec_flag && (au_br_mnt(br)->mnt_flags & MNT_NOEXEC)))
++ err = -EACCES;
++
++ return err;
++}
++
+/* ---------------------------------------------------------------------- */
+
+/* branch.c */
+struct au_opt_mod;
+int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount,
+ int *do_refresh);
++struct aufs_stfs;
++int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs);
+
+/* xino.c */
+static const loff_t au_loff_max = LLONG_MAX;
+static inline
+struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex)
+{
-+ return au_sbr(sb, bindex)->br_mnt;
++ return au_br_mnt(au_sbr(sb, bindex));
+}
+
+static inline
+struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex)
+{
-+ return au_sbr_mnt(sb, bindex)->mnt_sb;
++ return au_br_sb(au_sbr(sb, bindex));
+}
+
+static inline void au_sbr_put(struct super_block *sb, aufs_bindex_t bindex)
+#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&wbr->wbr_wh_rwsem)
+#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&wbr->wbr_wh_rwsem)
+
++/* ---------------------------------------------------------------------- */
++
++#ifdef CONFIG_AUFS_FHSM
++static inline void au_br_fhsm_init(struct au_br_fhsm *brfhsm)
++{
++ mutex_init(&brfhsm->bf_lock);
++ brfhsm->bf_jiffy = 0;
++ brfhsm->bf_readable = 0;
++}
++
++static inline void au_br_fhsm_fin(struct au_br_fhsm *brfhsm)
++{
++ mutex_destroy(&brfhsm->bf_lock);
++}
++#else
++AuStubVoid(au_br_fhsm_init, struct au_br_fhsm *brfhsm)
++AuStubVoid(au_br_fhsm_fin, struct au_br_fhsm *brfhsm)
++#endif
++
+#endif /* __KERNEL__ */
+#endif /* __AUFS_BRANCH_H__ */
diff -urN /usr/share/empty/fs/aufs/conf.mk linux/fs/aufs/conf.mk
--- /usr/share/empty/fs/aufs/conf.mk 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/conf.mk 2012-08-26 08:39:00.757174634 +0200
++++ linux/fs/aufs/conf.mk 2015-06-22 08:27:37.874168290 +0200
@@ -0,0 +1,38 @@
+
+AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS}
+ SBILIST \
+ HNOTIFY HFSNOTIFY \
+ EXPORT INO_T_64 \
++ XATTR \
++ FHSM \
+ RDU \
-+ PROC_MAP \
-+ SP_IATTR \
+ SHWH \
+ BR_RAMFS \
+ BR_FUSE POLL \
+-include ${srctree}/${src}/conf_priv.mk
diff -urN /usr/share/empty/fs/aufs/cpup.c linux/fs/aufs/cpup.c
--- /usr/share/empty/fs/aufs/cpup.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/cpup.c 2013-03-14 20:07:41.038119650 +0100
-@@ -0,0 +1,1085 @@
++++ linux/fs/aufs/cpup.c 2015-06-22 08:29:23.703424266 +0200
+@@ -0,0 +1,1308 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+#include <linux/mm.h>
+#include "aufs.h"
+
-+void au_cpup_attr_flags(struct inode *dst, struct inode *src)
++void au_cpup_attr_flags(struct inode *dst, unsigned int iflags)
+{
+ const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE
-+ | S_NOATIME | S_NOCMTIME;
++ | S_NOATIME | S_NOCMTIME | S_AUTOMOUNT;
++
++ BUILD_BUG_ON(sizeof(iflags) != sizeof(dst->i_flags));
+
-+ dst->i_flags |= src->i_flags & ~mask;
++ dst->i_flags |= iflags & ~mask;
+ if (au_test_fs_notime(dst->i_sb))
+ dst->i_flags |= S_NOATIME | S_NOCMTIME;
+}
+
+ /*
+ * 0 can happen in revalidating.
-+ * h_inode->i_mutex is not held, but it is harmless since once i_nlink
-+ * reaches 0, it will never become positive.
++ * h_inode->i_mutex may not be held here, but it is harmless since once
++ * i_nlink reaches 0, it will never become positive except O_TMPFILE
++ * case.
++ * todo: O_TMPFILE+linkat(AT_SYMLINK_FOLLOW) bypassing aufs may cause
++ * the incorrect link count.
+ */
+ set_nlink(inode, h_inode->i_nlink);
+
+ 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);
++ au_cpup_attr_flags(inode, h_inode->i_flags);
+}
+
+void au_cpup_igen(struct inode *inode, struct inode *h_inode)
+ attr.ia_valid = ATTR_FORCE | ATTR_MTIME | ATTR_MTIME_SET
+ | ATTR_ATIME | ATTR_ATIME_SET;
+
-+ err = vfsub_notify_change(&dt->dt_h_path, &attr);
++ /* no delegation since this is a directory */
++ err = vfsub_notify_change(&dt->dt_h_path, &attr, /*delegated*/NULL);
+ if (unlikely(err))
+ pr_warn("restoring timestamps failed(%d). ignored\n", err);
+}
+
+/* ---------------------------------------------------------------------- */
+
++/* internal use only */
++struct au_cpup_reg_attr {
++ int valid;
++ struct kstat st;
++ unsigned int iflags; /* inode->i_flags */
++};
++
+static noinline_for_stack
-+int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src)
++int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src,
++ struct au_cpup_reg_attr *h_src_attr)
+{
-+ int err, sbits;
++ int err, sbits, icex;
++ unsigned int mnt_flags;
++ unsigned char verbose;
+ struct iattr ia;
+ struct path h_path;
+ struct inode *h_isrc, *h_idst;
++ struct kstat *h_st;
++ struct au_branch *br;
+
+ h_path.dentry = au_h_dptr(dst, bindex);
+ h_idst = h_path.dentry->d_inode;
-+ h_path.mnt = au_sbr_mnt(dst->d_sb, bindex);
++ br = au_sbr(dst->d_sb, bindex);
++ h_path.mnt = au_br_mnt(br);
+ h_isrc = h_src->d_inode;
+ ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID
+ | ATTR_ATIME | ATTR_MTIME
+ | ATTR_ATIME_SET | ATTR_MTIME_SET;
-+ ia.ia_uid = h_isrc->i_uid;
-+ ia.ia_gid = h_isrc->i_gid;
-+ ia.ia_atime = h_isrc->i_atime;
-+ ia.ia_mtime = h_isrc->i_mtime;
-+ if (h_idst->i_mode != h_isrc->i_mode
-+ && !S_ISLNK(h_idst->i_mode)) {
-+ ia.ia_valid |= ATTR_MODE;
-+ ia.ia_mode = h_isrc->i_mode;
++ if (h_src_attr && h_src_attr->valid) {
++ h_st = &h_src_attr->st;
++ ia.ia_uid = h_st->uid;
++ ia.ia_gid = h_st->gid;
++ ia.ia_atime = h_st->atime;
++ ia.ia_mtime = h_st->mtime;
++ if (h_idst->i_mode != h_st->mode
++ && !S_ISLNK(h_idst->i_mode)) {
++ ia.ia_valid |= ATTR_MODE;
++ ia.ia_mode = h_st->mode;
++ }
++ sbits = !!(h_st->mode & (S_ISUID | S_ISGID));
++ au_cpup_attr_flags(h_idst, h_src_attr->iflags);
++ } else {
++ ia.ia_uid = h_isrc->i_uid;
++ ia.ia_gid = h_isrc->i_gid;
++ ia.ia_atime = h_isrc->i_atime;
++ ia.ia_mtime = h_isrc->i_mtime;
++ if (h_idst->i_mode != h_isrc->i_mode
++ && !S_ISLNK(h_idst->i_mode)) {
++ ia.ia_valid |= ATTR_MODE;
++ ia.ia_mode = h_isrc->i_mode;
++ }
++ sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID));
++ au_cpup_attr_flags(h_idst, h_isrc->i_flags);
+ }
-+ sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID));
-+ au_cpup_attr_flags(h_idst, h_isrc);
-+ err = vfsub_notify_change(&h_path, &ia);
++ /* no delegation since it is just created */
++ err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL);
+
+ /* 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);
++ err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL);
++ }
++
++ icex = br->br_perm & AuBrAttr_ICEX;
++ if (!err) {
++ mnt_flags = au_mntflags(dst->d_sb);
++ verbose = !!au_opt_test(mnt_flags, VERBOSE);
++ err = au_cpup_xattr(h_path.dentry, h_src, icex, verbose);
+ }
+
+ return err;
+ wbytes -= b;
+ p += b;
+ }
++ if (unlikely(err < 0))
++ break;
+ } else {
+ loff_t res;
+
+ AuLabel(last hole);
+
+ err = 1;
-+ if (au_test_nfs(dst->f_dentry->d_sb)) {
++ if (au_test_nfs(dst->f_path.dentry->d_sb)) {
+ /* nfs requires this step to make last hole */
+ /* is this only nfs? */
+ do {
+ 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;
++ h_mtx = &file_inode(dst)->i_mutex;
+ mutex_lock_nested(h_mtx, AuLsc_I_CHILD2);
-+ err = vfsub_notify_change(&dst->f_path, ia);
++ /* no delegation since it is just created */
++ err = vfsub_notify_change(&dst->f_path, ia,
++ /*delegated*/NULL);
+ mutex_unlock(h_mtx);
+ }
+ }
+ char *buf;
+
+ err = -ENOMEM;
-+ blksize = dst->f_dentry->d_sb->s_blocksize;
++ blksize = dst->f_path.dentry->d_sb->s_blocksize;
+ if (!blksize || PAGE_SIZE < blksize)
+ blksize = PAGE_SIZE;
+ AuDbg("blksize %lu\n", blksize);
+ * 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)
++static int au_cp_regular(struct au_cp_generic *cpg)
+{
+ int err, i;
+ enum { SRC, DST };
+ aufs_bindex_t bindex;
+ unsigned int flags;
+ struct dentry *dentry;
++ int force_wr;
+ struct file *file;
-+ void *label, *label_file;
++ void *label;
+ } *f, file[] = {
+ {
-+ .bindex = bsrc,
++ .bindex = cpg->bsrc,
+ .flags = O_RDONLY | O_NOATIME | O_LARGEFILE,
-+ .file = NULL,
-+ .label = &&out,
-+ .label_file = &&out_src
++ .label = &&out
+ },
+ {
-+ .bindex = bdst,
++ .bindex = cpg->bdst,
+ .flags = O_WRONLY | O_NOATIME | O_LARGEFILE,
-+ .file = NULL,
-+ .label = &&out_src,
-+ .label_file = &&out_dst
++ .force_wr = !!au_ftest_cpup(cpg->flags, RWDST),
++ .label = &&out_src
+ }
+ };
+ struct super_block *sb;
+
+ /* bsrc branch can be ro/rw. */
-+ sb = dentry->d_sb;
++ sb = cpg->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);
++ f->dentry = au_h_dptr(cpg->dentry, f->bindex);
++ f->file = au_h_open(cpg->dentry, f->bindex, f->flags,
++ /*file*/NULL, f->force_wr);
+ 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);
++ err = au_copy_file(file[DST].file, file[SRC].file, cpg->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);
+ 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)
++static int au_do_cpup_regular(struct au_cp_generic *cpg,
++ struct au_cpup_reg_attr *h_src_attr)
+{
+ int err, rerr;
+ loff_t l;
++ struct path h_path;
++ struct inode *h_src_inode, *h_dst_inode;
+
+ 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 */
++ h_src_inode = au_h_iptr(cpg->dentry->d_inode, cpg->bsrc);
++ l = i_size_read(h_src_inode);
++ if (cpg->len == -1 || l < cpg->len)
++ cpg->len = l;
++ if (cpg->len) {
++ /* try stopping to update while we are referencing */
++ mutex_lock_nested(&h_src_inode->i_mutex, AuLsc_I_CHILD);
++ au_pin_hdir_unlock(cpg->pin);
+
-+ 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;
++ h_path.dentry = au_h_dptr(cpg->dentry, cpg->bsrc);
++ h_path.mnt = au_sbr_mnt(cpg->dentry->d_sb, cpg->bsrc);
++ h_src_attr->iflags = h_src_inode->i_flags;
++ err = vfs_getattr(&h_path, &h_src_attr->st);
++ if (unlikely(err)) {
++ mutex_unlock(&h_src_inode->i_mutex);
++ goto out;
++ }
++ h_src_attr->valid = 1;
++ err = au_cp_regular(cpg);
++ mutex_unlock(&h_src_inode->i_mutex);
++ rerr = au_pin_hdir_relock(cpg->pin);
++ if (!err && rerr)
++ err = rerr;
++ }
++ if (!err && (h_src_inode->i_state & I_LINKABLE)) {
++ h_path.dentry = au_h_dptr(cpg->dentry, cpg->bdst);
++ h_dst_inode = h_path.dentry->d_inode;
++ spin_lock(&h_dst_inode->i_lock);
++ h_dst_inode->i_state |= I_LINKABLE;
++ spin_unlock(&h_dst_inode->i_lock);
+ }
+
+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 cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent,
++ struct au_cpup_reg_attr *h_src_attr)
+{
+ int err;
+ umode_t mode;
+ unsigned int mnt_flags;
-+ unsigned char isdir;
-+ const unsigned char do_dt = !!au_ftest_cpup(flags, DTIME);
++ unsigned char isdir, isreg, force;
++ const unsigned char do_dt = !!au_ftest_cpup(cpg->flags, DTIME);
+ struct au_dtime dt;
+ struct path h_path;
+ struct dentry *h_src, *h_dst, *h_parent;
+ struct super_block *sb;
+
+ /* bsrc branch can be ro/rw. */
-+ h_src = au_h_dptr(dentry, bsrc);
++ h_src = au_h_dptr(cpg->dentry, cpg->bsrc);
+ h_inode = h_src->d_inode;
-+ AuDebugOn(h_inode != au_h_iptr(dentry->d_inode, bsrc));
++ AuDebugOn(h_inode != au_h_iptr(cpg->dentry->d_inode, cpg->bsrc));
+
+ /* try stopping to be referenced while we are creating */
-+ h_dst = au_h_dptr(dentry, bdst);
++ h_dst = au_h_dptr(cpg->dentry, cpg->bdst);
++ if (au_ftest_cpup(cpg->flags, RENAME))
++ AuDebugOn(strncmp(h_dst->d_name.name, AUFS_WH_PFX,
++ AUFS_WH_PFX_LEN));
+ 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);
++ sb = cpg->dentry->d_sb;
++ h_path.mnt = au_sbr_mnt(sb, cpg->bdst);
+ if (do_dt) {
+ h_path.dentry = h_parent;
+ au_dtime_store(&dt, dst_parent, &h_path);
+ }
+ h_path.dentry = h_dst;
+
++ isreg = 0;
+ 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);
++ isreg = 1;
+ err = vfsub_create(h_dir, &h_path, mode | S_IWUSR,
+ /*want_excl*/true);
+ if (!err)
-+ err = au_do_cpup_regular
-+ (dentry, bdst, bsrc, len,
-+ au_h_iptr(dst_parent->d_inode, bdst), &h_path);
++ err = au_do_cpup_regular(cpg, h_src_attr);
+ break;
+ case S_IFDIR:
+ isdir = 1;
+ * strange behaviour from the users view,
+ * particularry setattr case
+ */
-+ if (au_ibstart(dst_parent->d_inode) == bdst)
++ if (au_ibstart(dst_parent->d_inode) == cpg->bdst)
+ au_cpup_attr_nlink(dst_parent->d_inode,
+ /*force*/1);
-+ au_cpup_attr_nlink(dentry->d_inode, /*force*/1);
++ au_cpup_attr_nlink(cpg->dentry->d_inode, /*force*/1);
+ }
+ break;
+ case S_IFLNK:
+ if (!au_opt_test(mnt_flags, UDBA_NONE)
+ && !isdir
+ && au_opt_test(mnt_flags, XINO)
-+ && h_inode->i_nlink == 1
++ && (h_inode->i_nlink == 1
++ || (h_inode->i_state & I_LINKABLE))
+ /* todo: unnecessary? */
-+ /* && dentry->d_inode->i_nlink == 1 */
-+ && bdst < bsrc
-+ && !au_ftest_cpup(flags, KEEPLINO))
-+ au_xino_write(sb, bsrc, h_inode->i_ino, /*ino*/0);
++ /* && cpg->dentry->d_inode->i_nlink == 1 */
++ && cpg->bdst < cpg->bsrc
++ && !au_ftest_cpup(cpg->flags, KEEPLINO))
++ au_xino_write(sb, cpg->bsrc, h_inode->i_ino, /*ino*/0);
+ /* ignore this error */
+
++ if (!err) {
++ force = 0;
++ if (isreg) {
++ force = !!cpg->len;
++ if (cpg->len == -1)
++ force = !!i_size_read(h_inode);
++ }
++ au_fhsm_wrote(sb, cpg->bdst, force);
++ }
++
+ if (do_dt)
+ au_dtime_revert(&dt);
+ return err;
+}
+
++static int au_do_ren_after_cpup(struct au_cp_generic *cpg, struct path *h_path)
++{
++ int err;
++ struct dentry *dentry, *h_dentry, *h_parent, *parent;
++ struct inode *h_dir;
++ aufs_bindex_t bdst;
++
++ dentry = cpg->dentry;
++ bdst = cpg->bdst;
++ h_dentry = au_h_dptr(dentry, bdst);
++ if (!au_ftest_cpup(cpg->flags, OVERWRITE)) {
++ dget(h_dentry);
++ au_set_h_dptr(dentry, bdst, NULL);
++ err = au_lkup_neg(dentry, bdst, /*wh*/0);
++ if (!err)
++ h_path->dentry = dget(au_h_dptr(dentry, bdst));
++ au_set_h_dptr(dentry, bdst, h_dentry);
++ } else {
++ err = 0;
++ parent = dget_parent(dentry);
++ h_parent = au_h_dptr(parent, bdst);
++ dput(parent);
++ h_path->dentry = vfsub_lkup_one(&dentry->d_name, h_parent);
++ if (IS_ERR(h_path->dentry))
++ err = PTR_ERR(h_path->dentry);
++ }
++ if (unlikely(err))
++ goto out;
++
++ h_parent = h_dentry->d_parent; /* dir inode is locked */
++ h_dir = h_parent->d_inode;
++ IMustLock(h_dir);
++ AuDbg("%pd %pd\n", h_dentry, h_path->dentry);
++ /* no delegation since it is just created */
++ err = vfsub_rename(h_dir, h_dentry, h_dir, h_path, /*delegated*/NULL);
++ dput(h_path->dentry);
++
++out:
++ 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.
++ * basic->bsrc can be larger than basic->bdst.
+ */
-+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)
++static int au_cpup_single(struct au_cp_generic *cpg, 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 inode *dst_inode, *h_dir, *inode, *delegated;
+ struct super_block *sb;
++ struct au_branch *br;
++ /* to reuduce stack size */
++ struct {
++ struct au_dtime dt;
++ struct path h_path;
++ struct au_cpup_reg_attr h_src_attr;
++ } *a;
+
-+ AuDebugOn(bsrc <= bdst);
++ err = -ENOMEM;
++ a = kmalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
++ a->h_src_attr.valid = 0;
+
-+ sb = dentry->d_sb;
-+ h_path.mnt = au_sbr_mnt(sb, bdst);
-+ h_dst = au_h_dptr(dentry, bdst);
++ sb = cpg->dentry->d_sb;
++ br = au_sbr(sb, cpg->bdst);
++ a->h_path.mnt = au_br_mnt(br);
++ h_dst = au_h_dptr(cpg->dentry, cpg->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;
++ h_src = au_h_dptr(cpg->dentry, cpg->bsrc);
++ inode = cpg->dentry->d_inode;
+
+ if (!dst_parent)
-+ dst_parent = dget_parent(dentry);
++ dst_parent = dget_parent(cpg->dentry);
+ else
+ dget(dst_parent);
+
+ plink = !!au_opt_test(au_mntflags(sb), PLINK);
-+ dst_inode = au_h_iptr(inode, bdst);
++ dst_inode = au_h_iptr(inode, cpg->bdst);
+ if (dst_inode) {
+ if (unlikely(!plink)) {
+ err = -EIO;
+ AuIOErr("hi%lu(i%lu) exists on b%d "
+ "but plink is disabled\n",
-+ dst_inode->i_ino, inode->i_ino, bdst);
-+ goto out;
++ dst_inode->i_ino, inode->i_ino, cpg->bdst);
++ goto out_parent;
+ }
+
+ if (dst_inode->i_nlink) {
-+ const int do_dt = au_ftest_cpup(flags, DTIME);
++ const int do_dt = au_ftest_cpup(cpg->flags, DTIME);
+
-+ h_src = au_plink_lkup(inode, bdst);
++ h_src = au_plink_lkup(inode, cpg->bdst);
+ err = PTR_ERR(h_src);
+ if (IS_ERR(h_src))
-+ goto out;
++ goto out_parent;
+ if (unlikely(!h_src->d_inode)) {
+ err = -EIO;
+ AuIOErr("i%lu exists on a upper branch "
+ "but not pseudo-linked\n",
+ inode->i_ino);
+ dput(h_src);
-+ goto out;
++ goto out_parent;
+ }
+
+ if (do_dt) {
-+ h_path.dentry = h_parent;
-+ au_dtime_store(&dt, dst_parent, &h_path);
++ a->h_path.dentry = h_parent;
++ au_dtime_store(&a->dt, dst_parent, &a->h_path);
+ }
-+ h_path.dentry = h_dst;
-+ err = vfsub_link(h_src, h_dir, &h_path);
++
++ a->h_path.dentry = h_dst;
++ delegated = NULL;
++ err = vfsub_link(h_src, h_dir, &a->h_path, &delegated);
++ if (!err && au_ftest_cpup(cpg->flags, RENAME))
++ err = au_do_ren_after_cpup(cpg, &a->h_path);
+ if (do_dt)
-+ au_dtime_revert(&dt);
++ au_dtime_revert(&a->dt);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal link\n");
++ iput(delegated);
++ }
+ dput(h_src);
-+ goto out;
++ goto out_parent;
+ } else
+ /* todo: cpup_wh_file? */
+ /* udba work */
+ au_update_ibrange(inode, /*do_put_zero*/1);
+ }
+
++ isdir = S_ISDIR(inode->i_mode);
+ old_ibstart = au_ibstart(inode);
-+ err = cpup_entry(dentry, bdst, bsrc, len, flags, dst_parent);
++ err = cpup_entry(cpg, dst_parent, &a->h_src_attr);
+ if (unlikely(err))
-+ goto out;
++ goto out_rev;
+ dst_inode = h_dst->d_inode;
+ mutex_lock_nested(&dst_inode->i_mutex, AuLsc_I_CHILD2);
++ /* todo: necessary? */
++ /* au_pin_hdir_unlock(cpg->pin); */
+
-+ err = cpup_iattr(dentry, bdst, h_src);
-+ isdir = S_ISDIR(dst_inode->i_mode);
-+ if (!err) {
-+ if (bdst < old_ibstart) {
-+ if (S_ISREG(inode->i_mode)) {
-+ err = au_dy_iaop(inode, bdst, dst_inode);
-+ if (unlikely(err))
-+ goto out_rev;
++ err = cpup_iattr(cpg->dentry, cpg->bdst, h_src, &a->h_src_attr);
++ if (unlikely(err)) {
++ /* todo: necessary? */
++ /* au_pin_hdir_relock(cpg->pin); */ /* ignore an error */
++ mutex_unlock(&dst_inode->i_mutex);
++ goto out_rev;
++ }
++
++ if (cpg->bdst < old_ibstart) {
++ if (S_ISREG(inode->i_mode)) {
++ err = au_dy_iaop(inode, cpg->bdst, dst_inode);
++ if (unlikely(err)) {
++ /* ignore an error */
++ /* au_pin_hdir_relock(cpg->pin); */
++ mutex_unlock(&dst_inode->i_mutex);
++ goto out_rev;
+ }
-+ 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 */
++ au_set_ibstart(inode, cpg->bdst);
++ } else
++ au_set_ibend(inode, cpg->bdst);
++ au_set_h_iptr(inode, cpg->bdst, au_igrab(dst_inode),
++ au_hi_flags(inode, isdir));
++
++ /* todo: necessary? */
++ /* err = au_pin_hdir_relock(cpg->pin); */
++ mutex_unlock(&dst_inode->i_mutex);
++ if (unlikely(err))
++ goto out_rev;
++
++ if (!isdir
++ && (h_src->d_inode->i_nlink > 1
++ || h_src->d_inode->i_state & I_LINKABLE)
++ && plink)
++ au_plink_append(inode, cpg->bdst, h_dst);
++
++ if (au_ftest_cpup(cpg->flags, RENAME)) {
++ a->h_path.dentry = h_dst;
++ err = au_do_ren_after_cpup(cpg, &a->h_path);
+ }
++ if (!err)
++ goto out_parent; /* success */
+
+ /* revert */
+out_rev:
-+ 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);
++ a->h_path.dentry = h_parent;
++ au_dtime_store(&a->dt, dst_parent, &a->h_path);
++ a->h_path.dentry = h_dst;
++ rerr = 0;
++ if (h_dst->d_inode) {
++ if (!isdir) {
++ /* no delegation since it is just created */
++ rerr = vfsub_unlink(h_dir, &a->h_path,
++ /*delegated*/NULL, /*force*/0);
++ } else
++ rerr = vfsub_rmdir(h_dir, &a->h_path);
++ }
++ au_dtime_revert(&a->dt);
+ if (rerr) {
+ AuIOErr("failed removing broken entry(%d, %d)\n", err, rerr);
+ err = -EIO;
+ }
-+
-+out:
++out_parent:
+ dput(dst_parent);
++ kfree(a);
++out:
+ return err;
+}
+
++#if 0 /* reserved */
+struct au_cpup_single_args {
+ int *errp;
-+ struct dentry *dentry;
-+ aufs_bindex_t bdst, bsrc;
-+ loff_t len;
-+ unsigned int flags;
++ struct au_cp_generic *cpg;
+ 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);
++
++ au_pin_hdir_acquire_nest(a->cpg->pin);
++ *a->errp = au_cpup_single(a->cpg, a->dst_parent);
++ au_pin_hdir_release(a->cpg->pin);
+}
++#endif
+
+/*
+ * prevent SIGXFSZ in copy-up.
+ * testing CAP_MKNOD is for generic fs,
+ * but CAP_FSETID is for xfs only, currently.
+ */
-+static int au_cpup_sio_test(struct super_block *sb, umode_t mode)
++static int au_cpup_sio_test(struct au_pin *pin, umode_t mode)
+{
+ int do_sio;
++ struct super_block *sb;
++ struct inode *h_dir;
+
+ do_sio = 0;
++ sb = au_pinned_parent(pin)->d_sb;
+ if (!au_wkq_test()
+ && (!au_sbi(sb)->si_plink_maint_pid
+ || au_plink_maint(sb, AuLock_NOPLM))) {
+ if (!do_sio)
+ do_sio = ((mode & (S_ISUID | S_ISGID))
+ && !capable(CAP_FSETID));
++ /* this workaround may be removed in the future */
++ if (!do_sio) {
++ h_dir = au_pinned_h_dir(pin);
++ do_sio = h_dir->i_mode & S_ISVTX;
++ }
+ }
+
+ return do_sio;
+}
+
-+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)
++#if 0 /* reserved */
++int au_sio_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent)
+{
+ int err, wkq_err;
+ struct dentry *h_dentry;
+
-+ h_dentry = au_h_dptr(dentry, bsrc);
-+ if (!au_cpup_sio_test(dentry->d_sb, h_dentry->d_inode->i_mode))
-+ err = au_cpup_single(dentry, bdst, bsrc, len, flags,
-+ dst_parent);
++ h_dentry = au_h_dptr(cpg->dentry, cpg->bsrc);
++ if (!au_cpup_sio_test(pin, h_dentry->d_inode->i_mode))
++ err = au_cpup_single(cpg, dst_parent);
+ else {
+ struct au_cpup_single_args args = {
+ .errp = &err,
-+ .dentry = dentry,
-+ .bdst = bdst,
-+ .bsrc = bsrc,
-+ .len = len,
-+ .flags = flags,
++ .cpg = cpg,
+ .dst_parent = dst_parent
+ };
+ wkq_err = au_wkq_wait(au_call_cpup_single, &args);
+
+ return err;
+}
++#endif
+
+/*
+ * 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)
++static int au_cpup_simple(struct au_cp_generic *cpg)
+{
+ int err;
-+ aufs_bindex_t bsrc, bend;
++ unsigned int flags_orig;
++ struct dentry *dentry;
+
-+ bend = au_dbend(dentry);
-+ for (bsrc = bdst + 1; bsrc <= bend; bsrc++)
-+ if (au_h_dptr(dentry, bsrc))
-+ break;
++ AuDebugOn(cpg->bsrc < 0);
++
++ dentry = cpg->dentry;
++ DiMustWriteLock(dentry);
+
-+ err = au_lkup_neg(dentry, bdst);
++ err = au_lkup_neg(dentry, cpg->bdst, /*wh*/1);
+ if (!err) {
-+ err = au_cpup_single(dentry, bdst, bsrc, len, flags, NULL);
++ flags_orig = cpg->flags;
++ au_fset_cpup(cpg->flags, RENAME);
++ err = au_cpup_single(cpg, NULL);
++ cpg->flags = flags_orig;
+ if (!err)
+ return 0; /* success */
+
+ /* revert */
-+ au_set_h_dptr(dentry, bdst, NULL);
-+ au_set_dbstart(dentry, bsrc);
++ au_set_h_dptr(dentry, cpg->bdst, NULL);
++ au_set_dbstart(dentry, cpg->bsrc);
+ }
+
+ return err;
+
+struct au_cpup_simple_args {
+ int *errp;
-+ struct dentry *dentry;
-+ aufs_bindex_t bdst;
-+ loff_t len;
-+ unsigned int flags;
++ struct au_cp_generic *cpg;
+};
+
+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);
++
++ au_pin_hdir_acquire_nest(a->cpg->pin);
++ *a->errp = au_cpup_simple(a->cpg);
++ au_pin_hdir_release(a->cpg->pin);
+}
+
-+int au_sio_cpup_simple(struct dentry *dentry, aufs_bindex_t bdst, loff_t len,
-+ unsigned int flags)
++static int au_do_sio_cpup_simple(struct au_cp_generic *cpg)
+{
+ int err, wkq_err;
-+ struct dentry *parent;
++ struct dentry *dentry, *parent;
++ struct file *h_file;
+ struct inode *h_dir;
+
++ dentry = cpg->dentry;
++ h_file = NULL;
++ if (au_ftest_cpup(cpg->flags, HOPEN)) {
++ AuDebugOn(cpg->bsrc < 0);
++ h_file = au_h_open_pre(dentry, cpg->bsrc, /*force_wr*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
++ }
++
+ parent = dget_parent(dentry);
-+ h_dir = au_h_iptr(parent->d_inode, bdst);
++ h_dir = au_h_iptr(parent->d_inode, cpg->bdst);
+ if (!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE)
-+ && !au_cpup_sio_test(dentry->d_sb, dentry->d_inode->i_mode))
-+ err = au_cpup_simple(dentry, bdst, len, flags);
++ && !au_cpup_sio_test(cpg->pin, dentry->d_inode->i_mode))
++ err = au_cpup_simple(cpg);
+ else {
+ struct au_cpup_simple_args args = {
+ .errp = &err,
-+ .dentry = dentry,
-+ .bdst = bdst,
-+ .len = len,
-+ .flags = flags
++ .cpg = cpg
+ };
+ wkq_err = au_wkq_wait(au_call_cpup_simple, &args);
+ if (unlikely(wkq_err))
+ }
+
+ dput(parent);
++ if (h_file)
++ au_h_open_post(dentry, cpg->bsrc, h_file);
++
++out:
+ return err;
+}
+
++int au_sio_cpup_simple(struct au_cp_generic *cpg)
++{
++ aufs_bindex_t bsrc, bend;
++ struct dentry *dentry, *h_dentry;
++
++ if (cpg->bsrc < 0) {
++ dentry = cpg->dentry;
++ bend = au_dbend(dentry);
++ for (bsrc = cpg->bdst + 1; bsrc <= bend; bsrc++) {
++ h_dentry = au_h_dptr(dentry, bsrc);
++ if (h_dentry) {
++ AuDebugOn(!h_dentry->d_inode);
++ break;
++ }
++ }
++ AuDebugOn(bsrc > bend);
++ cpg->bsrc = bsrc;
++ }
++ AuDebugOn(cpg->bsrc <= cpg->bdst);
++ return au_do_sio_cpup_simple(cpg);
++}
++
++int au_sio_cpdown_simple(struct au_cp_generic *cpg)
++{
++ AuDebugOn(cpg->bdst <= cpg->bsrc);
++ return au_do_sio_cpup_simple(cpg);
++}
++
+/* ---------------------------------------------------------------------- */
+
+/*
+ * 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)
++static int au_do_cpup_wh(struct au_cp_generic *cpg, struct dentry *wh_dentry,
++ struct file *file)
+{
+ int err;
-+ aufs_bindex_t bstart;
-+ struct au_dinfo *dinfo;
++ unsigned int flags_orig;
++ aufs_bindex_t bsrc_orig;
+ struct dentry *h_d_dst, *h_d_start;
++ struct au_dinfo *dinfo;
+ struct au_hdentry *hdp;
+
-+ dinfo = au_di(dentry);
++ dinfo = au_di(cpg->dentry);
+ AuRwMustWriteLock(&dinfo->di_rwsem);
+
-+ bstart = dinfo->di_bstart;
++ bsrc_orig = cpg->bsrc;
++ cpg->bsrc = dinfo->di_bstart;
+ hdp = dinfo->di_hdentry;
-+ h_d_dst = hdp[0 + bdst].hd_dentry;
-+ dinfo->di_bstart = bdst;
-+ hdp[0 + bdst].hd_dentry = wh_dentry;
++ h_d_dst = hdp[0 + cpg->bdst].hd_dentry;
++ dinfo->di_bstart = cpg->bdst;
++ hdp[0 + cpg->bdst].hd_dentry = wh_dentry;
++ h_d_start = NULL;
+ if (file) {
-+ h_d_start = hdp[0 + bstart].hd_dentry;
-+ hdp[0 + bstart].hd_dentry = au_hf_top(file)->f_dentry;
++ h_d_start = hdp[0 + cpg->bsrc].hd_dentry;
++ hdp[0 + cpg->bsrc].hd_dentry = au_hf_top(file)->f_path.dentry;
+ }
-+ err = au_cpup_single(dentry, bdst, bstart, len, !AuCpup_DTIME,
-+ /*h_parent*/NULL);
++ flags_orig = cpg->flags;
++ cpg->flags = !AuCpup_DTIME;
++ err = au_cpup_single(cpg, /*h_parent*/NULL);
++ cpg->flags = flags_orig;
+ if (file) {
+ if (!err)
+ err = au_reopen_nondir(file);
-+ hdp[0 + bstart].hd_dentry = h_d_start;
++ hdp[0 + cpg->bsrc].hd_dentry = h_d_start;
+ }
-+ hdp[0 + bdst].hd_dentry = h_d_dst;
-+ dinfo->di_bstart = bstart;
++ hdp[0 + cpg->bdst].hd_dentry = h_d_dst;
++ dinfo->di_bstart = cpg->bsrc;
++ cpg->bsrc = bsrc_orig;
+
+ return err;
+}
+
-+static int au_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len,
-+ struct file *file)
++static int au_cpup_wh(struct au_cp_generic *cpg, struct file *file)
+{
+ int err;
++ aufs_bindex_t bdst;
+ struct au_dtime dt;
-+ struct dentry *parent, *h_parent, *wh_dentry;
++ struct dentry *dentry, *parent, *h_parent, *wh_dentry;
+ struct au_branch *br;
+ struct path h_path;
+
++ dentry = cpg->dentry;
++ bdst = cpg->bdst;
+ br = au_sbr(dentry->d_sb, bdst);
+ parent = dget_parent(dentry);
+ h_parent = au_h_dptr(parent, bdst);
+ goto out;
+
+ h_path.dentry = h_parent;
-+ h_path.mnt = br->br_mnt;
++ h_path.mnt = au_br_mnt(br);
+ au_dtime_store(&dt, parent, &h_path);
-+ err = au_do_cpup_wh(dentry, bdst, wh_dentry, file, len);
++ err = au_do_cpup_wh(cpg, wh_dentry, file);
+ if (unlikely(err))
+ goto out_wh;
+
+ dget(wh_dentry);
+ h_path.dentry = wh_dentry;
-+ if (!S_ISDIR(wh_dentry->d_inode->i_mode))
-+ err = vfsub_unlink(h_parent->d_inode, &h_path, /*force*/0);
-+ else
++ if (!d_is_dir(wh_dentry)) {
++ /* no delegation since it is just created */
++ err = vfsub_unlink(h_parent->d_inode, &h_path,
++ /*delegated*/NULL, /*force*/0);
++ } else
+ err = vfsub_rmdir(h_parent->d_inode, &h_path);
+ if (unlikely(err)) {
-+ AuIOErr("failed remove copied-up tmp file %.*s(%d)\n",
-+ AuDLNPair(wh_dentry), err);
++ AuIOErr("failed remove copied-up tmp file %pd(%d)\n",
++ wh_dentry, err);
+ err = -EIO;
+ }
+ au_dtime_revert(&dt);
+
+struct au_cpup_wh_args {
+ int *errp;
-+ struct dentry *dentry;
-+ aufs_bindex_t bdst;
-+ loff_t len;
++ struct au_cp_generic *cpg;
+ 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);
++
++ au_pin_hdir_acquire_nest(a->cpg->pin);
++ *a->errp = au_cpup_wh(a->cpg, a->file);
++ au_pin_hdir_release(a->cpg->pin);
+}
+
-+int au_sio_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len,
-+ struct file *file)
++int au_sio_cpup_wh(struct au_cp_generic *cpg, 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;
++ aufs_bindex_t bdst;
++ struct dentry *dentry, *parent, *h_orph, *h_parent;
++ struct inode *dir, *h_dir, *h_tmpdir;
+ struct au_wbr *wbr;
++ struct au_pin wh_pin, *pin_orig;
+
++ dentry = cpg->dentry;
++ bdst = cpg->bdst;
+ 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;
++ pin_orig = NULL;
+ if (!h_dir->i_nlink) {
+ wbr = au_sbr(dentry->d_sb, bdst)->br_wbr;
+ h_orph = wbr->wbr_orph;
+ h_tmpdir = h_orph->d_inode;
+ au_set_h_iptr(dir, bdst, au_igrab(h_tmpdir), /*flags*/0);
+
-+ /* this temporary unlock is safe */
-+ if (file)
-+ h_dentry = au_hf_top(file)->f_dentry;
-+ else
-+ h_dentry = au_h_dptr(dentry, au_dbstart(dentry));
-+ h_inode = h_dentry->d_inode;
-+ IMustLock(h_inode);
-+ mutex_unlock(&h_inode->i_mutex);
+ mutex_lock_nested(&h_tmpdir->i_mutex, AuLsc_I_PARENT3);
-+ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
+ /* todo: au_h_open_pre()? */
++
++ pin_orig = cpg->pin;
++ au_pin_init(&wh_pin, dentry, bdst, AuLsc_DI_PARENT,
++ AuLsc_I_PARENT3, cpg->pin->udba, AuPin_DI_LOCKED);
++ cpg->pin = &wh_pin;
+ }
+
+ if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE)
-+ && !au_cpup_sio_test(dentry->d_sb, dentry->d_inode->i_mode))
-+ err = au_cpup_wh(dentry, bdst, len, file);
++ && !au_cpup_sio_test(cpg->pin, dentry->d_inode->i_mode))
++ err = au_cpup_wh(cpg, file);
+ else {
+ struct au_cpup_wh_args args = {
+ .errp = &err,
-+ .dentry = dentry,
-+ .bdst = bdst,
-+ .len = len,
++ .cpg = cpg,
+ .file = file
+ };
+ wkq_err = au_wkq_wait(au_call_cpup_wh, &args);
+ /* todo: au_h_open_post()? */
+ au_set_h_iptr(dir, bdst, au_igrab(h_dir), /*flags*/0);
+ au_set_h_dptr(parent, bdst, h_parent);
++ AuDebugOn(!pin_orig);
++ cpg->pin = pin_orig;
+ }
+ iput(h_dir);
+ dput(parent);
+/* 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 au_pin *pin,
+ struct dentry *h_parent, void *arg),
+ void *arg)
+{
+ au_pin_set_dentry(&pin, d);
+ err = au_do_pin(&pin);
+ if (!err) {
-+ err = cp(d, bdst, h_parent, arg);
++ err = cp(d, bdst, &pin, h_parent, arg);
+ au_unpin(&pin);
+ }
+ }
+}
+
+static int au_cpup_dir(struct dentry *dentry, aufs_bindex_t bdst,
-+ struct dentry *h_parent __maybe_unused ,
++ struct au_pin *pin,
++ struct dentry *h_parent __maybe_unused,
+ void *arg __maybe_unused)
+{
-+ return au_sio_cpup_simple(dentry, bdst, -1, AuCpup_DTIME);
++ struct au_cp_generic cpg = {
++ .dentry = dentry,
++ .bdst = bdst,
++ .bsrc = -1,
++ .len = 0,
++ .pin = pin,
++ .flags = AuCpup_DTIME
++ };
++ return au_sio_cpup_simple(&cpg);
+}
+
+int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst)
+}
diff -urN /usr/share/empty/fs/aufs/cpup.h linux/fs/aufs/cpup.h
--- /usr/share/empty/fs/aufs/cpup.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/cpup.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,81 @@
++++ linux/fs/aufs/cpup.h 2015-06-22 08:27:37.874168290 +0200
+@@ -0,0 +1,94 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+
+struct inode;
+struct file;
++struct au_pin;
+
-+void au_cpup_attr_flags(struct inode *dst, struct inode *src);
++void au_cpup_attr_flags(struct inode *dst, unsigned int iflags);
+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);
+
+/* ---------------------------------------------------------------------- */
+
++struct au_cp_generic {
++ struct dentry *dentry;
++ aufs_bindex_t bdst, bsrc;
++ loff_t len;
++ struct au_pin *pin;
++ unsigned int flags;
++};
++
+/* 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 AuCpup_DTIME 1 /* do dtime_store/revert */
++#define AuCpup_KEEPLINO (1 << 1) /* do not clear the lower xino,
++ for link(2) */
++#define AuCpup_RENAME (1 << 2) /* rename after cpup */
++#define AuCpup_HOPEN (1 << 3) /* call h_open_pre/post() in
++ cpup */
++#define AuCpup_OVERWRITE (1 << 4) /* allow overwriting the
++ existing entry */
++#define AuCpup_RWDST (1 << 5) /* force write target even if
++ the branch is marked as RO */
++
+#define au_ftest_cpup(flags, name) ((flags) & AuCpup_##name)
+#define au_fset_cpup(flags, name) \
+ do { (flags) |= AuCpup_##name; } while (0)
+ do { (flags) &= ~AuCpup_##name; } while (0)
+
+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_sio_cpup_simple(struct au_cp_generic *cpg);
++int au_sio_cpdown_simple(struct au_cp_generic *cpg);
++int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file);
+
+int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst,
+ int (*cp)(struct dentry *dentry, aufs_bindex_t bdst,
++ struct au_pin *pin,
+ struct dentry *h_parent, void *arg),
+ void *arg);
+int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst);
+#endif /* __AUFS_CPUP_H__ */
diff -urN /usr/share/empty/fs/aufs/dbgaufs.c linux/fs/aufs/dbgaufs.c
--- /usr/share/empty/fs/aufs/dbgaufs.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dbgaufs.c 2013-03-14 20:07:41.038119650 +0100
-@@ -0,0 +1,334 @@
++++ linux/fs/aufs/dbgaufs.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,432 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ if (!xf)
+ goto out;
+
-+ err = vfs_getattr(xf->f_vfsmnt, xf->f_dentry, &st);
++ err = vfs_getattr(&xf->f_path, &st);
+ if (!err) {
+ if (do_fcnt)
+ p->n = snprintf
+
+/* ---------------------------------------------------------------------- */
+
-+static int dbgaufs_xib_open(struct inode *inode, struct file *file)
++struct dbgaufs_plink_arg {
++ int n;
++ char a[];
++};
++
++static int dbgaufs_plink_release(struct inode *inode __maybe_unused,
++ struct file *file)
+{
-+ int err;
++ free_page((unsigned long)file->private_data);
++ return 0;
++}
++
++static int dbgaufs_plink_open(struct inode *inode, struct file *file)
++{
++ int err, i, limit;
++ unsigned long n, sum;
++ struct dbgaufs_plink_arg *p;
+ struct au_sbinfo *sbinfo;
+ struct super_block *sb;
++ struct au_sphlhead *sphl;
++
++ err = -ENOMEM;
++ p = (void *)get_zeroed_page(GFP_NOFS);
++ if (unlikely(!p))
++ goto out;
+
++ err = -EFBIG;
+ sbinfo = inode->i_private;
+ sb = sbinfo->si_sb;
+ si_noflush_read_lock(sb);
-+ err = dbgaufs_xi_open(sbinfo->si_xib, file, /*do_fcnt*/0);
-+ si_read_unlock(sb);
-+ return err;
-+}
++ if (au_opt_test(au_mntflags(sb), PLINK)) {
++ limit = PAGE_SIZE - sizeof(p->n);
++
++ /* the number of buckets */
++ n = snprintf(p->a + p->n, limit, "%d\n", AuPlink_NHASH);
++ p->n += n;
++ limit -= n;
++
++ sum = 0;
++ for (i = 0, sphl = sbinfo->si_plink;
++ i < AuPlink_NHASH;
++ i++, sphl++) {
++ n = au_sphl_count(sphl);
++ sum += n;
++
++ n = snprintf(p->a + p->n, limit, "%lu ", n);
++ p->n += n;
++ limit -= n;
++ if (unlikely(limit <= 0))
++ goto out_free;
++ }
++ p->a[p->n - 1] = '\n';
+
-+static const struct file_operations dbgaufs_xib_fop = {
-+ .owner = THIS_MODULE,
++ /* the sum of plinks */
++ n = snprintf(p->a + p->n, limit, "%lu\n", sum);
++ p->n += n;
++ limit -= n;
++ if (unlikely(limit <= 0))
++ goto out_free;
++ } else {
++#define str "1\n0\n0\n"
++ p->n = sizeof(str) - 1;
++ strcpy(p->a, str);
++#undef str
++ }
++ si_read_unlock(sb);
++
++ err = 0;
++ file->private_data = p;
++ goto out; /* success */
++
++out_free:
++ free_page((unsigned long)p);
++out:
++ return err;
++}
++
++static ssize_t dbgaufs_plink_read(struct file *file, char __user *buf,
++ size_t count, loff_t *ppos)
++{
++ struct dbgaufs_plink_arg *p;
++
++ p = file->private_data;
++ return simple_read_from_buffer(buf, count, ppos, p->a, p->n);
++}
++
++static const struct file_operations dbgaufs_plink_fop = {
++ .owner = THIS_MODULE,
++ .open = dbgaufs_plink_open,
++ .release = dbgaufs_plink_release,
++ .read = dbgaufs_plink_read
++};
++
++/* ---------------------------------------------------------------------- */
++
++static int dbgaufs_xib_open(struct inode *inode, struct file *file)
++{
++ int err;
++ struct au_sbinfo *sbinfo;
++ struct super_block *sb;
++
++ sbinfo = inode->i_private;
++ sb = sbinfo->si_sb;
++ si_noflush_read_lock(sb);
++ err = dbgaufs_xi_open(sbinfo->si_xib, file, /*do_fcnt*/0);
++ si_read_unlock(sb);
++ return err;
++}
++
++static const struct file_operations dbgaufs_xib_fop = {
++ .owner = THIS_MODULE,
+ .open = dbgaufs_xib_open,
+ .release = dbgaufs_xi_release,
+ .read = dbgaufs_xi_read
+
+ err = -ENOENT;
+ xf = NULL;
-+ name = &file->f_dentry->d_name;
++ name = &file->f_path.dentry->d_name;
+ if (unlikely(name->len < sizeof(DbgaufsXi_PREFIX)
+ || memcmp(name->name, DbgaufsXi_PREFIX,
+ sizeof(DbgaufsXi_PREFIX) - 1)))
+ for (; bindex <= bend; bindex++) {
+ br = au_sbr(sb, bindex);
+ xi = &br->br_xino;
-+ if (xi->xi_dbgaufs) {
-+ debugfs_remove(xi->xi_dbgaufs);
-+ xi->xi_dbgaufs = NULL;
-+ }
++ debugfs_remove(xi->xi_dbgaufs);
++ xi->xi_dbgaufs = NULL;
+ }
+}
+
+ int err;
+
+ /*
-+ * This function is a dynamic '__init' fucntion actually,
++ * This function is a dynamic '__init' function actually,
+ * so the tiny check for si_rwsem is unnecessary.
+ */
+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
+void dbgaufs_si_fin(struct au_sbinfo *sbinfo)
+{
+ /*
-+ * This function is a dynamic '__init' fucntion actually,
++ * This function is a dynamic '__fin' function actually,
+ * so the tiny check for si_rwsem is unnecessary.
+ */
+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
+ char name[SysaufsSiNameLen];
+
+ /*
-+ * This function is a dynamic '__init' fucntion actually,
++ * This function is a dynamic '__init' function actually,
+ * so the tiny check for si_rwsem is unnecessary.
+ */
+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
+ if (unlikely(!sbinfo->si_dbgaufs_xib))
+ goto out_dir;
+
++ sbinfo->si_dbgaufs_plink = debugfs_create_file
++ ("plink", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo,
++ &dbgaufs_plink_fop);
++ if (unlikely(!sbinfo->si_dbgaufs_plink))
++ goto out_dir;
++
+ err = dbgaufs_xigen_init(sbinfo);
+ if (!err)
+ goto out; /* success */
+}
diff -urN /usr/share/empty/fs/aufs/dbgaufs.h linux/fs/aufs/dbgaufs.h
--- /usr/share/empty/fs/aufs/dbgaufs.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dbgaufs.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,49 @@
++++ linux/fs/aufs/dbgaufs.h 2015-06-22 08:27:37.874168290 +0200
+@@ -0,0 +1,48 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+#endif /* __DBGAUFS_H__ */
diff -urN /usr/share/empty/fs/aufs/dcsub.c linux/fs/aufs/dcsub.c
--- /usr/share/empty/fs/aufs/dcsub.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dcsub.c 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,243 @@
++++ linux/fs/aufs/dcsub.c 2015-06-22 08:27:37.877501704 +0200
+@@ -0,0 +1,224 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ dpages->ndpage++;
+ }
+
-+ AuDebugOn(!dentry->d_count);
++ AuDebugOn(au_dcount(dentry) <= 0);
+ dpage->dentries[dpage->ndentry++] = dget_dlock(dentry);
+ return 0; /* success */
+
+ return err;
+}
+
-+int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root,
-+ au_dpages_test test, void *arg)
-+{
++/* todo: BAD approach */
++/* copied from linux/fs/dcache.c */
++enum d_walk_ret {
++ D_WALK_CONTINUE,
++ D_WALK_QUIT,
++ D_WALK_NORETRY,
++ D_WALK_SKIP,
++};
++
++extern void d_walk(struct dentry *parent, void *data,
++ enum d_walk_ret (*enter)(void *, struct dentry *),
++ void (*finish)(void *));
++
++struct ac_dpages_arg {
+ int err;
-+ struct dentry *this_parent;
-+ struct list_head *next;
-+ struct super_block *sb = root->d_sb;
++ struct au_dcsub_pages *dpages;
++ struct super_block *sb;
++ au_dpages_test test;
++ void *arg;
++};
+
-+ err = 0;
-+ write_seqlock(&rename_lock);
-+ this_parent = root;
-+ spin_lock(&this_parent->d_lock);
-+repeat:
-+ next = this_parent->d_subdirs.next;
-+resume:
-+ if (this_parent->d_sb == sb
-+ && !IS_ROOT(this_parent)
-+ && au_di(this_parent)
-+ && this_parent->d_count
-+ && (!test || test(this_parent, arg))) {
-+ err = au_dpages_append(dpages, this_parent, GFP_ATOMIC);
-+ if (unlikely(err))
-+ goto out;
-+ }
++static enum d_walk_ret au_call_dpages_append(void *_arg, struct dentry *dentry)
++{
++ enum d_walk_ret ret;
++ struct ac_dpages_arg *arg = _arg;
+
-+ while (next != &this_parent->d_subdirs) {
-+ struct list_head *tmp = next;
-+ struct dentry *dentry = list_entry(tmp, struct dentry,
-+ d_u.d_child);
-+
-+ next = tmp->next;
-+ spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-+ if (dentry->d_count) {
-+ if (!list_empty(&dentry->d_subdirs)) {
-+ spin_unlock(&this_parent->d_lock);
-+ spin_release(&dentry->d_lock.dep_map, 1,
-+ _RET_IP_);
-+ this_parent = dentry;
-+ spin_acquire(&this_parent->d_lock.dep_map, 0, 1,
-+ _RET_IP_);
-+ goto repeat;
-+ }
-+ if (dentry->d_sb == sb
-+ && au_di(dentry)
-+ && (!test || test(dentry, arg)))
-+ err = au_dpages_append(dpages, dentry,
-+ GFP_ATOMIC);
-+ }
-+ spin_unlock(&dentry->d_lock);
-+ if (unlikely(err))
-+ goto out;
++ ret = D_WALK_CONTINUE;
++ if (dentry->d_sb == arg->sb
++ && !IS_ROOT(dentry)
++ && au_dcount(dentry) > 0
++ && au_di(dentry)
++ && (!arg->test || arg->test(dentry, arg->arg))) {
++ arg->err = au_dpages_append(arg->dpages, dentry, GFP_ATOMIC);
++ if (unlikely(arg->err))
++ ret = D_WALK_QUIT;
+ }
+
-+ if (this_parent != root) {
-+ struct dentry *tmp;
-+ struct dentry *child;
++ return ret;
++}
+
-+ tmp = this_parent->d_parent;
-+ rcu_read_lock();
-+ spin_unlock(&this_parent->d_lock);
-+ child = this_parent;
-+ this_parent = tmp;
-+ spin_lock(&this_parent->d_lock);
-+ rcu_read_unlock();
-+ next = child->d_u.d_child.next;
-+ goto resume;
-+ }
++int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root,
++ au_dpages_test test, void *arg)
++{
++ struct ac_dpages_arg args = {
++ .err = 0,
++ .dpages = dpages,
++ .sb = root->d_sb,
++ .test = test,
++ .arg = arg
++ };
+
-+out:
-+ spin_unlock(&this_parent->d_lock);
-+ write_sequnlock(&rename_lock);
-+ return err;
++ d_walk(root, &args, au_call_dpages_append, NULL);
++
++ return args.err;
+}
+
+int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry,
+ write_seqlock(&rename_lock);
+ spin_lock(&dentry->d_lock);
+ if (do_include
-+ && dentry->d_count
++ && au_dcount(dentry) > 0
+ && (!test || test(dentry, arg)))
+ err = au_dpages_append(dpages, dentry, GFP_ATOMIC);
+ spin_unlock(&dentry->d_lock);
+ goto out;
+
+ /*
-+ * vfsmount_lock is unnecessary since this is a traverse in a single
++ * RCU for vfsmount is unnecessary since this is a traverse in a single
+ * mount
+ */
+ while (!IS_ROOT(dentry)) {
+ dentry = dentry->d_parent; /* rename_lock is locked */
+ spin_lock(&dentry->d_lock);
-+ if (dentry->d_count
++ if (au_dcount(dentry) > 0
+ && (!test || test(dentry, arg)))
+ err = au_dpages_append(dpages, dentry, GFP_ATOMIC);
+ spin_unlock(&dentry->d_lock);
+}
diff -urN /usr/share/empty/fs/aufs/dcsub.h linux/fs/aufs/dcsub.h
--- /usr/share/empty/fs/aufs/dcsub.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dcsub.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,94 @@
++++ linux/fs/aufs/dcsub.h 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,132 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+#include <linux/dcache.h>
+#include <linux/fs.h>
+
-+struct dentry;
-+
+struct au_dpage {
+ int ndentry;
+ struct dentry **dentries;
+
+/* ---------------------------------------------------------------------- */
+
++/*
++ * todo: in linux-3.13, several similar (but faster) helpers are added to
++ * include/linux/dcache.h. Try them (in the future).
++ */
++
+static inline int au_d_hashed_positive(struct dentry *d)
+{
+ int err;
+ struct inode *inode = d->d_inode;
++
+ err = 0;
+ if (unlikely(d_unhashed(d) || !inode || !inode->i_nlink))
+ err = -ENOENT;
+ return err;
+}
+
++static inline int au_d_linkable(struct dentry *d)
++{
++ int err;
++ struct inode *inode = d->d_inode;
++
++ err = au_d_hashed_positive(d);
++ if (err
++ && inode
++ && (inode->i_state & I_LINKABLE))
++ err = 0;
++ return err;
++}
++
+static inline int au_d_alive(struct dentry *d)
+{
+ int err;
+ struct inode *inode;
++
+ err = 0;
+ if (!IS_ROOT(d))
+ err = au_d_hashed_positive(d);
+static inline int au_alive_dir(struct dentry *d)
+{
+ int err;
++
+ err = au_d_alive(d);
+ if (unlikely(err || IS_DEADDIR(d->d_inode)))
+ err = -ENOENT;
+ return err;
+}
+
++static inline int au_qstreq(struct qstr *a, struct qstr *b)
++{
++ return a->len == b->len
++ && !memcmp(a->name, b->name, a->len);
++}
++
++/*
++ * by the commit
++ * 360f547 2015-01-25 dcache: let the dentry count go down to zero without
++ * taking d_lock
++ * the type of d_lockref.count became int, but the inlined function d_count()
++ * still returns unsigned int.
++ * I don't know why. Maybe it is for every d_count() users?
++ * Anyway au_dcount() lives on.
++ */
++static inline int au_dcount(struct dentry *d)
++{
++ return (int)d_count(d);
++}
++
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DCSUB_H__ */
diff -urN /usr/share/empty/fs/aufs/debug.c linux/fs/aufs/debug.c
--- /usr/share/empty/fs/aufs/debug.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/debug.c 2013-03-14 20:07:41.038119650 +0100
-@@ -0,0 +1,490 @@
++++ linux/fs/aufs/debug.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,438 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * debug print functions
+ */
+
-+#include <linux/vt_kern.h>
+#include "aufs.h"
+
-+int aufs_debug;
++/* Returns 0, or -errno. arg is in kp->arg. */
++static int param_atomic_t_set(const char *val, const struct kernel_param *kp)
++{
++ int err, n;
++
++ err = kstrtoint(val, 0, &n);
++ if (!err) {
++ if (n > 0)
++ au_debug_on();
++ else
++ au_debug_off();
++ }
++ return err;
++}
++
++/* Returns length written or -errno. Buffer is 4k (ie. be short!) */
++static int param_atomic_t_get(char *buffer, const struct kernel_param *kp)
++{
++ atomic_t *a;
++
++ a = kp->arg;
++ return sprintf(buffer, "%d", atomic_read(a));
++}
++
++static struct kernel_param_ops param_ops_atomic_t = {
++ .set = param_atomic_t_set,
++ .get = param_atomic_t_get
++ /* void (*free)(void *arg) */
++};
++
++atomic_t aufs_debug = ATOMIC_INIT(0);
+MODULE_PARM_DESC(debug, "debug print");
-+module_param_named(debug, aufs_debug, int, S_IRUGO | S_IWUSR | S_IWGRP);
++module_param_named(debug, aufs_debug, atomic_t, S_IRUGO | S_IWUSR | S_IWGRP);
+
++DEFINE_MUTEX(au_dbg_mtx); /* just to serialize the dbg msgs */
+char *au_plevel = KERN_DEBUG;
+#define dpri(fmt, ...) do { \
+ if ((au_plevel \
+{
+ unsigned long ul, n;
+ struct hlist_head *head;
-+ struct au_vdir_wh *tpos;
-+ struct hlist_node *pos;
++ struct au_vdir_wh *pos;
+
+ n = whlist->nh_num;
+ head = whlist->nh_head;
+ for (ul = 0; ul < n; ul++) {
-+ hlist_for_each_entry(tpos, pos, head, wh_hash)
++ hlist_for_each_entry(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);
++ pos->wh_bindex,
++ pos->wh_str.len, pos->wh_str.name,
++ pos->wh_str.len);
+ head++;
+ }
+}
+ return -1;
+ }
+
-+ /* the type of i_blocks depends upon CONFIG_LSF */
++ /* the type of i_blocks depends upon CONFIG_LBDAF */
+ BUILD_BUG_ON(sizeof(inode->i_blocks) != sizeof(unsigned long)
+ && sizeof(inode->i_blocks) != sizeof(u64));
+ if (wh) {
+void au_dpri_dalias(struct inode *inode)
+{
+ struct dentry *d;
-+ struct hlist_node *p;
+
+ spin_lock(&inode->i_lock);
-+ hlist_for_each_entry(d, p, &inode->i_dentry, d_alias)
++ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias)
+ au_dpri_dentry(d);
+ spin_unlock(&inode->i_lock);
+}
+{
+ struct dentry *wh = NULL;
+ int hn;
++ struct au_iinfo *iinfo;
+
+ if (!dentry || IS_ERR(dentry)) {
+ dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry));
+ }
+ /* do not call dget_parent() here */
+ /* note: access d_xxx without d_lock */
-+ dpri("d%d: %.*s?/%.*s, %s, cnt %d, flags 0x%x\n",
-+ bindex,
-+ AuDLNPair(dentry->d_parent), AuDLNPair(dentry),
++ dpri("d%d: %p, %pd2?, %s, cnt %d, flags 0x%x, %shashed\n",
++ bindex, dentry, dentry,
+ dentry->d_sb ? au_sbtype(dentry->d_sb) : "??",
-+ dentry->d_count, dentry->d_flags);
++ au_dcount(dentry), dentry->d_flags,
++ d_unhashed(dentry) ? "un" : "");
+ hn = -1;
+ if (bindex >= 0 && dentry->d_inode && au_test_aufs(dentry->d_sb)) {
-+ struct au_iinfo *iinfo = au_ii(dentry->d_inode);
++ iinfo = au_ii(dentry->d_inode);
+ if (iinfo) {
+ hn = !!au_hn(iinfo->ii_hinode + bindex);
+ wh = iinfo->ii_hinode[0 + bindex].hi_whdentry;
+ dinfo = au_di(dentry);
+ if (!dinfo)
+ return;
-+ dpri("d-1: bstart %d, bend %d, bwh %d, bdiropq %d, gen %d\n",
++ dpri("d-1: bstart %d, bend %d, bwh %d, bdiropq %d, gen %d, tmp %d\n",
+ dinfo->di_bstart, dinfo->di_bend,
-+ dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry));
++ dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry),
++ dinfo->di_tmpfile);
+ if (dinfo->di_bstart < 0)
+ return;
+ hdp = dinfo->di_hdentry;
+ }
+ a[0] = 0;
+ if (bindex < 0
-+ && file->f_dentry
-+ && au_test_aufs(file->f_dentry->d_sb)
++ && !IS_ERR_OR_NULL(file->f_path.dentry)
++ && au_test_aufs(file->f_path.dentry->d_sb)
+ && au_fi(file))
+ snprintf(a, sizeof(a), ", gen %d, mmapped %d",
+ au_figen(file), atomic_read(&au_fi(file)->fi_mmapped));
+ dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, v %llu, pos %llu%s\n",
+ bindex, file->f_mode, file->f_flags, (long)file_count(file),
+ file->f_version, file->f_pos, a);
-+ if (file->f_dentry)
-+ do_pri_dentry(bindex, file->f_dentry);
++ if (!IS_ERR_OR_NULL(file->f_path.dentry))
++ do_pri_dentry(bindex, file->f_path.dentry);
+ return 0;
+}
+
+ int err;
+
+ err = do_pri_file(-1, file);
-+ if (err || !file->f_dentry || !au_test_aufs(file->f_dentry->d_sb))
++ if (err
++ || IS_ERR_OR_NULL(file->f_path.dentry)
++ || !au_test_aufs(file->f_path.dentry->d_sb))
+ return;
+
+ finfo = au_fi(file);
+
+ if (!br || IS_ERR(br))
+ goto out;
-+ mnt = br->br_mnt;
++ mnt = au_br_mnt(br);
+ if (!mnt || IS_ERR(mnt))
+ goto out;
+ sb = mnt->mnt_sb;
+
+ a->mnt.mnt_sb = sb;
+ a->fake.br_perm = 0;
-+ a->fake.br_mnt = &a->mnt;
++ a->fake.br_path.mnt = &a->mnt;
+ a->fake.br_xino.xi_file = NULL;
+ atomic_set(&a->fake.br_count, 0);
+ smp_mb(); /* atomic_set */
+
+/* ---------------------------------------------------------------------- */
+
-+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_dinode(struct dentry *dentry, const char *func, int line)
+{
+ struct inode *h_inode, *inode = dentry->d_inode;
+ continue;
+ h_inode = au_h_iptr(inode, bindex);
+ if (unlikely(h_inode != h_dentry->d_inode)) {
-+ int old = au_debug_test();
-+ if (!old)
-+ au_debug(1);
++ au_debug_on();
+ AuDbg("b%d, %s:%d\n", bindex, func, line);
+ AuDbgDentry(dentry);
+ AuDbgInode(inode);
-+ if (!old)
-+ au_debug(0);
++ au_debug_off();
+ BUG();
+ }
+ }
+}
+
-+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));
-+ AuDebugOn(IS_ROOT(dentry));
-+ AuDebugOn(au_digen_test(parent, sigen));
-+ dput(parent);
-+}
-+
-+void au_dbg_verify_nondir_parent(struct dentry *dentry, unsigned int sigen)
-+{
-+ struct dentry *parent;
-+ struct inode *inode;
-+
-+ parent = dget_parent(dentry);
-+ inode = dentry->d_inode;
-+ AuDebugOn(inode && S_ISDIR(dentry->d_inode->i_mode));
-+ AuDebugOn(au_digen_test(parent, sigen));
-+ dput(parent);
-+}
-+
+void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen)
+{
+ int err, i, j;
+
+/* ---------------------------------------------------------------------- */
+
-+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 AuForceHnotify
-+ au_opt_set_udba(sbinfo->si_mntflags, UDBA_HNOTIFY);
-+#endif
-+#ifdef AuForceRd0
-+ sbinfo->si_rdblk = 0;
-+ sbinfo->si_rdhash = 0;
-+#endif
-+}
-+
+int __init au_debug_init(void)
+{
+ aufs_bindex_t bindex;
+ pr_warn("CONFIG_4KSTACKS is defined.\n");
+#endif
+
-+#ifdef AuForceNoBrs
-+ sysaufs_brs = 0;
-+#endif
-+
+ return 0;
+}
diff -urN /usr/share/empty/fs/aufs/debug.h linux/fs/aufs/debug.h
--- /usr/share/empty/fs/aufs/debug.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/debug.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,242 @@
++++ linux/fs/aufs/debug.h 2015-06-22 08:27:37.877501704 +0200
+@@ -0,0 +1,228 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+
+#ifdef __KERNEL__
+
++#include <linux/atomic.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/sysrq.h>
+#define AuDebugOn(a) BUG_ON(a)
+
+/* module parameter */
-+extern int aufs_debug;
-+static inline void au_debug(int n)
++extern atomic_t aufs_debug;
++static inline void au_debug_on(void)
++{
++ atomic_inc(&aufs_debug);
++}
++static inline void au_debug_off(void)
+{
-+ aufs_debug = n;
-+ smp_mb();
++ atomic_dec_if_positive(&aufs_debug);
+}
+
+static inline int au_debug_test(void)
+{
-+ return aufs_debug;
++ return atomic_read(&aufs_debug) > 0;
+}
+#else
+#define AuDebugOn(a) do {} while (0)
-+AuStubVoid(au_debug, int n)
++AuStubVoid(au_debug_on, void)
++AuStubVoid(au_debug_off, void)
+AuStubInt0(au_debug_test, void)
+#endif /* CONFIG_AUFS_DEBUG */
+
++#define param_check_atomic_t(name, p) __param_check(name, p, atomic_t)
++
+/* ---------------------------------------------------------------------- */
+
+/* debug print */
+
+/* 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;
+struct dentry;
+#ifdef CONFIG_AUFS_DEBUG
++extern struct mutex au_dbg_mtx;
+extern char *au_plevel;
+struct au_nhash;
+void au_dpri_whlist(struct au_nhash *whlist);
+struct super_block;
+void au_dpri_sb(struct super_block *sb);
+
-+void au_dbg_sleep_jiffy(int jiffy);
-+struct iattr;
-+void au_dbg_iattr(struct iattr *ia);
-+
+#define au_dbg_verify_dinode(d) __au_dbg_verify_dinode(d, __func__, __LINE__)
+void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line);
-+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_kthread(void);
+
+int __init au_debug_init(void);
-+void au_debug_sbinfo_init(struct au_sbinfo *sbinfo);
++
+#define AuDbgWhlist(w) do { \
++ mutex_lock(&au_dbg_mtx); \
+ AuDbg(#w "\n"); \
+ au_dpri_whlist(w); \
++ mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgVdir(v) do { \
++ mutex_lock(&au_dbg_mtx); \
+ AuDbg(#v "\n"); \
+ au_dpri_vdir(v); \
++ mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgInode(i) do { \
++ mutex_lock(&au_dbg_mtx); \
+ AuDbg(#i "\n"); \
+ au_dpri_inode(i); \
++ mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgDAlias(i) do { \
++ mutex_lock(&au_dbg_mtx); \
+ AuDbg(#i "\n"); \
+ au_dpri_dalias(i); \
++ mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgDentry(d) do { \
++ mutex_lock(&au_dbg_mtx); \
+ AuDbg(#d "\n"); \
+ au_dpri_dentry(d); \
++ mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgFile(f) do { \
++ mutex_lock(&au_dbg_mtx); \
+ AuDbg(#f "\n"); \
+ au_dpri_file(f); \
++ mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgSb(sb) do { \
++ mutex_lock(&au_dbg_mtx); \
+ 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); \
++ mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgSym(addr) do { \
+ sprint_symbol(sym, (unsigned long)addr); \
+ AuDbg("%s\n", sym); \
+} while (0)
-+
-+#define AuInfoSym(addr) do { \
-+ char sym[KSYM_SYMBOL_LEN]; \
-+ sprint_symbol(sym, (unsigned long)addr); \
-+ AuInfo("%s\n", sym); \
-+} while (0)
+#else
+AuStubVoid(au_dbg_verify_dinode, struct dentry *dentry)
+AuStubVoid(au_dbg_verify_dir_parent, struct dentry *dentry, unsigned int sigen)
+AuStubVoid(au_dbg_verify_gen, struct dentry *parent, unsigned int sigen)
+AuStubVoid(au_dbg_verify_kthread, void)
+AuStubInt0(__init au_debug_init, void)
-+AuStubVoid(au_debug_sbinfo_init, struct au_sbinfo *sbinfo)
+
+#define AuDbgWhlist(w) do {} while (0)
+#define AuDbgVdir(v) 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)
+#define AuDbgSym(addr) do {} while (0)
-+#define AuInfoSym(addr) do {} while (0)
+#endif /* CONFIG_AUFS_DEBUG */
+
+/* ---------------------------------------------------------------------- */
+#endif /* __AUFS_DEBUG_H__ */
diff -urN /usr/share/empty/fs/aufs/dentry.c linux/fs/aufs/dentry.c
--- /usr/share/empty/fs/aufs/dentry.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dentry.c 2013-03-14 20:07:41.038119650 +0100
-@@ -0,0 +1,1060 @@
++++ linux/fs/aufs/dentry.c 2015-06-22 08:27:37.877501704 +0200
+@@ -0,0 +1,1097 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+#include "aufs.h"
+
+#define AuLkup_ALLOW_NEG 1
++#define AuLkup_IGNORE_PERM (1 << 1)
+#define au_ftest_lkup(flags, name) ((flags) & AuLkup_##name)
+#define au_fset_lkup(flags, name) \
+ do { (flags) |= AuLkup_##name; } while (0)
+ struct au_do_lookup_args *args)
+{
+ struct dentry *h_dentry;
-+ struct inode *h_inode, *inode;
++ struct inode *h_inode;
+ struct au_branch *br;
+ int wh_found, opq;
+ unsigned char wh_able;
+ const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG);
++ const unsigned char ignore_perm = !!au_ftest_lkup(args->flags,
++ IGNORE_PERM);
+
+ wh_found = 0;
+ br = au_sbr(dentry->d_sb, bindex);
+ wh_able = !!au_br_whable(br->br_perm);
+ if (wh_able)
-+ wh_found = au_wh_test(h_parent, wh_name, br, /*try_sio*/0);
++ wh_found = au_wh_test(h_parent, wh_name, /*try_sio*/0);
+ h_dentry = ERR_PTR(wh_found);
+ if (!wh_found)
+ goto real_lookup;
+ return NULL; /* success */
+
+real_lookup:
-+ h_dentry = vfsub_lkup_one(&dentry->d_name, h_parent);
-+ if (IS_ERR(h_dentry))
++ if (!ignore_perm)
++ h_dentry = vfsub_lkup_one(&dentry->d_name, h_parent);
++ else
++ h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent);
++ if (IS_ERR(h_dentry)) {
++ if (PTR_ERR(h_dentry) == -ENAMETOOLONG
++ && !allow_neg)
++ h_dentry = NULL;
+ goto out;
++ }
+
+ h_inode = h_dentry->d_inode;
+ if (!h_inode) {
+ au_set_dbstart(dentry, bindex);
+ au_set_h_dptr(dentry, bindex, h_dentry);
+
-+ inode = dentry->d_inode;
-+ if (!h_inode || !S_ISDIR(h_inode->i_mode) || !wh_able
-+ || (inode && !S_ISDIR(inode->i_mode)))
++ if (!d_is_dir(h_dentry)
++ || !wh_able
++ || (d_is_positive(dentry) && !d_is_dir(dentry)))
+ goto out; /* success */
+
+ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
-+ opq = au_diropq_test(h_dentry, br);
++ opq = au_diropq_test(h_dentry);
+ mutex_unlock(&h_inode->i_mutex);
+ if (opq > 0)
+ au_set_dbdiropq(dentry, bindex);
+{
+ int npositive, err;
+ aufs_bindex_t bindex, btail, bdiropq;
-+ unsigned char isdir;
++ unsigned char isdir, dirperm1;
+ struct qstr whname;
+ struct au_do_lookup_args args = {
+ .flags = 0,
+ const struct qstr *name = &dentry->d_name;
+ struct dentry *parent;
+ struct inode *inode;
++ struct super_block *sb;
+
-+ err = au_test_shwh(dentry->d_sb, name);
++ sb = dentry->d_sb;
++ err = au_test_shwh(sb, name);
+ if (unlikely(err))
+ goto out;
+
+ goto out;
+
+ inode = dentry->d_inode;
-+ isdir = !!(inode && S_ISDIR(inode->i_mode));
++ isdir = !!d_is_dir(dentry);
+ if (!type)
+ au_fset_lkup(args.flags, ALLOW_NEG);
++ dirperm1 = !!au_opt_test(au_mntflags(sb), DIRPERM1);
+
+ npositive = 0;
+ parent = dget_parent(dentry);
+ continue;
+ }
+ h_parent = au_h_dptr(parent, bindex);
-+ if (!h_parent)
-+ continue;
-+ h_dir = h_parent->d_inode;
-+ if (!h_dir || !S_ISDIR(h_dir->i_mode))
++ if (!h_parent || !d_is_dir(h_parent))
+ continue;
+
++ h_dir = h_parent->d_inode;
+ mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_PARENT);
+ h_dentry = au_do_lookup(h_parent, dentry, bindex, &whname,
+ &args);
+ err = PTR_ERR(h_dentry);
+ if (IS_ERR(h_dentry))
+ goto out_parent;
-+ au_fclr_lkup(args.flags, ALLOW_NEG);
++ if (h_dentry)
++ au_fclr_lkup(args.flags, ALLOW_NEG);
++ if (dirperm1)
++ au_fset_lkup(args.flags, IGNORE_PERM);
+
+ if (au_dbwh(dentry) >= 0)
+ break;
+ au_update_dbstart(dentry);
+ }
+ err = npositive;
-+ if (unlikely(!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE)
++ if (unlikely(!au_opt_test(au_mntflags(sb), UDBA_NONE)
+ && au_dbstart(dentry) < 0)) {
+ err = -EIO;
-+ AuIOErr("both of real entry and whiteout found, %.*s, err %d\n",
-+ AuDLNPair(dentry), err);
++ AuIOErr("both of real entry and whiteout found, %pd, err %d\n",
++ dentry, err);
+ }
+
+out_parent:
+ return err;
+}
+
-+struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent,
-+ struct au_branch *br)
++struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent)
+{
+ struct dentry *dentry;
+ int wkq_err;
+/*
+ * lookup @dentry on @bindex which should be negative.
+ */
-+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex)
++int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh)
+{
+ int err;
+ struct dentry *parent, *h_parent, *h_dentry;
++ struct au_branch *br;
+
+ parent = dget_parent(dentry);
+ h_parent = au_h_dptr(parent, bindex);
-+ h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent,
-+ au_sbr(dentry->d_sb, bindex));
++ br = au_sbr(dentry->d_sb, bindex);
++ if (wh)
++ h_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name);
++ else
++ h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent);
+ err = PTR_ERR(h_dentry);
+ if (IS_ERR(h_dentry))
+ goto out;
+ if (unlikely(h_dentry->d_inode)) {
+ err = -EIO;
-+ AuIOErr("%.*s should be negative on b%d.\n",
-+ AuDLNPair(h_dentry), bindex);
++ AuIOErr("%pd should be negative on b%d.\n", h_dentry, bindex);
+ dput(h_dentry);
+ goto out;
+ }
+static void au_hide(struct dentry *dentry)
+{
+ int err;
-+ struct inode *inode;
+
+ AuDbgDentry(dentry);
-+ inode = dentry->d_inode;
-+ if (inode && S_ISDIR(inode->i_mode)) {
++ if (d_is_dir(dentry)) {
+ /* shrink_dcache_parent(dentry); */
+ err = au_hide_children(dentry);
+ if (unlikely(err))
-+ AuIOErr("%.*s, failed hiding children, ignored %d\n",
-+ AuDLNPair(dentry), err);
++ AuIOErr("%pd, failed hiding children, ignored %d\n",
++ dentry, err);
+ }
+ au_do_hide(dentry);
+}
+ if (!ebrange)
+ ebrange = au_do_refresh_hdentry(dentry, parent);
+
-+ if (d_unhashed(dentry) || ebrange) {
++ if (d_unhashed(dentry) || ebrange /* || dinfo->di_tmpfile */) {
+ AuDebugOn(au_dbstart(dentry) < 0 && au_dbend(dentry) >= 0);
+ if (inode)
+ err = au_refresh_hinode_self(inode);
+ au_update_digen(dentry);
+out:
+ if (unlikely(err && !(dentry->d_flags & DCACHE_NFSFS_RENAMED))) {
-+ AuIOErr("failed refreshing %.*s, %d\n",
-+ AuDLNPair(dentry), err);
++ AuIOErr("failed refreshing %pd, %d\n", dentry, err);
+ AuDbgDentry(dentry);
+ }
+ AuTraceErr(err);
+ int err;
+ umode_t mode, h_mode;
+ aufs_bindex_t bindex, btail, bstart, ibs, ibe;
-+ unsigned char plus, unhashed, is_root, h_plus;
++ unsigned char plus, unhashed, is_root, h_plus, h_nfs, tmpfile;
+ struct inode *h_inode, *h_cached_inode;
+ struct dentry *h_dentry;
+ struct qstr *name, *h_name;
+ unhashed = !!d_unhashed(dentry);
+ is_root = !!IS_ROOT(dentry);
+ name = &dentry->d_name;
++ tmpfile = au_di(dentry)->di_tmpfile;
+
+ /*
+ * Theoretically, REVAL test should be unnecessary in case of
+ * {FS,I}NOTIFY.
+ * But {fs,i}notify doesn't fire some necessary events,
+ * IN_ATTRIB for atime/nlink/pageio
-+ * IN_DELETE for NFS dentry
+ * Let's do REVAL test too.
+ */
+ if (do_udba && inode) {
+ if (!h_dentry)
+ continue;
+
-+ AuDbg("b%d, %.*s\n", bindex, AuDLNPair(h_dentry));
++ AuDbg("b%d, %pd\n", bindex, h_dentry);
++ h_nfs = !!au_test_nfs(h_dentry->d_sb);
+ spin_lock(&h_dentry->d_lock);
+ h_name = &h_dentry->d_name;
+ if (unlikely(do_udba
+ && !is_root
-+ && (unhashed != !!d_unhashed(h_dentry)
-+ || name->len != h_name->len
-+ || memcmp(name->name, h_name->name, name->len))
++ && ((!h_nfs
++ && (unhashed != !!d_unhashed(h_dentry)
++ || (!tmpfile
++ && !au_qstreq(name, h_name))
++ ))
++ || (h_nfs
++ && !(flags & LOOKUP_OPEN)
++ && (h_dentry->d_flags
++ & DCACHE_NFSFS_RENAMED)))
+ )) {
-+ AuDbg("unhash 0x%x 0x%x, %.*s %.*s\n",
-+ unhashed, d_unhashed(h_dentry),
-+ AuDLNPair(dentry), AuDLNPair(h_dentry));
++ int h_unhashed;
++
++ h_unhashed = d_unhashed(h_dentry);
+ spin_unlock(&h_dentry->d_lock);
++ AuDbg("unhash 0x%x 0x%x, %pd %pd\n",
++ unhashed, h_unhashed, dentry, h_dentry);
+ goto err;
+ }
+ spin_unlock(&h_dentry->d_lock);
+ if (inode && ibs <= bindex && bindex <= ibe)
+ h_cached_inode = au_h_iptr(inode, bindex);
+
-+ if (unlikely(plus != h_plus
-+ || mode != h_mode
++ if (!h_nfs) {
++ if (unlikely(plus != h_plus && !tmpfile))
++ goto err;
++ } else {
++ if (unlikely(!(h_dentry->d_flags & DCACHE_NFSFS_RENAMED)
++ && !is_root
++ && !IS_ROOT(h_dentry)
++ && unhashed != d_unhashed(h_dentry)))
++ goto err;
++ }
++ if (unlikely(mode != h_mode
+ || h_cached_inode != h_inode))
+ goto err;
+ continue;
+
-+ err:
++err:
+ err = -EINVAL;
+ break;
+ }
+
++ AuTraceErr(err);
+ return err;
+}
+
+ if (unlikely(!au_di(dentry)))
+ goto out;
+
-+ inode = dentry->d_inode;
-+ if (inode && is_bad_inode(inode))
-+ goto out;
-+
+ valid = 1;
+ sb = dentry->d_sb;
+ /*
+ AuTraceErr(err);
+ goto out;
+ }
++ inode = dentry->d_inode;
++ if (unlikely(inode && is_bad_inode(inode))) {
++ err = -EINVAL;
++ AuTraceErr(err);
++ goto out_dgrade;
++ }
+ if (unlikely(au_dbrange_test(dentry))) {
+ err = -EINVAL;
+ AuTraceErr(err);
+ di_downgrade_lock(dentry, AuLock_IR);
+
+ err = -EINVAL;
-+ if (inode && (IS_DEADDIR(inode) || !inode->i_nlink))
++ if (!(flags & (LOOKUP_OPEN | LOOKUP_EMPTY))
++ && inode
++ && !(inode->i_state && I_LINKABLE)
++ && (IS_DEADDIR(inode) || !inode->i_nlink))
+ goto out_inval;
+
+ do_udba = !au_opt_test(au_mntflags(sb), UDBA_NONE);
+ err = h_d_revalidate(dentry, inode, flags, do_udba);
+ if (unlikely(!err && do_udba && au_dbstart(dentry) < 0)) {
+ err = -EIO;
-+ AuDbg("both of real entry and whiteout found, %.*s, err %d\n",
-+ AuDLNPair(dentry), err);
++ AuDbg("both of real entry and whiteout found, %p, err %d\n",
++ dentry, err);
+ }
+ goto out_inval;
+
+ valid = !err;
+out:
+ if (!valid) {
-+ AuDbg("%.*s invalid, %d\n", AuDLNPair(dentry), valid);
++ AuDbg("%pd invalid, %d\n", dentry, valid);
+ d_drop(dentry);
+ }
+ return valid;
+}
+
+const struct dentry_operations aufs_dop = {
-+ .d_revalidate = aufs_d_revalidate,
-+ .d_release = aufs_d_release
++ .d_revalidate = aufs_d_revalidate,
++ .d_weak_revalidate = aufs_d_revalidate,
++ .d_release = aufs_d_release
+};
diff -urN /usr/share/empty/fs/aufs/dentry.h linux/fs/aufs/dentry.h
--- /usr/share/empty/fs/aufs/dentry.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dentry.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,234 @@
++++ linux/fs/aufs/dentry.h 2015-06-22 08:27:37.877501704 +0200
+@@ -0,0 +1,233 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+
+ struct au_rwsem di_rwsem;
+ aufs_bindex_t di_bstart, di_bend, di_bwh, di_bdiropq;
++ unsigned char di_tmpfile; /* to allow the different name */
+ struct au_hdentry *di_hdentry;
+} ____cacheline_aligned_in_smp;
+
+/* dentry.c */
+extern const struct dentry_operations aufs_dop;
+struct au_branch;
-+struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent,
-+ struct au_branch *br);
++struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent);
+int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir,
+ struct dentry *h_parent, struct au_branch *br);
+
+int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t bstart, mode_t type);
-+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex);
++int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh);
+int au_refresh_dentry(struct dentry *dentry, struct dentry *parent);
+int au_reval_dpath(struct dentry *dentry, unsigned int sigen);
+
+#endif /* __AUFS_DENTRY_H__ */
diff -urN /usr/share/empty/fs/aufs/dinfo.c linux/fs/aufs/dinfo.c
--- /usr/share/empty/fs/aufs/dinfo.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dinfo.c 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,543 @@
++++ linux/fs/aufs/dinfo.c 2015-06-22 08:27:37.877501704 +0200
+@@ -0,0 +1,544 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ dinfo->di_bend = -1;
+ dinfo->di_bwh = -1;
+ dinfo->di_bdiropq = -1;
++ dinfo->di_tmpfile = 0;
+ for (i = 0; i < nbr; i++)
+ dinfo->di_hdentry[i].hd_id = -1;
+ goto out;
+ return NULL;
+ AuDebugOn(bindex < 0);
+ d = au_di(dentry)->di_hdentry[0 + bindex].hd_dentry;
-+ AuDebugOn(d && d->d_count <= 0);
++ AuDebugOn(d && au_dcount(d) <= 0);
+ return d;
+}
+
+/*
+ * extended version of au_h_dptr().
-+ * returns a hashed and positive h_dentry in bindex, NULL, or error.
++ * returns a hashed and positive (or linkable) h_dentry in bindex, NULL, or
++ * error.
+ */
+struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex)
+{
+ if (au_dbstart(dentry) <= bindex
+ && bindex <= au_dbend(dentry))
+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry && !au_d_hashed_positive(h_dentry)) {
++ if (h_dentry && !au_d_linkable(h_dentry)) {
+ dget(h_dentry);
+ goto out; /* success */
+ }
+ h_dentry = d_find_alias(h_inode);
+ if (h_dentry) {
+ if (!IS_ERR(h_dentry)) {
-+ if (!au_d_hashed_positive(h_dentry))
++ if (!au_d_linkable(h_dentry))
+ goto out; /* success */
+ dput(h_dentry);
+ } else
+}
diff -urN /usr/share/empty/fs/aufs/dir.c linux/fs/aufs/dir.c
--- /usr/share/empty/fs/aufs/dir.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dir.c 2013-03-14 20:07:41.038119650 +0100
-@@ -0,0 +1,633 @@
++++ linux/fs/aufs/dir.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,751 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ nlink += h_dir->i_nlink - 2;
+ if (h_dir->i_nlink < 2)
+ nlink += 2;
++ smp_mb(); /* for i_nlink */
+ /* 0 can happen in revaliding */
+ set_nlink(dir, nlink);
+}
+ nlink -= h_dir->i_nlink - 2;
+ if (h_dir->i_nlink < 2)
+ nlink -= 2;
++ smp_mb(); /* for i_nlink */
+ /* nlink == 0 means the branch-fs is broken */
+ set_nlink(dir, nlink);
+}
+
+ sz = 0;
+ if (file) {
-+ AuDebugOn(!file->f_dentry);
-+ AuDebugOn(!file->f_dentry->d_inode);
-+ AuDebugOn(!S_ISDIR(file->f_dentry->d_inode->i_mode));
++ AuDebugOn(!d_is_dir(file->f_path.dentry));
+
+ bend = au_fbend_dir(file);
+ for (bindex = au_fbstart(file);
+ bindex <= bend && sz < KMALLOC_MAX_SIZE;
+ bindex++) {
+ h_file = au_hf_dir(file, bindex);
-+ if (h_file
-+ && h_file->f_dentry
-+ && h_file->f_dentry->d_inode)
-+ sz += i_size_read(h_file->f_dentry->d_inode);
++ if (h_file && file_inode(h_file))
++ sz += vfsub_f_size_read(h_file);
+ }
+ } else {
+ AuDebugOn(!dentry);
-+ AuDebugOn(!dentry->d_inode);
-+ AuDebugOn(!S_ISDIR(dentry->d_inode->i_mode));
++ AuDebugOn(!d_is_dir(dentry));
+
+ bend = au_dbtaildir(dentry);
+ for (bindex = au_dbstart(dentry);
+ return sz;
+}
+
-+/* ---------------------------------------------------------------------- */
++struct au_dir_ts_arg {
++ struct dentry *dentry;
++ aufs_bindex_t brid;
++};
+
-+static int reopen_dir(struct file *file)
++static void au_do_dir_ts(void *arg)
+{
++ struct au_dir_ts_arg *a = arg;
++ struct au_dtime dt;
++ struct path h_path;
++ struct inode *dir, *h_dir;
++ struct super_block *sb;
++ struct au_branch *br;
++ struct au_hinode *hdir;
+ 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);
++ aufs_bindex_t bstart, bindex;
+
-+ btail = au_dbtaildir(dentry);
-+ for (bindex = au_fbend_dir(file); btail < bindex; bindex--)
-+ au_set_h_fptr(file, bindex, NULL);
-+ au_set_fbend_dir(file, btail);
++ sb = a->dentry->d_sb;
++ dir = a->dentry->d_inode;
++ if (!dir)
++ goto out;
++ /* no dir->i_mutex lock */
++ aufs_read_lock(a->dentry, AuLock_DW | AuLock_DIR); /* noflush */
+
-+ flags = vfsub_file_flags(file);
-+ for (bindex = bstart; bindex <= btail; bindex++) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (!h_dentry)
-+ continue;
-+ h_file = au_hf_dir(file, bindex);
-+ if (h_file)
-+ continue;
++ bstart = au_ibstart(dir);
++ bindex = au_br_index(sb, a->brid);
++ if (bindex < bstart)
++ goto out_unlock;
+
-+ h_file = au_h_open(dentry, bindex, flags, file);
++ br = au_sbr(sb, bindex);
++ h_path.dentry = au_h_dptr(a->dentry, bindex);
++ if (!h_path.dentry)
++ goto out_unlock;
++ h_path.mnt = au_br_mnt(br);
++ au_dtime_store(&dt, a->dentry, &h_path);
++
++ br = au_sbr(sb, bstart);
++ if (!au_br_writable(br->br_perm))
++ goto out_unlock;
++ h_path.dentry = au_h_dptr(a->dentry, bstart);
++ h_path.mnt = au_br_mnt(br);
++ err = vfsub_mnt_want_write(h_path.mnt);
++ if (err)
++ goto out_unlock;
++ hdir = au_hi(dir, bstart);
++ au_hn_imtx_lock_nested(hdir, AuLsc_I_PARENT);
++ h_dir = au_h_iptr(dir, bstart);
++ if (h_dir->i_nlink
++ && timespec_compare(&h_dir->i_mtime, &dt.dt_mtime) < 0) {
++ dt.dt_h_path = h_path;
++ au_dtime_revert(&dt);
++ }
++ au_hn_imtx_unlock(hdir);
++ vfsub_mnt_drop_write(h_path.mnt);
++ au_cpup_attr_timesizes(dir);
++
++out_unlock:
++ aufs_read_unlock(a->dentry, AuLock_DW);
++out:
++ dput(a->dentry);
++ au_nwt_done(&au_sbi(sb)->si_nowait);
++ kfree(arg);
++}
++
++void au_dir_ts(struct inode *dir, aufs_bindex_t bindex)
++{
++ int perm, wkq_err;
++ aufs_bindex_t bstart;
++ struct au_dir_ts_arg *arg;
++ struct dentry *dentry;
++ struct super_block *sb;
++
++ IMustLock(dir);
++
++ dentry = d_find_any_alias(dir);
++ AuDebugOn(!dentry);
++ sb = dentry->d_sb;
++ bstart = au_ibstart(dir);
++ if (bstart == bindex) {
++ au_cpup_attr_timesizes(dir);
++ goto out;
++ }
++
++ perm = au_sbr_perm(sb, bstart);
++ if (!au_br_writable(perm))
++ goto out;
++
++ arg = kmalloc(sizeof(*arg), GFP_NOFS);
++ if (!arg)
++ goto out;
++
++ arg->dentry = dget(dentry); /* will be dput-ted by au_do_dir_ts() */
++ arg->brid = au_sbr_id(sb, bindex);
++ wkq_err = au_wkq_nowait(au_do_dir_ts, arg, sb, /*flags*/0);
++ if (unlikely(wkq_err)) {
++ pr_err("wkq %d\n", wkq_err);
++ dput(dentry);
++ kfree(arg);
++ }
++
++out:
++ dput(dentry);
++}
++
++/* ---------------------------------------------------------------------- */
++
++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_path.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_dir(file); btail < bindex; bindex--)
++ au_set_h_fptr(file, bindex, NULL);
++ au_set_fbend_dir(file, btail);
++
++ flags = vfsub_file_flags(file);
++ for (bindex = bstart; bindex <= btail; bindex++) {
++ h_dentry = au_h_dptr(dentry, bindex);
++ if (!h_dentry)
++ continue;
++ h_file = au_hf_dir(file, bindex);
++ if (h_file)
++ continue;
++
++ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
+ err = PTR_ERR(h_file);
+ if (IS_ERR(h_file))
+ goto out; /* close all? */
+ return err;
+}
+
-+static int do_open_dir(struct file *file, int flags)
++static int do_open_dir(struct file *file, int flags, struct file *h_file)
+{
+ int err;
+ aufs_bindex_t bindex, btail;
+ struct dentry *dentry, *h_dentry;
-+ struct file *h_file;
+
+ FiMustWriteLock(file);
++ AuDebugOn(h_file);
+
-+ dentry = file->f_dentry;
-+ err = au_alive_dir(dentry);
-+ if (unlikely(err))
-+ goto out;
-+
++ err = 0;
++ dentry = file->f_path.dentry;
+ file->f_version = dentry->d_inode->i_version;
+ bindex = au_dbstart(dentry);
+ au_set_fbstart(file, bindex);
+ if (!h_dentry)
+ continue;
+
-+ h_file = au_h_open(dentry, bindex, flags, file);
++ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
+ if (IS_ERR(h_file)) {
+ err = PTR_ERR(h_file);
+ break;
+ au_set_fbstart(file, -1);
+ au_set_fbend_dir(file, -1);
+
-+out:
+ return err;
+}
+
+ struct au_fidir *fidir;
+
+ err = -ENOMEM;
-+ sb = file->f_dentry->d_sb;
++ sb = file->f_path.dentry->d_sb;
+ si_read_lock(sb, AuLock_FLUSH);
+ fidir = au_fidir_alloc(sb);
+ if (fidir) {
-+ err = au_do_open(file, do_open_dir, fidir);
++ struct au_do_open_args args = {
++ .open = do_open_dir,
++ .fidir = fidir
++ };
++ err = au_do_open(file, &args);
+ if (unlikely(err))
+ kfree(fidir);
+ }
+ finfo = au_fi(file);
+ fidir = finfo->fi_hdir;
+ if (fidir) {
++ au_sphl_del(&finfo->fi_hlist,
++ &au_sbi(file->f_path.dentry->d_sb)->si_files);
+ vdir_cache = fidir->fd_vdir_cache; /* lock-free */
+ if (vdir_cache)
+ au_vdir_free(vdir_cache);
+ if (unlikely(err))
+ goto out;
+
-+ sb = file->f_dentry->d_sb;
-+ inode = file->f_dentry->d_inode;
++ inode = file_inode(file);
++ sb = inode->i_sb;
+ bend = au_fbend_dir(file);
+ for (bindex = au_fbstart(file); !err && bindex <= bend; bindex++) {
+ h_file = au_hf_dir(file, bindex);
+ struct mutex *mtx;
+
+ err = 0;
-+ dentry = file->f_dentry;
++ dentry = file->f_path.dentry;
+ mtx = &dentry->d_inode->i_mutex;
+ mutex_lock(mtx);
+ sb = dentry->d_sb;
+
+/* ---------------------------------------------------------------------- */
+
-+static int aufs_readdir(struct file *file, void *dirent, filldir_t filldir)
++static int aufs_iterate(struct file *file, struct dir_context *ctx)
+{
+ int err;
+ struct dentry *dentry;
+ struct inode *inode, *h_inode;
+ struct super_block *sb;
+
-+ dentry = file->f_dentry;
++ AuDbg("%pD, ctx{%pf, %llu}\n", file, ctx->actor, ctx->pos);
++
++ dentry = file->f_path.dentry;
+ inode = dentry->d_inode;
+ IMustLock(inode);
+
+
+ h_inode = au_h_iptr(inode, au_ibstart(inode));
+ if (!au_test_nfsd()) {
-+ err = au_vdir_fill_de(file, dirent, filldir);
++ err = au_vdir_fill_de(file, ctx);
+ fsstack_copy_attr_atime(inode, h_inode);
+ } else {
+ /*
+ atomic_inc(&h_inode->i_count);
+ di_read_unlock(dentry, AuLock_IR);
+ si_read_unlock(sb);
-+ err = au_vdir_fill_de(file, dirent, filldir);
++ err = au_vdir_fill_de(file, ctx);
+ fsstack_copy_attr_atime(inode, h_inode);
+ fi_write_unlock(file);
+ iput(h_inode);
+#endif
+
+struct test_empty_arg {
++ struct dir_context ctx;
+ 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,
++static int test_empty_cb(struct dir_context *ctx, const char *__name,
++ int namelen, loff_t offset __maybe_unused, u64 ino,
+ unsigned int d_type)
+{
-+ struct test_empty_arg *arg = __arg;
++ struct test_empty_arg *arg = container_of(ctx, struct test_empty_arg,
++ ctx);
+ char *name = (void *)__name;
+
+ arg->err = 0;
+
+ h_file = au_h_open(dentry, arg->bindex,
+ O_RDONLY | O_NONBLOCK | O_DIRECTORY | O_LARGEFILE,
-+ /*file*/NULL);
++ /*file*/NULL, /*force_wr*/0);
+ 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)
++ && !file_inode(h_file)->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);
++ err = vfsub_iterate_dir(h_file, &arg->ctx);
+ if (err >= 0)
+ err = arg->err;
+ } while (!err && au_ftest_testempty(arg->flags, CALLED));
+ unsigned int rdhash;
+ aufs_bindex_t bindex, bstart, btail;
+ struct au_nhash whlist;
-+ struct test_empty_arg arg;
++ struct test_empty_arg arg = {
++ .ctx = {
++ .actor = test_empty_cb
++ }
++ };
++ int (*test_empty)(struct dentry *dentry, struct test_empty_arg *arg);
+
+ SiMustAnyLock(dentry->d_sb);
+
+ bstart = au_dbstart(dentry);
+ if (au_opt_test(au_mntflags(dentry->d_sb), SHWH))
+ au_fset_testempty(arg.flags, SHWH);
++ test_empty = do_test_empty;
++ if (au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1))
++ test_empty = sio_test_empty;
+ arg.bindex = bstart;
-+ err = do_test_empty(dentry, &arg);
++ err = test_empty(dentry, &arg);
+ if (unlikely(err))
+ goto out_whlist;
+
+ h_dentry = au_h_dptr(dentry, bindex);
+ if (h_dentry && h_dentry->d_inode) {
+ arg.bindex = bindex;
-+ err = do_test_empty(dentry, &arg);
++ err = test_empty(dentry, &arg);
+ }
+ }
+
+int au_test_empty(struct dentry *dentry, struct au_nhash *whlist)
+{
+ int err;
-+ struct test_empty_arg arg;
++ struct test_empty_arg arg = {
++ .ctx = {
++ .actor = test_empty_cb
++ }
++ };
+ aufs_bindex_t bindex, btail;
+
+ err = 0;
+ .owner = THIS_MODULE,
+ .llseek = default_llseek,
+ .read = generic_read_dir,
-+ .readdir = aufs_readdir,
++ .iterate = aufs_iterate,
+ .unlocked_ioctl = aufs_ioctl_dir,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = aufs_compat_ioctl_dir,
+};
diff -urN /usr/share/empty/fs/aufs/dir.h linux/fs/aufs/dir.h
--- /usr/share/empty/fs/aufs/dir.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dir.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,137 @@
++++ linux/fs/aufs/dir.h 2015-06-22 08:27:37.877501704 +0200
+@@ -0,0 +1,131 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+void au_add_nlink(struct inode *dir, struct inode *h_dir);
+void au_sub_nlink(struct inode *dir, struct inode *h_dir);
+loff_t au_dir_size(struct file *file, struct dentry *dentry);
++void au_dir_ts(struct inode *dir, aufs_bindex_t bsrc);
+int au_test_empty_lower(struct dentry *dentry);
+int au_test_empty(struct dentry *dentry, struct au_nhash *whlist);
+
+ unsigned char shwh);
+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);
++int au_vdir_fill_de(struct file *file, struct dir_context *ctx);
+
+/* ioctl.c */
+long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg);
+ unsigned long arg);
+#endif
+#else
-+static inline long au_rdu_ioctl(struct file *file, unsigned int cmd,
-+ unsigned long arg)
-+{
-+ return -EINVAL;
-+}
++AuStub(long, au_rdu_ioctl, return -EINVAL, struct file *file,
++ unsigned int cmd, unsigned long arg)
+#ifdef CONFIG_COMPAT
-+static inline long au_rdu_compat_ioctl(struct file *file, unsigned int cmd,
-+ unsigned long arg)
-+{
-+ return -EINVAL;
-+}
++AuStub(long, au_rdu_compat_ioctl, return -EINVAL, struct file *file,
++ unsigned int cmd, unsigned long arg)
+#endif
+#endif
+
+#endif /* __AUFS_DIR_H__ */
diff -urN /usr/share/empty/fs/aufs/dynop.c linux/fs/aufs/dynop.c
--- /usr/share/empty/fs/aufs/dynop.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dynop.c 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,379 @@
++++ linux/fs/aufs/dynop.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,369 @@
+/*
-+ * Copyright (C) 2010-2013 Junjiro R. Okajima
++ * Copyright (C) 2010-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ DySetAop(invalidatepage);
+ DySetAop(releasepage);
+ DySetAop(freepage);
-+ /* these two will be changed according to an aufs mount option */
++ /* this one will be changed according to an aufs mount option */
+ DySetAop(direct_IO);
-+ DySetAop(get_xip_mem);
+ DySetAop(migratepage);
+ DySetAop(launder_page);
+ DySetAop(is_partially_uptodate);
++ DySetAop(is_dirty_writeback);
+ DySetAop(error_remove_page);
+ DySetAop(swap_activate);
+ DySetAop(swap_deactivate);
+
+ DyDbgSize(cnt, *h_aop);
-+ dyaop->da_get_xip_mem = h_aop->get_xip_mem;
+}
+
+/* ---------------------------------------------------------------------- */
+
+ key->dk_op.dy_hop = op->dy_hop;
+ kref_init(&key->dk_kref);
-+ p->set(key, op->dy_hop, br->br_mnt->mnt_sb);
++ p->set(key, op->dy_hop, au_br_sb(br));
+ old = dy_gadd(spl, key);
+ if (old) {
+ kfree(key);
+/* ---------------------------------------------------------------------- */
+/*
+ * Aufs prohibits O_DIRECT by defaut even if the branch supports it.
-+ * This behaviour is neccessary to return an error from open(O_DIRECT) instead
++ * This behaviour is necessary to return an error from open(O_DIRECT) instead
+ * of the succeeding I/O. The dio mount option enables O_DIRECT and makes
+ * open(O_DIRECT) always succeed, but the succeeding I/O may return an error.
+ * See the aufs manual in detail.
-+ *
-+ * To keep this behaviour, aufs has to set NULL to ->get_xip_mem too, and the
-+ * performance of fadvise() and madvise() may be affected.
+ */
+static void dy_adx(struct au_dyaop *dyaop, int do_dx)
+{
-+ if (!do_dx) {
++ if (!do_dx)
+ dyaop->da_op.direct_IO = NULL;
-+ dyaop->da_op.get_xip_mem = NULL;
-+ } else {
++ else
+ dyaop->da_op.direct_IO = aufs_aop.direct_IO;
-+ dyaop->da_op.get_xip_mem = aufs_aop.get_xip_mem;
-+ if (!dyaop->da_get_xip_mem)
-+ dyaop->da_op.get_xip_mem = NULL;
-+ }
+}
+
+static struct au_dyaop *dy_aget(struct au_branch *br,
+}
diff -urN /usr/share/empty/fs/aufs/dynop.h linux/fs/aufs/dynop.h
--- /usr/share/empty/fs/aufs/dynop.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/dynop.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,76 @@
++++ linux/fs/aufs/dynop.h 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,74 @@
+/*
-+ * Copyright (C) 2010-2013 Junjiro R. Okajima
++ * Copyright (C) 2010-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+
+#ifdef __KERNEL__
+
-+#include "inode.h"
++#include <linux/fs.h>
++#include <linux/kref.h>
+
+enum {AuDy_AOP, AuDyLast};
+
+struct au_dyaop {
+ struct au_dykey da_key;
+ struct address_space_operations da_op; /* not const */
-+ int (*da_get_xip_mem)(struct address_space *, pgoff_t, int,
-+ void **, unsigned long *);
+};
+
+/* ---------------------------------------------------------------------- */
+#endif /* __AUFS_DYNOP_H__ */
diff -urN /usr/share/empty/fs/aufs/export.c linux/fs/aufs/export.c
--- /usr/share/empty/fs/aufs/export.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/export.c 2013-03-14 20:07:41.038119650 +0100
-@@ -0,0 +1,827 @@
++++ linux/fs/aufs/export.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,831 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ file = sbinfo->si_xigen;
+ BUG_ON(!file);
+
-+ if (i_size_read(file->f_dentry->d_inode)
++ if (vfsub_f_size_read(file)
+ < pos + sizeof(inode->i_generation)) {
+ inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next);
+ sz = xino_fwrite(sbinfo->si_xwrite, file, &inode->i_generation,
+ struct dentry *dentry, *d;
+ struct inode *inode;
+ unsigned int sigen;
-+ struct hlist_node *p;
+
+ dentry = NULL;
+ inode = ilookup(sb, ino);
+ dentry = d_find_alias(inode);
+ else {
+ spin_lock(&inode->i_lock);
-+ hlist_for_each_entry(d, p, &inode->i_dentry, d_alias) {
++ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) {
+ spin_lock(&d->d_lock);
+ if (!au_test_anon(d)
+ && d->d_parent->d_inode->i_ino == dir_ino) {
+ };
+
+ get_fs_root(current->fs, &root);
-+ br_read_lock(&vfsmount_lock);
++ rcu_read_lock();
+ err = iterate_mounts(au_compare_mnt, &args, root.mnt);
-+ br_read_unlock(&vfsmount_lock);
++ rcu_read_unlock();
+ path_put(&root);
+ AuDebugOn(!err);
+ AuDebugOn(!args.mnt);
+}
+
+struct find_name_by_ino {
++ struct dir_context ctx;
+ int called, found;
+ ino_t ino;
+ char *name;
+};
+
+static int
-+find_name_by_ino(void *arg, const char *name, int namelen, loff_t offset,
-+ u64 ino, unsigned int d_type)
++find_name_by_ino(struct dir_context *ctx, const char *name, int namelen,
++ loff_t offset, u64 ino, unsigned int d_type)
+{
-+ struct find_name_by_ino *a = arg;
++ struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino,
++ ctx);
+
+ a->called++;
+ if (a->ino != ino)
+ struct dentry *dentry, *parent;
+ struct file *file;
+ struct inode *dir;
-+ struct find_name_by_ino arg;
++ struct find_name_by_ino arg = {
++ .ctx = {
++ .actor = find_name_by_ino
++ }
++ };
+ int err;
+
+ parent = path->dentry;
+ do {
+ arg.called = 0;
+ /* smp_mb(); */
-+ err = vfsub_readdir(file, find_name_by_ino, &arg);
++ err = vfsub_iterate_dir(file, &arg.ctx);
+ } while (!err && !arg.found && arg.called);
+ dentry = ERR_PTR(err);
+ if (unlikely(err))
+ struct path path;
+
+ br = au_sbr(sb, nsi_lock->bindex);
-+ h_mnt = br->br_mnt;
++ h_mnt = au_br_mnt(br);
+ h_sb = h_mnt->mnt_sb;
+ /* todo: call lower fh_to_dentry()? fh_to_parent()? */
+ h_parent = exportfs_decode_fh(h_mnt, (void *)(fh + Fh_tail),
+ ii_read_lock_child(inode);
+ bindex = au_ibstart(inode);
+ if (!dir) {
-+ dentry = d_find_alias(inode);
++ dentry = d_find_any_alias(inode);
+ if (unlikely(!dentry))
+ goto out_unlock;
+ AuDebugOn(au_test_anon(dentry));
+ ii_read_unlock(dir);
+ if (unlikely(!h_dir))
+ goto out_parent;
-+ h_parent = d_find_alias(h_dir);
++ h_parent = d_find_any_alias(h_dir);
+ if (unlikely(!h_parent))
+ goto out_hparent;
+
+ err = -EPERM;
+ br = au_sbr(sb, bindex);
-+ h_sb = br->br_mnt->mnt_sb;
++ h_sb = au_br_sb(br);
+ if (unlikely(!h_sb->s_export_op)) {
+ AuErr1("%s branch is not exportable\n", au_sbtype(h_sb));
+ goto out_hparent;
+ BUILD_BUG_ON(sizeof(u) != sizeof(int));
+ atomic_set(&sbinfo->si_xigen_next, u);
+}
-diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c
---- /usr/share/empty/fs/aufs/file.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/file.c 2013-03-14 20:07:41.041453062 +0100
-@@ -0,0 +1,683 @@
+diff -urN /usr/share/empty/fs/aufs/fhsm.c linux/fs/aufs/fhsm.c
+--- /usr/share/empty/fs/aufs/fhsm.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/fhsm.c 2015-06-22 08:27:37.880835119 +0200
+@@ -0,0 +1,426 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2011-2015 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
+ */
+
+/*
-+ * handling file/dir, and address_space operation
++ * File-based Hierarchy Storage Management
+ */
+
-+#ifdef CONFIG_AUFS_DEBUG
-+#include <linux/migrate.h>
-+#endif
-+#include <linux/pagemap.h>
++#include <linux/anon_inodes.h>
++#include <linux/poll.h>
++#include <linux/seq_file.h>
++#include <linux/statfs.h>
+#include "aufs.h"
+
-+/* drop flags for writing */
-+unsigned int au_file_roflags(unsigned int flags)
++static aufs_bindex_t au_fhsm_bottom(struct super_block *sb)
+{
-+ flags &= ~(O_WRONLY | O_RDWR | O_APPEND | O_CREAT | O_TRUNC);
-+ flags |= O_RDONLY | O_NOATIME;
-+ return flags;
++ struct au_sbinfo *sbinfo;
++ struct au_fhsm *fhsm;
++
++ SiMustAnyLock(sb);
++
++ sbinfo = au_sbi(sb);
++ fhsm = &sbinfo->si_fhsm;
++ AuDebugOn(!fhsm);
++ return fhsm->fhsm_bottom;
+}
+
-+/* common functions to regular file and dir */
-+struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags,
-+ struct file *file)
++void au_fhsm_set_bottom(struct super_block *sb, aufs_bindex_t bindex)
+{
-+ struct file *h_file;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct path h_path;
-+ int err, exec_flag;
++ struct au_sbinfo *sbinfo;
++ struct au_fhsm *fhsm;
+
-+ /* a race condition can happen between open and unlink/rmdir */
-+ h_file = ERR_PTR(-ENOENT);
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (au_test_nfsd() && !h_dentry)
-+ goto out;
-+ h_inode = h_dentry->d_inode;
-+ if (au_test_nfsd() && !h_inode)
-+ goto out;
-+ spin_lock(&h_dentry->d_lock);
-+ err = (!d_unhashed(dentry) && d_unlinked(h_dentry))
-+ || !h_inode
-+ /* || !dentry->d_inode->i_nlink */
-+ ;
-+ spin_unlock(&h_dentry->d_lock);
-+ if (unlikely(err))
-+ goto out;
++ SiMustWriteLock(sb);
+
-+ sb = dentry->d_sb;
-+ br = au_sbr(sb, bindex);
-+ h_file = ERR_PTR(-EACCES);
-+ exec_flag = flags & __FMODE_EXEC;
-+ if (exec_flag && (br->br_mnt->mnt_flags & MNT_NOEXEC))
-+ goto out;
++ sbinfo = au_sbi(sb);
++ fhsm = &sbinfo->si_fhsm;
++ AuDebugOn(!fhsm);
++ fhsm->fhsm_bottom = bindex;
++}
+
-+ /* drop flags for writing */
-+ if (au_test_ro(sb, bindex, dentry->d_inode))
-+ flags = au_file_roflags(flags);
-+ flags &= ~O_CREAT;
-+ atomic_inc(&br->br_count);
-+ h_path.dentry = h_dentry;
-+ h_path.mnt = br->br_mnt;
-+ if (!au_special_file(h_inode->i_mode))
-+ h_file = vfsub_dentry_open(&h_path, flags);
-+ else {
-+ /* this block depends upon the configuration */
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
-+ si_read_unlock(sb);
-+ h_file = vfsub_dentry_open(&h_path, flags);
-+ si_noflush_read_lock(sb);
-+ fi_write_lock(file);
-+ di_read_lock_child(dentry, AuLock_IR);
-+ }
-+ if (IS_ERR(h_file))
-+ goto out_br;
++/* ---------------------------------------------------------------------- */
+
-+ if (exec_flag) {
-+ err = deny_write_access(h_file);
-+ if (unlikely(err)) {
-+ fput(h_file);
-+ h_file = ERR_PTR(err);
-+ goto out_br;
-+ }
-+ }
-+ fsnotify_open(h_file);
-+ goto out; /* success */
++static int au_fhsm_test_jiffy(struct au_sbinfo *sbinfo, struct au_branch *br)
++{
++ struct au_br_fhsm *bf;
+
-+out_br:
-+ atomic_dec(&br->br_count);
-+out:
-+ return h_file;
++ bf = br->br_fhsm;
++ MtxMustLock(&bf->bf_lock);
++
++ return !bf->bf_readable
++ || time_after(jiffies,
++ bf->bf_jiffy + sbinfo->si_fhsm.fhsm_expire);
++}
++
++/* ---------------------------------------------------------------------- */
++
++static void au_fhsm_notify(struct super_block *sb, int val)
++{
++ struct au_sbinfo *sbinfo;
++ struct au_fhsm *fhsm;
++
++ SiMustAnyLock(sb);
++
++ sbinfo = au_sbi(sb);
++ fhsm = &sbinfo->si_fhsm;
++ if (au_fhsm_pid(fhsm)
++ && atomic_read(&fhsm->fhsm_readable) != -1) {
++ atomic_set(&fhsm->fhsm_readable, val);
++ if (val)
++ wake_up(&fhsm->fhsm_wqh);
++ }
+}
+
-+int au_do_open(struct file *file, int (*open)(struct file *file, int flags),
-+ struct au_fidir *fidir)
++static int au_fhsm_stfs(struct super_block *sb, aufs_bindex_t bindex,
++ struct aufs_stfs *rstfs, int do_lock, int do_notify)
+{
+ int err;
-+ struct dentry *dentry;
++ struct au_branch *br;
++ struct au_br_fhsm *bf;
+
-+ err = au_finfo_init(file, fidir);
-+ if (unlikely(err))
-+ goto out;
++ br = au_sbr(sb, bindex);
++ AuDebugOn(au_br_rdonly(br));
++ bf = br->br_fhsm;
++ AuDebugOn(!bf);
+
-+ dentry = file->f_dentry;
-+ di_read_lock_child(dentry, AuLock_IR);
-+ err = open(file, vfsub_file_flags(file));
-+ di_read_unlock(dentry, AuLock_IR);
++ if (do_lock)
++ mutex_lock(&bf->bf_lock);
++ else
++ MtxMustLock(&bf->bf_lock);
+
-+ fi_write_unlock(file);
++ /* sb->s_root for NFS is unreliable */
++ err = au_br_stfs(br, &bf->bf_stfs);
+ if (unlikely(err)) {
-+ au_fi(file)->fi_hdir = NULL;
-+ au_finfo_fin(file);
++ AuErr1("FHSM failed (%d), b%d, ignored.\n", bindex, err);
++ goto out;
+ }
+
++ bf->bf_jiffy = jiffies;
++ bf->bf_readable = 1;
++ if (do_notify)
++ au_fhsm_notify(sb, /*val*/1);
++ if (rstfs)
++ *rstfs = bf->bf_stfs;
++
+out:
++ if (do_lock)
++ mutex_unlock(&bf->bf_lock);
++ au_fhsm_notify(sb, /*val*/1);
++
+ return err;
+}
+
-+int au_reopen_nondir(struct file *file)
++void au_fhsm_wrote(struct super_block *sb, aufs_bindex_t bindex, int force)
+{
+ int err;
-+ aufs_bindex_t bstart;
-+ struct dentry *dentry;
-+ struct file *h_file, *h_file_tmp;
-+
-+ dentry = file->f_dentry;
-+ AuDebugOn(au_special_file(dentry->d_inode->i_mode));
-+ bstart = au_dbstart(dentry);
-+ h_file_tmp = NULL;
-+ if (au_fbstart(file) == bstart) {
-+ h_file = au_hf_top(file);
-+ if (file->f_mode == h_file->f_mode)
-+ return 0; /* success */
-+ h_file_tmp = h_file;
-+ get_file(h_file_tmp);
-+ au_set_h_fptr(file, bstart, NULL);
-+ }
-+ AuDebugOn(au_fi(file)->fi_hdir);
-+ AuDebugOn(au_fbstart(file) < bstart);
++ struct au_sbinfo *sbinfo;
++ struct au_fhsm *fhsm;
++ struct au_branch *br;
++ struct au_br_fhsm *bf;
+
-+ h_file = au_h_open(dentry, bstart, vfsub_file_flags(file) & ~O_TRUNC,
-+ file);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out; /* todo: close all? */
++ AuDbg("b%d, force %d\n", bindex, force);
++ SiMustAnyLock(sb);
+
-+ err = 0;
-+ au_set_fbstart(file, bstart);
-+ au_set_h_fptr(file, bstart, h_file);
-+ au_update_figen(file);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
++ sbinfo = au_sbi(sb);
++ fhsm = &sbinfo->si_fhsm;
++ if (!au_ftest_si(sbinfo, FHSM)
++ || fhsm->fhsm_bottom == bindex)
++ return;
+
-+out:
-+ if (h_file_tmp)
-+ fput(h_file_tmp);
-+ return err;
++ br = au_sbr(sb, bindex);
++ bf = br->br_fhsm;
++ AuDebugOn(!bf);
++ mutex_lock(&bf->bf_lock);
++ if (force
++ || au_fhsm_pid(fhsm)
++ || au_fhsm_test_jiffy(sbinfo, br))
++ err = au_fhsm_stfs(sb, bindex, /*rstfs*/NULL, /*do_lock*/0,
++ /*do_notify*/1);
++ mutex_unlock(&bf->bf_lock);
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_reopen_wh(struct file *file, aufs_bindex_t btgt,
-+ struct dentry *hi_wh)
++void au_fhsm_wrote_all(struct super_block *sb, int force)
+{
-+ int err;
-+ aufs_bindex_t bstart;
-+ struct au_dinfo *dinfo;
-+ struct dentry *h_dentry;
-+ struct au_hdentry *hdp;
++ aufs_bindex_t bindex, bend;
++ struct au_branch *br;
+
-+ dinfo = au_di(file->f_dentry);
-+ AuRwMustWriteLock(&dinfo->di_rwsem);
++ /* exclude the bottom */
++ bend = au_fhsm_bottom(sb);
++ for (bindex = 0; bindex < bend; bindex++) {
++ br = au_sbr(sb, bindex);
++ if (au_br_fhsm(br->br_perm))
++ au_fhsm_wrote(sb, bindex, force);
++ }
++}
+
-+ bstart = dinfo->di_bstart;
-+ dinfo->di_bstart = btgt;
-+ hdp = dinfo->di_hdentry;
-+ h_dentry = hdp[0 + btgt].hd_dentry;
-+ hdp[0 + btgt].hd_dentry = hi_wh;
-+ err = au_reopen_nondir(file);
-+ hdp[0 + btgt].hd_dentry = h_dentry;
-+ dinfo->di_bstart = bstart;
++/* ---------------------------------------------------------------------- */
+
-+ return err;
++static unsigned int au_fhsm_poll(struct file *file,
++ struct poll_table_struct *wait)
++{
++ unsigned int mask;
++ struct au_sbinfo *sbinfo;
++ struct au_fhsm *fhsm;
++
++ mask = 0;
++ sbinfo = file->private_data;
++ fhsm = &sbinfo->si_fhsm;
++ poll_wait(file, &fhsm->fhsm_wqh, wait);
++ if (atomic_read(&fhsm->fhsm_readable))
++ mask = POLLIN /* | POLLRDNORM */;
++
++ AuTraceErr((int)mask);
++ return mask;
+}
+
-+static int au_ready_to_write_wh(struct file *file, loff_t len,
-+ aufs_bindex_t bcpup)
++static int au_fhsm_do_read_one(struct aufs_stbr __user *stbr,
++ struct aufs_stfs *stfs, __s16 brid)
+{
+ int err;
-+ struct inode *inode, *h_inode;
-+ struct dentry *dentry, *h_dentry, *hi_wh;
-+
-+ dentry = file->f_dentry;
-+ au_update_dbstart(dentry);
-+ inode = dentry->d_inode;
-+ h_inode = NULL;
-+ if (au_dbstart(dentry) <= bcpup && au_dbend(dentry) >= bcpup) {
-+ h_dentry = au_h_dptr(dentry, bcpup);
-+ if (h_dentry)
-+ h_inode = h_dentry->d_inode;
-+ }
-+ hi_wh = au_hi_wh(inode, bcpup);
-+ if (!hi_wh && !h_inode)
-+ err = au_sio_cpup_wh(dentry, bcpup, len, file);
-+ else
-+ /* already copied-up after unlink */
-+ err = au_reopen_wh(file, bcpup, hi_wh);
+
-+ if (!err
-+ && inode->i_nlink > 1
-+ && au_opt_test(au_mntflags(dentry->d_sb), PLINK))
-+ au_plink_append(inode, bcpup, au_h_dptr(dentry, bcpup));
++ err = copy_to_user(&stbr->stfs, stfs, sizeof(*stfs));
++ if (!err)
++ err = __put_user(brid, &stbr->brid);
++ if (unlikely(err))
++ err = -EFAULT;
+
+ return err;
+}
+
-+/*
-+ * prepare the @file for writing.
-+ */
-+int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin)
++static ssize_t au_fhsm_do_read(struct super_block *sb,
++ struct aufs_stbr __user *stbr, size_t count)
+{
-+ int err;
-+ aufs_bindex_t bstart, bcpup, dbstart;
-+ struct dentry *dentry, *parent, *h_dentry;
-+ struct inode *h_inode, *inode;
-+ struct super_block *sb;
-+ struct file *h_file;
-+
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
-+ inode = dentry->d_inode;
-+ AuDebugOn(au_special_file(inode->i_mode));
-+ bstart = au_fbstart(file);
-+ err = au_test_ro(sb, bstart, inode);
-+ if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) {
-+ err = au_pin(pin, dentry, bstart, AuOpt_UDBA_NONE, /*flags*/0);
-+ goto out;
-+ }
++ ssize_t err;
++ int nstbr;
++ aufs_bindex_t bindex, bend;
++ struct au_branch *br;
++ struct au_br_fhsm *bf;
+
-+ /* need to cpup or reopen */
-+ parent = dget_parent(dentry);
-+ di_write_lock_parent(parent);
-+ err = AuWbrCopyup(au_sbi(sb), dentry);
-+ bcpup = err;
-+ if (unlikely(err < 0))
-+ goto out_dgrade;
++ /* except the bottom branch */
+ err = 0;
++ nstbr = 0;
++ bend = au_fhsm_bottom(sb);
++ for (bindex = 0; !err && bindex < bend; bindex++) {
++ br = au_sbr(sb, bindex);
++ if (!au_br_fhsm(br->br_perm))
++ continue;
+
-+ if (!d_unhashed(dentry) && !au_h_dptr(parent, bcpup)) {
-+ err = au_cpup_dirs(dentry, bcpup);
-+ if (unlikely(err))
-+ goto out_dgrade;
++ bf = br->br_fhsm;
++ mutex_lock(&bf->bf_lock);
++ if (bf->bf_readable) {
++ err = -EFAULT;
++ if (count >= sizeof(*stbr))
++ err = au_fhsm_do_read_one(stbr++, &bf->bf_stfs,
++ br->br_id);
++ if (!err) {
++ bf->bf_readable = 0;
++ count -= sizeof(*stbr);
++ nstbr++;
++ }
++ }
++ mutex_unlock(&bf->bf_lock);
+ }
++ if (!err)
++ err = sizeof(*stbr) * nstbr;
+
-+ err = au_pin(pin, dentry, bcpup, AuOpt_UDBA_NONE,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (unlikely(err))
-+ goto out_dgrade;
++ return err;
++}
+
-+ h_dentry = au_hf_top(file)->f_dentry;
-+ h_inode = h_dentry->d_inode;
-+ dbstart = au_dbstart(dentry);
-+ if (dbstart <= bcpup) {
-+ h_dentry = au_h_dptr(dentry, bcpup);
-+ AuDebugOn(!h_dentry);
-+ h_inode = h_dentry->d_inode;
-+ AuDebugOn(!h_inode);
-+ bstart = bcpup;
-+ }
++static ssize_t au_fhsm_read(struct file *file, char __user *buf, size_t count,
++ loff_t *pos)
++{
++ ssize_t err;
++ int readable;
++ aufs_bindex_t nfhsm, bindex, bend;
++ struct au_sbinfo *sbinfo;
++ struct au_fhsm *fhsm;
++ struct au_branch *br;
++ struct super_block *sb;
+
-+ if (dbstart <= bcpup /* just reopen */
-+ || !d_unhashed(dentry) /* copyup and reopen */
-+ ) {
-+ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
-+ h_file = au_h_open_pre(dentry, bstart);
-+ if (IS_ERR(h_file)) {
-+ err = PTR_ERR(h_file);
-+ h_file = NULL;
-+ } else {
-+ di_downgrade_lock(parent, AuLock_IR);
-+ if (dbstart > bcpup)
-+ err = au_sio_cpup_simple(dentry, bcpup, len,
-+ AuCpup_DTIME);
-+ if (!err)
-+ err = au_reopen_nondir(file);
-+ }
-+ mutex_unlock(&h_inode->i_mutex);
-+ au_h_open_post(dentry, bstart, h_file);
-+ } else { /* copyup as wh and reopen */
-+ /*
-+ * since writable hfsplus branch is not supported,
-+ * h_open_pre/post() are unnecessary.
-+ */
-+ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
-+ err = au_ready_to_write_wh(file, len, bcpup);
-+ di_downgrade_lock(parent, AuLock_IR);
-+ mutex_unlock(&h_inode->i_mutex);
++ err = 0;
++ sbinfo = file->private_data;
++ fhsm = &sbinfo->si_fhsm;
++need_data:
++ spin_lock_irq(&fhsm->fhsm_wqh.lock);
++ if (!atomic_read(&fhsm->fhsm_readable)) {
++ if (vfsub_file_flags(file) & O_NONBLOCK)
++ err = -EAGAIN;
++ else
++ err = wait_event_interruptible_locked_irq
++ (fhsm->fhsm_wqh,
++ atomic_read(&fhsm->fhsm_readable));
+ }
++ spin_unlock_irq(&fhsm->fhsm_wqh.lock);
++ if (unlikely(err))
++ goto out;
+
-+ if (!err) {
-+ au_pin_set_parent_lflag(pin, /*lflag*/0);
-+ goto out_dput; /* success */
++ /* sb may already be dead */
++ au_rw_read_lock(&sbinfo->si_rwsem);
++ readable = atomic_read(&fhsm->fhsm_readable);
++ if (readable > 0) {
++ sb = sbinfo->si_sb;
++ AuDebugOn(!sb);
++ /* exclude the bottom branch */
++ nfhsm = 0;
++ bend = au_fhsm_bottom(sb);
++ for (bindex = 0; bindex < bend; bindex++) {
++ br = au_sbr(sb, bindex);
++ if (au_br_fhsm(br->br_perm))
++ nfhsm++;
++ }
++ err = -EMSGSIZE;
++ if (nfhsm * sizeof(struct aufs_stbr) <= count) {
++ atomic_set(&fhsm->fhsm_readable, 0);
++ err = au_fhsm_do_read(sbinfo->si_sb, (void __user *)buf,
++ count);
++ }
+ }
-+ au_unpin(pin);
-+ goto out_unlock;
++ au_rw_read_unlock(&sbinfo->si_rwsem);
++ if (!readable)
++ goto need_data;
+
-+out_dgrade:
-+ di_downgrade_lock(parent, AuLock_IR);
-+out_unlock:
-+ di_read_unlock(parent, AuLock_IR);
-+out_dput:
-+ dput(parent);
+out:
+ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
++static int au_fhsm_release(struct inode *inode, struct file *file)
++{
++ struct au_sbinfo *sbinfo;
++ struct au_fhsm *fhsm;
+
-+int au_do_flush(struct file *file, fl_owner_t id,
-+ int (*flush)(struct file *file, fl_owner_t id))
++ /* sb may already be dead */
++ sbinfo = file->private_data;
++ fhsm = &sbinfo->si_fhsm;
++ spin_lock(&fhsm->fhsm_spin);
++ fhsm->fhsm_pid = 0;
++ spin_unlock(&fhsm->fhsm_spin);
++ kobject_put(&sbinfo->si_kobj);
++
++ return 0;
++}
++
++static const struct file_operations au_fhsm_fops = {
++ .owner = THIS_MODULE,
++ .llseek = noop_llseek,
++ .read = au_fhsm_read,
++ .poll = au_fhsm_poll,
++ .release = au_fhsm_release
++};
++
++int au_fhsm_fd(struct super_block *sb, int oflags)
+{
-+ int err;
-+ struct dentry *dentry;
-+ struct super_block *sb;
-+ struct inode *inode;
++ int err, fd;
++ struct au_sbinfo *sbinfo;
++ struct au_fhsm *fhsm;
+
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
-+ inode = dentry->d_inode;
-+ si_noflush_read_lock(sb);
-+ fi_read_lock(file);
-+ ii_read_lock_child(inode);
++ err = -EPERM;
++ if (unlikely(!capable(CAP_SYS_ADMIN)))
++ goto out;
+
-+ err = flush(file, id);
-+ au_cpup_attr_timesizes(inode);
++ err = -EINVAL;
++ if (unlikely(oflags & ~(O_CLOEXEC | O_NONBLOCK)))
++ goto out;
+
-+ ii_read_unlock(inode);
-+ fi_read_unlock(file);
++ err = 0;
++ sbinfo = au_sbi(sb);
++ fhsm = &sbinfo->si_fhsm;
++ spin_lock(&fhsm->fhsm_spin);
++ if (!fhsm->fhsm_pid)
++ fhsm->fhsm_pid = current->pid;
++ else
++ err = -EBUSY;
++ spin_unlock(&fhsm->fhsm_spin);
++ if (unlikely(err))
++ goto out;
++
++ oflags |= O_RDONLY;
++ /* oflags |= FMODE_NONOTIFY; */
++ fd = anon_inode_getfd("[aufs_fhsm]", &au_fhsm_fops, sbinfo, oflags);
++ err = fd;
++ if (unlikely(fd < 0))
++ goto out_pid;
++
++ /* succeed reglardless 'fhsm' status */
++ kobject_get(&sbinfo->si_kobj);
++ si_noflush_read_lock(sb);
++ if (au_ftest_si(sbinfo, FHSM))
++ au_fhsm_wrote_all(sb, /*force*/0);
+ si_read_unlock(sb);
++ goto out; /* success */
++
++out_pid:
++ spin_lock(&fhsm->fhsm_spin);
++ fhsm->fhsm_pid = 0;
++ spin_unlock(&fhsm->fhsm_spin);
++out:
++ AuTraceErr(err);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static int au_file_refresh_by_inode(struct file *file, int *need_reopen)
++int au_fhsm_br_alloc(struct au_branch *br)
+{
+ int err;
-+ aufs_bindex_t bstart;
-+ struct au_pin pin;
-+ struct au_finfo *finfo;
-+ struct dentry *dentry, *parent, *hi_wh;
-+ struct inode *inode;
-+ struct super_block *sb;
-+
-+ FiMustWriteLock(file);
+
+ err = 0;
-+ finfo = au_fi(file);
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
-+ inode = dentry->d_inode;
-+ bstart = au_ibstart(inode);
-+ if (bstart == finfo->fi_btop || IS_ROOT(dentry))
-+ goto out;
-+
-+ parent = dget_parent(dentry);
-+ if (au_test_ro(sb, bstart, inode)) {
-+ di_read_lock_parent(parent, !AuLock_IR);
-+ err = AuWbrCopyup(au_sbi(sb), dentry);
-+ bstart = err;
-+ di_read_unlock(parent, !AuLock_IR);
-+ if (unlikely(err < 0))
-+ goto out_parent;
-+ err = 0;
-+ }
++ br->br_fhsm = kmalloc(sizeof(*br->br_fhsm), GFP_NOFS);
++ if (br->br_fhsm)
++ au_br_fhsm_init(br->br_fhsm);
++ else
++ err = -ENOMEM;
+
-+ di_read_lock_parent(parent, AuLock_IR);
-+ hi_wh = au_hi_wh(inode, bstart);
-+ if (!S_ISDIR(inode->i_mode)
-+ && au_opt_test(au_mntflags(sb), PLINK)
-+ && au_plink_test(inode)
-+ && !d_unhashed(dentry)) {
-+ err = au_test_and_cpup_dirs(dentry, bstart);
-+ if (unlikely(err))
-+ goto out_unlock;
++ return err;
++}
+
-+ /* always superio. */
-+ err = au_pin(&pin, dentry, bstart, AuOpt_UDBA_NONE,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (!err)
-+ err = au_sio_cpup_simple(dentry, bstart, -1,
-+ AuCpup_DTIME);
-+ au_unpin(&pin);
-+ } else if (hi_wh) {
-+ /* already copied-up after unlink */
-+ err = au_reopen_wh(file, bstart, hi_wh);
-+ *need_reopen = 0;
-+ }
++/* ---------------------------------------------------------------------- */
+
-+out_unlock:
-+ di_read_unlock(parent, AuLock_IR);
-+out_parent:
-+ dput(parent);
-+out:
-+ return err;
++void au_fhsm_fin(struct super_block *sb)
++{
++ au_fhsm_notify(sb, /*val*/-1);
+}
+
-+static void au_do_refresh_dir(struct file *file)
++void au_fhsm_init(struct au_sbinfo *sbinfo)
+{
-+ aufs_bindex_t bindex, bend, new_bindex, brid;
-+ struct au_hfile *p, tmp, *q;
-+ struct au_finfo *finfo;
-+ struct super_block *sb;
-+ struct au_fidir *fidir;
++ struct au_fhsm *fhsm;
+
-+ FiMustWriteLock(file);
++ fhsm = &sbinfo->si_fhsm;
++ spin_lock_init(&fhsm->fhsm_spin);
++ init_waitqueue_head(&fhsm->fhsm_wqh);
++ atomic_set(&fhsm->fhsm_readable, 0);
++ fhsm->fhsm_expire
++ = msecs_to_jiffies(AUFS_FHSM_CACHE_DEF_SEC * MSEC_PER_SEC);
++ fhsm->fhsm_bottom = -1;
++}
+
-+ sb = file->f_dentry->d_sb;
-+ finfo = au_fi(file);
-+ fidir = finfo->fi_hdir;
-+ AuDebugOn(!fidir);
-+ p = fidir->fd_hfile + finfo->fi_btop;
-+ brid = p->hf_br->br_id;
-+ bend = fidir->fd_bbot;
-+ for (bindex = finfo->fi_btop; bindex <= bend; bindex++, p++) {
-+ if (!p->hf_file)
-+ continue;
++void au_fhsm_set(struct au_sbinfo *sbinfo, unsigned int sec)
++{
++ sbinfo->si_fhsm.fhsm_expire
++ = msecs_to_jiffies(sec * MSEC_PER_SEC);
++}
+
-+ new_bindex = au_br_index(sb, p->hf_br->br_id);
-+ if (new_bindex == bindex)
-+ continue;
-+ if (new_bindex < 0) {
-+ au_set_h_fptr(file, bindex, NULL);
-+ continue;
-+ }
++void au_fhsm_show(struct seq_file *seq, struct au_sbinfo *sbinfo)
++{
++ unsigned int u;
++
++ if (!au_ftest_si(sbinfo, FHSM))
++ return;
++
++ u = jiffies_to_msecs(sbinfo->si_fhsm.fhsm_expire) / MSEC_PER_SEC;
++ if (u != AUFS_FHSM_CACHE_DEF_SEC)
++ seq_printf(seq, ",fhsm_sec=%u", u);
++}
+diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c
+--- /usr/share/empty/fs/aufs/file.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/file.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,844 @@
++/*
++ * Copyright (C) 2005-2015 Junjiro R. Okajima
++ *
++ * This program, aufs is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ *
++ * This program is distributed in the hope that it will be useful,
++ * but WITHOUT ANY WARRANTY; without even the implied warranty of
++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++ * GNU General Public License for more details.
++ *
++ * You should have received a copy of the GNU General Public License
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
++ */
++
++/*
++ * handling file/dir, and address_space operation
++ */
++
++#ifdef CONFIG_AUFS_DEBUG
++#include <linux/migrate.h>
++#endif
++#include <linux/pagemap.h>
++#include "aufs.h"
++
++/* drop flags for writing */
++unsigned int au_file_roflags(unsigned int flags)
++{
++ flags &= ~(O_WRONLY | O_RDWR | O_APPEND | O_CREAT | O_TRUNC);
++ flags |= O_RDONLY | O_NOATIME;
++ return flags;
++}
++
++/* common functions to regular file and dir */
++struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags,
++ struct file *file, int force_wr)
++{
++ struct file *h_file;
++ struct dentry *h_dentry;
++ struct inode *h_inode;
++ struct super_block *sb;
++ struct au_branch *br;
++ struct path h_path;
++ int err;
++
++ /* a race condition can happen between open and unlink/rmdir */
++ h_file = ERR_PTR(-ENOENT);
++ h_dentry = au_h_dptr(dentry, bindex);
++ if (au_test_nfsd() && !h_dentry)
++ goto out;
++ h_inode = h_dentry->d_inode;
++ if (au_test_nfsd() && !h_inode)
++ goto out;
++ spin_lock(&h_dentry->d_lock);
++ err = (!d_unhashed(dentry) && d_unlinked(h_dentry))
++ || !h_inode
++ /* || !dentry->d_inode->i_nlink */
++ ;
++ spin_unlock(&h_dentry->d_lock);
++ if (unlikely(err))
++ goto out;
++
++ sb = dentry->d_sb;
++ br = au_sbr(sb, bindex);
++ err = au_br_test_oflag(flags, br);
++ h_file = ERR_PTR(err);
++ if (unlikely(err))
++ goto out;
++
++ /* drop flags for writing */
++ if (au_test_ro(sb, bindex, dentry->d_inode)) {
++ if (force_wr && !(flags & O_WRONLY))
++ force_wr = 0;
++ flags = au_file_roflags(flags);
++ if (force_wr) {
++ h_file = ERR_PTR(-EROFS);
++ flags = au_file_roflags(flags);
++ if (unlikely(vfsub_native_ro(h_inode)
++ || IS_APPEND(h_inode)))
++ goto out;
++ flags &= ~O_ACCMODE;
++ flags |= O_WRONLY;
++ }
++ }
++ flags &= ~O_CREAT;
++ atomic_inc(&br->br_count);
++ h_path.dentry = h_dentry;
++ h_path.mnt = au_br_mnt(br);
++ h_file = vfsub_dentry_open(&h_path, flags);
++ if (IS_ERR(h_file))
++ goto out_br;
++
++ if (flags & __FMODE_EXEC) {
++ err = deny_write_access(h_file);
++ if (unlikely(err)) {
++ fput(h_file);
++ h_file = ERR_PTR(err);
++ goto out_br;
++ }
++ }
++ fsnotify_open(h_file);
++ goto out; /* success */
++
++out_br:
++ atomic_dec(&br->br_count);
++out:
++ return h_file;
++}
++
++static int au_cmoo(struct dentry *dentry)
++{
++ int err, cmoo;
++ unsigned int udba;
++ struct path h_path;
++ struct au_pin pin;
++ struct au_cp_generic cpg = {
++ .dentry = dentry,
++ .bdst = -1,
++ .bsrc = -1,
++ .len = -1,
++ .pin = &pin,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN
++ };
++ struct inode *delegated;
++ struct super_block *sb;
++ struct au_sbinfo *sbinfo;
++ struct au_fhsm *fhsm;
++ pid_t pid;
++ struct au_branch *br;
++ struct dentry *parent;
++ struct au_hinode *hdir;
++
++ DiMustWriteLock(dentry);
++ IiMustWriteLock(dentry->d_inode);
++
++ err = 0;
++ if (IS_ROOT(dentry))
++ goto out;
++ cpg.bsrc = au_dbstart(dentry);
++ if (!cpg.bsrc)
++ goto out;
++
++ sb = dentry->d_sb;
++ sbinfo = au_sbi(sb);
++ fhsm = &sbinfo->si_fhsm;
++ pid = au_fhsm_pid(fhsm);
++ if (pid
++ && (current->pid == pid
++ || current->real_parent->pid == pid))
++ goto out;
++
++ br = au_sbr(sb, cpg.bsrc);
++ cmoo = au_br_cmoo(br->br_perm);
++ if (!cmoo)
++ goto out;
++ if (!d_is_reg(dentry))
++ cmoo &= AuBrAttr_COO_ALL;
++ if (!cmoo)
++ goto out;
++
++ parent = dget_parent(dentry);
++ di_write_lock_parent(parent);
++ err = au_wbr_do_copyup_bu(dentry, cpg.bsrc - 1);
++ cpg.bdst = err;
++ if (unlikely(err < 0)) {
++ err = 0; /* there is no upper writable branch */
++ goto out_dgrade;
++ }
++ AuDbg("bsrc %d, bdst %d\n", cpg.bsrc, cpg.bdst);
++
++ /* do not respect the coo attrib for the target branch */
++ err = au_cpup_dirs(dentry, cpg.bdst);
++ if (unlikely(err))
++ goto out_dgrade;
++
++ di_downgrade_lock(parent, AuLock_IR);
++ udba = au_opt_udba(sb);
++ err = au_pin(&pin, dentry, cpg.bdst, udba,
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (unlikely(err))
++ goto out_parent;
++
++ err = au_sio_cpup_simple(&cpg);
++ au_unpin(&pin);
++ if (unlikely(err))
++ goto out_parent;
++ if (!(cmoo & AuBrWAttr_MOO))
++ goto out_parent; /* success */
++
++ err = au_pin(&pin, dentry, cpg.bsrc, udba,
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (unlikely(err))
++ goto out_parent;
++
++ h_path.mnt = au_br_mnt(br);
++ h_path.dentry = au_h_dptr(dentry, cpg.bsrc);
++ hdir = au_hi(parent->d_inode, cpg.bsrc);
++ delegated = NULL;
++ err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated, /*force*/1);
++ au_unpin(&pin);
++ /* todo: keep h_dentry or not? */
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
++ }
++ if (unlikely(err)) {
++ pr_err("unlink %pd after coo failed (%d), ignored\n",
++ dentry, err);
++ err = 0;
++ }
++ goto out_parent; /* success */
++
++out_dgrade:
++ di_downgrade_lock(parent, AuLock_IR);
++out_parent:
++ di_read_unlock(parent, AuLock_IR);
++ dput(parent);
++out:
++ AuTraceErr(err);
++ return err;
++}
++
++int au_do_open(struct file *file, struct au_do_open_args *args)
++{
++ int err, no_lock = args->no_lock;
++ struct dentry *dentry;
++ struct au_finfo *finfo;
++
++ if (!no_lock)
++ err = au_finfo_init(file, args->fidir);
++ else {
++ lockdep_off();
++ err = au_finfo_init(file, args->fidir);
++ lockdep_on();
++ }
++ if (unlikely(err))
++ goto out;
++
++ dentry = file->f_path.dentry;
++ AuDebugOn(IS_ERR_OR_NULL(dentry));
++ if (!no_lock) {
++ di_write_lock_child(dentry);
++ err = au_cmoo(dentry);
++ di_downgrade_lock(dentry, AuLock_IR);
++ if (!err)
++ err = args->open(file, vfsub_file_flags(file), NULL);
++ di_read_unlock(dentry, AuLock_IR);
++ } else {
++ err = au_cmoo(dentry);
++ if (!err)
++ err = args->open(file, vfsub_file_flags(file),
++ args->h_file);
++ if (!err && au_fbstart(file) != au_dbstart(dentry))
++ /*
++ * cmoo happens after h_file was opened.
++ * need to refresh file later.
++ */
++ atomic_dec(&au_fi(file)->fi_generation);
++ }
++
++ finfo = au_fi(file);
++ if (!err) {
++ finfo->fi_file = file;
++ au_sphl_add(&finfo->fi_hlist,
++ &au_sbi(file->f_path.dentry->d_sb)->si_files);
++ }
++ if (!no_lock)
++ fi_write_unlock(file);
++ else {
++ lockdep_off();
++ fi_write_unlock(file);
++ lockdep_on();
++ }
++ if (unlikely(err)) {
++ finfo->fi_hdir = NULL;
++ au_finfo_fin(file);
++ }
++
++out:
++ return err;
++}
++
++int au_reopen_nondir(struct file *file)
++{
++ int err;
++ aufs_bindex_t bstart;
++ struct dentry *dentry;
++ struct file *h_file, *h_file_tmp;
++
++ dentry = file->f_path.dentry;
++ bstart = au_dbstart(dentry);
++ h_file_tmp = NULL;
++ if (au_fbstart(file) == bstart) {
++ h_file = au_hf_top(file);
++ if (file->f_mode == h_file->f_mode)
++ return 0; /* success */
++ h_file_tmp = h_file;
++ get_file(h_file_tmp);
++ au_set_h_fptr(file, bstart, NULL);
++ }
++ AuDebugOn(au_fi(file)->fi_hdir);
++ /*
++ * it can happen
++ * file exists on both of rw and ro
++ * open --> dbstart and fbstart are both 0
++ * prepend a branch as rw, "rw" become ro
++ * remove rw/file
++ * delete the top branch, "rw" becomes rw again
++ * --> dbstart is 1, fbstart is still 0
++ * write --> fbstart is 0 but dbstart is 1
++ */
++ /* AuDebugOn(au_fbstart(file) < bstart); */
++
++ h_file = au_h_open(dentry, bstart, vfsub_file_flags(file) & ~O_TRUNC,
++ file, /*force_wr*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file)) {
++ if (h_file_tmp) {
++ atomic_inc(&au_sbr(dentry->d_sb, bstart)->br_count);
++ au_set_h_fptr(file, bstart, h_file_tmp);
++ h_file_tmp = NULL;
++ }
++ goto out; /* todo: close all? */
++ }
++
++ err = 0;
++ au_set_fbstart(file, bstart);
++ au_set_h_fptr(file, bstart, h_file);
++ au_update_figen(file);
++ /* todo: necessary? */
++ /* file->f_ra = h_file->f_ra; */
++
++out:
++ if (h_file_tmp)
++ fput(h_file_tmp);
++ return err;
++}
++
++/* ---------------------------------------------------------------------- */
++
++static int au_reopen_wh(struct file *file, aufs_bindex_t btgt,
++ struct dentry *hi_wh)
++{
++ int err;
++ aufs_bindex_t bstart;
++ struct au_dinfo *dinfo;
++ struct dentry *h_dentry;
++ struct au_hdentry *hdp;
++
++ dinfo = au_di(file->f_path.dentry);
++ AuRwMustWriteLock(&dinfo->di_rwsem);
++
++ bstart = dinfo->di_bstart;
++ dinfo->di_bstart = btgt;
++ hdp = dinfo->di_hdentry;
++ h_dentry = hdp[0 + btgt].hd_dentry;
++ hdp[0 + btgt].hd_dentry = hi_wh;
++ err = au_reopen_nondir(file);
++ hdp[0 + btgt].hd_dentry = h_dentry;
++ dinfo->di_bstart = bstart;
++
++ return err;
++}
++
++static int au_ready_to_write_wh(struct file *file, loff_t len,
++ aufs_bindex_t bcpup, struct au_pin *pin)
++{
++ int err;
++ struct inode *inode, *h_inode;
++ struct dentry *h_dentry, *hi_wh;
++ struct au_cp_generic cpg = {
++ .dentry = file->f_path.dentry,
++ .bdst = bcpup,
++ .bsrc = -1,
++ .len = len,
++ .pin = pin
++ };
++
++ au_update_dbstart(cpg.dentry);
++ inode = cpg.dentry->d_inode;
++ h_inode = NULL;
++ if (au_dbstart(cpg.dentry) <= bcpup
++ && au_dbend(cpg.dentry) >= bcpup) {
++ h_dentry = au_h_dptr(cpg.dentry, bcpup);
++ if (h_dentry)
++ h_inode = h_dentry->d_inode;
++ }
++ hi_wh = au_hi_wh(inode, bcpup);
++ if (!hi_wh && !h_inode)
++ err = au_sio_cpup_wh(&cpg, file);
++ else
++ /* already copied-up after unlink */
++ err = au_reopen_wh(file, bcpup, hi_wh);
++
++ if (!err
++ && (inode->i_nlink > 1
++ || (inode->i_state & I_LINKABLE))
++ && au_opt_test(au_mntflags(cpg.dentry->d_sb), PLINK))
++ au_plink_append(inode, bcpup, au_h_dptr(cpg.dentry, bcpup));
++
++ return err;
++}
++
++/*
++ * prepare the @file for writing.
++ */
++int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin)
++{
++ int err;
++ aufs_bindex_t dbstart;
++ struct dentry *parent;
++ struct inode *inode;
++ struct super_block *sb;
++ struct file *h_file;
++ struct au_cp_generic cpg = {
++ .dentry = file->f_path.dentry,
++ .bdst = -1,
++ .bsrc = -1,
++ .len = len,
++ .pin = pin,
++ .flags = AuCpup_DTIME
++ };
++
++ sb = cpg.dentry->d_sb;
++ inode = cpg.dentry->d_inode;
++ cpg.bsrc = au_fbstart(file);
++ err = au_test_ro(sb, cpg.bsrc, inode);
++ if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) {
++ err = au_pin(pin, cpg.dentry, cpg.bsrc, AuOpt_UDBA_NONE,
++ /*flags*/0);
++ goto out;
++ }
++
++ /* need to cpup or reopen */
++ parent = dget_parent(cpg.dentry);
++ di_write_lock_parent(parent);
++ err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
++ cpg.bdst = err;
++ if (unlikely(err < 0))
++ goto out_dgrade;
++ err = 0;
++
++ if (!d_unhashed(cpg.dentry) && !au_h_dptr(parent, cpg.bdst)) {
++ err = au_cpup_dirs(cpg.dentry, cpg.bdst);
++ if (unlikely(err))
++ goto out_dgrade;
++ }
++
++ err = au_pin(pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (unlikely(err))
++ goto out_dgrade;
++
++ dbstart = au_dbstart(cpg.dentry);
++ if (dbstart <= cpg.bdst)
++ cpg.bsrc = cpg.bdst;
++
++ if (dbstart <= cpg.bdst /* just reopen */
++ || !d_unhashed(cpg.dentry) /* copyup and reopen */
++ ) {
++ h_file = au_h_open_pre(cpg.dentry, cpg.bsrc, /*force_wr*/0);
++ if (IS_ERR(h_file))
++ err = PTR_ERR(h_file);
++ else {
++ di_downgrade_lock(parent, AuLock_IR);
++ if (dbstart > cpg.bdst)
++ err = au_sio_cpup_simple(&cpg);
++ if (!err)
++ err = au_reopen_nondir(file);
++ au_h_open_post(cpg.dentry, cpg.bsrc, h_file);
++ }
++ } else { /* copyup as wh and reopen */
++ /*
++ * since writable hfsplus branch is not supported,
++ * h_open_pre/post() are unnecessary.
++ */
++ err = au_ready_to_write_wh(file, len, cpg.bdst, pin);
++ di_downgrade_lock(parent, AuLock_IR);
++ }
++
++ if (!err) {
++ au_pin_set_parent_lflag(pin, /*lflag*/0);
++ goto out_dput; /* success */
++ }
++ au_unpin(pin);
++ goto out_unlock;
++
++out_dgrade:
++ di_downgrade_lock(parent, AuLock_IR);
++out_unlock:
++ di_read_unlock(parent, AuLock_IR);
++out_dput:
++ dput(parent);
++out:
++ return err;
++}
++
++/* ---------------------------------------------------------------------- */
++
++int au_do_flush(struct file *file, fl_owner_t id,
++ int (*flush)(struct file *file, fl_owner_t id))
++{
++ int err;
++ struct super_block *sb;
++ struct inode *inode;
++
++ inode = file_inode(file);
++ sb = inode->i_sb;
++ si_noflush_read_lock(sb);
++ fi_read_lock(file);
++ ii_read_lock_child(inode);
++
++ err = flush(file, id);
++ au_cpup_attr_timesizes(inode);
++
++ ii_read_unlock(inode);
++ fi_read_unlock(file);
++ si_read_unlock(sb);
++ return err;
++}
++
++/* ---------------------------------------------------------------------- */
++
++static int au_file_refresh_by_inode(struct file *file, int *need_reopen)
++{
++ int err;
++ struct au_pin pin;
++ struct au_finfo *finfo;
++ struct dentry *parent, *hi_wh;
++ struct inode *inode;
++ struct super_block *sb;
++ struct au_cp_generic cpg = {
++ .dentry = file->f_path.dentry,
++ .bdst = -1,
++ .bsrc = -1,
++ .len = -1,
++ .pin = &pin,
++ .flags = AuCpup_DTIME
++ };
++
++ FiMustWriteLock(file);
++
++ err = 0;
++ finfo = au_fi(file);
++ sb = cpg.dentry->d_sb;
++ inode = cpg.dentry->d_inode;
++ cpg.bdst = au_ibstart(inode);
++ if (cpg.bdst == finfo->fi_btop || IS_ROOT(cpg.dentry))
++ goto out;
++
++ parent = dget_parent(cpg.dentry);
++ if (au_test_ro(sb, cpg.bdst, inode)) {
++ di_read_lock_parent(parent, !AuLock_IR);
++ err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
++ cpg.bdst = err;
++ di_read_unlock(parent, !AuLock_IR);
++ if (unlikely(err < 0))
++ goto out_parent;
++ err = 0;
++ }
++
++ di_read_lock_parent(parent, AuLock_IR);
++ hi_wh = au_hi_wh(inode, cpg.bdst);
++ if (!S_ISDIR(inode->i_mode)
++ && au_opt_test(au_mntflags(sb), PLINK)
++ && au_plink_test(inode)
++ && !d_unhashed(cpg.dentry)
++ && cpg.bdst < au_dbstart(cpg.dentry)) {
++ err = au_test_and_cpup_dirs(cpg.dentry, cpg.bdst);
++ if (unlikely(err))
++ goto out_unlock;
++
++ /* always superio. */
++ err = au_pin(&pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (!err) {
++ err = au_sio_cpup_simple(&cpg);
++ au_unpin(&pin);
++ }
++ } else if (hi_wh) {
++ /* already copied-up after unlink */
++ err = au_reopen_wh(file, cpg.bdst, hi_wh);
++ *need_reopen = 0;
++ }
++
++out_unlock:
++ di_read_unlock(parent, AuLock_IR);
++out_parent:
++ dput(parent);
++out:
++ return err;
++}
++
++static void au_do_refresh_dir(struct file *file)
++{
++ aufs_bindex_t bindex, bend, new_bindex, brid;
++ struct au_hfile *p, tmp, *q;
++ struct au_finfo *finfo;
++ struct super_block *sb;
++ struct au_fidir *fidir;
++
++ FiMustWriteLock(file);
++
++ sb = file->f_path.dentry->d_sb;
++ finfo = au_fi(file);
++ fidir = finfo->fi_hdir;
++ AuDebugOn(!fidir);
++ p = fidir->fd_hfile + finfo->fi_btop;
++ brid = p->hf_br->br_id;
++ bend = fidir->fd_bbot;
++ for (bindex = finfo->fi_btop; bindex <= bend; bindex++, p++) {
++ if (!p->hf_file)
++ continue;
++
++ new_bindex = au_br_index(sb, p->hf_br->br_id);
++ if (new_bindex == bindex)
++ continue;
++ if (new_bindex < 0) {
++ au_set_h_fptr(file, bindex, NULL);
++ continue;
++ }
+
+ /* swap two lower inode, and loop again */
+ q = fidir->fd_hfile + new_bindex;
+ }
+
+ p = fidir->fd_hfile;
-+ if (!au_test_mmapped(file) && !d_unlinked(file->f_dentry)) {
++ if (!au_test_mmapped(file) && !d_unlinked(file->f_path.dentry)) {
+ bend = au_sbend(sb);
+ for (finfo->fi_btop = 0; finfo->fi_btop <= bend;
+ finfo->fi_btop++, p++)
+ if (p->hf_file) {
-+ if (p->hf_file->f_dentry
-+ && p->hf_file->f_dentry->d_inode)
++ if (file_inode(p->hf_file))
+ break;
-+ else
-+ au_hfput(p, file);
++ au_hfput(p, file);
+ }
+ } else {
+ bend = au_br_index(sb, brid);
+ for (fidir->fd_bbot = bend; fidir->fd_bbot >= finfo->fi_btop;
+ fidir->fd_bbot--, p--)
+ if (p->hf_file) {
-+ if (p->hf_file->f_dentry
-+ && p->hf_file->f_dentry->d_inode)
++ if (file_inode(p->hf_file))
+ break;
-+ else
-+ au_hfput(p, file);
++ au_hfput(p, file);
+ }
+ AuDebugOn(fidir->fd_bbot < finfo->fi_btop);
+}
+ struct au_finfo *finfo;
+ struct au_hfile *hfile;
+
-+ dentry = file->f_dentry;
++ dentry = file->f_path.dentry;
+ finfo = au_fi(file);
+ if (!finfo->fi_hdir) {
+ hfile = &finfo->fi_htop;
+ struct inode *inode;
+
+ err = 0;
-+ dentry = file->f_dentry;
++ dentry = file->f_path.dentry;
+ inode = dentry->d_inode;
-+ AuDebugOn(au_special_file(inode->i_mode));
+ sigen = au_sigen(dentry->d_sb);
+ fi_write_lock(file);
+ figen = au_figen(file);
+
+/* it will never be called, but necessary to support O_DIRECT */
+static ssize_t aufs_direct_IO(int rw, struct kiocb *iocb,
-+ const struct iovec *iov, loff_t offset,
-+ unsigned long nr_segs)
-+{ BUG(); return 0; }
-+
-+/*
-+ * it will never be called, but madvise and fadvise behaves differently
-+ * when get_xip_mem is defined
-+ */
-+static int aufs_get_xip_mem(struct address_space *mapping, pgoff_t pgoff,
-+ int create, void **kmem, unsigned long *pfn)
++ struct iov_iter *iter, loff_t offset)
+{ BUG(); return 0; }
+
+/* they will never be called. */
+
+static int aufs_set_page_dirty(struct page *page)
+{ AuUnsupport(); return 0; }
-+static void aufs_invalidatepage(struct page *page, unsigned long offset)
++static void aufs_invalidatepage(struct page *page, unsigned int offset,
++ unsigned int length)
+{ AuUnsupport(); }
+static int aufs_releasepage(struct page *page, gfp_t gfp)
+{ AuUnsupport(); return 0; }
+static int aufs_launder_page(struct page *page)
+{ AuUnsupport(); return 0; }
+static int aufs_is_partially_uptodate(struct page *page,
-+ read_descriptor_t *desc,
-+ unsigned long from)
++ unsigned long from,
++ unsigned long count)
+{ AuUnsupport(); return 0; }
++static void aufs_is_dirty_writeback(struct page *page, bool *dirty,
++ bool *writeback)
++{ AuUnsupport(); }
+static int aufs_error_remove_page(struct address_space *mapping,
+ struct page *page)
+{ AuUnsupport(); return 0; }
+const struct address_space_operations aufs_aop = {
+ .readpage = aufs_readpage,
+ .direct_IO = aufs_direct_IO,
-+ .get_xip_mem = aufs_get_xip_mem,
+#ifdef CONFIG_AUFS_DEBUG
+ .writepage = aufs_writepage,
+ /* no writepages, because of writepage */
+ .migratepage = aufs_migratepage,
+ .launder_page = aufs_launder_page,
+ .is_partially_uptodate = aufs_is_partially_uptodate,
++ .is_dirty_writeback = aufs_is_dirty_writeback,
+ .error_remove_page = aufs_error_remove_page,
+ .swap_activate = aufs_swap_activate,
+ .swap_deactivate = aufs_swap_deactivate
+};
diff -urN /usr/share/empty/fs/aufs/file.h linux/fs/aufs/file.h
--- /usr/share/empty/fs/aufs/file.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/file.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,298 @@
++++ linux/fs/aufs/file.h 2015-06-22 08:27:37.880835119 +0200
+@@ -0,0 +1,291 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ atomic_t fi_mmapped;
+ };
+ struct au_fidir *fi_hdir; /* for dir only */
++
++ struct hlist_node fi_hlist;
++ struct file *fi_file; /* very ugly */
+} ____cacheline_aligned_in_smp;
+
+/* ---------------------------------------------------------------------- */
+extern const struct address_space_operations aufs_aop;
+unsigned int au_file_roflags(unsigned int flags);
+struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags,
-+ struct file *file);
-+int au_do_open(struct file *file, int (*open)(struct file *file, int flags),
-+ struct au_fidir *fidir);
++ struct file *file, int force_wr);
++struct au_do_open_args {
++ int no_lock;
++ int (*open)(struct file *file, int flags,
++ struct file *h_file);
++ struct au_fidir *fidir;
++ struct file *h_file;
++};
++int au_do_open(struct file *file, struct au_do_open_args *args);
+int au_reopen_nondir(struct file *file);
+struct au_pin;
+int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin);
+
+#ifdef CONFIG_AUFS_BR_HFSPLUS
+/* hfsplus.c */
-+struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex);
++struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex,
++ int force_wr);
+void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex,
+ struct file *h_file);
+#else
-+static inline
-+struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex)
-+{
-+ return NULL;
-+}
-+
++AuStub(struct file *, au_h_open_pre, return NULL, struct dentry *dentry,
++ aufs_bindex_t bindex, int force_wr)
+AuStubVoid(au_h_open_post, struct dentry *dentry, aufs_bindex_t bindex,
+ struct file *h_file);
+#endif
+
+/* f_op.c */
+extern const struct file_operations aufs_file_fop;
-+int au_do_open_nondir(struct file *file, int flags);
++int au_do_open_nondir(struct file *file, int flags, struct file *h_file);
+int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file);
-+
-+#ifdef CONFIG_AUFS_SP_IATTR
-+/* f_op_sp.c */
-+int au_special_file(umode_t mode);
-+void au_init_special_fop(struct inode *inode, umode_t mode, dev_t rdev);
-+#else
-+AuStubInt0(au_special_file, umode_t mode)
-+static inline void au_init_special_fop(struct inode *inode, umode_t mode,
-+ dev_t rdev)
-+{
-+ init_special_inode(inode, mode, rdev);
-+}
-+#endif
++struct file *au_read_pre(struct file *file, int keep_fi);
+
+/* finfo.c */
+void au_hfput(struct au_hfile *hf, struct file *file);
+#ifdef CONFIG_COMPAT
+long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
+ unsigned long arg);
++long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
++ unsigned long arg);
+#endif
+
+/* ---------------------------------------------------------------------- */
+static inline void au_vm_prfile_set(struct vm_area_struct *vma,
+ struct file *file)
+{
-+#ifdef CONFIG_AUFS_PROC_MAP
+ get_file(file);
+ vma->vm_prfile = file;
+#ifndef CONFIG_MMU
+ get_file(file);
+ vma->vm_region->vm_prfile = file;
+#endif
-+#endif
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_FILE_H__ */
diff -urN /usr/share/empty/fs/aufs/finfo.c linux/fs/aufs/finfo.c
--- /usr/share/empty/fs/aufs/finfo.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/finfo.c 2013-02-19 08:40:03.946892891 +0100
++++ linux/fs/aufs/finfo.c 2015-06-22 08:29:23.706757681 +0200
@@ -0,0 +1,157 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ au_hfput(hf, file);
+ if (val) {
+ FiMustWriteLock(file);
++ AuDebugOn(IS_ERR_OR_NULL(file->f_path.dentry));
+ hf->hf_file = val;
-+ hf->hf_br = au_sbr(file->f_dentry->d_sb, bindex);
++ hf->hf_br = au_sbr(file->f_path.dentry->d_sb, bindex);
+ }
+}
+
+void au_update_figen(struct file *file)
+{
-+ atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_dentry));
++ atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_path.dentry));
+ /* smp_mb(); */ /* atomic_set */
+}
+
+{
+ struct au_finfo *finfo;
+
-+ au_nfiles_dec(file->f_dentry->d_sb);
++ au_nfiles_dec(file->f_path.dentry->d_sb);
+
+ finfo = au_fi(file);
+ AuDebugOn(finfo->fi_hdir);
+ struct dentry *dentry;
+
+ err = -ENOMEM;
-+ dentry = file->f_dentry;
++ dentry = file->f_path.dentry;
+ finfo = au_cache_alloc_finfo();
+ if (unlikely(!finfo))
+ goto out;
+}
diff -urN /usr/share/empty/fs/aufs/f_op.c linux/fs/aufs/f_op.c
--- /usr/share/empty/fs/aufs/f_op.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/f_op.c 2013-03-14 20:07:41.041453062 +0100
-@@ -0,0 +1,723 @@
++++ linux/fs/aufs/f_op.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,748 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * file and vm operations
+ */
+
++#include <linux/aio.h>
+#include <linux/fs_stack.h>
+#include <linux/mman.h>
+#include <linux/security.h>
+#include "aufs.h"
+
-+int au_do_open_nondir(struct file *file, int flags)
++int au_do_open_nondir(struct file *file, int flags, struct file *h_file)
+{
+ int err;
+ aufs_bindex_t bindex;
-+ struct file *h_file;
+ struct dentry *dentry;
+ struct au_finfo *finfo;
++ struct inode *h_inode;
+
+ FiMustWriteLock(file);
+
-+ dentry = file->f_dentry;
-+ err = au_d_alive(dentry);
-+ if (unlikely(err))
-+ goto out;
-+
++ err = 0;
++ dentry = file->f_path.dentry;
++ AuDebugOn(IS_ERR_OR_NULL(dentry));
+ finfo = au_fi(file);
+ memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop));
+ atomic_set(&finfo->fi_mmapped, 0);
+ bindex = au_dbstart(dentry);
-+ h_file = au_h_open(dentry, bindex, flags, file);
++ if (!h_file)
++ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
++ else
++ get_file(h_file);
+ if (IS_ERR(h_file))
+ err = PTR_ERR(h_file);
+ else {
++ if ((flags & __O_TMPFILE)
++ && !(flags & O_EXCL)) {
++ h_inode = file_inode(h_file);
++ spin_lock(&h_inode->i_lock);
++ h_inode->i_state |= I_LINKABLE;
++ spin_unlock(&h_inode->i_lock);
++ }
+ au_set_fbstart(file, bindex);
+ au_set_h_fptr(file, bindex, h_file);
+ au_update_figen(file);
+ /* file->f_ra = h_file->f_ra; */
+ }
+
-+out:
+ return err;
+}
+
+{
+ int err;
+ struct super_block *sb;
++ struct au_do_open_args args = {
++ .open = au_do_open_nondir
++ };
+
-+ AuDbg("%.*s, f_flags 0x%x, f_mode 0x%x\n",
-+ AuDLNPair(file->f_dentry), vfsub_file_flags(file),
-+ file->f_mode);
++ AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n",
++ file, vfsub_file_flags(file), file->f_mode);
+
-+ sb = file->f_dentry->d_sb;
++ sb = file->f_path.dentry->d_sb;
+ si_read_lock(sb, AuLock_FLUSH);
-+ err = au_do_open(file, au_do_open_nondir, /*fidir*/NULL);
++ err = au_do_open(file, &args);
+ si_read_unlock(sb);
+ return err;
+}
+ aufs_bindex_t bindex;
+
+ finfo = au_fi(file);
++ au_sphl_del(&finfo->fi_hlist,
++ &au_sbi(file->f_path.dentry->d_sb)->si_files);
+ bindex = finfo->fi_btop;
+ if (bindex >= 0)
+ au_set_h_fptr(file, bindex, NULL);
+ * read functions after [fdi]_rwsem are released, but it should be harmless.
+ */
+
-+static ssize_t aufs_read(struct file *file, char __user *buf, size_t count,
-+ loff_t *ppos)
++/* Callers should call au_read_post() or fput() in the end */
++struct file *au_read_pre(struct file *file, int keep_fi)
+{
-+ ssize_t err;
-+ struct dentry *dentry;
+ struct file *h_file;
-+ struct super_block *sb;
++ int err;
+
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0);
-+ if (unlikely(err))
-+ goto out;
++ if (!err) {
++ di_read_unlock(file->f_path.dentry, AuLock_IR);
++ h_file = au_hf_top(file);
++ get_file(h_file);
++ if (!keep_fi)
++ fi_read_unlock(file);
++ } else
++ h_file = ERR_PTR(err);
+
-+ h_file = au_hf_top(file);
-+ get_file(h_file);
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_read_unlock(file);
++ return h_file;
++}
+
-+ /* filedata may be obsoleted by concurrent copyup, but no problem */
-+ err = vfsub_read_u(h_file, buf, count, ppos);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
++static void au_read_post(struct inode *inode, struct file *h_file)
++{
+ /* update without lock, I don't think it a problem */
-+ fsstack_copy_attr_atime(dentry->d_inode, h_file->f_dentry->d_inode);
++ fsstack_copy_attr_atime(inode, file_inode(h_file));
+ fput(h_file);
-+
-+out:
-+ si_read_unlock(sb);
-+ return err;
+}
+
++struct au_write_pre {
++ blkcnt_t blks;
++ aufs_bindex_t bstart;
++};
++
+/*
-+ * todo: very ugly
-+ * it locks both of i_mutex and si_rwsem for read in safe.
-+ * if the plink maintenance mode continues forever (that is the problem),
-+ * may loop forever.
++ * return with iinfo is write-locked
++ * callers should call au_write_post() or iinfo_write_unlock() + fput() in the
++ * end
+ */
-+static void au_mtx_and_read_lock(struct inode *inode)
-+{
-+ int err;
-+ struct super_block *sb = inode->i_sb;
-+
-+ while (1) {
-+ mutex_lock(&inode->i_mutex);
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (!err)
-+ break;
-+ mutex_unlock(&inode->i_mutex);
-+ si_read_lock(sb, AuLock_NOPLMW);
-+ si_read_unlock(sb);
-+ }
-+}
-+
-+static ssize_t aufs_write(struct file *file, const char __user *ubuf,
-+ size_t count, loff_t *ppos)
++static struct file *au_write_pre(struct file *file, int do_ready,
++ struct au_write_pre *wpre)
+{
-+ ssize_t err;
-+ struct au_pin pin;
-+ struct dentry *dentry;
-+ struct super_block *sb;
-+ struct inode *inode;
+ struct file *h_file;
-+ char __user *buf = (char __user *)ubuf;
-+
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
-+ inode = dentry->d_inode;
-+ au_mtx_and_read_lock(inode);
-+
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = au_ready_to_write(file, -1, &pin);
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ if (unlikely(err)) {
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
-+ goto out;
-+ }
-+
-+ h_file = au_hf_top(file);
-+ get_file(h_file);
-+ au_unpin(&pin);
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
-+
-+ err = vfsub_write_u(h_file, buf, count, ppos);
-+ ii_write_lock_child(inode);
-+ au_cpup_attr_timesizes(inode);
-+ inode->i_mode = h_file->f_dentry->d_inode->i_mode;
-+ ii_write_unlock(inode);
-+ fput(h_file);
-+
-+out:
-+ si_read_unlock(sb);
-+ mutex_unlock(&inode->i_mutex);
-+ return err;
-+}
-+
-+static ssize_t au_do_aio(struct file *h_file, int rw, struct kiocb *kio,
-+ const struct iovec *iov, unsigned long nv, loff_t pos)
-+{
-+ ssize_t err;
-+ struct file *file;
-+ ssize_t (*func)(struct kiocb *, const struct iovec *, unsigned long,
-+ loff_t);
-+
-+ err = security_file_permission(h_file, rw);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = -ENOSYS;
-+ func = NULL;
-+ if (rw == MAY_READ)
-+ func = h_file->f_op->aio_read;
-+ else if (rw == MAY_WRITE)
-+ func = h_file->f_op->aio_write;
-+ if (func) {
-+ file = kio->ki_filp;
-+ kio->ki_filp = h_file;
-+ lockdep_off();
-+ err = func(kio, iov, nv, pos);
-+ lockdep_on();
-+ kio->ki_filp = file;
-+ } else
-+ /* currently there is no such fs */
-+ WARN_ON_ONCE(1);
-+
-+out:
-+ return err;
-+}
-+
-+static ssize_t aufs_aio_read(struct kiocb *kio, const struct iovec *iov,
-+ unsigned long nv, loff_t pos)
-+{
-+ ssize_t err;
-+ struct file *file, *h_file;
+ struct dentry *dentry;
-+ struct super_block *sb;
-+
-+ file = kio->ki_filp;
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0);
-+ if (unlikely(err))
-+ goto out;
-+
-+ h_file = au_hf_top(file);
-+ get_file(h_file);
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_read_unlock(file);
-+
-+ err = au_do_aio(h_file, MAY_READ, kio, iov, nv, pos);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+ /* update without lock, I don't think it a problem */
-+ fsstack_copy_attr_atime(dentry->d_inode, h_file->f_dentry->d_inode);
-+ fput(h_file);
-+
-+out:
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+static ssize_t aufs_aio_write(struct kiocb *kio, const struct iovec *iov,
-+ unsigned long nv, loff_t pos)
-+{
-+ ssize_t err;
++ int err;
+ struct au_pin pin;
-+ struct dentry *dentry;
-+ struct inode *inode;
-+ struct file *file, *h_file;
-+ struct super_block *sb;
-+
-+ file = kio->ki_filp;
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
-+ inode = dentry->d_inode;
-+ au_mtx_and_read_lock(inode);
+
+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = au_ready_to_write(file, -1, &pin);
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ if (unlikely(err)) {
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
++ h_file = ERR_PTR(err);
++ if (unlikely(err))
+ goto out;
++
++ dentry = file->f_path.dentry;
++ if (do_ready) {
++ err = au_ready_to_write(file, -1, &pin);
++ if (unlikely(err)) {
++ h_file = ERR_PTR(err);
++ di_write_unlock(dentry);
++ goto out_fi;
++ }
+ }
+
++ di_downgrade_lock(dentry, /*flags*/0);
++ if (wpre)
++ wpre->bstart = au_fbstart(file);
+ h_file = au_hf_top(file);
+ get_file(h_file);
-+ au_unpin(&pin);
-+ di_read_unlock(dentry, AuLock_IR);
++ if (wpre)
++ wpre->blks = file_inode(h_file)->i_blocks;
++ if (do_ready)
++ au_unpin(&pin);
++ di_read_unlock(dentry, /*flags*/0);
++
++out_fi:
+ fi_write_unlock(file);
++out:
++ return h_file;
++}
++
++static void au_write_post(struct inode *inode, struct file *h_file,
++ struct au_write_pre *wpre, ssize_t written)
++{
++ struct inode *h_inode;
+
-+ err = au_do_aio(h_file, MAY_WRITE, kio, iov, nv, pos);
-+ ii_write_lock_child(inode);
+ au_cpup_attr_timesizes(inode);
-+ inode->i_mode = h_file->f_dentry->d_inode->i_mode;
++ AuDebugOn(au_ibstart(inode) != wpre->bstart);
++ h_inode = file_inode(h_file);
++ inode->i_mode = h_inode->i_mode;
+ ii_write_unlock(inode);
+ fput(h_file);
+
-+out:
-+ si_read_unlock(sb);
-+ mutex_unlock(&inode->i_mutex);
-+ return err;
++ /* AuDbg("blks %llu, %llu\n", (u64)blks, (u64)h_inode->i_blocks); */
++ if (written > 0)
++ au_fhsm_wrote(inode->i_sb, wpre->bstart,
++ /*force*/h_inode->i_blocks > wpre->blks);
+}
+
-+static ssize_t aufs_splice_read(struct file *file, loff_t *ppos,
-+ struct pipe_inode_info *pipe, size_t len,
-+ unsigned int flags)
++static ssize_t aufs_read(struct file *file, char __user *buf, size_t count,
++ loff_t *ppos)
+{
+ ssize_t err;
++ struct inode *inode;
+ struct file *h_file;
-+ struct dentry *dentry;
+ struct super_block *sb;
+
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
++ inode = file_inode(file);
++ sb = inode->i_sb;
+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0);
-+ if (unlikely(err))
-+ goto out;
+
-+ err = -EINVAL;
-+ h_file = au_hf_top(file);
-+ get_file(h_file);
-+ if (au_test_loopback_kthread()) {
-+ au_warn_loopback(h_file->f_dentry->d_sb);
-+ if (file->f_mapping != h_file->f_mapping) {
-+ file->f_mapping = h_file->f_mapping;
-+ smp_mb(); /* unnecessary? */
-+ }
-+ }
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_read_unlock(file);
++ h_file = au_read_pre(file, /*keep_fi*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
+
-+ err = vfsub_splice_to(h_file, ppos, pipe, len, flags);
-+ /* todo: necessasry? */
++ /* filedata may be obsoleted by concurrent copyup, but no problem */
++ err = vfsub_read_u(h_file, buf, count, ppos);
++ /* todo: necessary? */
+ /* file->f_ra = h_file->f_ra; */
-+ /* update without lock, I don't think it a problem */
-+ fsstack_copy_attr_atime(dentry->d_inode, h_file->f_dentry->d_inode);
-+ fput(h_file);
++ au_read_post(inode, h_file);
+
+out:
+ si_read_unlock(sb);
+ return err;
+}
+
-+static ssize_t
-+aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos,
-+ size_t len, unsigned int flags)
++/*
++ * todo: very ugly
++ * it locks both of i_mutex and si_rwsem for read in safe.
++ * if the plink maintenance mode continues forever (that is the problem),
++ * may loop forever.
++ */
++static void au_mtx_and_read_lock(struct inode *inode)
++{
++ int err;
++ struct super_block *sb = inode->i_sb;
++
++ while (1) {
++ mutex_lock(&inode->i_mutex);
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (!err)
++ break;
++ mutex_unlock(&inode->i_mutex);
++ si_read_lock(sb, AuLock_NOPLMW);
++ si_read_unlock(sb);
++ }
++}
++
++static ssize_t aufs_write(struct file *file, const char __user *ubuf,
++ size_t count, loff_t *ppos)
+{
+ ssize_t err;
-+ struct au_pin pin;
-+ struct dentry *dentry;
++ struct au_write_pre wpre;
+ struct inode *inode;
+ struct file *h_file;
-+ struct super_block *sb;
++ char __user *buf = (char __user *)ubuf;
+
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
-+ inode = dentry->d_inode;
++ inode = file_inode(file);
+ au_mtx_and_read_lock(inode);
+
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = au_ready_to_write(file, -1, &pin);
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ if (unlikely(err)) {
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
++ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
+ goto out;
-+ }
-+
-+ h_file = au_hf_top(file);
-+ get_file(h_file);
-+ au_unpin(&pin);
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
+
-+ err = vfsub_splice_from(pipe, h_file, ppos, len, flags);
-+ ii_write_lock_child(inode);
-+ au_cpup_attr_timesizes(inode);
-+ inode->i_mode = h_file->f_dentry->d_inode->i_mode;
-+ ii_write_unlock(inode);
-+ fput(h_file);
++ err = vfsub_write_u(h_file, buf, count, ppos);
++ au_write_post(inode, h_file, &wpre, err);
+
+out:
-+ si_read_unlock(sb);
++ si_read_unlock(inode->i_sb);
+ mutex_unlock(&inode->i_mutex);
+ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * The locking order around current->mmap_sem.
-+ * - in most and regular cases
-+ * file I/O syscall -- aufs_read() or something
-+ * -- si_rwsem for read -- mmap_sem
-+ * (Note that [fdi]i_rwsem are released before mmap_sem).
-+ * - in mmap case
-+ * mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem
-+ * This AB-BA order is definitly bad, but is not a problem since "si_rwsem for
-+ * read" allows muliple processes to acquire it and [fdi]i_rwsem are not held in
-+ * file I/O. Aufs needs to stop lockdep in aufs_mmap() though.
-+ * It means that when aufs acquires si_rwsem for write, the process should never
-+ * acquire mmap_sem.
-+ *
-+ * Actually aufs_readdir() holds [fdi]i_rwsem before mmap_sem, but this is not a
-+ * problem either since any directory is not able to be mmap-ed.
-+ * The similar scenario is applied to aufs_readlink() too.
-+ */
-+
-+/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */
-+#define AuConv_VM_PROT(f, b) _calc_vm_trans(f, VM_##b, PROT_##b)
-+
-+static unsigned long au_arch_prot_conv(unsigned long flags)
-+{
-+ /* currently ppc64 only */
-+#ifdef CONFIG_PPC64
-+ /* cf. linux/arch/powerpc/include/asm/mman.h */
-+ AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO);
-+ return AuConv_VM_PROT(flags, SAO);
-+#else
-+ AuDebugOn(arch_calc_vm_prot_bits(-1));
-+ return 0;
-+#endif
-+}
-+
-+static unsigned long au_prot_conv(unsigned long flags)
-+{
-+ return AuConv_VM_PROT(flags, READ)
-+ | AuConv_VM_PROT(flags, WRITE)
-+ | AuConv_VM_PROT(flags, EXEC)
-+ | au_arch_prot_conv(flags);
-+}
-+
-+/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */
-+#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b)
-+
-+static unsigned long au_flag_conv(unsigned long flags)
-+{
-+ return AuConv_VM_MAP(flags, GROWSDOWN)
-+ | AuConv_VM_MAP(flags, DENYWRITE)
-+ | AuConv_VM_MAP(flags, LOCKED);
-+}
-+
-+static int aufs_mmap(struct file *file, struct vm_area_struct *vma)
++static ssize_t au_do_iter(struct file *h_file, int rw, struct kiocb *kio,
++ struct iov_iter *iov_iter)
+{
-+ int err;
-+ aufs_bindex_t bstart;
-+ const unsigned char wlock
-+ = (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED);
-+ struct dentry *dentry;
-+ struct super_block *sb;
-+ struct file *h_file;
-+ struct au_branch *br;
-+ struct au_pin pin;
-+
-+ AuDbgVmRegion(file, vma);
++ ssize_t err;
++ struct file *file;
++ ssize_t (*iter)(struct kiocb *, struct iov_iter *);
++ ssize_t (*aio)(struct kiocb *, const struct iovec *, unsigned long,
++ loff_t);
+
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
-+ lockdep_off();
-+ si_read_lock(sb, AuLock_NOPLMW);
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1);
++ err = security_file_permission(h_file, rw);
+ if (unlikely(err))
+ goto out;
+
-+ if (wlock) {
-+ err = au_ready_to_write(file, -1, &pin);
-+ di_write_unlock(dentry);
-+ if (unlikely(err)) {
-+ fi_write_unlock(file);
-+ goto out;
-+ }
-+ au_unpin(&pin);
-+ } else
-+ di_write_unlock(dentry);
-+
-+ bstart = au_fbstart(file);
-+ br = au_sbr(sb, bstart);
-+ h_file = au_hf_top(file);
-+ get_file(h_file);
-+ au_set_mmapped(file);
-+ fi_write_unlock(file);
-+ lockdep_on();
-+
-+ au_vm_file_reset(vma, h_file);
-+ err = security_mmap_file(h_file, au_prot_conv(vma->vm_flags),
-+ au_flag_conv(vma->vm_flags));
-+ if (!err)
-+ err = h_file->f_op->mmap(h_file, vma);
-+ if (unlikely(err))
-+ goto out_reset;
++ err = -ENOSYS;
++ iter = NULL;
++ aio = NULL;
++ if (rw == MAY_READ) {
++ iter = h_file->f_op->read_iter;
++ aio = h_file->f_op->aio_read;
++ } else if (rw == MAY_WRITE) {
++ iter = h_file->f_op->write_iter;
++ aio = h_file->f_op->aio_write;
++ }
+
-+ au_vm_prfile_set(vma, file);
-+ /* update without lock, I don't think it a problem */
-+ fsstack_copy_attr_atime(file->f_dentry->d_inode,
-+ h_file->f_dentry->d_inode);
-+ goto out_fput; /* success */
++ file = kio->ki_filp;
++ kio->ki_filp = h_file;
++ if (iter) {
++ lockdep_off();
++ err = iter(kio, iov_iter);
++ lockdep_on();
++ } else if (aio) {
++ lockdep_off();
++ err = aio(kio, iov_iter->iov, iov_iter->nr_segs, kio->ki_pos);
++ lockdep_on();
++ } else
++ /* currently there is no such fs */
++ WARN_ON_ONCE(1);
++ kio->ki_filp = file;
+
-+out_reset:
-+ au_unset_mmapped(file);
-+ au_vm_file_reset(vma, file);
-+out_fput:
-+ fput(h_file);
-+ lockdep_off();
+out:
-+ si_read_unlock(sb);
-+ lockdep_on();
-+ AuTraceErr(err);
+ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end,
-+ int datasync)
++static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter)
+{
-+ int err;
-+ struct au_pin pin;
-+ struct dentry *dentry;
++ ssize_t err;
++ struct file *file, *h_file;
+ struct inode *inode;
-+ struct file *h_file;
+ struct super_block *sb;
+
-+ dentry = file->f_dentry;
-+ inode = dentry->d_inode;
-+ sb = dentry->d_sb;
-+ mutex_lock(&inode->i_mutex);
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = 0; /* -EBADF; */ /* posix? */
-+ if (unlikely(!(file->f_mode & FMODE_WRITE)))
-+ goto out_si;
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1);
-+ if (unlikely(err))
-+ goto out_si;
++ file = kio->ki_filp;
++ inode = file_inode(file);
++ sb = inode->i_sb;
++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
-+ err = au_ready_to_write(file, -1, &pin);
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ au_unpin(&pin);
++ h_file = au_read_pre(file, /*keep_fi*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
+
-+ err = -EINVAL;
-+ h_file = au_hf_top(file);
-+ err = vfsub_fsync(h_file, &h_file->f_path, datasync);
-+ au_cpup_attr_timesizes(inode);
++ err = au_do_iter(h_file, MAY_READ, kio, iov_iter);
++ /* todo: necessary? */
++ /* file->f_ra = h_file->f_ra; */
++ au_read_post(inode, h_file);
+
-+out_unlock:
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
-+out_si:
-+ si_read_unlock(sb);
+out:
-+ mutex_unlock(&inode->i_mutex);
++ si_read_unlock(sb);
+ return err;
+}
+
-+/* no one supports this operation, currently */
-+#if 0
-+static int aufs_aio_fsync_nondir(struct kiocb *kio, int datasync)
++static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter)
+{
-+ int err;
-+ struct au_pin pin;
-+ struct dentry *dentry;
++ ssize_t err;
++ struct au_write_pre wpre;
+ struct inode *inode;
+ struct file *file, *h_file;
+
+ file = kio->ki_filp;
-+ dentry = file->f_dentry;
-+ inode = dentry->d_inode;
++ inode = file_inode(file);
+ au_mtx_and_read_lock(inode);
+
-+ err = 0; /* -EBADF; */ /* posix? */
-+ if (unlikely(!(file->f_mode & FMODE_WRITE)))
-+ goto out;
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1);
-+ if (unlikely(err))
++ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
+ goto out;
+
-+ err = au_ready_to_write(file, -1, &pin);
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ au_unpin(&pin);
-+
-+ err = -ENOSYS;
-+ h_file = au_hf_top(file);
-+ if (h_file->f_op && h_file->f_op->aio_fsync) {
-+ struct dentry *h_d;
-+ struct mutex *h_mtx;
-+
-+ h_d = h_file->f_dentry;
-+ h_mtx = &h_d->d_inode->i_mutex;
-+ if (!is_sync_kiocb(kio)) {
-+ get_file(h_file);
-+ fput(file);
-+ }
-+ kio->ki_filp = h_file;
-+ err = h_file->f_op->aio_fsync(kio, datasync);
-+ mutex_lock_nested(h_mtx, AuLsc_I_CHILD);
-+ if (!err)
-+ vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL);
-+ /*ignore*/
-+ au_cpup_attr_timesizes(inode);
-+ mutex_unlock(h_mtx);
-+ }
++ err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter);
++ au_write_post(inode, h_file, &wpre, err);
+
-+out_unlock:
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
+out:
-+ si_read_unlock(inode->sb);
++ si_read_unlock(inode->i_sb);
+ mutex_unlock(&inode->i_mutex);
+ return err;
+}
-+#endif
+
-+static int aufs_fasync(int fd, struct file *file, int flag)
++static ssize_t aufs_splice_read(struct file *file, loff_t *ppos,
++ struct pipe_inode_info *pipe, size_t len,
++ unsigned int flags)
+{
-+ int err;
++ ssize_t err;
+ struct file *h_file;
-+ struct dentry *dentry;
++ struct inode *inode;
+ struct super_block *sb;
+
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
++ inode = file_inode(file);
++ sb = inode->i_sb;
+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0);
-+ if (unlikely(err))
-+ goto out;
+
-+ h_file = au_hf_top(file);
-+ if (h_file->f_op && h_file->f_op->fasync)
-+ err = h_file->f_op->fasync(fd, h_file, flag);
++ h_file = au_read_pre(file, /*keep_fi*/1);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
+
-+ di_read_unlock(dentry, AuLock_IR);
++ if (au_test_loopback_kthread()) {
++ au_warn_loopback(h_file->f_path.dentry->d_sb);
++ if (file->f_mapping != h_file->f_mapping) {
++ file->f_mapping = h_file->f_mapping;
++ smp_mb(); /* unnecessary? */
++ }
++ }
+ fi_read_unlock(file);
+
++ err = vfsub_splice_to(h_file, ppos, pipe, len, flags);
++ /* todo: necessasry? */
++ /* file->f_ra = h_file->f_ra; */
++ au_read_post(inode, h_file);
++
+out:
+ si_read_unlock(sb);
+ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+/* no one supports this operation, currently */
-+#if 0
-+static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset,
-+ size_t len, loff_t *pos , int more)
++static ssize_t
++aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos,
++ size_t len, unsigned int flags)
+{
++ ssize_t err;
++ struct au_write_pre wpre;
++ struct inode *inode;
++ struct file *h_file;
++
++ inode = file_inode(file);
++ au_mtx_and_read_lock(inode);
++
++ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
++
++ err = vfsub_splice_from(pipe, h_file, ppos, len, flags);
++ au_write_post(inode, h_file, &wpre, err);
++
++out:
++ si_read_unlock(inode->i_sb);
++ mutex_unlock(&inode->i_mutex);
++ return err;
+}
-+#endif
+
-+/* ---------------------------------------------------------------------- */
++static long aufs_fallocate(struct file *file, int mode, loff_t offset,
++ loff_t len)
++{
++ long err;
++ struct au_write_pre wpre;
++ struct inode *inode;
++ struct file *h_file;
+
-+const struct file_operations aufs_file_fop = {
-+ .owner = THIS_MODULE,
++ inode = file_inode(file);
++ au_mtx_and_read_lock(inode);
+
-+ .llseek = default_llseek,
++ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
+
-+ .read = aufs_read,
-+ .write = aufs_write,
-+ .aio_read = aufs_aio_read,
-+ .aio_write = aufs_aio_write,
-+#ifdef CONFIG_AUFS_POLL
-+ .poll = aufs_poll,
-+#endif
-+ .unlocked_ioctl = aufs_ioctl_nondir,
-+#ifdef CONFIG_COMPAT
-+ .compat_ioctl = aufs_ioctl_nondir, /* same */
-+#endif
-+ .mmap = aufs_mmap,
-+ .open = aufs_open_nondir,
-+ .flush = aufs_flush_nondir,
-+ .release = aufs_release_nondir,
-+ .fsync = aufs_fsync_nondir,
-+ /* .aio_fsync = aufs_aio_fsync_nondir, */
-+ .fasync = aufs_fasync,
-+ /* .sendpage = aufs_sendpage, */
-+ .splice_write = aufs_splice_write,
-+ .splice_read = aufs_splice_read,
-+#if 0
-+ .aio_splice_write = aufs_aio_splice_write,
-+ .aio_splice_read = aufs_aio_splice_read
-+#endif
-+};
-diff -urN /usr/share/empty/fs/aufs/f_op_sp.c linux/fs/aufs/f_op_sp.c
---- /usr/share/empty/fs/aufs/f_op_sp.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/f_op_sp.c 2013-03-14 20:07:41.041453062 +0100
-@@ -0,0 +1,295 @@
-+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-+ */
++ lockdep_off();
++ err = vfs_fallocate(h_file, mode, offset, len);
++ lockdep_on();
++ au_write_post(inode, h_file, &wpre, /*written*/1);
++
++out:
++ si_read_unlock(inode->i_sb);
++ mutex_unlock(&inode->i_mutex);
++ return err;
++}
++
++/* ---------------------------------------------------------------------- */
+
+/*
-+ * file operations for special files.
-+ * while they exist in aufs virtually,
-+ * their file I/O is handled out of aufs.
++ * The locking order around current->mmap_sem.
++ * - in most and regular cases
++ * file I/O syscall -- aufs_read() or something
++ * -- si_rwsem for read -- mmap_sem
++ * (Note that [fdi]i_rwsem are released before mmap_sem).
++ * - in mmap case
++ * mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem
++ * This AB-BA order is definitly bad, but is not a problem since "si_rwsem for
++ * read" allows muliple processes to acquire it and [fdi]i_rwsem are not held in
++ * file I/O. Aufs needs to stop lockdep in aufs_mmap() though.
++ * It means that when aufs acquires si_rwsem for write, the process should never
++ * acquire mmap_sem.
++ *
++ * Actually aufs_iterate() holds [fdi]i_rwsem before mmap_sem, but this is not a
++ * problem either since any directory is not able to be mmap-ed.
++ * The similar scenario is applied to aufs_readlink() too.
+ */
+
-+#include "aufs.h"
++#if 0 /* stop calling security_file_mmap() */
++/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */
++#define AuConv_VM_PROT(f, b) _calc_vm_trans(f, VM_##b, PROT_##b)
+
-+static ssize_t aufs_aio_read_sp(struct kiocb *kio, const struct iovec *iov,
-+ unsigned long nv, loff_t pos)
++static unsigned long au_arch_prot_conv(unsigned long flags)
+{
-+ ssize_t err;
-+ aufs_bindex_t bstart;
-+ unsigned char wbr;
-+ struct file *file, *h_file;
-+ struct super_block *sb;
++ /* currently ppc64 only */
++#ifdef CONFIG_PPC64
++ /* cf. linux/arch/powerpc/include/asm/mman.h */
++ AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO);
++ return AuConv_VM_PROT(flags, SAO);
++#else
++ AuDebugOn(arch_calc_vm_prot_bits(-1));
++ return 0;
++#endif
++}
+
-+ file = kio->ki_filp;
-+ sb = file->f_dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ fi_read_lock(file);
-+ bstart = au_fbstart(file);
-+ h_file = au_hf_top(file);
-+ fi_read_unlock(file);
-+ wbr = !!au_br_writable(au_sbr(sb, bstart)->br_perm);
-+ si_read_unlock(sb);
++static unsigned long au_prot_conv(unsigned long flags)
++{
++ return AuConv_VM_PROT(flags, READ)
++ | AuConv_VM_PROT(flags, WRITE)
++ | AuConv_VM_PROT(flags, EXEC)
++ | au_arch_prot_conv(flags);
++}
+
-+ /* do not change the file in kio */
-+ AuDebugOn(!h_file->f_op || !h_file->f_op->aio_read);
-+ err = h_file->f_op->aio_read(kio, iov, nv, pos);
-+ if (err > 0 && wbr)
-+ file_accessed(h_file);
++/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */
++#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b)
+
-+ return err;
++static unsigned long au_flag_conv(unsigned long flags)
++{
++ return AuConv_VM_MAP(flags, GROWSDOWN)
++ | AuConv_VM_MAP(flags, DENYWRITE)
++ | AuConv_VM_MAP(flags, LOCKED);
+}
++#endif
+
-+static ssize_t aufs_aio_write_sp(struct kiocb *kio, const struct iovec *iov,
-+ unsigned long nv, loff_t pos)
++static int aufs_mmap(struct file *file, struct vm_area_struct *vma)
+{
-+ ssize_t err;
-+ aufs_bindex_t bstart;
-+ unsigned char wbr;
++ int err;
++ const unsigned char wlock
++ = (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED);
+ struct super_block *sb;
-+ struct file *file, *h_file;
++ struct file *h_file;
++ struct inode *inode;
++
++ AuDbgVmRegion(file, vma);
++
++ inode = file_inode(file);
++ sb = inode->i_sb;
++ lockdep_off();
++ si_read_lock(sb, AuLock_NOPLMW);
++
++ h_file = au_write_pre(file, wlock, /*wpre*/NULL);
++ lockdep_on();
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
++
++ err = 0;
++ au_set_mmapped(file);
++ au_vm_file_reset(vma, h_file);
++ /*
++ * we cannot call security_mmap_file() here since it may acquire
++ * mmap_sem or i_mutex.
++ *
++ * err = security_mmap_file(h_file, au_prot_conv(vma->vm_flags),
++ * au_flag_conv(vma->vm_flags));
++ */
++ if (!err)
++ err = h_file->f_op->mmap(h_file, vma);
++ if (!err) {
++ au_vm_prfile_set(vma, file);
++ fsstack_copy_attr_atime(inode, file_inode(h_file));
++ goto out_fput; /* success */
++ }
++ au_unset_mmapped(file);
++ au_vm_file_reset(vma, file);
+
-+ file = kio->ki_filp;
-+ sb = file->f_dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ fi_read_lock(file);
-+ bstart = au_fbstart(file);
-+ h_file = au_hf_top(file);
-+ fi_read_unlock(file);
-+ wbr = !!au_br_writable(au_sbr(sb, bstart)->br_perm);
++out_fput:
++ lockdep_off();
++ ii_write_unlock(inode);
++ lockdep_on();
++ fput(h_file);
++out:
++ lockdep_off();
+ si_read_unlock(sb);
-+
-+ /* do not change the file in kio */
-+ AuDebugOn(!h_file->f_op || !h_file->f_op->aio_write);
-+ err = h_file->f_op->aio_write(kio, iov, nv, pos);
++ lockdep_on();
++ AuTraceErr(err);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static int aufs_release_sp(struct inode *inode, struct file *file)
++static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end,
++ int datasync)
+{
+ int err;
++ struct au_write_pre wpre;
++ struct inode *inode;
+ struct file *h_file;
+
-+ fi_read_lock(file);
-+ h_file = au_hf_top(file);
-+ fi_read_unlock(file);
-+ /* close this fifo in aufs */
-+ err = h_file->f_op->release(inode, file); /* ignore */
-+ aufs_release_nondir(inode, file); /* ignore */
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* currently, support only FIFO */
-+enum {
-+ AuSp_FIFO, AuSp_FIFO_R, AuSp_FIFO_W, AuSp_FIFO_RW,
-+ /* AuSp_SOCK, AuSp_CHR, AuSp_BLK, */
-+ AuSp_Last
-+};
-+static int aufs_open_sp(struct inode *inode, struct file *file);
-+static struct au_sp_fop {
-+ int done;
-+ struct file_operations fop; /* not 'const' */
-+ spinlock_t spin;
-+} au_sp_fop[AuSp_Last] = {
-+ [AuSp_FIFO] = {
-+ .fop = {
-+ .owner = THIS_MODULE,
-+ .open = aufs_open_sp
-+ }
-+ }
-+};
-+
-+static void au_init_fop_sp(struct file *file)
-+{
-+ struct au_sp_fop *p;
-+ int i;
-+ struct file *h_file;
++ err = 0; /* -EBADF; */ /* posix? */
++ if (unlikely(!(file->f_mode & FMODE_WRITE)))
++ goto out;
+
-+ p = au_sp_fop;
-+ if (unlikely(!p->done)) {
-+ /* initialize first time only */
-+ static DEFINE_SPINLOCK(spin);
++ inode = file_inode(file);
++ au_mtx_and_read_lock(inode);
+
-+ spin_lock(&spin);
-+ if (!p->done) {
-+ BUILD_BUG_ON(sizeof(au_sp_fop)/sizeof(*au_sp_fop)
-+ != AuSp_Last);
-+ for (i = 0; i < AuSp_Last; i++)
-+ spin_lock_init(&p[i].spin);
-+ p->done = 1;
-+ }
-+ spin_unlock(&spin);
-+ }
++ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out_unlock;
+
-+ switch (file->f_mode & (FMODE_READ | FMODE_WRITE)) {
-+ case FMODE_READ:
-+ i = AuSp_FIFO_R;
-+ break;
-+ case FMODE_WRITE:
-+ i = AuSp_FIFO_W;
-+ break;
-+ case FMODE_READ | FMODE_WRITE:
-+ i = AuSp_FIFO_RW;
-+ break;
-+ default:
-+ BUG();
-+ }
++ err = vfsub_fsync(h_file, &h_file->f_path, datasync);
++ au_write_post(inode, h_file, &wpre, /*written*/0);
+
-+ p += i;
-+ if (unlikely(!p->done)) {
-+ /* initialize first time only */
-+ h_file = au_hf_top(file);
-+ spin_lock(&p->spin);
-+ if (!p->done) {
-+ p->fop = *h_file->f_op;
-+ p->fop.owner = THIS_MODULE;
-+ if (p->fop.aio_read)
-+ p->fop.aio_read = aufs_aio_read_sp;
-+ if (p->fop.aio_write)
-+ p->fop.aio_write = aufs_aio_write_sp;
-+ p->fop.release = aufs_release_sp;
-+ p->done = 1;
-+ }
-+ spin_unlock(&p->spin);
-+ }
-+ file->f_op = &p->fop;
++out_unlock:
++ si_read_unlock(inode->i_sb);
++ mutex_unlock(&inode->i_mutex);
++out:
++ return err;
+}
+
-+static int au_cpup_sp(struct dentry *dentry)
++/* no one supports this operation, currently */
++#if 0
++static int aufs_aio_fsync_nondir(struct kiocb *kio, int datasync)
+{
+ int err;
-+ aufs_bindex_t bcpup;
-+ struct au_pin pin;
-+ struct au_wr_dir_args wr_dir_args = {
-+ .force_btgt = -1,
-+ .flags = 0
-+ };
-+
-+ AuDbg("%.*s\n", AuDLNPair(dentry));
++ struct au_write_pre wpre;
++ struct inode *inode;
++ struct file *file, *h_file;
+
-+ di_read_unlock(dentry, AuLock_IR);
-+ di_write_lock_child(dentry);
-+ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args);
-+ if (unlikely(err < 0))
++ err = 0; /* -EBADF; */ /* posix? */
++ if (unlikely(!(file->f_mode & FMODE_WRITE)))
+ goto out;
-+ bcpup = err;
-+ err = 0;
-+ if (bcpup == au_dbstart(dentry))
-+ goto out; /* success */
+
-+ err = au_pin(&pin, dentry, bcpup, au_opt_udba(dentry->d_sb),
-+ AuPin_MNT_WRITE);
-+ if (!err) {
-+ err = au_sio_cpup_simple(dentry, bcpup, -1, AuCpup_DTIME);
-+ au_unpin(&pin);
++ file = kio->ki_filp;
++ inode = file_inode(file);
++ au_mtx_and_read_lock(inode);
++
++ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out_unlock;
++
++ err = -ENOSYS;
++ h_file = au_hf_top(file);
++ if (h_file->f_op->aio_fsync) {
++ struct mutex *h_mtx;
++
++ h_mtx = &file_inode(h_file)->i_mutex;
++ if (!is_sync_kiocb(kio)) {
++ get_file(h_file);
++ fput(file);
++ }
++ kio->ki_filp = h_file;
++ err = h_file->f_op->aio_fsync(kio, datasync);
++ mutex_lock_nested(h_mtx, AuLsc_I_CHILD);
++ if (!err)
++ vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL);
++ /*ignore*/
++ mutex_unlock(h_mtx);
+ }
++ au_write_post(inode, h_file, &wpre, /*written*/0);
+
++out_unlock:
++ si_read_unlock(inode->sb);
++ mutex_unlock(&inode->i_mutex);
+out:
-+ di_downgrade_lock(dentry, AuLock_IR);
+ return err;
+}
++#endif
+
-+static int au_do_open_sp(struct file *file, int flags)
++static int aufs_fasync(int fd, struct file *file, int flag)
+{
+ int err;
-+ struct dentry *dentry;
-+ struct super_block *sb;
+ struct file *h_file;
-+ struct inode *h_inode;
-+
-+ dentry = file->f_dentry;
-+ AuDbg("%.*s\n", AuDLNPair(dentry));
++ struct super_block *sb;
+
-+ /*
-+ * try copying-up.
-+ * operate on the ro branch is not an error.
-+ */
-+ au_cpup_sp(dentry); /* ignore */
++ sb = file->f_path.dentry->d_sb;
++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
-+ /* prepare h_file */
-+ err = au_do_open_nondir(file, vfsub_file_flags(file));
-+ if (unlikely(err))
++ h_file = au_read_pre(file, /*keep_fi*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
+ goto out;
+
-+ sb = dentry->d_sb;
-+ h_file = au_hf_top(file);
-+ h_inode = h_file->f_dentry->d_inode;
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
-+ si_read_unlock(sb);
-+ /* open this fifo in aufs */
-+ err = h_inode->i_fop->open(file->f_dentry->d_inode, file);
-+ si_noflush_read_lock(sb);
-+ fi_write_lock(file);
-+ di_read_lock_child(dentry, AuLock_IR);
-+ if (!err)
-+ au_init_fop_sp(file);
++ if (h_file->f_op->fasync)
++ err = h_file->f_op->fasync(fd, h_file, flag);
++ fput(h_file); /* instead of au_read_post() */
+
+out:
++ si_read_unlock(sb);
+ return err;
+}
+
-+static int aufs_open_sp(struct inode *inode, struct file *file)
-+{
-+ int err;
-+ struct super_block *sb;
++/* ---------------------------------------------------------------------- */
+
-+ sb = file->f_dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ err = au_do_open(file, au_do_open_sp, /*fidir*/NULL);
-+ si_read_unlock(sb);
-+ return err;
++/* no one supports this operation, currently */
++#if 0
++static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset,
++ size_t len, loff_t *pos, int more)
++{
+}
++#endif
+
+/* ---------------------------------------------------------------------- */
+
-+void au_init_special_fop(struct inode *inode, umode_t mode, dev_t rdev)
-+{
-+ init_special_inode(inode, mode, rdev);
++const struct file_operations aufs_file_fop = {
++ .owner = THIS_MODULE,
+
-+ switch (mode & S_IFMT) {
-+ case S_IFIFO:
-+ inode->i_fop = &au_sp_fop[AuSp_FIFO].fop;
-+ /*FALLTHROUGH*/
-+ case S_IFCHR:
-+ case S_IFBLK:
-+ case S_IFSOCK:
-+ break;
-+ default:
-+ AuDebugOn(1);
-+ }
-+}
++ .llseek = default_llseek,
+
-+int au_special_file(umode_t mode)
-+{
-+ int ret;
++ .read = aufs_read,
++ .write = aufs_write,
++ .read_iter = aufs_read_iter,
++ .write_iter = aufs_write_iter,
+
-+ ret = 0;
-+ switch (mode & S_IFMT) {
-+ case S_IFIFO:
++#ifdef CONFIG_AUFS_POLL
++ .poll = aufs_poll,
++#endif
++ .unlocked_ioctl = aufs_ioctl_nondir,
++#ifdef CONFIG_COMPAT
++ .compat_ioctl = aufs_compat_ioctl_nondir,
++#endif
++ .mmap = aufs_mmap,
++ .open = aufs_open_nondir,
++ .flush = aufs_flush_nondir,
++ .release = aufs_release_nondir,
++ .fsync = aufs_fsync_nondir,
++ /* .aio_fsync = aufs_aio_fsync_nondir, */
++ .fasync = aufs_fasync,
++ /* .sendpage = aufs_sendpage, */
++ .splice_write = aufs_splice_write,
++ .splice_read = aufs_splice_read,
+#if 0
-+ case S_IFCHR:
-+ case S_IFBLK:
-+ case S_IFSOCK:
++ .aio_splice_write = aufs_aio_splice_write,
++ .aio_splice_read = aufs_aio_splice_read,
+#endif
-+ ret = 1;
-+ }
-+
-+ return ret;
-+}
++ .fallocate = aufs_fallocate
++};
diff -urN /usr/share/empty/fs/aufs/fstype.h linux/fs/aufs/fstype.h
--- /usr/share/empty/fs/aufs/fstype.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/fstype.h 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,481 @@
++++ linux/fs/aufs/fstype.h 2015-06-22 08:27:37.880835119 +0200
+@@ -0,0 +1,400 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+#include <linux/fs.h>
+#include <linux/magic.h>
+#include <linux/romfs_fs.h>
++#include <linux/nfs_fs.h>
+
+static inline int au_test_aufs(struct super_block *sb)
+{
+
+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;
++#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_romfs(struct super_block *sb __maybe_unused)
+{
-+#if defined(CONFIG_ISO9660_FS) || defined(CONFIG_ISO9660_FS_MODULE)
-+ return sb->s_magic == ISOFS_SUPER_MAGIC;
++#if defined(CONFIG_ROMFS_FS) || defined(CONFIG_ROMFS_FS_MODULE)
++ return sb->s_magic == ROMFS_MAGIC;
+#else
+ return 0;
+#endif
+#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)
++static inline int au_test_xfs(struct super_block *sb __maybe_unused)
+{
-+#if defined(CONFIG_9P_FS) || defined(CONFIG_9P_FS_MODULE)
-+ return sb->s_magic == V9FS_MAGIC;
++#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_ext4(struct super_block *sb __maybe_unused)
++static inline int au_test_tmpfs(struct super_block *sb __maybe_unused)
+{
-+#if defined(CONFIG_EXT4DEV_FS) || defined(CONFIG_EXT4DEV_FS_MODULE)
-+ return sb->s_magic == EXT4_SUPER_MAGIC;
++#ifdef CONFIG_TMPFS
++ return sb->s_magic == TMPFS_MAGIC;
+#else
+ return 0;
+#endif
+}
+
-+static inline int au_test_sysv(struct super_block *sb __maybe_unused)
++static inline int au_test_ecryptfs(struct super_block *sb __maybe_unused)
+{
-+#if defined(CONFIG_SYSV_FS) || defined(CONFIG_SYSV_FS_MODULE)
-+ return !strcmp(au_sbtype(sb), "sysv");
++#if defined(CONFIG_ECRYPT_FS) || defined(CONFIG_ECRYPT_FS_MODULE)
++ return !strcmp(au_sbtype(sb), "ecryptfs");
+#else
+ return 0;
+#endif
+#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 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 */
+ ;
+}
+
+ || au_test_btrfs(sb)
+ || au_test_ubifs(sb)
+ || au_test_hfsplus(sb) /* maintained, but incorrect */
-+ /* || au_test_ext4(sb) */ /* untested */
-+ /* || au_test_ocfs2(sb) */ /* untested */
-+ /* || au_test_ocfs2_dlmfs(sb) */ /* untested */
-+ /* || au_test_sysv(sb) */ /* untested */
+ /* || au_test_minix(sb) */ /* untested */
+ ;
+}
+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);
+ || au_test_ramfs(sb)
+#endif
+ || au_test_ubifs(sb)
-+ || au_test_btrfs(sb)
+ || au_test_hfsplus(sb);
+}
+
+ return au_test_nfs(sb)
+ || au_test_fuse(sb)
+ || au_test_ubifs(sb)
-+ /* || au_test_cifs(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)
-+ || au_test_ubifs(sb);
-+}
-+
+/* temporary support for i#1 in cramfs */
+static inline int au_test_fs_unique_ino(struct inode *inode)
+{
+ || au_test_romfs(sb);
+}
+
++/*
++ * test if the @inode is nfs with 'noacl' option
++ * NFS always sets MS_POSIXACL regardless its mount option 'noacl.'
++ */
++static inline int au_test_nfs_noacl(struct inode *inode)
++{
++ return au_test_nfs(inode->i_sb)
++ /* && IS_POSIXACL(inode) */
++ && !nfs_server_capable(inode, NFS_CAP_ACLS);
++}
++
+#endif /* __KERNEL__ */
+#endif /* __AUFS_FSTYPE_H__ */
diff -urN /usr/share/empty/fs/aufs/hfsnotify.c linux/fs/aufs/hfsnotify.c
--- /usr/share/empty/fs/aufs/hfsnotify.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/hfsnotify.c 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,293 @@
++++ linux/fs/aufs/hfsnotify.c 2015-06-22 08:27:37.880835119 +0200
+@@ -0,0 +1,288 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ hn_mark);
+ AuDbg("here\n");
+ au_cache_free_hnotify(hn);
-+ smp_mb__before_atomic_dec();
++ smp_mb__before_atomic();
+ if (atomic64_dec_and_test(&au_hfsn_ifree))
+ wake_up(&au_hfsn_wq);
+}
+ * by udba rename or rmdir, aufs assign a new inode to the known
+ * h_inode, so specify 1 to allow dups.
+ */
++ lockdep_off();
+ err = fsnotify_add_mark(mark, br->br_hfsn->hfsn_group, hinode->hi_inode,
+ /*mnt*/NULL, /*allow_dups*/1);
+ /* even if err */
+ fsnotify_put_mark(mark);
++ lockdep_on();
+
+ return err;
+}
+ group = mark->group;
+ fsnotify_get_group(group);
+ spin_unlock(&mark->lock);
++ lockdep_off();
+ fsnotify_destroy_mark(mark, group);
+ fsnotify_put_group(group);
++ lockdep_on();
+
+ /* free hn by myself */
+ return 0;
+static char *au_hfsn_name(u32 mask)
+{
+#ifdef CONFIG_AUFS_DEBUG
-+#define test_ret(flag) if (mask & flag) \
-+ return #flag;
++#define test_ret(flag) \
++ do { \
++ if (mask & flag) \
++ return #flag; \
++ } while (0)
+ test_ret(FS_ACCESS);
+ test_ret(FS_MODIFY);
+ test_ret(FS_ATTRIB);
+ test_ret(FS_UNMOUNT);
+ test_ret(FS_Q_OVERFLOW);
+ test_ret(FS_IN_IGNORED);
-+ test_ret(FS_IN_ISDIR);
++ test_ret(FS_ISDIR);
+ test_ret(FS_IN_ONESHOT);
+ test_ret(FS_EVENT_ON_CHILD);
+ return "";
+}
+
+static int au_hfsn_handle_event(struct fsnotify_group *group,
++ struct inode *inode,
+ struct fsnotify_mark *inode_mark,
+ struct fsnotify_mark *vfsmount_mark,
-+ struct fsnotify_event *event)
++ u32 mask, void *data, int data_type,
++ const unsigned char *file_name, u32 cookie)
+{
+ int err;
+ struct au_hnotify *hnotify;
+ struct inode *h_dir, *h_inode;
-+ __u32 mask;
-+ struct qstr h_child_qstr = QSTR_INIT(event->file_name, event->name_len);
++ struct qstr h_child_qstr = QSTR_INIT(file_name, strlen(file_name));
+
-+ AuDebugOn(event->data_type != FSNOTIFY_EVENT_INODE);
++ AuDebugOn(data_type != FSNOTIFY_EVENT_INODE);
+
+ err = 0;
+ /* if FS_UNMOUNT happens, there must be another bug */
-+ mask = event->mask;
+ AuDebugOn(mask & FS_UNMOUNT);
+ if (mask & (FS_IN_IGNORED | FS_UNMOUNT))
+ goto out;
+
-+ h_dir = event->to_tell;
-+ h_inode = event->inode;
++ h_dir = inode;
++ h_inode = NULL;
+#ifdef AuDbgHnotify
-+ au_debug(1);
++ au_debug_on();
+ if (1 || h_child_qstr.len != sizeof(AUFS_XINO_FNAME) - 1
+ || strncmp(h_child_qstr.name, AUFS_XINO_FNAME, h_child_qstr.len)) {
+ AuDbg("i%lu, mask 0x%x %s, hcname %.*s, hi%lu\n",
+ AuLNPair(&h_child_qstr), h_inode ? h_inode->i_ino : 0);
+ /* WARN_ON(1); */
+ }
-+ au_debug(0);
++ au_debug_off();
+#endif
+
+ AuDebugOn(!inode_mark);
+ return err;
+}
+
-+/* isn't it waste to ask every registered 'group'? */
-+/* copied from linux/fs/notify/inotify/inotify_fsnotiry.c */
-+/* it should be exported to modules */
-+static bool au_hfsn_should_send_event(struct fsnotify_group *group,
-+ struct inode *h_inode,
-+ struct fsnotify_mark *inode_mark,
-+ struct fsnotify_mark *vfsmount_mark,
-+ __u32 mask, void *data, int data_type)
-+{
-+ mask = (mask & ~FS_EVENT_ON_CHILD);
-+ return inode_mark->mask & mask;
-+}
-+
+static struct fsnotify_ops au_hfsn_ops = {
-+ .should_send_event = au_hfsn_should_send_event,
+ .handle_event = au_hfsn_handle_event,
+ .free_group_priv = au_hfsn_free_group
+};
+ struct au_br_hfsnotify *hfsn;
+
+ hfsn = br->br_hfsn;
-+ if (hfsn)
++ if (hfsn) {
++ lockdep_off();
+ fsnotify_put_group(hfsn->hfsn_group);
++ lockdep_on();
++ }
+}
+
+static int au_hfsn_init_br(struct au_branch *br, int perm)
+};
diff -urN /usr/share/empty/fs/aufs/hfsplus.c linux/fs/aufs/hfsplus.c
--- /usr/share/empty/fs/aufs/hfsplus.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/hfsplus.c 2013-02-19 08:40:03.946892891 +0100
-@@ -0,0 +1,57 @@
++++ linux/fs/aufs/hfsplus.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,56 @@
+/*
-+ * Copyright (C) 2010-2013 Junjiro R. Okajima
++ * Copyright (C) 2010-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+
+#include "aufs.h"
+
-+struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex)
++struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex,
++ int force_wr)
+{
+ struct file *h_file;
+ struct dentry *h_dentry;
+ h_dentry = au_h_dptr(dentry, bindex);
+ AuDebugOn(!h_dentry);
+ AuDebugOn(!h_dentry->d_inode);
-+ IMustLock(h_dentry->d_inode);
+
+ h_file = NULL;
+ if (au_test_hfsplus(h_dentry->d_sb)
-+ && S_ISREG(h_dentry->d_inode->i_mode))
++ && d_is_reg(h_dentry))
+ h_file = au_h_open(dentry, bindex,
+ O_RDONLY | O_NOATIME | O_LARGEFILE,
-+ /*file*/NULL);
++ /*file*/NULL, force_wr);
+ return h_file;
+}
+
+}
diff -urN /usr/share/empty/fs/aufs/hnotify.c linux/fs/aufs/hnotify.c
--- /usr/share/empty/fs/aufs/hnotify.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/hnotify.c 2013-03-14 20:07:41.041453062 +0100
-@@ -0,0 +1,713 @@
++++ linux/fs/aufs/hnotify.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,714 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ int err;
+ struct dentry *d;
+ struct qstr *dname;
-+ struct hlist_node *p;
+
+ err = 1;
+ if (unlikely(inode->i_ino == AUFS_ROOT_INO)) {
+ AuDebugOn(!name);
+ au_iigen_dec(inode);
+ spin_lock(&inode->i_lock);
-+ hlist_for_each_entry(d, p, &inode->i_dentry, d_alias) {
++ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) {
+ spin_lock(&d->d_lock);
+ dname = &d->d_name;
+ if (dname->len != nlen
+ spin_unlock(&inode->i_lock);
+ } else {
+ au_fset_si(au_sbi(inode->i_sb), FAILED_REFRESH_DIR);
-+ d = d_find_alias(inode);
++ d = d_find_any_alias(inode);
+ if (!d) {
+ au_iigen_dec(inode);
+ goto out;
+static int hn_job(struct hn_job_args *a)
+{
+ const unsigned int isdir = au_ftest_hnjob(a->flags, ISDIR);
++ int e;
+
+ /* reset xino */
+ if (au_ftest_hnjob(a->flags, XINO0) && a->inode)
+ && a->inode
+ && a->h_inode) {
+ mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD);
-+ if (!a->h_inode->i_nlink)
++ if (!a->h_inode->i_nlink
++ && !(a->h_inode->i_state & I_LINKABLE))
+ hn_xino(a->inode, a->h_inode); /* ignore this error */
+ mutex_unlock(&a->h_inode->i_mutex);
+ }
+
+ /* make the generation obsolete */
+ if (au_ftest_hnjob(a->flags, GEN)) {
-+ int err = -1;
++ e = -1;
+ if (a->inode)
-+ err = hn_gen_by_inode(a->h_name, a->h_nlen, a->inode,
++ e = hn_gen_by_inode(a->h_name, a->h_nlen, a->inode,
+ isdir);
-+ if (err && a->dentry)
++ if (e && a->dentry)
+ hn_gen_by_name(a->dentry, isdir);
+ /* ignore this error */
+ }
+ if (au_ftest_hnjob(a->flags, MNTPNT)
+ && a->dentry
+ && d_mountpoint(a->dentry))
-+ pr_warn("mount-point %.*s is removed or renamed\n",
-+ AuDLNPair(a->dentry));
++ pr_warn("mount-point %pd is removed or renamed\n", a->dentry);
+
+ return 0;
+}
+ struct dentry *dentry, *d, *parent;
+ struct qstr *dname;
+
-+ parent = d_find_alias(dir);
++ parent = d_find_any_alias(dir);
+ if (!parent)
+ return NULL;
+
+ dentry = NULL;
+ spin_lock(&parent->d_lock);
-+ list_for_each_entry(d, &parent->d_subdirs, d_u.d_child) {
-+ /* AuDbg("%.*s\n", AuDLNPair(d)); */
++ list_for_each_entry(d, &parent->d_subdirs, d_child) {
++ /* AuDbg("%pd\n", d); */
+ spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
+ dname = &d->d_name;
+ if (dname->len != nlen || memcmp(dname->name, name, nlen))
+ au_digen_dec(d);
+ else
+ goto cont_unlock;
-+ if (d->d_count) {
++ if (au_dcount(d) > 0) {
+ dentry = dget_dlock(d);
+ spin_unlock(&d->d_lock);
+ break;
+ }
+
-+ cont_unlock:
++cont_unlock:
+ spin_unlock(&d->d_lock);
+ }
+ spin_unlock(&parent->d_lock);
+ au_fset_hnjob(flags[AuHn_CHILD], MNTPNT);
+ /*FALLTHROUGH*/
+ case FS_CREATE:
-+ AuDebugOn(!h_child_name || !h_child_inode);
++ AuDebugOn(!h_child_name);
+ break;
+
+ case FS_DELETE:
+ p[len] = 0;
+ }
+
++ /* NFS fires the event for silly-renamed one from kworker */
+ f = 0;
-+ if (!dir->i_nlink)
++ if (!dir->i_nlink
++ || (au_test_nfs(h_dir->i_sb) && (mask & FS_DELETE)))
+ f = AuWkq_NEST;
+ err = au_wkq_nowait(au_hn_bh, args, dir->i_sb, f);
+ if (unlikely(err)) {
+}
diff -urN /usr/share/empty/fs/aufs/iinfo.c linux/fs/aufs/iinfo.c
--- /usr/share/empty/fs/aufs/iinfo.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/iinfo.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,276 @@
++++ linux/fs/aufs/iinfo.c 2015-06-22 08:27:37.884168534 +0200
+@@ -0,0 +1,277 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ struct inode *h_i;
+
+ h_i = iinfo->ii_hinode[0 + bindex].hi_inode;
-+ if (h_i && !h_i->i_nlink)
++ if (h_i
++ && !h_i->i_nlink
++ && !(h_i->i_state & I_LINKABLE))
+ au_set_h_iptr(inode, bindex, NULL, 0);
+ }
+ }
+}
diff -urN /usr/share/empty/fs/aufs/inode.c linux/fs/aufs/inode.c
--- /usr/share/empty/fs/aufs/inode.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/inode.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,492 @@
++++ linux/fs/aufs/inode.c 2015-06-22 08:27:37.884168534 +0200
+@@ -0,0 +1,495 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ case S_IFSOCK:
+ btail = au_dbtail(dentry);
+ inode->i_op = &aufs_iop;
-+ au_init_special_fop(inode, mode, h_inode->i_rdev);
++ init_special_inode(inode, mode, h_inode->i_rdev);
+ break;
+ default:
+ AuIOErr("Unknown file type 0%o\n", mode);
+ au_igrab(h_dentry->d_inode), flags);
+ }
+ au_cpup_attr_all(inode, /*force*/1);
++ /*
++ * to force calling aufs_get_acl() every time,
++ * do not call cache_no_acl() for aufs inode.
++ */
+
+out:
+ return err;
+/* todo: return with unlocked? */
+struct inode *au_new_inode(struct dentry *dentry, int must_new)
+{
-+ struct inode *inode, *h_inode;
++ struct inode *inode;
+ struct dentry *h_dentry;
+ struct super_block *sb;
+ struct mutex *mtx;
+ sb = dentry->d_sb;
+ bstart = au_dbstart(dentry);
+ h_dentry = au_h_dptr(dentry, bstart);
-+ h_inode = h_dentry->d_inode;
-+ h_ino = h_inode->i_ino;
++ h_ino = h_dentry->d_inode->i_ino;
+
+ /*
+ * stop 'race'-ing between hardlinks under different
+ * parents.
+ */
+ mtx = NULL;
-+ if (!S_ISDIR(h_inode->i_mode))
++ if (!d_is_dir(h_dentry))
+ mtx = &au_sbr(sb, bstart)->br_xino.xi_nondir_mtx;
+
+new_ino:
+ AuDbg("%lx, new %d\n", inode->i_state, !!(inode->i_state & I_NEW));
+ if (inode->i_state & I_NEW) {
+ /* verbose coding for lock class name */
-+ if (unlikely(S_ISLNK(h_inode->i_mode)))
++ if (unlikely(d_is_symlink(h_dentry)))
+ au_rw_class(&au_ii(inode)->ii_rwsem,
+ au_lc_key + AuLcSymlink_IIINFO);
-+ else if (unlikely(S_ISDIR(h_inode->i_mode)))
++ else if (unlikely(d_is_dir(h_dentry)))
+ au_rw_class(&au_ii(inode)->ii_rwsem,
+ au_lc_key + AuLcDir_IIINFO);
+ else /* likely */
+
+ if (unlikely(au_test_fs_unique_ino(h_dentry->d_inode)))
+ AuWarn1("Warning: Un-notified UDBA or repeatedly renamed dir,"
-+ " b%d, %s, %.*s, hi%lu, i%lu.\n",
-+ bstart, au_sbtype(h_dentry->d_sb), AuDLNPair(dentry),
++ " b%d, %s, %pd, hi%lu, i%lu.\n",
++ bstart, au_sbtype(h_dentry->d_sb), dentry,
+ (unsigned long)h_ino, (unsigned long)ino);
+ ino = 0;
+ err = au_xino_write(sb, bstart, h_ino, /*ino*/0);
+ struct inode *inode)
+{
+ int err;
++ struct inode *hi;
+
+ err = au_br_rdonly(au_sbr(sb, bindex));
+
+ * permission check is unnecessary since vfsub routine
+ * will be called later
+ */
-+ struct inode *hi = au_h_iptr(inode, bindex);
++ hi = au_h_iptr(inode, bindex);
+ if (hi)
+ err = IS_IMMUTABLE(hi) ? -EROFS : 0;
+ }
+}
diff -urN /usr/share/empty/fs/aufs/inode.h linux/fs/aufs/inode.h
--- /usr/share/empty/fs/aufs/inode.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/inode.h 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,588 @@
++++ linux/fs/aufs/inode.h 2015-06-22 08:27:37.884168534 +0200
+@@ -0,0 +1,673 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ struct dentry *parent;
+ struct au_hinode *hdir;
+ struct vfsmount *h_mnt;
++
++ /* temporary unlock/relock for copyup */
++ struct dentry *h_dentry, *h_parent;
++ struct au_branch *br;
++ struct task_struct *task;
+};
+
++void au_pin_hdir_unlock(struct au_pin *p);
++int au_pin_hdir_lock(struct au_pin *p);
++int au_pin_hdir_relock(struct au_pin *p);
++void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task);
++void au_pin_hdir_acquire_nest(struct au_pin *p);
++void au_pin_hdir_release(struct au_pin *p);
++
+/* ---------------------------------------------------------------------- */
+
+static inline struct au_iinfo *au_ii(struct inode *inode)
+/* au_wr_dir flags */
+#define AuWrDir_ADD_ENTRY 1
+#define AuWrDir_ISDIR (1 << 1)
++#define AuWrDir_TMPFILE (1 << 2)
+#define au_ftest_wrdir(flags, name) ((flags) & AuWrDir_##name)
+#define au_fset_wrdir(flags, name) \
+ do { (flags) |= AuWrDir_##name; } while (0)
+ unsigned int udba, unsigned char flags) __must_check;
+int au_do_pin(struct au_pin *pin) __must_check;
+void au_unpin(struct au_pin *pin);
++int au_reval_for_attr(struct dentry *dentry, unsigned int sigen);
++
++#define AuIcpup_DID_CPUP 1
++#define au_ftest_icpup(flags, name) ((flags) & AuIcpup_##name)
++#define au_fset_icpup(flags, name) \
++ do { (flags) |= AuIcpup_##name; } while (0)
++#define au_fclr_icpup(flags, name) \
++ do { (flags) &= ~AuIcpup_##name; } while (0)
++
++struct au_icpup_args {
++ unsigned char flags;
++ unsigned char pin_flags;
++ aufs_bindex_t btgt;
++ unsigned int udba;
++ struct au_pin pin;
++ struct path h_path;
++ struct inode *h_inode;
++};
++
++int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
++ struct au_icpup_args *a);
++
++int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path);
+
+/* i_op_add.c */
+int au_may_add(struct dentry *dentry, aufs_bindex_t bindex,
+int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname);
+int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+ bool want_excl);
++struct vfsub_aopen_args;
++int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
++ struct vfsub_aopen_args *args);
++int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode);
+int aufs_link(struct dentry *src_dentry, struct inode *dir,
+ struct dentry *dentry);
+int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
+#ifdef CONFIG_PROC_FS
+/* plink.c */
+int au_plink_maint(struct super_block *sb, int flags);
++struct au_sbinfo;
+void au_plink_maint_leave(struct au_sbinfo *sbinfo);
+int au_plink_maint_enter(struct super_block *sb);
+#ifdef CONFIG_AUFS_DEBUG
+AuStubVoid(au_plink_half_refresh, struct super_block *sb, aufs_bindex_t br_id);
+#endif /* CONFIG_PROC_FS */
+
++#ifdef CONFIG_AUFS_XATTR
++/* xattr.c */
++int au_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, int ignore_flags,
++ unsigned int verbose);
++ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size);
++ssize_t aufs_getxattr(struct dentry *dentry, const char *name, void *value,
++ size_t size);
++int aufs_setxattr(struct dentry *dentry, const char *name, const void *value,
++ size_t size, int flags);
++int aufs_removexattr(struct dentry *dentry, const char *name);
++
++/* void au_xattr_init(struct super_block *sb); */
++#else
++AuStubInt0(au_cpup_xattr, struct dentry *h_dst, struct dentry *h_src,
++ int ignore_flags, unsigned int verbose);
++/* AuStubVoid(au_xattr_init, struct super_block *sb); */
++#endif
++
++#ifdef CONFIG_FS_POSIX_ACL
++struct posix_acl *aufs_get_acl(struct inode *inode, int type);
++int aufs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
++#endif
++
++#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
++enum {
++ AU_XATTR_SET,
++ AU_XATTR_REMOVE,
++ AU_ACL_SET
++};
++
++struct au_srxattr {
++ int type;
++ union {
++ struct {
++ const char *name;
++ const void *value;
++ size_t size;
++ int flags;
++ } set;
++ struct {
++ const char *name;
++ } remove;
++ struct {
++ struct posix_acl *acl;
++ int type;
++ } acl_set;
++ } u;
++};
++ssize_t au_srxattr(struct dentry *dentry, struct au_srxattr *arg);
++#endif
++
+/* ---------------------------------------------------------------------- */
+
+/* lock subclass for iinfo */
+ }
+}
+
++#if 0 /* reserved */
+static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent)
+{
+ if (pin) {
+ pin->parent = dget(parent);
+ }
+}
++#endif
+
+/* ---------------------------------------------------------------------- */
+
+}
+
+#else
-+static inline
-+int au_hn_alloc(struct au_hinode *hinode __maybe_unused,
-+ struct inode *inode __maybe_unused)
-+{
-+ return -EOPNOTSUPP;
-+}
-+
-+static inline struct au_hnotify *au_hn(struct au_hinode *hinode)
-+{
-+ return NULL;
-+}
-+
++AuStub(int, au_hn_alloc, return -EOPNOTSUPP,
++ struct au_hinode *hinode __maybe_unused,
++ struct inode *inode __maybe_unused)
++AuStub(struct au_hnotify *, au_hn, return NULL, struct au_hinode *hinode)
+AuStubVoid(au_hn_free, struct au_hinode *hinode __maybe_unused)
+AuStubVoid(au_hn_ctl, struct au_hinode *hinode __maybe_unused,
+ int do_set __maybe_unused)
+#endif /* __AUFS_INODE_H__ */
diff -urN /usr/share/empty/fs/aufs/ioctl.c linux/fs/aufs/ioctl.c
--- /usr/share/empty/fs/aufs/ioctl.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/ioctl.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,196 @@
++++ linux/fs/aufs/ioctl.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,219 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * ioctl
+ * plink-management and readdir in userspace.
+ * assist the pathconf(3) wrapper library.
++ * move-down
++ * File-based Hierarchical Storage Management.
+ */
+
++#include <linux/compat.h>
++#include <linux/file.h>
+#include "aufs.h"
+
+static int au_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg)
+ goto out;
+ }
+
-+ fd = get_unused_fd();
++ fd = get_unused_fd_flags(0);
+ err = fd;
+ if (unlikely(fd < 0))
+ goto out;
+ }
+ AuDbg("wbi %d\n", wbi);
+ if (wbi >= 0)
-+ h_file = au_h_open(root, wbi, wbrfd.oflags, NULL);
++ h_file = au_h_open(root, wbi, wbrfd.oflags, NULL,
++ /*force_wr*/0);
+
+out_unlock:
+ aufs_read_unlock(root, AuLock_IR);
+long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ long err;
++ struct dentry *dentry;
+
+ switch (cmd) {
+ case AUFS_CTL_RDU:
+ err = au_ibusy_ioctl(file, arg);
+ break;
+
++ case AUFS_CTL_BRINFO:
++ err = au_brinfo_ioctl(file, arg);
++ break;
++
++ case AUFS_CTL_FHSM_FD:
++ dentry = file->f_path.dentry;
++ if (IS_ROOT(dentry))
++ err = au_fhsm_fd(dentry->d_sb, arg);
++ else
++ err = -ENOTTY;
++ break;
++
+ default:
+ /* do not call the lower */
+ AuDbg("0x%x\n", cmd);
+ long err;
+
+ switch (cmd) {
++ case AUFS_CTL_MVDOWN:
++ err = au_mvdown(file->f_path.dentry, (void __user *)arg);
++ break;
++
+ case AUFS_CTL_WBR_FD:
+ err = au_wbr_fd(&file->f_path, (void __user *)arg);
+ break;
+ err = au_ibusy_compat_ioctl(file, arg);
+ break;
+
++ case AUFS_CTL_BRINFO:
++ err = au_brinfo_compat_ioctl(file, arg);
++ break;
++
+ default:
+ err = aufs_ioctl_dir(file, cmd, arg);
+ }
+ return err;
+}
+
-+#if 0 /* unused yet */
+long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ return aufs_ioctl_nondir(file, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
-+#endif
diff -urN /usr/share/empty/fs/aufs/i_op_add.c linux/fs/aufs/i_op_add.c
--- /usr/share/empty/fs/aufs/i_op_add.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/i_op_add.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,713 @@
++++ linux/fs/aufs/i_op_add.c 2015-06-22 08:27:37.880835119 +0200
+@@ -0,0 +1,930 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ int err, rerr;
+ aufs_bindex_t bwh;
+ struct path h_path;
++ struct super_block *sb;
+ struct inode *inode, *h_dir;
+ struct dentry *wh;
+
+ bwh = -1;
++ sb = dir->i_sb;
+ if (wh_dentry) {
+ h_dir = wh_dentry->d_parent->d_inode; /* dir inode is locked */
+ IMustLock(h_dir);
+ AuDebugOn(au_h_iptr(dir, bindex) != h_dir);
+ bwh = au_dbwh(dentry);
+ h_path.dentry = wh_dentry;
-+ h_path.mnt = au_sbr_mnt(dir->i_sb, bindex);
++ h_path.mnt = au_sbr_mnt(sb, bindex);
+ err = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path,
+ dentry);
+ if (unlikely(err))
+ d_instantiate(dentry, inode);
+ dir = dentry->d_parent->d_inode; /* dir inode is locked */
+ IMustLock(dir);
-+ if (au_ibstart(dir) == au_dbstart(dentry))
-+ au_cpup_attr_timesizes(dir);
++ au_dir_ts(dir, bindex);
+ dir->i_version++;
++ au_fhsm_wrote(sb, bindex, /*force*/0);
+ return 0; /* success */
+ }
+
+ wh = au_wh_create(dentry, bwh, wh_dentry->d_parent);
+ rerr = PTR_ERR(wh);
+ if (IS_ERR(wh)) {
-+ AuIOErr("%.*s reverting whiteout failed(%d, %d)\n",
-+ AuDLNPair(dentry), err, rerr);
++ AuIOErr("%pd reverting whiteout failed(%d, %d)\n",
++ dentry, err, rerr);
+ err = -EIO;
+ } else
+ dput(wh);
+ unsigned int udba;
+ aufs_bindex_t bcpup;
+
-+ AuDbg("%.*s\n", AuDLNPair(dentry));
++ AuDbg("%pd\n", dentry);
+
+ err = au_wr_dir(dentry, src_dentry, wr_dir_args);
+ bcpup = err;
+ if (dt) {
+ struct path tmp = {
+ .dentry = h_parent,
-+ .mnt = br->br_mnt
++ .mnt = au_br_mnt(br)
+ };
+ au_dtime_store(dt, au_pinned_parent(pin), &tmp);
+ }
+ if (bcpup != au_dbwh(dentry))
+ goto out; /* success */
+
++ /*
++ * ENAMETOOLONG here means that if we allowed create such name, then it
++ * would not be able to removed in the future. So we don't allow such
++ * name here and we don't handle ENAMETOOLONG differently here.
++ */
+ wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br);
+
+out_unpin:
+ int type;
+ union {
+ struct {
-+ umode_t mode;
-+ bool want_excl;
++ umode_t mode;
++ bool want_excl;
++ bool try_aopen;
++ struct vfsub_aopen_args *aopen;
+ } c;
+ struct {
+ const char *symname;
+static int add_simple(struct inode *dir, struct dentry *dentry,
+ struct simple_arg *arg)
+{
-+ int err;
++ int err, rerr;
+ aufs_bindex_t bstart;
+ unsigned char created;
-+ struct au_dtime dt;
-+ struct au_pin pin;
-+ struct path h_path;
++ const unsigned char try_aopen
++ = (arg->type == Creat && arg->u.c.try_aopen);
+ struct dentry *wh_dentry, *parent;
+ struct inode *h_dir;
-+ struct au_wr_dir_args wr_dir_args = {
-+ .force_btgt = -1,
-+ .flags = AuWrDir_ADD_ENTRY
-+ };
++ struct super_block *sb;
++ struct au_branch *br;
++ /* to reuduce stack size */
++ struct {
++ struct au_dtime dt;
++ struct au_pin pin;
++ struct path h_path;
++ struct au_wr_dir_args wr_dir_args;
++ } *a;
+
-+ AuDbg("%.*s\n", AuDLNPair(dentry));
++ AuDbg("%pd\n", dentry);
+ IMustLock(dir);
+
-+ parent = dentry->d_parent; /* dir inode is locked */
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
-+ if (unlikely(err))
++ err = -ENOMEM;
++ a = kmalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
+ goto out;
++ a->wr_dir_args.force_btgt = -1;
++ a->wr_dir_args.flags = AuWrDir_ADD_ENTRY;
++
++ parent = dentry->d_parent; /* dir inode is locked */
++ if (!try_aopen) {
++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
++ if (unlikely(err))
++ goto out_free;
++ }
+ err = au_d_may_add(dentry);
+ if (unlikely(err))
+ goto out_unlock;
-+ di_write_lock_parent(parent);
-+ wh_dentry = lock_hdir_lkup_wh(dentry, &dt, /*src_dentry*/NULL, &pin,
-+ &wr_dir_args);
++ if (!try_aopen)
++ di_write_lock_parent(parent);
++ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL,
++ &a->pin, &a->wr_dir_args);
+ err = PTR_ERR(wh_dentry);
+ if (IS_ERR(wh_dentry))
+ goto out_parent;
+
+ bstart = au_dbstart(dentry);
-+ h_path.dentry = au_h_dptr(dentry, bstart);
-+ h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart);
-+ h_dir = au_pinned_h_dir(&pin);
++ sb = dentry->d_sb;
++ br = au_sbr(sb, bstart);
++ a->h_path.dentry = au_h_dptr(dentry, bstart);
++ a->h_path.mnt = au_br_mnt(br);
++ h_dir = au_pinned_h_dir(&a->pin);
+ switch (arg->type) {
+ case Creat:
-+ err = vfsub_create(h_dir, &h_path, arg->u.c.mode,
-+ arg->u.c.want_excl);
++ err = 0;
++ if (!try_aopen || !h_dir->i_op->atomic_open)
++ err = vfsub_create(h_dir, &a->h_path, arg->u.c.mode,
++ arg->u.c.want_excl);
++ else
++ err = vfsub_atomic_open(h_dir, a->h_path.dentry,
++ arg->u.c.aopen, br);
+ break;
+ case Symlink:
-+ err = vfsub_symlink(h_dir, &h_path, arg->u.s.symname);
++ err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname);
+ break;
+ case Mknod:
-+ err = vfsub_mknod(h_dir, &h_path, arg->u.m.mode, arg->u.m.dev);
++ err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode,
++ arg->u.m.dev);
+ break;
+ default:
+ BUG();
+ err = epilog(dir, bstart, wh_dentry, dentry);
+
+ /* revert */
-+ if (unlikely(created && err && h_path.dentry->d_inode)) {
-+ int rerr;
-+ rerr = vfsub_unlink(h_dir, &h_path, /*force*/0);
++ if (unlikely(created && err && a->h_path.dentry->d_inode)) {
++ /* no delegation since it is just created */
++ rerr = vfsub_unlink(h_dir, &a->h_path, /*delegated*/NULL,
++ /*force*/0);
+ if (rerr) {
-+ AuIOErr("%.*s revert failure(%d, %d)\n",
-+ AuDLNPair(dentry), err, rerr);
++ AuIOErr("%pd revert failure(%d, %d)\n",
++ dentry, err, rerr);
+ err = -EIO;
+ }
-+ au_dtime_revert(&dt);
++ au_dtime_revert(&a->dt);
+ }
+
-+ au_unpin(&pin);
++ if (!err && try_aopen && !h_dir->i_op->atomic_open)
++ *arg->u.c.aopen->opened |= FILE_CREATED;
++
++ au_unpin(&a->pin);
+ dput(wh_dentry);
+
+out_parent:
-+ di_write_unlock(parent);
++ if (!try_aopen)
++ di_write_unlock(parent);
+out_unlock:
+ if (unlikely(err)) {
+ au_update_dbstart(dentry);
+ d_drop(dentry);
+ }
-+ aufs_read_unlock(dentry, AuLock_DW);
++ if (!try_aopen)
++ aufs_read_unlock(dentry, AuLock_DW);
++out_free:
++ kfree(a);
+out:
+ return err;
+}
+ return add_simple(dir, dentry, &arg);
+}
+
++int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
++ struct vfsub_aopen_args *aopen_args)
++{
++ struct simple_arg arg = {
++ .type = Creat,
++ .u.c = {
++ .mode = aopen_args->create_mode,
++ .want_excl = aopen_args->open_flag & O_EXCL,
++ .try_aopen = true,
++ .aopen = aopen_args
++ }
++ };
++ return add_simple(dir, dentry, &arg);
++}
++
++int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
++{
++ int err;
++ aufs_bindex_t bindex;
++ struct super_block *sb;
++ struct dentry *parent, *h_parent, *h_dentry;
++ struct inode *h_dir, *inode;
++ struct vfsmount *h_mnt;
++ struct au_wr_dir_args wr_dir_args = {
++ .force_btgt = -1,
++ .flags = AuWrDir_TMPFILE
++ };
++
++ /* copy-up may happen */
++ mutex_lock(&dir->i_mutex);
++
++ sb = dir->i_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (unlikely(err))
++ goto out;
++
++ err = au_di_init(dentry);
++ if (unlikely(err))
++ goto out_si;
++
++ err = -EBUSY;
++ parent = d_find_any_alias(dir);
++ AuDebugOn(!parent);
++ di_write_lock_parent(parent);
++ if (unlikely(parent->d_inode != dir))
++ goto out_parent;
++
++ err = au_digen_test(parent, au_sigen(sb));
++ if (unlikely(err))
++ goto out_parent;
++
++ bindex = au_dbstart(parent);
++ au_set_dbstart(dentry, bindex);
++ au_set_dbend(dentry, bindex);
++ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args);
++ bindex = err;
++ if (unlikely(err < 0))
++ goto out_parent;
++
++ err = -EOPNOTSUPP;
++ h_dir = au_h_iptr(dir, bindex);
++ if (unlikely(!h_dir->i_op->tmpfile))
++ goto out_parent;
++
++ h_mnt = au_sbr_mnt(sb, bindex);
++ err = vfsub_mnt_want_write(h_mnt);
++ if (unlikely(err))
++ goto out_parent;
++
++ h_parent = au_h_dptr(parent, bindex);
++ err = inode_permission(h_parent->d_inode, MAY_WRITE | MAY_EXEC);
++ if (unlikely(err))
++ goto out_mnt;
++
++ err = -ENOMEM;
++ h_dentry = d_alloc(h_parent, &dentry->d_name);
++ if (unlikely(!h_dentry))
++ goto out_mnt;
++
++ err = h_dir->i_op->tmpfile(h_dir, h_dentry, mode);
++ if (unlikely(err))
++ goto out_dentry;
++
++ au_set_dbstart(dentry, bindex);
++ au_set_dbend(dentry, bindex);
++ au_set_h_dptr(dentry, bindex, dget(h_dentry));
++ inode = au_new_inode(dentry, /*must_new*/1);
++ if (IS_ERR(inode)) {
++ err = PTR_ERR(inode);
++ au_set_h_dptr(dentry, bindex, NULL);
++ au_set_dbstart(dentry, -1);
++ au_set_dbend(dentry, -1);
++ } else {
++ if (!inode->i_nlink)
++ set_nlink(inode, 1);
++ d_tmpfile(dentry, inode);
++ au_di(dentry)->di_tmpfile = 1;
++
++ /* update without i_mutex */
++ if (au_ibstart(dir) == au_dbstart(dentry))
++ au_cpup_attr_timesizes(dir);
++ }
++
++out_dentry:
++ dput(h_dentry);
++out_mnt:
++ vfsub_mnt_drop_write(h_mnt);
++out_parent:
++ di_write_unlock(parent);
++ dput(parent);
++ di_write_unlock(dentry);
++ if (!err)
++#if 0
++ /* verbose coding for lock class name */
++ au_rw_class(&au_di(dentry)->di_rwsem,
++ au_lc_key + AuLcNonDir_DIINFO);
++#else
++ ;
++#endif
++ else {
++ au_di_fin(dentry);
++ dentry->d_fsdata = NULL;
++ }
++out_si:
++ si_read_unlock(sb);
++out:
++ mutex_unlock(&dir->i_mutex);
++ return err;
++}
++
+/* ---------------------------------------------------------------------- */
+
+struct au_link_args {
+{
+ int err;
+ struct dentry *h_src_dentry;
-+ struct mutex *h_mtx;
-+ struct file *h_file;
++ struct au_cp_generic cpg = {
++ .dentry = src_dentry,
++ .bdst = a->bdst,
++ .bsrc = a->bsrc,
++ .len = -1,
++ .pin = &a->pin,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN /* | AuCpup_KEEPLINO */
++ };
+
+ di_read_lock_parent(a->src_parent, AuLock_IR);
+ err = au_test_and_cpup_dirs(src_dentry, a->bdst);
+ goto out;
+
+ h_src_dentry = au_h_dptr(src_dentry, a->bsrc);
-+ h_mtx = &h_src_dentry->d_inode->i_mutex;
+ err = au_pin(&a->pin, src_dentry, a->bdst,
+ au_opt_udba(src_dentry->d_sb),
+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+ if (unlikely(err))
+ goto out;
-+ mutex_lock_nested(h_mtx, AuLsc_I_CHILD);
-+ h_file = au_h_open_pre(src_dentry, a->bsrc);
-+ if (IS_ERR(h_file)) {
-+ err = PTR_ERR(h_file);
-+ h_file = NULL;
-+ } else
-+ err = au_sio_cpup_simple(src_dentry, a->bdst, -1,
-+ AuCpup_DTIME /* | AuCpup_KEEPLINO */);
-+ mutex_unlock(h_mtx);
-+ au_h_open_post(src_dentry, a->bsrc, h_file);
++
++ err = au_sio_cpup_simple(&cpg);
+ au_unpin(&a->pin);
+
+out:
+ return err;
+}
+
-+static int au_cpup_or_link(struct dentry *src_dentry, struct au_link_args *a)
++static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry,
++ struct au_link_args *a)
+{
+ int err;
+ unsigned char plink;
-+ struct inode *h_inode, *inode;
++ aufs_bindex_t bend;
+ struct dentry *h_src_dentry;
++ struct inode *h_inode, *inode, *delegated;
+ struct super_block *sb;
+ struct file *h_file;
+
+ h_inode = au_h_iptr(inode, a->bdst);
+ if (!h_inode || !h_inode->i_nlink) {
+ /* copyup src_dentry as the name of dentry. */
-+ au_set_dbstart(src_dentry, a->bdst);
-+ au_set_h_dptr(src_dentry, a->bdst, dget(a->h_path.dentry));
-+ h_inode = au_h_dptr(src_dentry, a->bsrc)->d_inode;
-+ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
-+ h_file = au_h_open_pre(src_dentry, a->bsrc);
-+ if (IS_ERR(h_file)) {
++ bend = au_dbend(dentry);
++ if (bend < a->bsrc)
++ au_set_dbend(dentry, a->bsrc);
++ au_set_h_dptr(dentry, a->bsrc,
++ dget(au_h_dptr(src_dentry, a->bsrc)));
++ dget(a->h_path.dentry);
++ au_set_h_dptr(dentry, a->bdst, NULL);
++ AuDbg("temporary d_inode...\n");
++ spin_lock(&dentry->d_lock);
++ dentry->d_inode = src_dentry->d_inode; /* tmp */
++ spin_unlock(&dentry->d_lock);
++ h_file = au_h_open_pre(dentry, a->bsrc, /*force_wr*/0);
++ if (IS_ERR(h_file))
+ err = PTR_ERR(h_file);
-+ h_file = NULL;
-+ } else
-+ err = au_sio_cpup_single(src_dentry, a->bdst, a->bsrc,
-+ -1, AuCpup_KEEPLINO,
-+ a->parent);
-+ mutex_unlock(&h_inode->i_mutex);
-+ au_h_open_post(src_dentry, a->bsrc, h_file);
-+ au_set_h_dptr(src_dentry, a->bdst, NULL);
-+ au_set_dbstart(src_dentry, a->bsrc);
++ else {
++ struct au_cp_generic cpg = {
++ .dentry = dentry,
++ .bdst = a->bdst,
++ .bsrc = -1,
++ .len = -1,
++ .pin = &a->pin,
++ .flags = AuCpup_KEEPLINO
++ };
++ err = au_sio_cpup_simple(&cpg);
++ au_h_open_post(dentry, a->bsrc, h_file);
++ if (!err) {
++ dput(a->h_path.dentry);
++ a->h_path.dentry = au_h_dptr(dentry, a->bdst);
++ } else
++ au_set_h_dptr(dentry, a->bdst,
++ a->h_path.dentry);
++ }
++ spin_lock(&dentry->d_lock);
++ dentry->d_inode = NULL; /* restore */
++ spin_unlock(&dentry->d_lock);
++ AuDbg("temporary d_inode...done\n");
++ au_set_h_dptr(dentry, a->bsrc, NULL);
++ au_set_dbend(dentry, bend);
+ } else {
+ /* the inode of src_dentry already exists on a.bdst branch */
+ h_src_dentry = d_find_alias(h_inode);
+
+ }
+ if (h_src_dentry) {
++ delegated = NULL;
+ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
-+ &a->h_path);
++ &a->h_path, &delegated);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal link\n");
++ iput(delegated);
++ }
+ dput(h_src_dentry);
+ } else {
+ AuIOErr("no dentry found for hi%lu on b%d\n",
+ struct au_dtime dt;
+ struct au_link_args *a;
+ struct dentry *wh_dentry, *h_src_dentry;
-+ struct inode *inode;
++ struct inode *inode, *delegated;
+ struct super_block *sb;
+ struct au_wr_dir_args wr_dir_args = {
+ /* .force_btgt = -1, */
+ AuLock_NOPLM | AuLock_GEN);
+ if (unlikely(err))
+ goto out_kfree;
-+ err = au_d_hashed_positive(src_dentry);
++ err = au_d_linkable(src_dentry);
+ if (unlikely(err))
+ goto out_unlock;
+ err = au_d_may_add(dentry);
+ a->h_path.mnt = au_sbr_mnt(sb, a->bdst);
+ a->bsrc = au_ibstart(inode);
+ h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
++ if (!h_src_dentry && au_di(src_dentry)->di_tmpfile)
++ h_src_dentry = dget(au_hi_wh(inode, a->bsrc));
+ if (!h_src_dentry) {
+ a->bsrc = au_dbstart(src_dentry);
+ h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
+ AuDebugOn(!h_src_dentry);
-+ } else if (IS_ERR(h_src_dentry))
++ } else if (IS_ERR(h_src_dentry)) {
++ err = PTR_ERR(h_src_dentry);
+ goto out_parent;
++ }
+
+ if (au_opt_test(au_mntflags(sb), PLINK)) {
+ if (a->bdst < a->bsrc
+ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */)
-+ err = au_cpup_or_link(src_dentry, a);
-+ else
++ err = au_cpup_or_link(src_dentry, dentry, a);
++ else {
++ delegated = NULL;
+ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
-+ &a->h_path);
++ &a->h_path, &delegated);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal link\n");
++ iput(delegated);
++ }
++ }
+ dput(h_src_dentry);
+ } else {
+ /*
+ if (!err) {
+ h_src_dentry = au_h_dptr(src_dentry, a->bdst);
+ err = -ENOENT;
-+ if (h_src_dentry && h_src_dentry->d_inode)
++ if (h_src_dentry && h_src_dentry->d_inode) {
++ delegated = NULL;
+ err = vfsub_link(h_src_dentry,
+ au_pinned_h_dir(&a->pin),
-+ &a->h_path);
++ &a->h_path, &delegated);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry"
++ " for NFSv4 delegation"
++ " for an internal link\n");
++ iput(delegated);
++ }
++ }
+ }
+ }
+ if (unlikely(err))
+ goto out_revert;
+ }
+
++ au_dir_ts(dir, a->bdst);
+ dir->i_version++;
-+ if (au_ibstart(dir) == au_dbstart(dentry))
-+ au_cpup_attr_timesizes(dir);
+ inc_nlink(inode);
+ inode->i_ctime = dir->i_ctime;
+ d_instantiate(dentry, au_igrab(inode));
+ if (d_unhashed(a->h_path.dentry))
+ /* some filesystem calls d_drop() */
+ d_drop(dentry);
++ /* some filesystems consume an inode even hardlink */
++ au_fhsm_wrote(sb, a->bdst, /*force*/0);
+ goto out_unpin; /* success */
+
+out_revert:
-+ rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path, /*force*/0);
++ /* no delegation since it is just created */
++ rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path,
++ /*delegated*/NULL, /*force*/0);
+ if (unlikely(rerr)) {
-+ AuIOErr("%.*s reverting failed(%d, %d)\n",
-+ AuDLNPair(dentry), err, rerr);
++ AuIOErr("%pd reverting failed(%d, %d)\n", dentry, err, rerr);
+ err = -EIO;
+ }
+ au_dtime_revert(&dt);
+out_kfree:
+ kfree(a);
+out:
++ AuTraceErr(err);
+ return err;
+}
+
+ rerr = au_diropq_remove(dentry, bindex);
+ mutex_unlock(h_mtx);
+ if (rerr) {
-+ AuIOErr("%.*s reverting diropq failed(%d, %d)\n",
-+ AuDLNPair(dentry), err, rerr);
++ AuIOErr("%pd reverting diropq failed(%d, %d)\n",
++ dentry, err, rerr);
+ err = -EIO;
+ }
+ }
+ AuLabel(revert dir);
+ rerr = vfsub_rmdir(au_pinned_h_dir(&a->pin), &h_path);
+ if (rerr) {
-+ AuIOErr("%.*s reverting dir failed(%d, %d)\n",
-+ AuDLNPair(dentry), err, rerr);
++ AuIOErr("%pd reverting dir failed(%d, %d)\n",
++ dentry, err, rerr);
+ err = -EIO;
+ }
+ au_dtime_revert(&a->dt);
+}
diff -urN /usr/share/empty/fs/aufs/i_op.c linux/fs/aufs/i_op.c
--- /usr/share/empty/fs/aufs/i_op.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/i_op.c 2013-03-14 20:07:41.041453062 +0100
-@@ -0,0 +1,1030 @@
++++ linux/fs/aufs/i_op.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,1445 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * - skip the lower fs test in the case of write to ro branch.
+ * - nfs dir permission write check is optimized, but a policy for
+ * link/rename requires a real check.
++ * - nfs always sets MS_POSIXACL regardless its mount option 'noacl.'
++ * in this case, generic_permission() returns -EOPNOTSUPP.
+ */
+ if ((write_mask && !au_br_writable(brperm))
+ || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode)
+ && write_mask && !(mask & MAY_READ))
+ || !h_inode->i_op->permission) {
+ /* AuLabel(generic_permission); */
++ /* AuDbg("get_acl %pf\n", h_inode->i_op->get_acl); */
+ err = generic_permission(h_inode, mask);
++ if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode))
++ err = h_inode->i_op->permission(h_inode, mask);
++ AuTraceErr(err);
+ } else {
+ /* AuLabel(h_inode->permission); */
+ err = h_inode->i_op->permission(h_inode, mask);
+ goto out;
+#endif
+
-+ if (!isdir || write_mask) {
++ if (!isdir
++ || write_mask
++ || au_opt_test(au_mntflags(sb), DIRPERM1)) {
+ err = au_busy_or_stale();
+ h_inode = au_h_iptr(inode, au_ibstart(inode));
+ if (unlikely(!h_inode
+ err = 0;
+ bindex = au_ibstart(inode);
+ br = au_sbr(sb, bindex);
-+ err = h_permission(h_inode, mask, br->br_mnt, br->br_perm);
++ err = h_permission(h_inode, mask, au_br_mnt(br), br->br_perm);
+ if (write_mask
+ && !err
+ && !special_file(h_inode->i_mode)) {
+ break;
+
+ br = au_sbr(sb, bindex);
-+ err = h_permission(h_inode, mask, br->br_mnt,
++ err = h_permission(h_inode, mask, au_br_mnt(br),
+ br->br_perm);
+ }
+ }
+
+ if (npositive) {
+ inode = au_new_inode(dentry, /*must_new*/0);
-+ ret = (void *)inode;
-+ }
-+ if (IS_ERR(inode)) {
-+ inode = NULL;
-+ goto out_unlock;
++ if (IS_ERR(inode)) {
++ ret = (void *)inode;
++ inode = NULL;
++ goto out_unlock;
++ }
+ }
+
++ if (inode)
++ atomic_inc(&inode->i_count);
+ ret = d_splice_alias(inode, dentry);
+#if 0
+ if (unlikely(d_need_lookup(dentry))) {
+ spin_unlock(&dentry->d_lock);
+ } else
+#endif
-+ if (unlikely(IS_ERR(ret) && inode)) {
-+ ii_write_unlock(inode);
-+ iput(inode);
-+ inode = NULL;
++ if (inode) {
++ if (!IS_ERR(ret)) {
++ iput(inode);
++ if (ret && ret != dentry)
++ ii_write_unlock(inode);
++ } else {
++ ii_write_unlock(inode);
++ iput(inode);
++ inode = NULL;
++ }
+ }
+
+out_unlock:
+
+/* ---------------------------------------------------------------------- */
+
++struct aopen_node {
++ struct hlist_node hlist;
++ struct file *file, *h_file;
++};
++
++static int au_do_aopen(struct inode *inode, struct file *file)
++{
++ struct au_sphlhead *aopen;
++ struct aopen_node *node;
++ struct au_do_open_args args = {
++ .no_lock = 1,
++ .open = au_do_open_nondir
++ };
++
++ aopen = &au_sbi(inode->i_sb)->si_aopen;
++ spin_lock(&aopen->spin);
++ hlist_for_each_entry(node, &aopen->head, hlist)
++ if (node->file == file) {
++ args.h_file = node->h_file;
++ break;
++ }
++ spin_unlock(&aopen->spin);
++ /* AuDebugOn(!args.h_file); */
++
++ return au_do_open(file, &args);
++}
++
++static int aufs_atomic_open(struct inode *dir, struct dentry *dentry,
++ struct file *file, unsigned int open_flag,
++ umode_t create_mode, int *opened)
++{
++ int err, h_opened = *opened;
++ struct dentry *parent;
++ struct dentry *d;
++ struct au_sphlhead *aopen;
++ struct vfsub_aopen_args args = {
++ .open_flag = open_flag,
++ .create_mode = create_mode,
++ .opened = &h_opened
++ };
++ struct aopen_node aopen_node = {
++ .file = file
++ };
++
++ IMustLock(dir);
++ AuDbg("open_flag 0x%x\n", open_flag);
++ AuDbgDentry(dentry);
++
++ err = 0;
++ if (!au_di(dentry)) {
++ d = aufs_lookup(dir, dentry, /*flags*/0);
++ if (IS_ERR(d)) {
++ err = PTR_ERR(d);
++ goto out;
++ } else if (d) {
++ /*
++ * obsoleted dentry found.
++ * another error will be returned later.
++ */
++ d_drop(d);
++ dput(d);
++ AuDbgDentry(d);
++ }
++ AuDbgDentry(dentry);
++ }
++
++ if (d_is_positive(dentry)
++ || d_unhashed(dentry)
++ || d_unlinked(dentry)
++ || !(open_flag & O_CREAT))
++ goto out_no_open;
++
++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
++ if (unlikely(err))
++ goto out;
++
++ parent = dentry->d_parent; /* dir is locked */
++ di_write_lock_parent(parent);
++ err = au_lkup_dentry(dentry, /*bstart*/0, /*type*/0);
++ if (unlikely(err))
++ goto out_unlock;
++
++ AuDbgDentry(dentry);
++ if (d_is_positive(dentry))
++ goto out_unlock;
++
++ args.file = get_empty_filp();
++ err = PTR_ERR(args.file);
++ if (IS_ERR(args.file))
++ goto out_unlock;
++
++ args.file->f_flags = file->f_flags;
++ err = au_aopen_or_create(dir, dentry, &args);
++ AuTraceErr(err);
++ AuDbgFile(args.file);
++ if (unlikely(err < 0)) {
++ if (h_opened & FILE_OPENED)
++ fput(args.file);
++ else
++ put_filp(args.file);
++ goto out_unlock;
++ }
++
++ /* some filesystems don't set FILE_CREATED while succeeded? */
++ *opened |= FILE_CREATED;
++ if (h_opened & FILE_OPENED)
++ aopen_node.h_file = args.file;
++ else {
++ put_filp(args.file);
++ args.file = NULL;
++ }
++ aopen = &au_sbi(dir->i_sb)->si_aopen;
++ au_sphl_add(&aopen_node.hlist, aopen);
++ err = finish_open(file, dentry, au_do_aopen, opened);
++ au_sphl_del(&aopen_node.hlist, aopen);
++ AuTraceErr(err);
++ AuDbgFile(file);
++ if (aopen_node.h_file)
++ fput(aopen_node.h_file);
++
++out_unlock:
++ di_write_unlock(parent);
++ aufs_read_unlock(dentry, AuLock_DW);
++ AuDbgDentry(dentry);
++ if (unlikely(err))
++ goto out;
++out_no_open:
++ if (!err && !(*opened & FILE_CREATED)) {
++ AuLabel(out_no_open);
++ dget(dentry);
++ err = finish_no_open(file, dentry);
++ }
++out:
++ AuDbg("%pd%s%s\n", dentry,
++ (*opened & FILE_CREATED) ? " created" : "",
++ (*opened & FILE_OPENED) ? " opened" : "");
++ AuTraceErr(err);
++ return err;
++}
++
++
++/* ---------------------------------------------------------------------- */
++
+static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent,
+ const unsigned char add_entry, aufs_bindex_t bcpup,
+ aufs_bindex_t bstart)
+
+ err = 0;
+ if (!au_h_dptr(parent, bcpup)) {
-+ if (bstart < bcpup)
++ if (bstart > bcpup)
++ err = au_cpup_dirs(dentry, bcpup);
++ else if (bstart < bcpup)
+ err = au_cpdown_dirs(dentry, bcpup);
+ else
-+ err = au_cpup_dirs(dentry, bcpup);
++ BUG();
+ }
-+ if (!err && add_entry) {
++ if (!err && add_entry && !au_ftest_wrdir(add_entry, TMPFILE)) {
+ h_parent = au_h_dptr(parent, bcpup);
+ h_dir = h_parent->d_inode;
+ mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_PARENT);
-+ err = au_lkup_neg(dentry, bcpup);
++ err = au_lkup_neg(dentry, bcpup, /*wh*/0);
+ /* todo: no unlock here */
+ mutex_unlock(&h_dir->i_mutex);
+
+ struct au_wr_dir_args *args)
+{
+ int err;
++ unsigned int flags;
+ aufs_bindex_t bcpup, bstart, src_bstart;
-+ const unsigned char add_entry = !!au_ftest_wrdir(args->flags,
-+ ADD_ENTRY);
++ const unsigned char add_entry
++ = au_ftest_wrdir(args->flags, ADD_ENTRY)
++ | au_ftest_wrdir(args->flags, TMPFILE);
+ struct super_block *sb;
+ struct dentry *parent;
+ struct au_sbinfo *sbinfo;
+ if (src_bstart < bstart)
+ bcpup = src_bstart;
+ } else if (add_entry) {
-+ err = AuWbrCreate(sbinfo, dentry,
-+ au_ftest_wrdir(args->flags, ISDIR));
++ flags = 0;
++ if (au_ftest_wrdir(args->flags, ISDIR))
++ au_fset_wbr(flags, DIR);
++ err = AuWbrCreate(sbinfo, dentry, flags);
+ bcpup = err;
+ }
+
+ au_set_dbstart(dentry, bcpup);
+ au_set_dbend(dentry, bcpup);
+ }
-+ AuDebugOn(add_entry && !au_h_dptr(dentry, bcpup));
++ AuDebugOn(add_entry
++ && !au_ftest_wrdir(args->flags, TMPFILE)
++ && !au_h_dptr(dentry, bcpup));
+ }
+
+out:
+
+/* ---------------------------------------------------------------------- */
+
++void au_pin_hdir_unlock(struct au_pin *p)
++{
++ if (p->hdir)
++ au_hn_imtx_unlock(p->hdir);
++}
++
++int au_pin_hdir_lock(struct au_pin *p)
++{
++ int err;
++
++ err = 0;
++ if (!p->hdir)
++ goto out;
++
++ /* even if an error happens later, keep this lock */
++ au_hn_imtx_lock_nested(p->hdir, p->lsc_hi);
++
++ err = -EBUSY;
++ if (unlikely(p->hdir->hi_inode != p->h_parent->d_inode))
++ goto out;
++
++ err = 0;
++ if (p->h_dentry)
++ err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode,
++ p->h_parent, p->br);
++
++out:
++ return err;
++}
++
++int au_pin_hdir_relock(struct au_pin *p)
++{
++ int err, i;
++ struct inode *h_i;
++ struct dentry *h_d[] = {
++ p->h_dentry,
++ p->h_parent
++ };
++
++ err = au_pin_hdir_lock(p);
++ if (unlikely(err))
++ goto out;
++
++ for (i = 0; !err && i < sizeof(h_d)/sizeof(*h_d); i++) {
++ if (!h_d[i])
++ continue;
++ h_i = h_d[i]->d_inode;
++ if (h_i)
++ err = !h_i->i_nlink;
++ }
++
++out:
++ return err;
++}
++
++void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task)
++{
++#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP)
++ p->hdir->hi_inode->i_mutex.owner = task;
++#endif
++}
++
++void au_pin_hdir_acquire_nest(struct au_pin *p)
++{
++ if (p->hdir) {
++ mutex_acquire_nest(&p->hdir->hi_inode->i_mutex.dep_map,
++ p->lsc_hi, 0, NULL, _RET_IP_);
++ au_pin_hdir_set_owner(p, current);
++ }
++}
++
++void au_pin_hdir_release(struct au_pin *p)
++{
++ if (p->hdir) {
++ au_pin_hdir_set_owner(p, p->task);
++ mutex_release(&p->hdir->hi_inode->i_mutex.dep_map, 1, _RET_IP_);
++ }
++}
++
+struct dentry *au_pinned_h_parent(struct au_pin *pin)
+{
+ if (pin && pin->parent)
+
+void au_unpin(struct au_pin *p)
+{
++ if (p->hdir)
++ au_pin_hdir_unlock(p);
+ if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE))
+ vfsub_mnt_drop_write(p->h_mnt);
+ if (!p->hdir)
+ return;
+
-+ au_hn_imtx_unlock(p->hdir);
+ if (!au_ftest_pin(p->flags, DI_LOCKED))
+ di_read_unlock(p->parent, AuLock_IR);
+ iput(p->hdir->hi_inode);
+ p->parent = NULL;
+ p->hdir = NULL;
+ p->h_mnt = NULL;
++ /* do not clear p->task */
+}
+
+int au_do_pin(struct au_pin *p)
+{
+ int err;
+ struct super_block *sb;
-+ struct dentry *h_dentry, *h_parent;
-+ struct au_branch *br;
+ struct inode *h_dir;
+
+ err = 0;
+ sb = p->dentry->d_sb;
-+ br = au_sbr(sb, p->bindex);
++ p->br = au_sbr(sb, p->bindex);
+ if (IS_ROOT(p->dentry)) {
+ if (au_ftest_pin(p->flags, MNT_WRITE)) {
-+ p->h_mnt = br->br_mnt;
++ p->h_mnt = au_br_mnt(p->br);
+ err = vfsub_mnt_want_write(p->h_mnt);
+ if (unlikely(err)) {
+ au_fclr_pin(p->flags, MNT_WRITE);
+ goto out;
+ }
+
-+ h_dentry = NULL;
++ p->h_dentry = NULL;
+ if (p->bindex <= au_dbend(p->dentry))
-+ h_dentry = au_h_dptr(p->dentry, p->bindex);
++ p->h_dentry = au_h_dptr(p->dentry, p->bindex);
+
+ p->parent = dget_parent(p->dentry);
+ if (!au_ftest_pin(p->flags, DI_LOCKED))
+ di_read_lock(p->parent, AuLock_IR, p->lsc_di);
+
+ h_dir = NULL;
-+ h_parent = au_h_dptr(p->parent, p->bindex);
++ p->h_parent = au_h_dptr(p->parent, p->bindex);
+ p->hdir = au_hi(p->parent->d_inode, p->bindex);
+ if (p->hdir)
+ h_dir = p->hdir->hi_inode;
+ * if DI_LOCKED is not set, then p->parent may be different
+ * and h_parent can be NULL.
+ */
-+ if (unlikely(!p->hdir || !h_dir || !h_parent)) {
++ if (unlikely(!p->hdir || !h_dir || !p->h_parent)) {
+ err = -EBUSY;
+ if (!au_ftest_pin(p->flags, DI_LOCKED))
+ di_read_unlock(p->parent, AuLock_IR);
+ goto out_err;
+ }
+
-+ au_igrab(h_dir);
-+ au_hn_imtx_lock_nested(p->hdir, p->lsc_hi);
-+
-+ if (unlikely(p->hdir->hi_inode != h_parent->d_inode)) {
-+ err = -EBUSY;
-+ goto out_unpin;
-+ }
-+ if (h_dentry) {
-+ err = au_h_verify(h_dentry, p->udba, h_dir, h_parent, br);
-+ if (unlikely(err)) {
-+ au_fclr_pin(p->flags, MNT_WRITE);
-+ goto out_unpin;
-+ }
-+ }
-+
+ if (au_ftest_pin(p->flags, MNT_WRITE)) {
-+ p->h_mnt = br->br_mnt;
++ p->h_mnt = au_br_mnt(p->br);
+ err = vfsub_mnt_want_write(p->h_mnt);
+ if (unlikely(err)) {
+ au_fclr_pin(p->flags, MNT_WRITE);
-+ goto out_unpin;
++ if (!au_ftest_pin(p->flags, DI_LOCKED))
++ di_read_unlock(p->parent, AuLock_IR);
++ dput(p->parent);
++ p->parent = NULL;
++ goto out_err;
+ }
+ }
-+ goto out; /* success */
+
-+out_unpin:
++ au_igrab(h_dir);
++ err = au_pin_hdir_lock(p);
++ if (!err)
++ goto out; /* success */
++
+ au_unpin(p);
++
+out_err:
+ pr_err("err %d\n", err);
+ err = au_busy_or_stale();
+ p->parent = NULL;
+ p->hdir = NULL;
+ p->h_mnt = NULL;
++
++ p->h_dentry = NULL;
++ p->h_parent = NULL;
++ p->br = NULL;
++ p->task = current;
+}
+
+int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
+ * for ->setattr(), ia->ia_file is passed from ftruncate only.
+ */
+/* todo: consolidate with do_refresh() and simple_reval_dpath() */
-+static int au_reval_for_attr(struct dentry *dentry, unsigned int sigen)
++int au_reval_for_attr(struct dentry *dentry, unsigned int sigen)
+{
+ int err;
+ struct inode *inode;
+ return err;
+}
+
-+#define AuIcpup_DID_CPUP 1
-+#define au_ftest_icpup(flags, name) ((flags) & AuIcpup_##name)
-+#define au_fset_icpup(flags, name) \
-+ do { (flags) |= AuIcpup_##name; } while (0)
-+#define au_fclr_icpup(flags, name) \
-+ do { (flags) &= ~AuIcpup_##name; } while (0)
-+
-+struct au_icpup_args {
-+ unsigned char flags;
-+ unsigned char pin_flags;
-+ aufs_bindex_t btgt;
-+ unsigned int udba;
-+ struct au_pin pin;
-+ struct path h_path;
-+ struct inode *h_inode;
-+};
-+
-+static int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
-+ struct au_icpup_args *a)
++int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
++ struct au_icpup_args *a)
+{
+ int err;
+ loff_t sz;
+ aufs_bindex_t bstart, ibstart;
+ struct dentry *hi_wh, *parent;
+ struct inode *inode;
-+ struct file *h_file;
+ struct au_wr_dir_args wr_dir_args = {
+ .force_btgt = -1,
+ .flags = 0
+ };
+
-+ bstart = au_dbstart(dentry);
-+ inode = dentry->d_inode;
-+ if (S_ISDIR(inode->i_mode))
++ if (d_is_dir(dentry))
+ au_fset_wrdir(wr_dir_args.flags, ISDIR);
+ /* plink or hi_wh() case */
++ bstart = au_dbstart(dentry);
++ inode = dentry->d_inode;
+ ibstart = au_ibstart(inode);
+ if (bstart != ibstart && !au_test_ro(inode->i_sb, ibstart, inode))
+ wr_dir_args.force_btgt = ibstart;
+
+ a->h_path.dentry = au_h_dptr(dentry, bstart);
+ a->h_inode = a->h_path.dentry->d_inode;
-+ mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD);
+ sz = -1;
-+ if ((ia->ia_valid & ATTR_SIZE) && ia->ia_size < i_size_read(a->h_inode))
-+ sz = ia->ia_size;
++ if (ia && (ia->ia_valid & ATTR_SIZE)) {
++ mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD);
++ if (ia->ia_size < i_size_read(a->h_inode))
++ sz = ia->ia_size;
++ mutex_unlock(&a->h_inode->i_mutex);
++ }
+
-+ h_file = NULL;
+ hi_wh = NULL;
+ if (au_ftest_icpup(a->flags, DID_CPUP) && d_unlinked(dentry)) {
+ hi_wh = au_hi_wh(inode, a->btgt);
+ if (!hi_wh) {
-+ err = au_sio_cpup_wh(dentry, a->btgt, sz, /*file*/NULL);
++ struct au_cp_generic cpg = {
++ .dentry = dentry,
++ .bdst = a->btgt,
++ .bsrc = -1,
++ .len = sz,
++ .pin = &a->pin
++ };
++ err = au_sio_cpup_wh(&cpg, /*file*/NULL);
+ if (unlikely(err))
+ goto out_unlock;
+ hi_wh = au_hi_wh(inode, a->btgt);
+ goto out; /* success */
+
+ if (!d_unhashed(dentry)) {
-+ h_file = au_h_open_pre(dentry, bstart);
-+ if (IS_ERR(h_file)) {
-+ err = PTR_ERR(h_file);
-+ h_file = NULL;
-+ } else
-+ err = au_sio_cpup_simple(dentry, a->btgt, sz,
-+ AuCpup_DTIME);
++ struct au_cp_generic cpg = {
++ .dentry = dentry,
++ .bdst = a->btgt,
++ .bsrc = bstart,
++ .len = sz,
++ .pin = &a->pin,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN
++ };
++ err = au_sio_cpup_simple(&cpg);
+ if (!err)
+ a->h_path.dentry = au_h_dptr(dentry, a->btgt);
+ } else if (!hi_wh)
+ a->h_path.dentry = hi_wh; /* do not dget here */
+
+out_unlock:
-+ mutex_unlock(&a->h_inode->i_mutex);
-+ au_h_open_post(dentry, bstart, h_file);
+ a->h_inode = a->h_path.dentry->d_inode;
-+ if (!err) {
-+ mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD);
++ if (!err)
+ goto out; /* success */
-+ }
-+
+ au_unpin(&a->pin);
+out_parent:
+ if (parent) {
+ dput(parent);
+ }
+out:
++ if (!err)
++ mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD);
+ return err;
+}
+
+static int aufs_setattr(struct dentry *dentry, struct iattr *ia)
+{
+ int err;
-+ struct inode *inode;
++ struct inode *inode, *delegated;
+ struct super_block *sb;
+ struct file *file;
+ struct au_icpup_args *a;
+
+ if (ia->ia_valid & ATTR_FILE) {
+ /* currently ftruncate(2) only */
-+ AuDebugOn(!S_ISREG(inode->i_mode));
++ AuDebugOn(!d_is_reg(dentry));
+ file = ia->ia_file;
+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1);
+ if (unlikely(err))
+ goto out_unlock;
+ } else if ((ia->ia_valid & (ATTR_UID | ATTR_GID))
+ && (ia->ia_valid & ATTR_CTIME)) {
-+ err = security_path_chown(&a->h_path, vfsub_ia_uid(ia),
-+ vfsub_ia_gid(ia));
++ err = security_path_chown(&a->h_path, ia->ia_uid, ia->ia_gid);
+ if (unlikely(err))
+ goto out_unlock;
+ }
+ mutex_unlock(&a->h_inode->i_mutex);
+ err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f);
+ mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD);
-+ } else
-+ err = vfsub_notify_change(&a->h_path, ia);
++ } else {
++ delegated = NULL;
++ while (1) {
++ err = vfsub_notify_change(&a->h_path, ia, &delegated);
++ if (delegated) {
++ err = break_deleg_wait(&delegated);
++ if (!err)
++ continue;
++ }
++ break;
++ }
++ }
+ if (!err)
+ au_cpup_attr_changeable(inode);
+
+ return err;
+}
+
++#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
++static int au_h_path_to_set_attr(struct dentry *dentry,
++ struct au_icpup_args *a, struct path *h_path)
++{
++ int err;
++ struct super_block *sb;
++
++ sb = dentry->d_sb;
++ a->udba = au_opt_udba(sb);
++ /* no d_unlinked(), to set UDBA_NONE for root */
++ if (d_unhashed(dentry))
++ a->udba = AuOpt_UDBA_NONE;
++ if (a->udba != AuOpt_UDBA_NONE) {
++ AuDebugOn(IS_ROOT(dentry));
++ err = au_reval_for_attr(dentry, au_sigen(sb));
++ if (unlikely(err))
++ goto out;
++ }
++ err = au_pin_and_icpup(dentry, /*ia*/NULL, a);
++ if (unlikely(err < 0))
++ goto out;
++
++ h_path->dentry = a->h_path.dentry;
++ h_path->mnt = au_sbr_mnt(sb, a->btgt);
++
++out:
++ return err;
++}
++
++ssize_t au_srxattr(struct dentry *dentry, struct au_srxattr *arg)
++{
++ int err;
++ struct path h_path;
++ struct super_block *sb;
++ struct au_icpup_args *a;
++ struct inode *inode, *h_inode;
++
++ inode = dentry->d_inode;
++ IMustLock(inode);
++
++ err = -ENOMEM;
++ a = kzalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
++
++ sb = dentry->d_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (unlikely(err))
++ goto out_kfree;
++
++ h_path.dentry = NULL; /* silence gcc */
++ di_write_lock_child(dentry);
++ err = au_h_path_to_set_attr(dentry, a, &h_path);
++ if (unlikely(err))
++ goto out_di;
++
++ mutex_unlock(&a->h_inode->i_mutex);
++ switch (arg->type) {
++ case AU_XATTR_SET:
++ err = vfsub_setxattr(h_path.dentry,
++ arg->u.set.name, arg->u.set.value,
++ arg->u.set.size, arg->u.set.flags);
++ break;
++ case AU_XATTR_REMOVE:
++ err = vfsub_removexattr(h_path.dentry, arg->u.remove.name);
++ break;
++ case AU_ACL_SET:
++ err = -EOPNOTSUPP;
++ h_inode = h_path.dentry->d_inode;
++ if (h_inode->i_op->set_acl)
++ err = h_inode->i_op->set_acl(h_inode,
++ arg->u.acl_set.acl,
++ arg->u.acl_set.type);
++ break;
++ }
++ if (!err)
++ au_cpup_attr_timesizes(inode);
++
++ au_unpin(&a->pin);
++ if (unlikely(err))
++ au_update_dbstart(dentry);
++
++out_di:
++ di_write_unlock(dentry);
++ si_read_unlock(sb);
++out_kfree:
++ kfree(a);
++out:
++ AuTraceErr(err);
++ return err;
++}
++#endif
++
+static void au_refresh_iattr(struct inode *inode, struct kstat *st,
+ unsigned int nlink)
+{
+ unsigned int n;
+
+ inode->i_mode = st->mode;
-+ i_uid_write(inode, st->uid);
-+ i_gid_write(inode, st->gid);
++ /* don't i_[ug]id_write() here */
++ inode->i_uid = st->uid;
++ inode->i_gid = st->gid;
+ inode->i_atime = st->atime;
+ inode->i_mtime = st->mtime;
+ inode->i_ctime = st->ctime;
+ n = inode->i_nlink;
+ n -= nlink;
+ n += st->nlink;
++ smp_mb(); /* for i_nlink */
+ /* 0 can happen */
+ set_nlink(inode, n);
+ }
+ spin_unlock(&inode->i_lock);
+}
+
-+static int aufs_getattr(struct vfsmount *mnt __maybe_unused,
-+ struct dentry *dentry, struct kstat *st)
++/*
++ * common routine for aufs_getattr() and aufs_getxattr().
++ * returns zero or negative (an error).
++ * @dentry will be read-locked in success.
++ */
++int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path)
+{
+ int err;
-+ unsigned int mnt_flags;
++ unsigned int mnt_flags, sigen;
++ unsigned char udba_none;
+ aufs_bindex_t bindex;
-+ unsigned char udba_none, positive;
+ struct super_block *sb, *h_sb;
+ struct inode *inode;
-+ struct vfsmount *h_mnt;
-+ struct dentry *h_dentry;
+
++ h_path->mnt = NULL;
++ h_path->dentry = NULL;
++
++ err = 0;
+ sb = dentry->d_sb;
-+ inode = dentry->d_inode;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out;
+ mnt_flags = au_mntflags(sb);
+ udba_none = !!au_opt_test(mnt_flags, UDBA_NONE);
+
+ /* support fstat(2) */
+ if (!d_unlinked(dentry) && !udba_none) {
-+ unsigned int sigen = au_sigen(sb);
++ sigen = au_sigen(sb);
+ err = au_digen_test(dentry, sigen);
+ if (!err) {
+ di_read_lock_child(dentry, AuLock_IR);
+ err = au_dbrange_test(dentry);
-+ if (unlikely(err))
-+ goto out_unlock;
++ if (unlikely(err)) {
++ di_read_unlock(dentry, AuLock_IR);
++ goto out;
++ }
+ } else {
+ AuDebugOn(IS_ROOT(dentry));
+ di_write_lock_child(dentry);
+ err = au_dbrange_test(dentry);
+ if (!err)
+ err = au_reval_for_attr(dentry, sigen);
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ if (unlikely(err))
-+ goto out_unlock;
++ if (!err)
++ di_downgrade_lock(dentry, AuLock_IR);
++ else {
++ di_write_unlock(dentry);
++ goto out;
++ }
+ }
+ } else
+ di_read_lock_child(dentry, AuLock_IR);
+
++ inode = dentry->d_inode;
+ bindex = au_ibstart(inode);
-+ h_mnt = au_sbr_mnt(sb, bindex);
-+ h_sb = h_mnt->mnt_sb;
-+ if (!au_test_fs_bad_iattr(h_sb) && udba_none)
-+ goto out_fill; /* success */
++ h_path->mnt = au_sbr_mnt(sb, bindex);
++ h_sb = h_path->mnt->mnt_sb;
++ if (!force
++ && !au_test_fs_bad_iattr(h_sb)
++ && udba_none)
++ goto out; /* success */
+
-+ h_dentry = NULL;
+ if (au_dbstart(dentry) == bindex)
-+ h_dentry = dget(au_h_dptr(dentry, bindex));
++ h_path->dentry = au_h_dptr(dentry, bindex);
+ else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) {
-+ h_dentry = au_plink_lkup(inode, bindex);
-+ if (IS_ERR(h_dentry))
-+ goto out_fill; /* pretending success */
++ h_path->dentry = au_plink_lkup(inode, bindex);
++ if (IS_ERR(h_path->dentry))
++ /* pretending success */
++ h_path->dentry = NULL;
++ else
++ dput(h_path->dentry);
+ }
-+ /* illegally overlapped or something */
-+ if (unlikely(!h_dentry))
++
++out:
++ return err;
++}
++
++static int aufs_getattr(struct vfsmount *mnt __maybe_unused,
++ struct dentry *dentry, struct kstat *st)
++{
++ int err;
++ unsigned char positive;
++ struct path h_path;
++ struct inode *inode;
++ struct super_block *sb;
++
++ inode = dentry->d_inode;
++ sb = dentry->d_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (unlikely(err))
++ goto out;
++ err = au_h_path_getattr(dentry, /*force*/0, &h_path);
++ if (unlikely(err))
++ goto out_si;
++ if (unlikely(!h_path.dentry))
++ /* illegally overlapped or something */
+ goto out_fill; /* pretending success */
+
-+ positive = !!h_dentry->d_inode;
++ positive = !!h_path.dentry->d_inode;
+ if (positive)
-+ err = vfs_getattr(h_mnt, h_dentry, st);
-+ dput(h_dentry);
++ err = vfs_getattr(&h_path, st);
+ if (!err) {
+ if (positive)
-+ au_refresh_iattr(inode, st, h_dentry->d_inode->i_nlink);
++ au_refresh_iattr(inode, st,
++ h_path.dentry->d_inode->i_nlink);
+ goto out_fill; /* success */
+ }
+ AuTraceErr(err);
-+ goto out_unlock;
++ goto out_di;
+
+out_fill:
+ generic_fillattr(inode, st);
-+out_unlock:
++out_di:
+ di_read_unlock(dentry, AuLock_IR);
++out_si:
+ si_read_unlock(sb);
+out:
+ AuTraceErr(err);
+ h_inode = au_h_iptr(inode, au_ibstart(inode));
+ err = vfsub_update_time(h_inode, ts, flags);
+ lockdep_off();
++ if (!err)
++ au_cpup_attr_timesizes(inode);
+ ii_write_unlock(inode);
+ si_read_unlock(sb);
+ lockdep_on();
++
++ if (!err && (flags & S_VERSION))
++ inode_inc_iversion(inode);
++
+ return err;
+}
+
+
+struct inode_operations aufs_symlink_iop = {
+ .permission = aufs_permission,
++#ifdef CONFIG_FS_POSIX_ACL
++ .get_acl = aufs_get_acl,
++ .set_acl = aufs_set_acl, /* unsupport for symlink? */
++#endif
++
+ .setattr = aufs_setattr,
+ .getattr = aufs_getattr,
+
++#ifdef CONFIG_AUFS_XATTR
++ .setxattr = aufs_setxattr,
++ .getxattr = aufs_getxattr,
++ .listxattr = aufs_listxattr,
++ .removexattr = aufs_removexattr,
++#endif
++
+ .readlink = aufs_readlink,
+ .follow_link = aufs_follow_link,
+ .put_link = aufs_put_link,
+ .rename = aufs_rename,
+
+ .permission = aufs_permission,
++#ifdef CONFIG_FS_POSIX_ACL
++ .get_acl = aufs_get_acl,
++ .set_acl = aufs_set_acl,
++#endif
++
+ .setattr = aufs_setattr,
+ .getattr = aufs_getattr,
+
-+ .update_time = aufs_update_time
-+ /* no support for atomic_open() */
++#ifdef CONFIG_AUFS_XATTR
++ .setxattr = aufs_setxattr,
++ .getxattr = aufs_getxattr,
++ .listxattr = aufs_listxattr,
++ .removexattr = aufs_removexattr,
++#endif
++
++ .update_time = aufs_update_time,
++ .atomic_open = aufs_atomic_open,
++ .tmpfile = aufs_tmpfile
+};
+
+struct inode_operations aufs_iop = {
+ .permission = aufs_permission,
++#ifdef CONFIG_FS_POSIX_ACL
++ .get_acl = aufs_get_acl,
++ .set_acl = aufs_set_acl,
++#endif
++
+ .setattr = aufs_setattr,
+ .getattr = aufs_getattr,
+
++#ifdef CONFIG_AUFS_XATTR
++ .setxattr = aufs_setxattr,
++ .getxattr = aufs_getxattr,
++ .listxattr = aufs_listxattr,
++ .removexattr = aufs_removexattr,
++#endif
++
+ .update_time = aufs_update_time
+};
diff -urN /usr/share/empty/fs/aufs/i_op_del.c linux/fs/aufs/i_op_del.c
--- /usr/share/empty/fs/aufs/i_op_del.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/i_op_del.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,477 @@
++++ linux/fs/aufs/i_op_del.c 2015-06-22 08:27:37.884168534 +0200
+@@ -0,0 +1,506 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * let's try heavy test.
+ */
+ err = -EACCES;
-+ if (unlikely(au_test_h_perm(h_parent->d_inode, MAY_EXEC | MAY_WRITE)))
++ if (unlikely(!au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1)
++ && au_test_h_perm(h_parent->d_inode,
++ MAY_EXEC | MAY_WRITE)))
+ goto out;
+
-+ h_latest = au_sio_lkup_one(&dentry->d_name, h_parent,
-+ au_sbr(dentry->d_sb, bindex));
++ h_latest = au_sio_lkup_one(&dentry->d_name, h_parent);
+ err = -EIO;
+ if (IS_ERR(h_latest))
+ goto out;
+
+ err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist);
+ if (unlikely(err)) {
-+ AuIOErr("rmdir %.*s, b%d failed, %d. ignored\n",
-+ AuDLNPair(h_dentry), bindex, err);
++ AuIOErr("rmdir %pd, b%d failed, %d. ignored\n",
++ h_dentry, bindex, err);
+ err = 0;
+ }
+
+ d_drop(dentry);
+ inode->i_ctime = dir->i_ctime;
+
-+ if (au_ibstart(dir) == bindex)
-+ au_cpup_attr_timesizes(dir);
++ au_dir_ts(dir, bindex);
+ dir->i_version++;
+}
+
+ return 0;
+ }
+
-+ AuIOErr("%.*s reverting whiteout failed(%d, %d)\n",
-+ AuDLNPair(dentry), err, rerr);
++ AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr);
+ return -EIO;
+}
+
+{
+ int err;
+ aufs_bindex_t bwh, bindex, bstart;
-+ struct au_dtime dt;
-+ struct au_pin pin;
-+ struct path h_path;
-+ struct inode *inode, *h_dir;
++ struct inode *inode, *h_dir, *delegated;
+ struct dentry *parent, *wh_dentry;
++ /* to reuduce stack size */
++ struct {
++ struct au_dtime dt;
++ struct au_pin pin;
++ struct path h_path;
++ } *a;
+
+ IMustLock(dir);
+
++ err = -ENOMEM;
++ a = kmalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
++
+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
+ if (unlikely(err))
-+ goto out;
++ goto out_free;
+ err = au_d_hashed_positive(dentry);
+ if (unlikely(err))
+ goto out_unlock;
+ inode = dentry->d_inode;
+ IMustLock(inode);
+ err = -EISDIR;
-+ if (unlikely(S_ISDIR(inode->i_mode)))
++ if (unlikely(d_is_dir(dentry)))
+ goto out_unlock; /* possible? */
+
+ bstart = au_dbstart(dentry);
+ bindex = -1;
+ parent = dentry->d_parent; /* dir inode is locked */
+ di_write_lock_parent(parent);
-+ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &dt, &pin);
++ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &a->dt,
++ &a->pin);
+ err = PTR_ERR(wh_dentry);
+ if (IS_ERR(wh_dentry))
+ goto out_parent;
+
-+ h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart);
-+ h_path.dentry = au_h_dptr(dentry, bstart);
-+ dget(h_path.dentry);
++ a->h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart);
++ a->h_path.dentry = au_h_dptr(dentry, bstart);
++ dget(a->h_path.dentry);
+ if (bindex == bstart) {
-+ h_dir = au_pinned_h_dir(&pin);
-+ err = vfsub_unlink(h_dir, &h_path, /*force*/0);
++ h_dir = au_pinned_h_dir(&a->pin);
++ delegated = NULL;
++ err = vfsub_unlink(h_dir, &a->h_path, &delegated, /*force*/0);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
++ }
+ } else {
+ /* dir inode is locked */
+ h_dir = wh_dentry->d_parent->d_inode;
+
+ /* update target timestamps */
+ if (bindex == bstart) {
-+ vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/
-+ inode->i_ctime = h_path.dentry->d_inode->i_ctime;
++ vfsub_update_h_iattr(&a->h_path, /*did*/NULL);
++ /*ignore*/
++ inode->i_ctime = a->h_path.dentry->d_inode->i_ctime;
+ } else
+ /* todo: this timestamp may be reverted later */
+ inode->i_ctime = h_dir->i_ctime;
+ if (wh_dentry) {
+ int rerr;
+
-+ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, &dt);
++ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
++ &a->dt);
+ if (rerr)
+ err = rerr;
+ }
+
+out_unpin:
-+ au_unpin(&pin);
++ au_unpin(&a->pin);
+ dput(wh_dentry);
-+ dput(h_path.dentry);
++ dput(a->h_path.dentry);
+out_parent:
+ di_write_unlock(parent);
+out_unlock:
+ aufs_read_unlock(dentry, AuLock_DW);
++out_free:
++ kfree(a);
+out:
+ return err;
+}
+{
+ int err, rmdir_later;
+ aufs_bindex_t bwh, bindex, bstart;
-+ struct au_dtime dt;
-+ struct au_pin pin;
+ struct inode *inode;
+ struct dentry *parent, *wh_dentry, *h_dentry;
+ struct au_whtmp_rmdir *args;
++ /* to reuduce stack size */
++ struct {
++ struct au_dtime dt;
++ struct au_pin pin;
++ } *a;
+
+ IMustLock(dir);
+
++ err = -ENOMEM;
++ a = kmalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
++
+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
+ if (unlikely(err))
-+ goto out;
++ goto out_free;
+ err = au_alive_dir(dentry);
+ if (unlikely(err))
+ goto out_unlock;
+ inode = dentry->d_inode;
+ IMustLock(inode);
+ err = -ENOTDIR;
-+ if (unlikely(!S_ISDIR(inode->i_mode)))
++ if (unlikely(!d_is_dir(dentry)))
+ goto out_unlock; /* possible? */
+
+ err = -ENOMEM;
+ bstart = au_dbstart(dentry);
+ bwh = au_dbwh(dentry);
+ bindex = -1;
-+ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &dt, &pin);
++ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &a->dt,
++ &a->pin);
+ err = PTR_ERR(wh_dentry);
+ if (IS_ERR(wh_dentry))
+ goto out_parent;
+ if (wh_dentry) {
+ int rerr;
+
-+ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, &dt);
++ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
++ &a->dt);
+ if (rerr)
+ err = rerr;
+ }
+
+out_unpin:
-+ au_unpin(&pin);
++ au_unpin(&a->pin);
+ dput(wh_dentry);
+ dput(h_dentry);
+out_parent:
+ au_whtmp_rmdir_free(args);
+out_unlock:
+ aufs_read_unlock(dentry, AuLock_DW);
++out_free:
++ kfree(a);
+out:
+ AuTraceErr(err);
+ return err;
+}
diff -urN /usr/share/empty/fs/aufs/i_op_ren.c linux/fs/aufs/i_op_ren.c
--- /usr/share/empty/fs/aufs/i_op_ren.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/i_op_ren.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,1026 @@
++++ linux/fs/aufs/i_op_ren.c 2015-06-22 08:27:37.884168534 +0200
+@@ -0,0 +1,1015 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+#define AuRen_MNT_WRITE (1 << 4)
+#define AuRen_DT_DSTDIR (1 << 5)
+#define AuRen_DIROPQ (1 << 6)
-+#define AuRen_CPUP (1 << 7)
+#define au_ftest_ren(flags, name) ((flags) & AuRen_##name)
+#define au_fset_ren(flags, name) \
+ do { (flags) |= AuRen_##name; } while (0)
+ au_hn_imtx_unlock(a->src_hinode);
+ au_set_dbdiropq(a->src_dentry, a->src_bdiropq);
+ if (rerr)
-+ RevertFailure("remove diropq %.*s", AuDLNPair(a->src_dentry));
++ RevertFailure("remove diropq %pd", a->src_dentry);
+}
+
+static void au_ren_rev_rename(int err, struct au_ren_args *a)
+{
+ int rerr;
++ struct inode *delegated;
+
+ a->h_path.dentry = vfsub_lkup_one(&a->src_dentry->d_name,
+ a->src_h_parent);
+ rerr = PTR_ERR(a->h_path.dentry);
+ if (IS_ERR(a->h_path.dentry)) {
-+ RevertFailure("lkup one %.*s", AuDLNPair(a->src_dentry));
++ RevertFailure("lkup one %pd", a->src_dentry);
+ return;
+ }
+
++ delegated = NULL;
+ rerr = vfsub_rename(a->dst_h_dir,
+ au_h_dptr(a->src_dentry, a->btgt),
-+ a->src_h_dir, &a->h_path);
++ a->src_h_dir, &a->h_path, &delegated);
++ if (unlikely(rerr == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal rename\n");
++ iput(delegated);
++ }
+ d_drop(a->h_path.dentry);
+ dput(a->h_path.dentry);
+ /* au_set_h_dptr(a->src_dentry, a->btgt, NULL); */
+ if (rerr)
-+ RevertFailure("rename %.*s", AuDLNPair(a->src_dentry));
-+}
-+
-+static void au_ren_rev_cpup(int err, struct au_ren_args *a)
-+{
-+ int rerr;
-+
-+ a->h_path.dentry = a->dst_h_dentry;
-+ rerr = vfsub_unlink(a->dst_h_dir, &a->h_path, /*force*/0);
-+ au_set_h_dptr(a->src_dentry, a->btgt, NULL);
-+ au_set_dbstart(a->src_dentry, a->src_bstart);
-+ if (rerr)
-+ RevertFailure("unlink %.*s", AuDLNPair(a->dst_h_dentry));
++ RevertFailure("rename %pd", a->src_dentry);
+}
+
+static void au_ren_rev_whtmp(int err, struct au_ren_args *a)
+{
+ int rerr;
++ struct inode *delegated;
+
+ a->h_path.dentry = vfsub_lkup_one(&a->dst_dentry->d_name,
+ a->dst_h_parent);
+ rerr = PTR_ERR(a->h_path.dentry);
+ if (IS_ERR(a->h_path.dentry)) {
-+ RevertFailure("lkup one %.*s", AuDLNPair(a->dst_dentry));
++ RevertFailure("lkup one %pd", a->dst_dentry);
+ return;
+ }
+ if (a->h_path.dentry->d_inode) {
+ return;
+ }
+
-+ rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path);
++ delegated = NULL;
++ rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path,
++ &delegated);
++ if (unlikely(rerr == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal rename\n");
++ iput(delegated);
++ }
+ d_drop(a->h_path.dentry);
+ dput(a->h_path.dentry);
+ if (!rerr)
+ au_set_h_dptr(a->dst_dentry, a->btgt, dget(a->h_dst));
+ else
-+ RevertFailure("rename %.*s", AuDLNPair(a->h_dst));
++ RevertFailure("rename %pd", a->h_dst);
+}
+
+static void au_ren_rev_whsrc(int err, struct au_ren_args *a)
+ rerr = au_wh_unlink_dentry(a->src_h_dir, &a->h_path, a->src_dentry);
+ au_set_dbwh(a->src_dentry, a->src_bwh);
+ if (rerr)
-+ RevertFailure("unlink %.*s", AuDLNPair(a->src_wh_dentry));
++ RevertFailure("unlink %pd", a->src_wh_dentry);
+}
+#undef RevertFailure
+
+{
+ int err;
+ struct dentry *d;
++ struct inode *delegated;
+
+ d = a->src_dentry;
+ if (au_dbstart(d) == a->btgt) {
+ && au_dbdiropq(d) == a->btgt)
+ au_fclr_ren(a->flags, DIROPQ);
+ AuDebugOn(au_dbstart(d) != a->btgt);
++ delegated = NULL;
+ err = vfsub_rename(a->src_h_dir, au_h_dptr(d, a->btgt),
-+ a->dst_h_dir, &a->h_path);
-+ } else {
-+ struct mutex *h_mtx = &a->src_h_dentry->d_inode->i_mutex;
-+ struct file *h_file;
-+
-+ au_fset_ren(a->flags, CPUP);
-+ mutex_lock_nested(h_mtx, AuLsc_I_CHILD);
-+ au_set_dbstart(d, a->btgt);
-+ au_set_h_dptr(d, a->btgt, dget(a->dst_h_dentry));
-+ h_file = au_h_open_pre(d, a->src_bstart);
-+ if (IS_ERR(h_file)) {
-+ err = PTR_ERR(h_file);
-+ h_file = NULL;
-+ } else
-+ err = au_sio_cpup_single(d, a->btgt, a->src_bstart, -1,
-+ !AuCpup_DTIME, a->dst_parent);
-+ mutex_unlock(h_mtx);
-+ au_h_open_post(d, a->src_bstart, h_file);
-+ if (!err) {
-+ d = a->dst_dentry;
-+ au_set_h_dptr(d, a->btgt, NULL);
-+ au_update_dbstart(d);
-+ } else {
-+ au_set_h_dptr(d, a->btgt, NULL);
-+ au_set_dbstart(d, a->src_bstart);
++ a->dst_h_dir, &a->h_path, &delegated);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal rename\n");
++ iput(delegated);
+ }
-+ }
++ } else
++ BUG();
++
+ if (!err && a->h_dst)
+ /* it will be set to dinfo later */
+ dget(a->h_dst);
+ || au_test_fs_remote(a->h_dst->d_sb)) {
+ err = au_whtmp_rmdir(dir, a->btgt, a->h_dst, &a->whlist);
+ if (unlikely(err))
-+ pr_warn("failed removing whtmp dir %.*s (%d), "
-+ "ignored.\n", AuDLNPair(a->h_dst), err);
++ pr_warn("failed removing whtmp dir %pd (%d), "
++ "ignored.\n", a->h_dst, err);
+ } else {
+ au_nhash_wh_free(&a->thargs->whlist);
+ a->thargs->whlist = a->whlist;
+ au_hn_imtx_unlock(a->src_hinode);
+ if (IS_ERR(diropq))
+ err = PTR_ERR(diropq);
-+ dput(diropq);
++ else
++ dput(diropq);
+
+ return err;
+}
+
+ d = a->dst_dentry;
+ au_set_h_dptr(d, a->btgt, NULL);
-+ err = au_lkup_neg(d, a->btgt);
++ err = au_lkup_neg(d, a->btgt, /*wh*/0);
+ if (unlikely(err))
+ goto out_whtmp;
+ a->dst_h_dentry = au_h_dptr(d, a->btgt);
+ }
+
-+ /* cpup src */
-+ if (a->dst_h_dentry->d_inode && a->src_bstart != a->btgt) {
-+ struct mutex *h_mtx = &a->src_h_dentry->d_inode->i_mutex;
-+ struct file *h_file;
-+
-+ mutex_lock_nested(h_mtx, AuLsc_I_CHILD);
-+ AuDebugOn(au_dbstart(a->src_dentry) != a->src_bstart);
-+ h_file = au_h_open_pre(a->src_dentry, a->src_bstart);
-+ if (IS_ERR(h_file)) {
-+ err = PTR_ERR(h_file);
-+ h_file = NULL;
-+ } else
-+ err = au_sio_cpup_simple(a->src_dentry, a->btgt, -1,
-+ !AuCpup_DTIME);
-+ mutex_unlock(h_mtx);
-+ au_h_open_post(a->src_dentry, a->src_bstart, h_file);
-+ if (unlikely(err))
-+ goto out_whtmp;
-+ }
++ BUG_ON(a->dst_h_dentry->d_inode && a->src_bstart != a->btgt);
+
+ /* rename by vfs_rename or cpup */
+ d = a->dst_dentry;
+ if (a->thargs)
+ au_ren_del_whtmp(a); /* ignore this error */
+
++ au_fhsm_wrote(a->src_dentry->d_sb, a->btgt, /*force*/0);
+ err = 0;
+ goto out_success;
+
+ if (au_ftest_ren(a->flags, DIROPQ))
+ au_ren_rev_diropq(err, a);
+out_rename:
-+ if (!au_ftest_ren(a->flags, CPUP))
-+ au_ren_rev_rename(err, a);
-+ else
-+ au_ren_rev_cpup(err, a);
++ au_ren_rev_rename(err, a);
+ dput(a->h_dst);
+out_whtmp:
+ if (a->thargs)
+ */
+static void au_ren_unlock(struct au_ren_args *a)
+{
-+ struct super_block *sb;
-+
-+ sb = a->dst_dentry->d_sb;
-+ if (au_ftest_ren(a->flags, MNT_WRITE))
-+ vfsub_mnt_drop_write(a->br->br_mnt);
+ vfsub_unlock_rename(a->src_h_parent, a->src_hdir,
+ a->dst_h_parent, a->dst_hdir);
++ if (au_ftest_ren(a->flags, MNT_WRITE))
++ vfsub_mnt_drop_write(au_br_mnt(a->br));
+}
+
+static int au_ren_lock(struct au_ren_args *a)
+ a->src_hdir = au_hi(a->src_dir, a->btgt);
+ a->dst_h_parent = au_h_dptr(a->dst_parent, a->btgt);
+ a->dst_hdir = au_hi(a->dst_dir, a->btgt);
++
++ err = vfsub_mnt_want_write(au_br_mnt(a->br));
++ if (unlikely(err))
++ goto out;
++ au_fset_ren(a->flags, MNT_WRITE);
+ a->h_trap = vfsub_lock_rename(a->src_h_parent, a->src_hdir,
+ a->dst_h_parent, a->dst_hdir);
+ udba = au_opt_udba(a->src_dentry->d_sb);
+ err = au_h_verify(a->dst_h_dentry, udba,
+ a->dst_h_parent->d_inode, a->dst_h_parent,
+ a->br);
-+ if (!err) {
-+ err = vfsub_mnt_want_write(a->br->br_mnt);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ au_fset_ren(a->flags, MNT_WRITE);
++ if (!err)
+ goto out; /* success */
-+ }
+
+ err = au_busy_or_stale();
-+
-+out_unlock:
+ au_ren_unlock(a);
++
+out:
+ return err;
+}
+ au_cpup_attr_nlink(dir, /*force*/1);
+ }
+
-+ if (au_ibstart(dir) == a->btgt)
-+ au_cpup_attr_timesizes(dir);
++ au_dir_ts(dir, a->btgt);
+
+ if (au_ftest_ren(a->flags, ISSAMEDIR))
+ return;
+ dir->i_version++;
+ if (au_ftest_ren(a->flags, ISDIR))
+ au_cpup_attr_nlink(dir, /*force*/1);
-+ if (au_ibstart(dir) == a->btgt)
-+ au_cpup_attr_timesizes(dir);
++ au_dir_ts(dir, a->btgt);
+}
+
+static void au_ren_refresh(struct au_ren_args *a)
+ /* reduce stack space */
+ struct au_ren_args *a;
+
-+ AuDbg("%.*s, %.*s\n", AuDLNPair(_src_dentry), AuDLNPair(_dst_dentry));
++ AuDbg("%pd, %pd\n", _src_dentry, _dst_dentry);
+ IMustLock(_src_dir);
+ IMustLock(_dst_dir);
+
+
+ err = -ENOTDIR;
+ flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN;
-+ if (S_ISDIR(a->src_inode->i_mode)) {
++ if (d_is_dir(a->src_dentry)) {
+ au_fset_ren(a->flags, ISDIR);
-+ if (unlikely(a->dst_inode && !S_ISDIR(a->dst_inode->i_mode)))
++ if (unlikely(d_is_positive(a->dst_dentry)
++ && !d_is_dir(a->dst_dentry)))
+ goto out_free;
+ err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry,
+ AuLock_DIR | flags);
+ if (unlikely(err < 0))
+ goto out_parent;
+ a->br = au_sbr(a->dst_dentry->d_sb, a->btgt);
-+ a->h_path.mnt = a->br->br_mnt;
++ a->h_path.mnt = au_br_mnt(a->br);
+
+ /* are they available to be renamed */
+ err = au_ren_may_dir(a);
+ if (err)
+ au_fset_ren(a->flags, WHSRC);
+
++ /* cpup src */
++ if (a->src_bstart != a->btgt) {
++ struct au_pin pin;
++
++ err = au_pin(&pin, a->src_dentry, a->btgt,
++ au_opt_udba(a->src_dentry->d_sb),
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (!err) {
++ struct au_cp_generic cpg = {
++ .dentry = a->src_dentry,
++ .bdst = a->btgt,
++ .bsrc = a->src_bstart,
++ .len = -1,
++ .pin = &pin,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN
++ };
++ AuDebugOn(au_dbstart(a->src_dentry) != a->src_bstart);
++ err = au_sio_cpup_simple(&cpg);
++ au_unpin(&pin);
++ }
++ if (unlikely(err))
++ goto out_children;
++ a->src_bstart = a->btgt;
++ a->src_h_dentry = au_h_dptr(a->src_dentry, a->btgt);
++ au_fset_ren(a->flags, WHSRC);
++ }
++
+ /* lock them all */
+ err = au_ren_lock(a);
+ if (unlikely(err))
++ /* leave the copied-up one */
+ goto out_children;
+
+ if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE))
+}
diff -urN /usr/share/empty/fs/aufs/Kconfig linux/fs/aufs/Kconfig
--- /usr/share/empty/fs/aufs/Kconfig 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/Kconfig 2013-03-14 20:07:41.038119650 +0100
-@@ -0,0 +1,203 @@
++++ linux/fs/aufs/Kconfig 2015-06-22 08:27:37.874168290 +0200
+@@ -0,0 +1,185 @@
+config AUFS_FS
+ tristate "Aufs (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
+ /* typedef unsigned long/int __kernel_ino_t */
+ /* alpha and s390x are int */
+
-+config AUFS_RDU
-+ bool "Readdir in userspace"
-+ help
-+ Aufs has two methods to provide a merged view for a directory,
-+ by a user-space library and by kernel-space natively. The latter
-+ is always enabled but sometimes large and slow.
-+ If you enable this option, install the library in aufs2-util
-+ package, and set some environment variables for your readdir(3),
-+ then the work will be handled in user-space which generally
-+ shows better performance in most cases.
-+ See detail in aufs.5.
++config AUFS_XATTR
++ bool "support for XATTR/EA (including Security Labels)"
++ help
++ If your branch fs supports XATTR/EA and you want to make them
++ available in aufs too, then enable this opsion and specify the
++ branch attributes for EA.
++ See detail in aufs.5.
++
++config AUFS_FHSM
++ bool "File-based Hierarchical Storage Management"
++ help
++ Hierarchical Storage Management (or HSM) is a well-known feature
++ in the storage world. Aufs provides this feature as file-based.
++ with multiple branches.
++ These multiple branches are prioritized, ie. the topmost one
++ should be the fastest drive and be used heavily.
++
++config AUFS_RDU
++ bool "Readdir in userspace"
++ help
++ Aufs has two methods to provide a merged view for a directory,
++ by a user-space library and by kernel-space natively. The latter
++ is always enabled but sometimes large and slow.
++ If you enable this option, install the library in aufs2-util
++ package, and set some environment variables for your readdir(3),
++ then the work will be handled in user-space which generally
++ shows better performance in most cases.
++ See detail in aufs.5.
++
++config AUFS_SHWH
++ bool "Show whiteouts"
++ help
++ If you want to make the whiteouts in aufs visible, then enable
++ this option and specify 'shwh' mount option. Although it may
++ sounds like philosophy or something, but in technically it
++ simply shows the name of whiteout with keeping its behaviour.
++
++config AUFS_BR_RAMFS
++ bool "Ramfs (initramfs/rootfs) as an aufs branch"
++ help
++ If you want to use ramfs as an aufs branch fs, then enable this
++ option. Generally tmpfs is recommended.
++ Aufs prohibited them to be a branch fs by default, because
++ initramfs becomes unusable after switch_root or something
++ generally. If you sets initramfs as an aufs branch and boot your
++ system by switch_root, you will meet a problem easily since the
++ files in initramfs may be inaccessible.
++ Unless you are going to use ramfs as an aufs branch fs without
++ switch_root or something, leave it N.
++
++config AUFS_BR_FUSE
++ bool "Fuse fs as an aufs branch"
++ depends on FUSE_FS
++ select AUFS_POLL
++ help
++ If you want to use fuse-based userspace filesystem as an aufs
++ branch fs, then enable this option.
++ It implements the internal poll(2) operation which is
++ implemented by fuse only (curretnly).
++
++config AUFS_POLL
++ bool
++ help
++ Automatic configuration for internal use.
++
++config AUFS_BR_HFSPLUS
++ bool "Hfsplus as an aufs branch"
++ depends on HFSPLUS_FS
++ default y
++ help
++ If you want to use hfsplus fs as an aufs branch fs, then enable
++ this option. This option introduces a small overhead at
++ copying-up a file on hfsplus.
++
++config AUFS_BDEV_LOOP
++ bool
++ depends on BLK_DEV_LOOP
++ default y
++ help
++ Automatic configuration for internal use.
++ Convert =[ym] into =y.
++
++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.
++endif
+diff -urN /usr/share/empty/fs/aufs/loop.c linux/fs/aufs/loop.c
+--- /usr/share/empty/fs/aufs/loop.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/loop.c 2015-06-22 08:29:23.706757681 +0200
+@@ -0,0 +1,145 @@
++/*
++ * Copyright (C) 2005-2015 Junjiro R. Okajima
++ *
++ * This program, aufs is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ *
++ * This program is distributed in the hope that it will be useful,
++ * but WITHOUT ANY WARRANTY; without even the implied warranty of
++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++ * GNU General Public License for more details.
++ *
++ * You should have received a copy of the GNU General Public License
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
++ */
++
++/*
++ * support for loopback block device as a branch
++ */
++
++#include "aufs.h"
++
++/* added into drivers/block/loop.c */
++static struct file *(*backing_file_func)(struct super_block *sb);
++
++/*
++ * test if two lower dentries have overlapping branches.
++ */
++int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding)
++{
++ struct super_block *h_sb;
++ struct file *backing_file;
++
++ if (unlikely(!backing_file_func)) {
++ /* don't load "loop" module here */
++ backing_file_func = symbol_get(loop_backing_file);
++ if (unlikely(!backing_file_func))
++ /* "loop" module is not loaded */
++ return 0;
++ }
++
++ h_sb = h_adding->d_sb;
++ backing_file = backing_file_func(h_sb);
++ if (!backing_file)
++ return 0;
++
++ h_adding = backing_file->f_path.dentry;
++ /*
++ * h_adding can be local NFS.
++ * in this case aufs cannot detect the loop.
++ */
++ if (unlikely(h_adding->d_sb == sb))
++ return 1;
++ return !!au_test_subdir(h_adding, sb->s_root);
++}
++
++/* true if a kernel thread named 'loop[0-9].*' accesses a file */
++int au_test_loopback_kthread(void)
++{
++ int ret;
++ struct task_struct *tsk = current;
++ char c, comm[sizeof(tsk->comm)];
++
++ ret = 0;
++ if (tsk->flags & PF_KTHREAD) {
++ get_task_comm(comm, tsk);
++ c = comm[4];
++ ret = ('0' <= c && c <= '9'
++ && !strncmp(comm, "loop", 4));
++ }
++
++ return ret;
++}
++
++/* ---------------------------------------------------------------------- */
++
++#define au_warn_loopback_step 16
++static int au_warn_loopback_nelem = au_warn_loopback_step;
++static unsigned long *au_warn_loopback_array;
++
++void au_warn_loopback(struct super_block *h_sb)
++{
++ int i, new_nelem;
++ unsigned long *a, magic;
++ static DEFINE_SPINLOCK(spin);
++
++ magic = h_sb->s_magic;
++ spin_lock(&spin);
++ a = au_warn_loopback_array;
++ for (i = 0; i < au_warn_loopback_nelem && *a; i++)
++ if (a[i] == magic) {
++ spin_unlock(&spin);
++ return;
++ }
++
++ /* h_sb is new to us, print it */
++ if (i < au_warn_loopback_nelem) {
++ a[i] = magic;
++ goto pr;
++ }
++
++ /* expand the array */
++ new_nelem = au_warn_loopback_nelem + au_warn_loopback_step;
++ a = au_kzrealloc(au_warn_loopback_array,
++ au_warn_loopback_nelem * sizeof(unsigned long),
++ new_nelem * sizeof(unsigned long), GFP_ATOMIC);
++ if (a) {
++ au_warn_loopback_nelem = new_nelem;
++ au_warn_loopback_array = a;
++ a[i] = magic;
++ goto pr;
++ }
++
++ spin_unlock(&spin);
++ AuWarn1("realloc failed, ignored\n");
++ return;
++
++pr:
++ spin_unlock(&spin);
++ pr_warn("you may want to try another patch for loopback file "
++ "on %s(0x%lx) branch\n", au_sbtype(h_sb), magic);
++}
++
++int au_loopback_init(void)
++{
++ int err;
++ struct super_block *sb __maybe_unused;
++
++ AuDebugOn(sizeof(sb->s_magic) != sizeof(unsigned long));
++
++ err = 0;
++ au_warn_loopback_array = kcalloc(au_warn_loopback_step,
++ sizeof(unsigned long), GFP_NOFS);
++ if (unlikely(!au_warn_loopback_array))
++ err = -ENOMEM;
++
++ return err;
++}
++
++void au_loopback_fin(void)
++{
++ symbol_put(loop_backing_file);
++ kfree(au_warn_loopback_array);
++}
+diff -urN /usr/share/empty/fs/aufs/loop.h linux/fs/aufs/loop.h
+--- /usr/share/empty/fs/aufs/loop.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/loop.h 2015-06-22 08:27:37.884168534 +0200
+@@ -0,0 +1,52 @@
++/*
++ * Copyright (C) 2005-2015 Junjiro R. Okajima
++ *
++ * This program, aufs is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ *
++ * This program is distributed in the hope that it will be useful,
++ * but WITHOUT ANY WARRANTY; without even the implied warranty of
++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++ * GNU General Public License for more details.
++ *
++ * You should have received a copy of the GNU General Public License
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
++ */
++
++/*
++ * support for loopback mount as a branch
++ */
++
++#ifndef __AUFS_LOOP_H__
++#define __AUFS_LOOP_H__
++
++#ifdef __KERNEL__
++
++struct dentry;
++struct super_block;
++
++#ifdef CONFIG_AUFS_BDEV_LOOP
++/* drivers/block/loop.c */
++struct file *loop_backing_file(struct super_block *sb);
++
++/* loop.c */
++int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding);
++int au_test_loopback_kthread(void);
++void au_warn_loopback(struct super_block *h_sb);
++
++int au_loopback_init(void);
++void au_loopback_fin(void);
++#else
++AuStubInt0(au_test_loopback_overlap, struct super_block *sb,
++ struct dentry *h_adding)
++AuStubInt0(au_test_loopback_kthread, void)
++AuStubVoid(au_warn_loopback, struct super_block *h_sb)
+
-+config AUFS_PROC_MAP
-+ bool "support for /proc/maps and lsof(1)"
-+ depends on PROC_FS
-+ help
-+ When you issue mmap(2) in aufs, it is actually a direct mmap(2)
-+ call to the file on the branch fs since the file in aufs is
-+ purely virtual. And the file path printed in /proc/maps (and
-+ others) will be the path on the branch fs. In most cases, it
-+ does no harm. But some utilities like lsof(1) may confuse since
-+ the utility or user may expect the file path in aufs to be
-+ printed.
-+ To address this issue, aufs provides a patch which introduces a
-+ new member called vm_prfile into struct vm_are_struct. The patch
-+ is meaningless without enabling this configuration since nobody
-+ sets the new vm_prfile member.
-+ If you don't apply the patch, then enabling this configuration
-+ will cause a compile error.
-+ This approach is fragile since if someone else make some changes
-+ around vm_file, then vm_prfile may not work anymore. As a
-+ workaround such case, aufs provides this configuration. If you
-+ disable it, then lsof(1) may produce incorrect result but the
-+ problem will be gone even if the aufs patch is applied (I hope).
-+
-+config AUFS_SP_IATTR
-+ bool "Respect the attributes (mtime/ctime mainly) of special files"
-+ help
-+ When you write something to a special file, some attributes of it
-+ (mtime/ctime mainly) may be updated. Generally such updates are
-+ less important (actually some device drivers and NFS ignore
-+ it). But some applications (such like test program) requires
-+ such updates. If you need these updates, then enable this
-+ configuration which introduces some overhead.
-+ Currently this configuration handles FIFO only.
++AuStubInt0(au_loopback_init, void)
++AuStubVoid(au_loopback_fin, void)
++#endif /* BLK_DEV_LOOP */
+
-+config AUFS_SHWH
-+ bool "Show whiteouts"
-+ help
-+ If you want to make the whiteouts in aufs visible, then enable
-+ this option and specify 'shwh' mount option. Although it may
-+ sounds like philosophy or something, but in technically it
-+ simply shows the name of whiteout with keeping its behaviour.
++#endif /* __KERNEL__ */
++#endif /* __AUFS_LOOP_H__ */
+diff -urN /usr/share/empty/fs/aufs/magic.mk linux/fs/aufs/magic.mk
+--- /usr/share/empty/fs/aufs/magic.mk 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/magic.mk 2015-06-22 08:27:37.884168534 +0200
+@@ -0,0 +1,30 @@
+
-+config AUFS_BR_RAMFS
-+ bool "Ramfs (initramfs/rootfs) as an aufs branch"
-+ help
-+ If you want to use ramfs as an aufs branch fs, then enable this
-+ option. Generally tmpfs is recommended.
-+ Aufs prohibited them to be a branch fs by default, because
-+ initramfs becomes unusable after switch_root or something
-+ generally. If you sets initramfs as an aufs branch and boot your
-+ system by switch_root, you will meet a problem easily since the
-+ files in initramfs may be inaccessible.
-+ Unless you are going to use ramfs as an aufs branch fs without
-+ switch_root or something, leave it N.
++# defined in ${srctree}/fs/fuse/inode.c
++# tristate
++ifdef CONFIG_FUSE_FS
++ccflags-y += -DFUSE_SUPER_MAGIC=0x65735546
++endif
+
-+config AUFS_BR_FUSE
-+ bool "Fuse fs as an aufs branch"
-+ depends on FUSE_FS
-+ select AUFS_POLL
-+ help
-+ If you want to use fuse-based userspace filesystem as an aufs
-+ branch fs, then enable this option.
-+ It implements the internal poll(2) operation which is
-+ implemented by fuse only (curretnly).
++# defined in ${srctree}/fs/xfs/xfs_sb.h
++# tristate
++ifdef CONFIG_XFS_FS
++ccflags-y += -DXFS_SB_MAGIC=0x58465342
++endif
+
-+config AUFS_POLL
-+ bool
-+ help
-+ Automatic configuration for internal use.
++# defined in ${srctree}/fs/configfs/mount.c
++# tristate
++ifdef CONFIG_CONFIGFS_FS
++ccflags-y += -DCONFIGFS_MAGIC=0x62656570
++endif
+
-+config AUFS_BR_HFSPLUS
-+ bool "Hfsplus as an aufs branch"
-+ depends on HFSPLUS_FS
-+ default y
-+ help
-+ If you want to use hfsplus fs as an aufs branch fs, then enable
-+ this option. This option introduces a small overhead at
-+ copying-up a file on hfsplus.
++# defined in ${srctree}/fs/ubifs/ubifs.h
++# tristate
++ifdef CONFIG_UBIFS_FS
++ccflags-y += -DUBIFS_SUPER_MAGIC=0x24051905
++endif
+
-+config AUFS_BDEV_LOOP
-+ bool
-+ depends on BLK_DEV_LOOP
-+ default y
-+ help
-+ Automatic configuration for internal use.
-+ Convert =[ym] into =y.
++# defined in ${srctree}/fs/hfsplus/hfsplus_raw.h
++# tristate
++ifdef CONFIG_HFSPLUS_FS
++ccflags-y += -DHFSPLUS_SUPER_MAGIC=0x482b
++endif
+diff -urN /usr/share/empty/fs/aufs/Makefile linux/fs/aufs/Makefile
+--- /usr/share/empty/fs/aufs/Makefile 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/Makefile 2015-06-22 08:27:37.874168290 +0200
+@@ -0,0 +1,44 @@
+
-+config AUFS_DEBUG
-+ bool "Debug aufs"
-+ help
-+ Enable this to compile aufs internal debug code.
-+ It will have a negative impact to the performance.
++include ${src}/magic.mk
++ifeq (${CONFIG_AUFS_FS},m)
++include ${src}/conf.mk
++endif
++-include ${src}/priv_def.mk
+
-+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.
++# cf. include/linux/kernel.h
++# enable pr_debug
++ccflags-y += -DDEBUG
++# sparse requires the full pathname
++ifdef M
++ccflags-y += -include ${M}/../../include/uapi/linux/aufs_type.h
++else
++ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h
+endif
-diff -urN /usr/share/empty/fs/aufs/loop.c linux/fs/aufs/loop.c
---- /usr/share/empty/fs/aufs/loop.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/loop.c 2013-03-14 20:07:18.764260309 +0100
-@@ -0,0 +1,135 @@
++
++obj-$(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 wbr_policy.o \
++ dinfo.o dentry.o \
++ dynop.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 \
++ mvdown.o ioctl.o
++
++# all are boolean
++aufs-$(CONFIG_PROC_FS) += procfs.o plink.o
++aufs-$(CONFIG_SYSFS) += sysfs.o
++aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o
++aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o
++aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o
++aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o
++aufs-$(CONFIG_AUFS_EXPORT) += export.o
++aufs-$(CONFIG_AUFS_XATTR) += xattr.o
++aufs-$(CONFIG_FS_POSIX_ACL) += posix_acl.o
++aufs-$(CONFIG_AUFS_FHSM) += fhsm.o
++aufs-$(CONFIG_AUFS_POLL) += poll.o
++aufs-$(CONFIG_AUFS_RDU) += rdu.o
++aufs-$(CONFIG_AUFS_BR_HFSPLUS) += hfsplus.o
++aufs-$(CONFIG_AUFS_DEBUG) += debug.o
++aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o
+diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c
+--- /usr/share/empty/fs/aufs/module.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/module.c 2015-06-22 08:27:37.884168534 +0200
+@@ -0,0 +1,210 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
-+ * support for loopback block device as a branch
++ * module global variables and operations
+ */
+
-+#include <linux/loop.h>
++#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;
++}
++
++/* ---------------------------------------------------------------------- */
++
+/*
-+ * test if two lower dentries have overlapping branches.
++ * aufs caches
+ */
-+int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding)
++struct kmem_cache *au_cachep[AuCache_Last];
++static int __init au_cache_init(void)
+{
-+ struct super_block *h_sb;
-+ struct loop_device *l;
-+
-+ h_sb = h_adding->d_sb;
-+ if (MAJOR(h_sb->s_dev) != LOOP_MAJOR)
++ au_cachep[AuCache_DINFO] = AuCacheCtor(au_dinfo, au_di_init_once);
++ if (au_cachep[AuCache_DINFO])
++ /* SLAB_DESTROY_BY_RCU */
++ au_cachep[AuCache_ICNTNR] = AuCacheCtor(au_icntnr,
++ au_icntnr_init_once);
++ if (au_cachep[AuCache_ICNTNR])
++ au_cachep[AuCache_FINFO] = AuCacheCtor(au_finfo,
++ au_fi_init_once);
++ 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;
+
-+ l = h_sb->s_bdev->bd_disk->private_data;
-+ h_adding = l->lo_backing_file->f_dentry;
-+ /*
-+ * h_adding can be local NFS.
-+ * in this case aufs cannot detect the loop.
-+ */
-+ if (unlikely(h_adding->d_sb == sb))
-+ return 1;
-+ return !!au_test_subdir(h_adding, sb->s_root);
++ return -ENOMEM;
+}
+
-+/* true if a kernel thread named 'loop[0-9].*' accesses a file */
-+int au_test_loopback_kthread(void)
++static void au_cache_fin(void)
+{
-+ int ret;
-+ struct task_struct *tsk = current;
-+ char c, comm[sizeof(tsk->comm)];
++ int i;
+
-+ ret = 0;
-+ if (tsk->flags & PF_KTHREAD) {
-+ get_task_comm(comm, tsk);
-+ c = comm[4];
-+ ret = ('0' <= c && c <= '9'
-+ && !strncmp(comm, "loop", 4));
-+ }
++ /*
++ * Make sure all delayed rcu free inodes are flushed before we
++ * destroy cache.
++ */
++ rcu_barrier();
+
-+ return ret;
++ /* excluding AuCache_HNOTIFY */
++ BUILD_BUG_ON(AuCache_HNOTIFY + 1 != AuCache_Last);
++ for (i = 0; i < AuCache_HNOTIFY; i++)
++ if (au_cachep[i]) {
++ kmem_cache_destroy(au_cachep[i]);
++ au_cachep[i] = NULL;
++ }
+}
+
+/* ---------------------------------------------------------------------- */
+
-+#define au_warn_loopback_step 16
-+static int au_warn_loopback_nelem = au_warn_loopback_step;
-+static unsigned long *au_warn_loopback_array;
++int au_dir_roflags;
+
-+void au_warn_loopback(struct super_block *h_sb)
-+{
-+ int i, new_nelem;
-+ unsigned long *a, magic;
-+ static DEFINE_SPINLOCK(spin);
++#ifdef CONFIG_AUFS_SBILIST
++/*
++ * iterate_supers_type() doesn't protect us from
++ * remounting (branch management)
++ */
++struct au_splhead au_sbilist;
++#endif
++
++struct lock_class_key au_lc_key[AuLcKey_Last];
++
++/*
++ * functions for module interface.
++ */
++MODULE_LICENSE("GPL");
++/* MODULE_LICENSE("GPL v2"); */
++MODULE_AUTHOR("Junjiro R. Okajima <aufs-users@lists.sourceforge.net>");
++MODULE_DESCRIPTION(AUFS_NAME
++ " -- Advanced multi layered unification filesystem");
++MODULE_VERSION(AUFS_VERSION);
++MODULE_ALIAS_FS(AUFS_NAME);
+
-+ magic = h_sb->s_magic;
-+ spin_lock(&spin);
-+ a = au_warn_loopback_array;
-+ for (i = 0; i < au_warn_loopback_nelem && *a; i++)
-+ if (a[i] == magic) {
-+ spin_unlock(&spin);
-+ return;
-+ }
++/* 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);
+
-+ /* h_sb is new to us, print it */
-+ if (i < au_warn_loopback_nelem) {
-+ a[i] = magic;
-+ goto pr;
-+ }
++/* this module parameter has no meaning when USER_NS is disabled */
++static bool au_userns;
++MODULE_PARM_DESC(allow_userns, "allow unprivileged to mount under userns");
++module_param_named(allow_userns, au_userns, bool, S_IRUGO);
+
-+ /* expand the array */
-+ new_nelem = au_warn_loopback_nelem + au_warn_loopback_step;
-+ a = au_kzrealloc(au_warn_loopback_array,
-+ au_warn_loopback_nelem * sizeof(unsigned long),
-+ new_nelem * sizeof(unsigned long), GFP_ATOMIC);
-+ if (a) {
-+ au_warn_loopback_nelem = new_nelem;
-+ au_warn_loopback_array = a;
-+ a[i] = magic;
-+ goto pr;
-+ }
++/* ---------------------------------------------------------------------- */
+
-+ spin_unlock(&spin);
-+ AuWarn1("realloc failed, ignored\n");
-+ return;
++static char au_esc_chars[0x20 + 3]; /* 0x01-0x20, backslash, del, and NULL */
+
-+pr:
-+ spin_unlock(&spin);
-+ pr_warn("you may want to try another patch for loopback file "
-+ "on %s(0x%lx) branch\n", au_sbtype(h_sb), magic);
++int au_seq_path(struct seq_file *seq, struct path *path)
++{
++ return seq_path(seq, path, au_esc_chars);
+}
+
-+int au_loopback_init(void)
++/* ---------------------------------------------------------------------- */
++
++static int __init aufs_init(void)
+{
-+ int err;
-+ struct super_block *sb __maybe_unused;
++ int err, i;
++ char *p;
+
-+ AuDebugOn(sizeof(sb->s_magic) != sizeof(unsigned long));
++ p = au_esc_chars;
++ for (i = 1; i <= ' '; i++)
++ *p++ = i;
++ *p++ = '\\';
++ *p++ = '\x7f';
++ *p = 0;
+
-+ err = 0;
-+ au_warn_loopback_array = kcalloc(au_warn_loopback_step,
-+ sizeof(unsigned long), GFP_NOFS);
-+ if (unlikely(!au_warn_loopback_array))
-+ err = -ENOMEM;
++ au_dir_roflags = au_file_roflags(O_DIRECTORY | O_LARGEFILE);
++
++ au_sbilist_init();
++ sysaufs_brs_init();
++ au_debug_init();
++ au_dy_init();
++ err = sysaufs_init();
++ if (unlikely(err))
++ goto out;
++ err = au_procfs_init();
++ if (unlikely(err))
++ goto out_sysaufs;
++ err = au_wkq_init();
++ if (unlikely(err))
++ goto out_procfs;
++ err = au_loopback_init();
++ if (unlikely(err))
++ goto out_wkq;
++ err = au_hnotify_init();
++ if (unlikely(err))
++ goto out_loopback;
++ err = au_sysrq_init();
++ if (unlikely(err))
++ goto out_hin;
++ err = au_cache_init();
++ if (unlikely(err))
++ goto out_sysrq;
++
++ aufs_fs_type.fs_flags |= au_userns ? FS_USERNS_MOUNT : 0;
++ err = register_filesystem(&aufs_fs_type);
++ if (unlikely(err))
++ goto out_cache;
++
++ /* since we define pr_fmt, call printk directly */
++ printk(KERN_INFO AUFS_NAME " " AUFS_VERSION "\n");
++ goto out; /* success */
+
++out_cache:
++ au_cache_fin();
++out_sysrq:
++ au_sysrq_fin();
++out_hin:
++ au_hnotify_fin();
++out_loopback:
++ au_loopback_fin();
++out_wkq:
++ au_wkq_fin();
++out_procfs:
++ au_procfs_fin();
++out_sysaufs:
++ sysaufs_fin();
++ au_dy_fin();
++out:
+ return err;
+}
+
-+void au_loopback_fin(void)
++static void __exit aufs_exit(void)
+{
-+ kfree(au_warn_loopback_array);
++ unregister_filesystem(&aufs_fs_type);
++ au_cache_fin();
++ au_sysrq_fin();
++ au_hnotify_fin();
++ au_loopback_fin();
++ au_wkq_fin();
++ au_procfs_fin();
++ sysaufs_fin();
++ au_dy_fin();
+}
-diff -urN /usr/share/empty/fs/aufs/loop.h linux/fs/aufs/loop.h
---- /usr/share/empty/fs/aufs/loop.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/loop.h 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,50 @@
++
++module_init(aufs_init);
++module_exit(aufs_exit);
+diff -urN /usr/share/empty/fs/aufs/module.h linux/fs/aufs/module.h
+--- /usr/share/empty/fs/aufs/module.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/module.h 2015-06-22 08:27:37.884168534 +0200
+@@ -0,0 +1,104 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
-+ * support for loopback mount as a branch
++ * module initialization and module-global
+ */
+
-+#ifndef __AUFS_LOOP_H__
-+#define __AUFS_LOOP_H__
++#ifndef __AUFS_MODULE_H__
++#define __AUFS_MODULE_H__
+
+#ifdef __KERNEL__
+
-+struct dentry;
-+struct super_block;
-+
-+#ifdef CONFIG_AUFS_BDEV_LOOP
-+/* loop.c */
-+int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding);
-+int au_test_loopback_kthread(void);
-+void au_warn_loopback(struct super_block *h_sb);
++#include <linux/slab.h>
+
-+int au_loopback_init(void);
-+void au_loopback_fin(void);
-+#else
-+AuStubInt0(au_test_loopback_overlap, struct super_block *sb,
-+ struct dentry *h_adding)
-+AuStubInt0(au_test_loopback_kthread, void)
-+AuStubVoid(au_warn_loopback, struct super_block *h_sb)
++struct path;
++struct seq_file;
+
-+AuStubInt0(au_loopback_init, void)
-+AuStubVoid(au_loopback_fin, void)
-+#endif /* BLK_DEV_LOOP */
++/* module parameters */
++extern int sysaufs_brs;
+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_LOOP_H__ */
-diff -urN /usr/share/empty/fs/aufs/magic.mk linux/fs/aufs/magic.mk
---- /usr/share/empty/fs/aufs/magic.mk 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/magic.mk 2012-08-26 08:39:00.760508065 +0200
-@@ -0,0 +1,54 @@
++/* ---------------------------------------------------------------------- */
+
-+# defined in ${srctree}/fs/fuse/inode.c
-+# tristate
-+ifdef CONFIG_FUSE_FS
-+ccflags-y += -DFUSE_SUPER_MAGIC=0x65735546
-+endif
++extern int au_dir_roflags;
+
-+# defined in ${srctree}/fs/ocfs2/ocfs2_fs.h
-+# tristate
-+ifdef CONFIG_OCFS2_FS
-+ccflags-y += -DOCFS2_SUPER_MAGIC=0x7461636f
-+endif
++enum {
++ AuLcNonDir_FIINFO,
++ AuLcNonDir_DIINFO,
++ AuLcNonDir_IIINFO,
+
-+# defined in ${srctree}/fs/ocfs2/dlm/userdlm.h
-+# tristate
-+ifdef CONFIG_OCFS2_FS_O2CB
-+ccflags-y += -DDLMFS_MAGIC=0x76a9f425
-+endif
++ AuLcDir_FIINFO,
++ AuLcDir_DIINFO,
++ AuLcDir_IIINFO,
+
-+# defined in ${srctree}/fs/cifs/cifsfs.c
-+# tristate
-+ifdef CONFIG_CIFS_FS
-+ccflags-y += -DCIFS_MAGIC_NUMBER=0xFF534D42
-+endif
++ AuLcSymlink_DIINFO,
++ AuLcSymlink_IIINFO,
+
-+# defined in ${srctree}/fs/xfs/xfs_sb.h
-+# tristate
-+ifdef CONFIG_XFS_FS
-+ccflags-y += -DXFS_SB_MAGIC=0x58465342
-+endif
++ AuLcKey_Last
++};
++extern struct lock_class_key au_lc_key[AuLcKey_Last];
+
-+# defined in ${srctree}/fs/configfs/mount.c
-+# tristate
-+ifdef CONFIG_CONFIGFS_FS
-+ccflags-y += -DCONFIGFS_MAGIC=0x62656570
-+endif
++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);
+
-+# defined in ${srctree}/fs/9p/v9fs.h
-+# tristate
-+ifdef CONFIG_9P_FS
-+ccflags-y += -DV9FS_MAGIC=0x01021997
-+endif
++#ifdef CONFIG_PROC_FS
++/* procfs.c */
++int __init au_procfs_init(void);
++void au_procfs_fin(void);
++#else
++AuStubInt0(au_procfs_init, void);
++AuStubVoid(au_procfs_fin, void);
++#endif
+
-+# defined in ${srctree}/fs/ubifs/ubifs.h
-+# tristate
-+ifdef CONFIG_UBIFS_FS
-+ccflags-y += -DUBIFS_SUPER_MAGIC=0x24051905
-+endif
++/* ---------------------------------------------------------------------- */
+
-+# defined in ${srctree}/fs/hfsplus/hfsplus_raw.h
-+# tristate
-+ifdef CONFIG_HFSPLUS_FS
-+ccflags-y += -DHFSPLUS_SUPER_MAGIC=0x482b
-+endif
-diff -urN /usr/share/empty/fs/aufs/Makefile linux/fs/aufs/Makefile
---- /usr/share/empty/fs/aufs/Makefile 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/Makefile 2012-08-26 08:39:00.757174634 +0200
-@@ -0,0 +1,42 @@
++/* kmem cache */
++enum {
++ AuCache_DINFO,
++ AuCache_ICNTNR,
++ AuCache_FINFO,
++ AuCache_VDIR,
++ AuCache_DEHSTR,
++ AuCache_HNOTIFY, /* must be last */
++ AuCache_Last
++};
+
-+include ${src}/magic.mk
-+ifeq (${CONFIG_AUFS_FS},m)
-+include ${src}/conf.mk
-+endif
-+-include ${src}/priv_def.mk
++#define AuCacheFlags (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD)
++#define AuCache(type) KMEM_CACHE(type, AuCacheFlags)
++#define AuCacheCtor(type, ctor) \
++ kmem_cache_create(#type, sizeof(struct type), \
++ __alignof__(struct type), AuCacheFlags, ctor)
+
-+# cf. include/linux/kernel.h
-+# enable pr_debug
-+ccflags-y += -DDEBUG
-+# sparse requires the full pathname
-+ifdef M
-+ccflags-y += -include ${M}/../../include/linux/aufs_type.h
-+else
-+ccflags-y += -include ${srctree}/include/linux/aufs_type.h
-+endif
++extern struct kmem_cache *au_cachep[];
+
-+obj-$(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 wbr_policy.o \
-+ dinfo.o dentry.o \
-+ dynop.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
++#define AuCacheFuncs(name, index) \
++static inline struct au_##name *au_cache_alloc_##name(void) \
++{ return kmem_cache_alloc(au_cachep[AuCache_##index], GFP_NOFS); } \
++static inline void au_cache_free_##name(struct au_##name *p) \
++{ kmem_cache_free(au_cachep[AuCache_##index], p); }
+
-+# all are boolean
-+aufs-$(CONFIG_PROC_FS) += procfs.o plink.o
-+aufs-$(CONFIG_SYSFS) += sysfs.o
-+aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o
-+aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o
-+aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o
-+aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o
-+aufs-$(CONFIG_AUFS_EXPORT) += export.o
-+aufs-$(CONFIG_AUFS_POLL) += poll.o
-+aufs-$(CONFIG_AUFS_RDU) += rdu.o
-+aufs-$(CONFIG_AUFS_SP_IATTR) += f_op_sp.o
-+aufs-$(CONFIG_AUFS_BR_HFSPLUS) += hfsplus.o
-+aufs-$(CONFIG_AUFS_DEBUG) += debug.o
-+aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o
-diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c
---- /usr/share/empty/fs/aufs/module.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/module.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,202 @@
++AuCacheFuncs(dinfo, DINFO);
++AuCacheFuncs(icntnr, ICNTNR);
++AuCacheFuncs(finfo, FINFO);
++AuCacheFuncs(vdir, VDIR);
++AuCacheFuncs(vdir_dehstr, DEHSTR);
++#ifdef CONFIG_AUFS_HNOTIFY
++AuCacheFuncs(hnotify, HNOTIFY);
++#endif
++
++#endif /* __KERNEL__ */
++#endif /* __AUFS_MODULE_H__ */
+diff -urN /usr/share/empty/fs/aufs/mvdown.c linux/fs/aufs/mvdown.c
+--- /usr/share/empty/fs/aufs/mvdown.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/mvdown.c 2015-06-22 08:27:37.884168534 +0200
+@@ -0,0 +1,694 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2011-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
-+ * module global variables and operations
++ * move-down, opposite of copy-up
+ */
+
-+#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)
++struct au_mvd_args {
++ struct {
++ struct super_block *h_sb;
++ struct dentry *h_parent;
++ struct au_hinode *hdir;
++ struct inode *h_dir, *h_inode;
++ struct au_pin pin;
++ } info[AUFS_MVDOWN_NARRAY];
++
++ struct aufs_mvdown mvdown;
++ struct dentry *dentry, *parent;
++ struct inode *inode, *dir;
++ struct super_block *sb;
++ aufs_bindex_t bopq, bwh, bfound;
++ unsigned char rename_lock;
++};
++
++#define mvd_errno mvdown.au_errno
++#define mvd_bsrc mvdown.stbr[AUFS_MVDOWN_UPPER].bindex
++#define mvd_src_brid mvdown.stbr[AUFS_MVDOWN_UPPER].brid
++#define mvd_bdst mvdown.stbr[AUFS_MVDOWN_LOWER].bindex
++#define mvd_dst_brid mvdown.stbr[AUFS_MVDOWN_LOWER].brid
++
++#define mvd_h_src_sb info[AUFS_MVDOWN_UPPER].h_sb
++#define mvd_h_src_parent info[AUFS_MVDOWN_UPPER].h_parent
++#define mvd_hdir_src info[AUFS_MVDOWN_UPPER].hdir
++#define mvd_h_src_dir info[AUFS_MVDOWN_UPPER].h_dir
++#define mvd_h_src_inode info[AUFS_MVDOWN_UPPER].h_inode
++#define mvd_pin_src info[AUFS_MVDOWN_UPPER].pin
++
++#define mvd_h_dst_sb info[AUFS_MVDOWN_LOWER].h_sb
++#define mvd_h_dst_parent info[AUFS_MVDOWN_LOWER].h_parent
++#define mvd_hdir_dst info[AUFS_MVDOWN_LOWER].hdir
++#define mvd_h_dst_dir info[AUFS_MVDOWN_LOWER].h_dir
++#define mvd_h_dst_inode info[AUFS_MVDOWN_LOWER].h_inode
++#define mvd_pin_dst info[AUFS_MVDOWN_LOWER].pin
++
++#define AU_MVD_PR(flag, ...) do { \
++ if (flag) \
++ pr_err(__VA_ARGS__); \
++ } while (0)
++
++static int find_lower_writable(struct au_mvd_args *a)
+{
-+ if (new_sz <= nused)
-+ return p;
++ struct super_block *sb;
++ aufs_bindex_t bindex, bend;
++ struct au_branch *br;
+
-+ p = krealloc(p, new_sz, gfp);
-+ if (p)
-+ memset(p + nused, 0, new_sz - nused);
-+ return p;
-+}
++ sb = a->sb;
++ bindex = a->mvd_bsrc;
++ bend = au_sbend(sb);
++ if (a->mvdown.flags & AUFS_MVDOWN_FHSM_LOWER)
++ for (bindex++; bindex <= bend; bindex++) {
++ br = au_sbr(sb, bindex);
++ if (au_br_fhsm(br->br_perm)
++ && (!(au_br_sb(br)->s_flags & MS_RDONLY)))
++ return bindex;
++ }
++ else if (!(a->mvdown.flags & AUFS_MVDOWN_ROLOWER))
++ for (bindex++; bindex <= bend; bindex++) {
++ br = au_sbr(sb, bindex);
++ if (!au_br_rdonly(br))
++ return bindex;
++ }
++ else
++ for (bindex++; bindex <= bend; bindex++) {
++ br = au_sbr(sb, bindex);
++ if (!(au_br_sb(br)->s_flags & MS_RDONLY)) {
++ if (au_br_rdonly(br))
++ a->mvdown.flags
++ |= AUFS_MVDOWN_ROLOWER_R;
++ return bindex;
++ }
++ }
+
-+/* ---------------------------------------------------------------------- */
++ return -1;
++}
+
-+/*
-+ * aufs caches
-+ */
-+struct kmem_cache *au_cachep[AuCache_Last];
-+static int __init au_cache_init(void)
++/* make the parent dir on bdst */
++static int au_do_mkdir(const unsigned char dmsg, struct au_mvd_args *a)
+{
-+ au_cachep[AuCache_DINFO] = AuCacheCtor(au_dinfo, au_di_init_once);
-+ if (au_cachep[AuCache_DINFO])
-+ /* SLAB_DESTROY_BY_RCU */
-+ au_cachep[AuCache_ICNTNR] = AuCacheCtor(au_icntnr,
-+ au_icntnr_init_once);
-+ if (au_cachep[AuCache_ICNTNR])
-+ au_cachep[AuCache_FINFO] = AuCacheCtor(au_finfo,
-+ au_fi_init_once);
-+ 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;
++ int err;
+
-+ return -ENOMEM;
++ err = 0;
++ a->mvd_hdir_src = au_hi(a->dir, a->mvd_bsrc);
++ a->mvd_hdir_dst = au_hi(a->dir, a->mvd_bdst);
++ a->mvd_h_src_parent = au_h_dptr(a->parent, a->mvd_bsrc);
++ a->mvd_h_dst_parent = NULL;
++ if (au_dbend(a->parent) >= a->mvd_bdst)
++ a->mvd_h_dst_parent = au_h_dptr(a->parent, a->mvd_bdst);
++ if (!a->mvd_h_dst_parent) {
++ err = au_cpdown_dirs(a->dentry, a->mvd_bdst);
++ if (unlikely(err)) {
++ AU_MVD_PR(dmsg, "cpdown_dirs failed\n");
++ goto out;
++ }
++ a->mvd_h_dst_parent = au_h_dptr(a->parent, a->mvd_bdst);
++ }
++
++out:
++ AuTraceErr(err);
++ return err;
+}
+
-+static void au_cache_fin(void)
++/* lock them all */
++static int au_do_lock(const unsigned char dmsg, struct au_mvd_args *a)
+{
-+ int i;
++ int err;
++ struct dentry *h_trap;
+
-+ /*
-+ * Make sure all delayed rcu free inodes are flushed before we
-+ * destroy cache.
-+ */
-+ rcu_barrier();
++ a->mvd_h_src_sb = au_sbr_sb(a->sb, a->mvd_bsrc);
++ a->mvd_h_dst_sb = au_sbr_sb(a->sb, a->mvd_bdst);
++ err = au_pin(&a->mvd_pin_dst, a->dentry, a->mvd_bdst,
++ au_opt_udba(a->sb),
++ AuPin_MNT_WRITE | AuPin_DI_LOCKED);
++ AuTraceErr(err);
++ if (unlikely(err)) {
++ AU_MVD_PR(dmsg, "pin_dst failed\n");
++ goto out;
++ }
+
-+ /* excluding AuCache_HNOTIFY */
-+ BUILD_BUG_ON(AuCache_HNOTIFY + 1 != AuCache_Last);
-+ for (i = 0; i < AuCache_HNOTIFY; i++)
-+ if (au_cachep[i]) {
-+ kmem_cache_destroy(au_cachep[i]);
-+ au_cachep[i] = NULL;
++ if (a->mvd_h_src_sb != a->mvd_h_dst_sb) {
++ a->rename_lock = 0;
++ au_pin_init(&a->mvd_pin_src, a->dentry, a->mvd_bsrc,
++ AuLsc_DI_PARENT, AuLsc_I_PARENT3,
++ au_opt_udba(a->sb),
++ AuPin_MNT_WRITE | AuPin_DI_LOCKED);
++ err = au_do_pin(&a->mvd_pin_src);
++ AuTraceErr(err);
++ a->mvd_h_src_dir = a->mvd_h_src_parent->d_inode;
++ if (unlikely(err)) {
++ AU_MVD_PR(dmsg, "pin_src failed\n");
++ goto out_dst;
+ }
++ goto out; /* success */
++ }
++
++ a->rename_lock = 1;
++ au_pin_hdir_unlock(&a->mvd_pin_dst);
++ err = au_pin(&a->mvd_pin_src, a->dentry, a->mvd_bsrc,
++ au_opt_udba(a->sb),
++ AuPin_MNT_WRITE | AuPin_DI_LOCKED);
++ AuTraceErr(err);
++ a->mvd_h_src_dir = a->mvd_h_src_parent->d_inode;
++ if (unlikely(err)) {
++ AU_MVD_PR(dmsg, "pin_src failed\n");
++ au_pin_hdir_lock(&a->mvd_pin_dst);
++ goto out_dst;
++ }
++ au_pin_hdir_unlock(&a->mvd_pin_src);
++ h_trap = vfsub_lock_rename(a->mvd_h_src_parent, a->mvd_hdir_src,
++ a->mvd_h_dst_parent, a->mvd_hdir_dst);
++ if (h_trap) {
++ err = (h_trap != a->mvd_h_src_parent);
++ if (err)
++ err = (h_trap != a->mvd_h_dst_parent);
++ }
++ BUG_ON(err); /* it should never happen */
++ if (unlikely(a->mvd_h_src_dir != au_pinned_h_dir(&a->mvd_pin_src))) {
++ err = -EBUSY;
++ AuTraceErr(err);
++ vfsub_unlock_rename(a->mvd_h_src_parent, a->mvd_hdir_src,
++ a->mvd_h_dst_parent, a->mvd_hdir_dst);
++ au_pin_hdir_lock(&a->mvd_pin_src);
++ au_unpin(&a->mvd_pin_src);
++ au_pin_hdir_lock(&a->mvd_pin_dst);
++ goto out_dst;
++ }
++ goto out; /* success */
++
++out_dst:
++ au_unpin(&a->mvd_pin_dst);
++out:
++ AuTraceErr(err);
++ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
++static void au_do_unlock(const unsigned char dmsg, struct au_mvd_args *a)
++{
++ if (!a->rename_lock)
++ au_unpin(&a->mvd_pin_src);
++ else {
++ vfsub_unlock_rename(a->mvd_h_src_parent, a->mvd_hdir_src,
++ a->mvd_h_dst_parent, a->mvd_hdir_dst);
++ au_pin_hdir_lock(&a->mvd_pin_src);
++ au_unpin(&a->mvd_pin_src);
++ au_pin_hdir_lock(&a->mvd_pin_dst);
++ }
++ au_unpin(&a->mvd_pin_dst);
++}
+
-+int au_dir_roflags;
++/* copy-down the file */
++static int au_do_cpdown(const unsigned char dmsg, struct au_mvd_args *a)
++{
++ int err;
++ struct au_cp_generic cpg = {
++ .dentry = a->dentry,
++ .bdst = a->mvd_bdst,
++ .bsrc = a->mvd_bsrc,
++ .len = -1,
++ .pin = &a->mvd_pin_dst,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN
++ };
++
++ AuDbg("b%d, b%d\n", cpg.bsrc, cpg.bdst);
++ if (a->mvdown.flags & AUFS_MVDOWN_OWLOWER)
++ au_fset_cpup(cpg.flags, OVERWRITE);
++ if (a->mvdown.flags & AUFS_MVDOWN_ROLOWER)
++ au_fset_cpup(cpg.flags, RWDST);
++ err = au_sio_cpdown_simple(&cpg);
++ if (unlikely(err))
++ AU_MVD_PR(dmsg, "cpdown failed\n");
++
++ AuTraceErr(err);
++ return err;
++}
+
-+#ifdef CONFIG_AUFS_SBILIST
+/*
-+ * iterate_supers_type() doesn't protect us from
-+ * remounting (branch management)
++ * unlink the whiteout on bdst if exist which may be created by UDBA while we
++ * were sleeping
+ */
-+struct au_splhead au_sbilist;
-+#endif
++static int au_do_unlink_wh(const unsigned char dmsg, struct au_mvd_args *a)
++{
++ int err;
++ struct path h_path;
++ struct au_branch *br;
++ struct inode *delegated;
+
-+struct lock_class_key au_lc_key[AuLcKey_Last];
++ br = au_sbr(a->sb, a->mvd_bdst);
++ h_path.dentry = au_wh_lkup(a->mvd_h_dst_parent, &a->dentry->d_name, br);
++ err = PTR_ERR(h_path.dentry);
++ if (IS_ERR(h_path.dentry)) {
++ AU_MVD_PR(dmsg, "wh_lkup failed\n");
++ goto out;
++ }
++
++ err = 0;
++ if (h_path.dentry->d_inode) {
++ h_path.mnt = au_br_mnt(br);
++ delegated = NULL;
++ err = vfsub_unlink(a->mvd_h_dst_parent->d_inode, &h_path,
++ &delegated, /*force*/0);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
++ }
++ if (unlikely(err))
++ AU_MVD_PR(dmsg, "wh_unlink failed\n");
++ }
++ dput(h_path.dentry);
++
++out:
++ AuTraceErr(err);
++ return err;
++}
+
+/*
-+ * functions for module interface.
++ * unlink the topmost h_dentry
+ */
-+MODULE_LICENSE("GPL");
-+/* MODULE_LICENSE("GPL v2"); */
-+MODULE_AUTHOR("Junjiro R. Okajima <aufs-users@lists.sourceforge.net>");
-+MODULE_DESCRIPTION(AUFS_NAME
-+ " -- Advanced multi layered unification filesystem");
-+MODULE_VERSION(AUFS_VERSION);
++static int au_do_unlink(const unsigned char dmsg, struct au_mvd_args *a)
++{
++ int err;
++ struct path h_path;
++ struct inode *delegated;
+
-+/* 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);
++ h_path.mnt = au_sbr_mnt(a->sb, a->mvd_bsrc);
++ h_path.dentry = au_h_dptr(a->dentry, a->mvd_bsrc);
++ delegated = NULL;
++ err = vfsub_unlink(a->mvd_h_src_dir, &h_path, &delegated, /*force*/0);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
++ }
++ if (unlikely(err))
++ AU_MVD_PR(dmsg, "unlink failed\n");
+
-+/* ---------------------------------------------------------------------- */
++ AuTraceErr(err);
++ return err;
++}
+
-+static char au_esc_chars[0x20 + 3]; /* 0x01-0x20, backslash, del, and NULL */
++/* Since mvdown succeeded, we ignore an error of this function */
++static void au_do_stfs(const unsigned char dmsg, struct au_mvd_args *a)
++{
++ int err;
++ struct au_branch *br;
+
-+int au_seq_path(struct seq_file *seq, struct path *path)
++ a->mvdown.flags |= AUFS_MVDOWN_STFS_FAILED;
++ br = au_sbr(a->sb, a->mvd_bsrc);
++ err = au_br_stfs(br, &a->mvdown.stbr[AUFS_MVDOWN_UPPER].stfs);
++ if (!err) {
++ br = au_sbr(a->sb, a->mvd_bdst);
++ a->mvdown.stbr[AUFS_MVDOWN_LOWER].brid = br->br_id;
++ err = au_br_stfs(br, &a->mvdown.stbr[AUFS_MVDOWN_LOWER].stfs);
++ }
++ if (!err)
++ a->mvdown.flags &= ~AUFS_MVDOWN_STFS_FAILED;
++ else
++ AU_MVD_PR(dmsg, "statfs failed (%d), ignored\n", err);
++}
++
++/*
++ * copy-down the file and unlink the bsrc file.
++ * - unlink the bdst whout if exist
++ * - copy-down the file (with whtmp name and rename)
++ * - unlink the bsrc file
++ */
++static int au_do_mvdown(const unsigned char dmsg, struct au_mvd_args *a)
+{
-+ return seq_path(seq, path, au_esc_chars);
++ int err;
++
++ err = au_do_mkdir(dmsg, a);
++ if (!err)
++ err = au_do_lock(dmsg, a);
++ if (unlikely(err))
++ goto out;
++
++ /*
++ * do not revert the activities we made on bdst since they should be
++ * harmless in aufs.
++ */
++
++ err = au_do_cpdown(dmsg, a);
++ if (!err)
++ err = au_do_unlink_wh(dmsg, a);
++ if (!err && !(a->mvdown.flags & AUFS_MVDOWN_KUPPER))
++ err = au_do_unlink(dmsg, a);
++ if (unlikely(err))
++ goto out_unlock;
++
++ AuDbg("%pd2, 0x%x, %d --> %d\n",
++ a->dentry, a->mvdown.flags, a->mvd_bsrc, a->mvd_bdst);
++ if (find_lower_writable(a) < 0)
++ a->mvdown.flags |= AUFS_MVDOWN_BOTTOM;
++
++ if (a->mvdown.flags & AUFS_MVDOWN_STFS)
++ au_do_stfs(dmsg, a);
++
++ /* maintain internal array */
++ if (!(a->mvdown.flags & AUFS_MVDOWN_KUPPER)) {
++ au_set_h_dptr(a->dentry, a->mvd_bsrc, NULL);
++ au_set_dbstart(a->dentry, a->mvd_bdst);
++ au_set_h_iptr(a->inode, a->mvd_bsrc, NULL, /*flags*/0);
++ au_set_ibstart(a->inode, a->mvd_bdst);
++ }
++ if (au_dbend(a->dentry) < a->mvd_bdst)
++ au_set_dbend(a->dentry, a->mvd_bdst);
++ if (au_ibend(a->inode) < a->mvd_bdst)
++ au_set_ibend(a->inode, a->mvd_bdst);
++
++out_unlock:
++ au_do_unlock(dmsg, a);
++out:
++ AuTraceErr(err);
++ return err;
++}
++
++/* ---------------------------------------------------------------------- */
++
++/* make sure the file is idle */
++static int au_mvd_args_busy(const unsigned char dmsg, struct au_mvd_args *a)
++{
++ int err, plinked;
++
++ err = 0;
++ plinked = !!au_opt_test(au_mntflags(a->sb), PLINK);
++ if (au_dbstart(a->dentry) == a->mvd_bsrc
++ && au_dcount(a->dentry) == 1
++ && atomic_read(&a->inode->i_count) == 1
++ /* && a->mvd_h_src_inode->i_nlink == 1 */
++ && (!plinked || !au_plink_test(a->inode))
++ && a->inode->i_nlink == 1)
++ goto out;
++
++ err = -EBUSY;
++ AU_MVD_PR(dmsg,
++ "b%d, d{b%d, c%d?}, i{c%d?, l%u}, hi{l%u}, p{%d, %d}\n",
++ a->mvd_bsrc, au_dbstart(a->dentry), au_dcount(a->dentry),
++ atomic_read(&a->inode->i_count), a->inode->i_nlink,
++ a->mvd_h_src_inode->i_nlink,
++ plinked, plinked ? au_plink_test(a->inode) : 0);
++
++out:
++ AuTraceErr(err);
++ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+static int __init aufs_init(void)
++/* make sure the parent dir is fine */
++static int au_mvd_args_parent(const unsigned char dmsg,
++ struct au_mvd_args *a)
+{
-+ 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);
++ int err;
++ aufs_bindex_t bindex;
+
-+ au_sbilist_init();
-+ sysaufs_brs_init();
-+ au_debug_init();
-+ au_dy_init();
-+ err = sysaufs_init();
-+ if (unlikely(err))
++ err = 0;
++ if (unlikely(au_alive_dir(a->parent))) {
++ err = -ENOENT;
++ AU_MVD_PR(dmsg, "parent dir is dead\n");
+ goto out;
-+ err = au_procfs_init();
-+ if (unlikely(err))
-+ goto out_sysaufs;
-+ err = au_wkq_init();
-+ if (unlikely(err))
-+ goto out_procfs;
-+ err = au_loopback_init();
-+ if (unlikely(err))
-+ goto out_wkq;
-+ err = au_hnotify_init();
-+ if (unlikely(err))
-+ goto out_loopback;
-+ 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;
-+ /* since we define pr_fmt, call printk directly */
-+ printk(KERN_INFO AUFS_NAME " " AUFS_VERSION "\n");
-+ goto out; /* success */
++ }
++
++ a->bopq = au_dbdiropq(a->parent);
++ bindex = au_wbr_nonopq(a->dentry, a->mvd_bdst);
++ AuDbg("b%d\n", bindex);
++ if (unlikely((bindex >= 0 && bindex < a->mvd_bdst)
++ || (a->bopq != -1 && a->bopq < a->mvd_bdst))) {
++ err = -EINVAL;
++ a->mvd_errno = EAU_MVDOWN_OPAQUE;
++ AU_MVD_PR(dmsg, "ancestor is opaque b%d, b%d\n",
++ a->bopq, a->mvd_bdst);
++ }
+
-+out_cache:
-+ au_cache_fin();
-+out_sysrq:
-+ au_sysrq_fin();
-+out_hin:
-+ au_hnotify_fin();
-+out_loopback:
-+ au_loopback_fin();
-+out_wkq:
-+ au_wkq_fin();
-+out_procfs:
-+ au_procfs_fin();
-+out_sysaufs:
-+ sysaufs_fin();
-+ au_dy_fin();
+out:
++ AuTraceErr(err);
+ return err;
+}
+
-+static void __exit aufs_exit(void)
++static int au_mvd_args_intermediate(const unsigned char dmsg,
++ struct au_mvd_args *a)
+{
-+ unregister_filesystem(&aufs_fs_type);
-+ au_cache_fin();
-+ au_sysrq_fin();
-+ au_hnotify_fin();
-+ au_loopback_fin();
-+ au_wkq_fin();
-+ au_procfs_fin();
-+ sysaufs_fin();
-+ au_dy_fin();
-+}
++ int err;
++ struct au_dinfo *dinfo, *tmp;
+
-+module_init(aufs_init);
-+module_exit(aufs_exit);
-diff -urN /usr/share/empty/fs/aufs/module.h linux/fs/aufs/module.h
---- /usr/share/empty/fs/aufs/module.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/module.h 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,105 @@
-+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-+ */
++ /* lookup the next lower positive entry */
++ err = -ENOMEM;
++ tmp = au_di_alloc(a->sb, AuLsc_DI_TMP);
++ if (unlikely(!tmp))
++ goto out;
+
-+/*
-+ * module initialization and module-global
-+ */
++ a->bfound = -1;
++ a->bwh = -1;
++ dinfo = au_di(a->dentry);
++ au_di_cp(tmp, dinfo);
++ au_di_swap(tmp, dinfo);
+
-+#ifndef __AUFS_MODULE_H__
-+#define __AUFS_MODULE_H__
++ /* returns the number of positive dentries */
++ err = au_lkup_dentry(a->dentry, a->mvd_bsrc + 1, /*type*/0);
++ if (!err)
++ a->bwh = au_dbwh(a->dentry);
++ else if (err > 0)
++ a->bfound = au_dbstart(a->dentry);
+
-+#ifdef __KERNEL__
++ au_di_swap(tmp, dinfo);
++ au_rw_write_unlock(&tmp->di_rwsem);
++ au_di_free(tmp);
++ if (unlikely(err < 0))
++ AU_MVD_PR(dmsg, "failed look-up lower\n");
+
-+#include <linux/slab.h>
++ /*
++ * here, we have these cases.
++ * bfound == -1
++ * no positive dentry under bsrc. there are more sub-cases.
++ * bwh < 0
++ * there no whiteout, we can safely move-down.
++ * bwh <= bsrc
++ * impossible
++ * bsrc < bwh && bwh < bdst
++ * there is a whiteout on RO branch. cannot proceed.
++ * bwh == bdst
++ * there is a whiteout on the RW target branch. it should
++ * be removed.
++ * bdst < bwh
++ * there is a whiteout somewhere unrelated branch.
++ * -1 < bfound && bfound <= bsrc
++ * impossible.
++ * bfound < bdst
++ * found, but it is on RO branch between bsrc and bdst. cannot
++ * proceed.
++ * bfound == bdst
++ * found, replace it if AUFS_MVDOWN_FORCE is set. otherwise return
++ * error.
++ * bdst < bfound
++ * found, after we create the file on bdst, it will be hidden.
++ */
+
-+struct path;
-+struct seq_file;
++ AuDebugOn(a->bfound == -1
++ && a->bwh != -1
++ && a->bwh <= a->mvd_bsrc);
++ AuDebugOn(-1 < a->bfound
++ && a->bfound <= a->mvd_bsrc);
+
-+/* module parameters */
-+extern int sysaufs_brs;
++ err = -EINVAL;
++ if (a->bfound == -1
++ && a->mvd_bsrc < a->bwh
++ && a->bwh != -1
++ && a->bwh < a->mvd_bdst) {
++ a->mvd_errno = EAU_MVDOWN_WHITEOUT;
++ AU_MVD_PR(dmsg, "bsrc %d, bdst %d, bfound %d, bwh %d\n",
++ a->mvd_bsrc, a->mvd_bdst, a->bfound, a->bwh);
++ goto out;
++ } else if (a->bfound != -1 && a->bfound < a->mvd_bdst) {
++ a->mvd_errno = EAU_MVDOWN_UPPER;
++ AU_MVD_PR(dmsg, "bdst %d, bfound %d\n",
++ a->mvd_bdst, a->bfound);
++ goto out;
++ }
+
-+/* ---------------------------------------------------------------------- */
++ err = 0; /* success */
+
-+extern int au_dir_roflags;
++out:
++ AuTraceErr(err);
++ return err;
++}
+
-+enum {
-+ AuLcNonDir_FIINFO,
-+ AuLcNonDir_DIINFO,
-+ AuLcNonDir_IIINFO,
++static int au_mvd_args_exist(const unsigned char dmsg, struct au_mvd_args *a)
++{
++ int err;
+
-+ AuLcDir_FIINFO,
-+ AuLcDir_DIINFO,
-+ AuLcDir_IIINFO,
++ err = 0;
++ if (!(a->mvdown.flags & AUFS_MVDOWN_OWLOWER)
++ && a->bfound == a->mvd_bdst)
++ err = -EEXIST;
++ AuTraceErr(err);
++ return err;
++}
+
-+ AuLcSymlink_DIINFO,
-+ AuLcSymlink_IIINFO,
++static int au_mvd_args(const unsigned char dmsg, struct au_mvd_args *a)
++{
++ int err;
++ struct au_branch *br;
+
-+ AuLcKey_Last
-+};
-+extern struct lock_class_key au_lc_key[AuLcKey_Last];
++ err = -EISDIR;
++ if (unlikely(S_ISDIR(a->inode->i_mode)))
++ goto out;
+
-+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);
++ err = -EINVAL;
++ if (!(a->mvdown.flags & AUFS_MVDOWN_BRID_UPPER))
++ a->mvd_bsrc = au_ibstart(a->inode);
++ else {
++ a->mvd_bsrc = au_br_index(a->sb, a->mvd_src_brid);
++ if (unlikely(a->mvd_bsrc < 0
++ || (a->mvd_bsrc < au_dbstart(a->dentry)
++ || au_dbend(a->dentry) < a->mvd_bsrc
++ || !au_h_dptr(a->dentry, a->mvd_bsrc))
++ || (a->mvd_bsrc < au_ibstart(a->inode)
++ || au_ibend(a->inode) < a->mvd_bsrc
++ || !au_h_iptr(a->inode, a->mvd_bsrc)))) {
++ a->mvd_errno = EAU_MVDOWN_NOUPPER;
++ AU_MVD_PR(dmsg, "no upper\n");
++ goto out;
++ }
++ }
++ if (unlikely(a->mvd_bsrc == au_sbend(a->sb))) {
++ a->mvd_errno = EAU_MVDOWN_BOTTOM;
++ AU_MVD_PR(dmsg, "on the bottom\n");
++ goto out;
++ }
++ a->mvd_h_src_inode = au_h_iptr(a->inode, a->mvd_bsrc);
++ br = au_sbr(a->sb, a->mvd_bsrc);
++ err = au_br_rdonly(br);
++ if (!(a->mvdown.flags & AUFS_MVDOWN_ROUPPER)) {
++ if (unlikely(err))
++ goto out;
++ } else if (!(vfsub_native_ro(a->mvd_h_src_inode)
++ || IS_APPEND(a->mvd_h_src_inode))) {
++ if (err)
++ a->mvdown.flags |= AUFS_MVDOWN_ROUPPER_R;
++ /* go on */
++ } else
++ goto out;
+
-+#ifdef CONFIG_PROC_FS
-+/* procfs.c */
-+int __init au_procfs_init(void);
-+void au_procfs_fin(void);
-+#else
-+AuStubInt0(au_procfs_init, void);
-+AuStubVoid(au_procfs_fin, void);
-+#endif
++ err = -EINVAL;
++ if (!(a->mvdown.flags & AUFS_MVDOWN_BRID_LOWER)) {
++ a->mvd_bdst = find_lower_writable(a);
++ if (unlikely(a->mvd_bdst < 0)) {
++ a->mvd_errno = EAU_MVDOWN_BOTTOM;
++ AU_MVD_PR(dmsg, "no writable lower branch\n");
++ goto out;
++ }
++ } else {
++ a->mvd_bdst = au_br_index(a->sb, a->mvd_dst_brid);
++ if (unlikely(a->mvd_bdst < 0
++ || au_sbend(a->sb) < a->mvd_bdst)) {
++ a->mvd_errno = EAU_MVDOWN_NOLOWERBR;
++ AU_MVD_PR(dmsg, "no lower brid\n");
++ goto out;
++ }
++ }
+
-+/* ---------------------------------------------------------------------- */
++ err = au_mvd_args_busy(dmsg, a);
++ if (!err)
++ err = au_mvd_args_parent(dmsg, a);
++ if (!err)
++ err = au_mvd_args_intermediate(dmsg, a);
++ if (!err)
++ err = au_mvd_args_exist(dmsg, a);
++ if (!err)
++ AuDbg("b%d, b%d\n", a->mvd_bsrc, a->mvd_bdst);
+
-+/* kmem cache */
-+enum {
-+ AuCache_DINFO,
-+ AuCache_ICNTNR,
-+ AuCache_FINFO,
-+ AuCache_VDIR,
-+ AuCache_DEHSTR,
-+ AuCache_HNOTIFY, /* must be last */
-+ AuCache_Last
-+};
++out:
++ AuTraceErr(err);
++ return err;
++}
+
-+#define AuCacheFlags (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD)
-+#define AuCache(type) KMEM_CACHE(type, AuCacheFlags)
-+#define AuCacheCtor(type, ctor) \
-+ kmem_cache_create(#type, sizeof(struct type), \
-+ __alignof__(struct type), AuCacheFlags, ctor)
++int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *uarg)
++{
++ int err, e;
++ unsigned char dmsg;
++ struct au_mvd_args *args;
+
-+extern struct kmem_cache *au_cachep[];
++ err = -EPERM;
++ if (unlikely(!capable(CAP_SYS_ADMIN)))
++ goto out;
+
-+#define AuCacheFuncs(name, index) \
-+static inline struct au_##name *au_cache_alloc_##name(void) \
-+{ return kmem_cache_alloc(au_cachep[AuCache_##index], GFP_NOFS); } \
-+static inline void au_cache_free_##name(struct au_##name *p) \
-+{ kmem_cache_free(au_cachep[AuCache_##index], p); }
++ err = -ENOMEM;
++ args = kmalloc(sizeof(*args), GFP_NOFS);
++ if (unlikely(!args))
++ goto out;
+
-+AuCacheFuncs(dinfo, DINFO);
-+AuCacheFuncs(icntnr, ICNTNR);
-+AuCacheFuncs(finfo, FINFO);
-+AuCacheFuncs(vdir, VDIR);
-+AuCacheFuncs(vdir_dehstr, DEHSTR);
-+#ifdef CONFIG_AUFS_HNOTIFY
-+AuCacheFuncs(hnotify, HNOTIFY);
-+#endif
++ err = copy_from_user(&args->mvdown, uarg, sizeof(args->mvdown));
++ if (!err)
++ err = !access_ok(VERIFY_WRITE, uarg, sizeof(*uarg));
++ if (unlikely(err)) {
++ err = -EFAULT;
++ AuTraceErr(err);
++ goto out_free;
++ }
++ AuDbg("flags 0x%x\n", args->mvdown.flags);
++ args->mvdown.flags &= ~(AUFS_MVDOWN_ROLOWER_R | AUFS_MVDOWN_ROUPPER_R);
++ args->mvdown.au_errno = 0;
++ args->dentry = dentry;
++ args->inode = dentry->d_inode;
++ args->sb = dentry->d_sb;
+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_MODULE_H__ */
++ err = -ENOENT;
++ dmsg = !!(args->mvdown.flags & AUFS_MVDOWN_DMSG);
++ args->parent = dget_parent(dentry);
++ args->dir = args->parent->d_inode;
++ mutex_lock_nested(&args->dir->i_mutex, I_MUTEX_PARENT);
++ dput(args->parent);
++ if (unlikely(args->parent != dentry->d_parent)) {
++ AU_MVD_PR(dmsg, "parent dir is moved\n");
++ goto out_dir;
++ }
++
++ mutex_lock_nested(&args->inode->i_mutex, I_MUTEX_CHILD);
++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH);
++ if (unlikely(err))
++ goto out_inode;
++
++ di_write_lock_parent(args->parent);
++ err = au_mvd_args(dmsg, args);
++ if (unlikely(err))
++ goto out_parent;
++
++ err = au_do_mvdown(dmsg, args);
++ if (unlikely(err))
++ goto out_parent;
++
++ au_cpup_attr_timesizes(args->dir);
++ au_cpup_attr_timesizes(args->inode);
++ au_cpup_igen(args->inode, au_h_iptr(args->inode, args->mvd_bdst));
++ /* au_digen_dec(dentry); */
++
++out_parent:
++ di_write_unlock(args->parent);
++ aufs_read_unlock(dentry, AuLock_DW);
++out_inode:
++ mutex_unlock(&args->inode->i_mutex);
++out_dir:
++ mutex_unlock(&args->dir->i_mutex);
++out_free:
++ e = copy_to_user(uarg, &args->mvdown, sizeof(args->mvdown));
++ if (unlikely(e))
++ err = -EFAULT;
++ kfree(args);
++out:
++ AuTraceErr(err);
++ return err;
++}
diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c
--- /usr/share/empty/fs/aufs/opts.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/opts.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,1677 @@
++++ linux/fs/aufs/opts.c 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,1854 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+
+enum {
+ Opt_br,
-+ Opt_add, Opt_del, Opt_mod, Opt_reorder, Opt_append, Opt_prepend,
-+ Opt_idel, Opt_imod, Opt_ireorder,
-+ Opt_dirwh, Opt_rdcache, Opt_rdblk, Opt_rdhash, Opt_rendir,
++ Opt_add, Opt_del, Opt_mod, Opt_append, Opt_prepend,
++ Opt_idel, Opt_imod,
++ Opt_dirwh, Opt_rdcache, Opt_rdblk, Opt_rdhash,
+ Opt_rdblk_def, Opt_rdhash_def,
-+ Opt_xino, Opt_zxino, Opt_noxino,
++ Opt_xino, Opt_noxino,
+ Opt_trunc_xino, Opt_trunc_xino_v, Opt_notrunc_xino,
+ Opt_trunc_xino_path, Opt_itrunc_xino,
+ Opt_trunc_xib, Opt_notrunc_xib,
+ Opt_plink, Opt_noplink, Opt_list_plink,
+ Opt_udba,
+ Opt_dio, Opt_nodio,
-+ /* Opt_lock, Opt_unlock, */
-+ Opt_cmd, Opt_cmd_args,
+ Opt_diropq_a, Opt_diropq_w,
+ Opt_warn_perm, Opt_nowarn_perm,
+ Opt_wbr_copyup, Opt_wbr_create,
++ Opt_fhsm_sec,
+ Opt_refrof, Opt_norefrof,
+ Opt_verbose, Opt_noverbose,
+ Opt_sum, Opt_nosum, Opt_wsum,
++ Opt_dirperm1, Opt_nodirperm1,
++ Opt_acl, Opt_noacl,
+ Opt_tail, Opt_ignore, Opt_ignore_silent, Opt_err
+};
+
+ {Opt_dio, "dio"},
+ {Opt_nodio, "nodio"},
+
++#ifdef CONFIG_AUFS_FHSM
++ {Opt_fhsm_sec, "fhsm_sec=%d"},
++#else
++ {Opt_ignore_silent, "fhsm_sec=%d"},
++#endif
++
+ {Opt_diropq_a, "diropq=always"},
+ {Opt_diropq_a, "diropq=a"},
+ {Opt_diropq_w, "diropq=whiteouted"},
+ {Opt_nowarn_perm, "nowarn_perm"},
+
+ /* keep them temporary */
-+ {Opt_ignore_silent, "coo=%s"},
+ {Opt_ignore_silent, "nodlgt"},
-+ {Opt_ignore_silent, "nodirperm1"},
+ {Opt_ignore_silent, "clean_plink"},
+
+#ifdef CONFIG_AUFS_SHWH
+#endif
+ {Opt_noshwh, "noshwh"},
+
-+ {Opt_rendir, "rendir=%d"},
++ {Opt_dirperm1, "dirperm1"},
++ {Opt_nodirperm1, "nodirperm1"},
+
+ {Opt_refrof, "refrof"},
+ {Opt_norefrof, "norefrof"},
+ {Opt_wbr_copyup, "copyup=%s"},
+ {Opt_wbr_copyup, "copyup_policy=%s"},
+
++ /* generic VFS flag */
++#ifdef CONFIG_FS_POSIX_ACL
++ {Opt_acl, "acl"},
++ {Opt_noacl, "noacl"},
++#else
++ {Opt_ignore_silent, "acl"},
++ {Opt_ignore_silent, "noacl"},
++#endif
++
+ /* internal use for the scripts */
+ {Opt_ignore_silent, "si=%s"},
+
+
+/* ---------------------------------------------------------------------- */
+
-+static const char *au_parser_pattern(int val, struct match_token *token)
++static const char *au_parser_pattern(int val, match_table_t tbl)
+{
-+ while (token->pattern) {
-+ if (token->token == val)
-+ return token->pattern;
-+ token++;
++ struct match_token *p;
++
++ p = tbl;
++ while (p->pattern) {
++ if (p->token == val)
++ return p->pattern;
++ p++;
+ }
+ BUG();
+ return "??";
+}
+
++static const char *au_optstr(int *val, match_table_t tbl)
++{
++ struct match_token *p;
++ int v;
++
++ v = *val;
++ if (!v)
++ goto out;
++ p = tbl;
++ while (p->pattern) {
++ if (p->token
++ && (v & p->token) == p->token) {
++ *val &= ~p->token;
++ return p->pattern;
++ }
++ p++;
++ }
++
++out:
++ return NULL;
++}
++
+/* ---------------------------------------------------------------------- */
+
+static match_table_t brperm = {
+ {0, NULL}
+};
+
-+static match_table_t brrattr = {
++static match_table_t brattr = {
++ /* general */
++ {AuBrAttr_COO_REG, AUFS_BRATTR_COO_REG},
++ {AuBrAttr_COO_ALL, AUFS_BRATTR_COO_ALL},
++ /* 'unpin' attrib is meaningless since linux-3.18-rc1 */
++ {AuBrAttr_UNPIN, AUFS_BRATTR_UNPIN},
++#ifdef CONFIG_AUFS_FHSM
++ {AuBrAttr_FHSM, AUFS_BRATTR_FHSM},
++#endif
++#ifdef CONFIG_AUFS_XATTR
++ {AuBrAttr_ICEX, AUFS_BRATTR_ICEX},
++ {AuBrAttr_ICEX_SEC, AUFS_BRATTR_ICEX_SEC},
++ {AuBrAttr_ICEX_SYS, AUFS_BRATTR_ICEX_SYS},
++ {AuBrAttr_ICEX_TR, AUFS_BRATTR_ICEX_TR},
++ {AuBrAttr_ICEX_USR, AUFS_BRATTR_ICEX_USR},
++ {AuBrAttr_ICEX_OTH, AUFS_BRATTR_ICEX_OTH},
++#endif
++
++ /* ro/rr branch */
+ {AuBrRAttr_WH, AUFS_BRRATTR_WH},
-+ {0, NULL}
-+};
+
-+static match_table_t brwattr = {
++ /* rw branch */
++ {AuBrWAttr_MOO, AUFS_BRWATTR_MOO},
+ {AuBrWAttr_NoLinkWH, AUFS_BRWATTR_NLWH},
++
+ {0, NULL}
+};
+
-+#define AuBrStr_LONGEST AUFS_BRPERM_RW "+" AUFS_BRWATTR_NLWH
-+
+static int br_attr_val(char *str, match_table_t table, substring_t args[])
+{
+ int attr, v;
+ if (p)
+ *p = 0;
+ v = match_token(str, table, args);
-+ if (v)
++ if (v) {
++ if (v & AuBrAttr_CMOO_Mask)
++ attr &= ~AuBrAttr_CMOO_Mask;
+ attr |= v;
-+ else {
++ } else {
+ if (p)
+ *p = '+';
+ pr_warn("ignored branch attribute %s\n", str);
+ return attr;
+}
+
++static int au_do_optstr_br_attr(au_br_perm_str_t *str, int perm)
++{
++ int sz;
++ const char *p;
++ char *q;
++
++ q = str->a;
++ *q = 0;
++ p = au_optstr(&perm, brattr);
++ if (p) {
++ sz = strlen(p);
++ memcpy(q, p, sz + 1);
++ q += sz;
++ } else
++ goto out;
++
++ do {
++ p = au_optstr(&perm, brattr);
++ if (p) {
++ *q++ = '+';
++ sz = strlen(p);
++ memcpy(q, p, sz + 1);
++ q += sz;
++ }
++ } while (p);
++
++out:
++ return q - str->a;
++}
++
+static int noinline_for_stack br_perm_val(char *perm)
+{
-+ int val;
++ int val, bad, sz;
+ char *p;
+ substring_t args[MAX_OPT_ARGS];
++ au_br_perm_str_t attr;
+
+ p = strchr(perm, '+');
+ if (p)
+ if (!p)
+ goto out;
+
-+ switch (val) {
++ val |= br_attr_val(p + 1, brattr, args);
++
++ bad = 0;
++ switch (val & AuBrPerm_Mask) {
+ case AuBrPerm_RO:
+ case AuBrPerm_RR:
-+ val |= br_attr_val(p + 1, brrattr, args);
++ bad = val & AuBrWAttr_Mask;
++ val &= ~AuBrWAttr_Mask;
+ break;
+ case AuBrPerm_RW:
-+ val |= br_attr_val(p + 1, brwattr, args);
++ bad = val & AuBrRAttr_Mask;
++ val &= ~AuBrRAttr_Mask;
+ break;
+ }
+
++ /*
++ * 'unpin' attrib becomes meaningless since linux-3.18-rc1, but aufs
++ * does not treat it as an error, just warning.
++ * this is a tiny guard for the user operation.
++ */
++ if (val & AuBrAttr_UNPIN) {
++ bad |= AuBrAttr_UNPIN;
++ val &= ~AuBrAttr_UNPIN;
++ }
++
++ if (unlikely(bad)) {
++ sz = au_do_optstr_br_attr(&attr, bad);
++ AuDebugOn(!sz);
++ pr_warn("ignored branch attribute %s\n", attr.a);
++ }
++
+out:
+ return val;
+}
+
-+/* Caller should free the return value */
-+char *au_optstr_br_perm(int brperm)
++void au_optstr_br_perm(au_br_perm_str_t *str, int perm)
+{
-+ char *p, a[sizeof(AuBrStr_LONGEST)];
++ au_br_perm_str_t attr;
++ const char *p;
++ char *q;
+ int sz;
+
-+#define SetPerm(str) do { \
-+ sz = sizeof(str); \
-+ memcpy(a, str, sz); \
-+ p = a + sz - 1; \
-+ } while (0)
-+
-+#define AppendAttr(flag, str) do { \
-+ if (brperm & flag) { \
-+ sz = sizeof(str); \
-+ *p++ = '+'; \
-+ memcpy(p, str, sz); \
-+ p += sz - 1; \
-+ } \
-+ } while (0)
++ q = str->a;
++ p = au_optstr(&perm, brperm);
++ AuDebugOn(!p || !*p);
++ sz = strlen(p);
++ memcpy(q, p, sz + 1);
++ q += sz;
+
-+ switch (brperm & AuBrPerm_Mask) {
-+ case AuBrPerm_RO:
-+ SetPerm(AUFS_BRPERM_RO);
-+ break;
-+ case AuBrPerm_RR:
-+ SetPerm(AUFS_BRPERM_RR);
-+ break;
-+ case AuBrPerm_RW:
-+ SetPerm(AUFS_BRPERM_RW);
-+ break;
-+ default:
-+ AuDebugOn(1);
++ sz = au_do_optstr_br_attr(&attr, perm);
++ if (sz) {
++ *q++ = '+';
++ memcpy(q, attr.a, sz + 1);
+ }
+
-+ AppendAttr(AuBrRAttr_WH, AUFS_BRRATTR_WH);
-+ AppendAttr(AuBrWAttr_NoLinkWH, AUFS_BRWATTR_NLWH);
-+
-+ AuDebugOn(strlen(a) >= sizeof(a));
-+ return kstrdup(a, GFP_NOFS);
-+#undef SetPerm
-+#undef AppendAttr
++ AuDebugOn(strlen(str->a) >= sizeof(str->a));
+}
+
+/* ---------------------------------------------------------------------- */
+
+const char *au_optstr_udba(int udba)
+{
-+ return au_parser_pattern(udba, (void *)udbalevel);
++ return au_parser_pattern(udba, udbalevel);
+}
+
+/* ---------------------------------------------------------------------- */
+ {AuWbrCreate_MFSRRV, "mfsrr:%d:%d"},
+ {AuWbrCreate_PMFS, "pmfs"},
+ {AuWbrCreate_PMFSV, "pmfs:%d"},
++ {AuWbrCreate_PMFSRR, "pmfsrr:%d"},
++ {AuWbrCreate_PMFSRRV, "pmfsrr:%d:%d"},
+
+ {-1, NULL}
+};
+ create->wbr_create = err;
+ switch (err) {
+ case AuWbrCreate_MFSRRV:
++ case AuWbrCreate_PMFSRRV:
+ e = au_wbr_mfs_wmark(&args[0], str, create);
+ if (!e)
+ e = au_wbr_mfs_sec(&args[1], str, create);
+ err = e;
+ break;
+ case AuWbrCreate_MFSRR:
++ case AuWbrCreate_PMFSRR:
+ e = au_wbr_mfs_wmark(&args[0], str, create);
+ if (unlikely(e)) {
+ err = e;
+
+const char *au_optstr_wbr_create(int wbr_create)
+{
-+ return au_parser_pattern(wbr_create, (void *)au_wbr_create_policy);
++ return au_parser_pattern(wbr_create, au_wbr_create_policy);
+}
+
+static match_table_t au_wbr_copyup_policy = {
+
+const char *au_optstr_wbr_copyup(int wbr_copyup)
+{
-+ return au_parser_pattern(wbr_copyup, (void *)au_wbr_copyup_policy);
++ return au_parser_pattern(wbr_copyup, au_wbr_copyup_policy);
+}
+
+/* ---------------------------------------------------------------------- */
+ break;
+ case Opt_xino:
+ u.xino = &opt->xino;
-+ AuDbg("xino {%s %.*s}\n",
-+ u.xino->path,
-+ AuDLNPair(u.xino->file->f_dentry));
++ AuDbg("xino {%s %pD}\n", u.xino->path, u.xino->file);
+ break;
+ case Opt_trunc_xino:
+ AuLabel(trunc_xino);
+ u.xino_itrunc = &opt->xino_itrunc;
+ AuDbg("trunc_xino %d\n", u.xino_itrunc->bindex);
+ break;
-+
+ case Opt_noxino:
+ AuLabel(noxino);
+ break;
+ case Opt_noshwh:
+ AuLabel(noshwh);
+ break;
++ case Opt_dirperm1:
++ AuLabel(dirperm1);
++ break;
++ case Opt_nodirperm1:
++ AuLabel(nodirperm1);
++ break;
+ case Opt_plink:
+ AuLabel(plink);
+ break;
+ u.create->mfsrr_watermark);
+ break;
+ case AuWbrCreate_MFSRRV:
++ case AuWbrCreate_PMFSRRV:
+ AuDbg("%llu watermark, %d sec\n",
+ u.create->mfsrr_watermark,
+ u.create->mfs_second);
+ AuDbg("copyup %d, %s\n", opt->wbr_copyup,
+ au_optstr_wbr_copyup(opt->wbr_copyup));
+ break;
++ case Opt_fhsm_sec:
++ AuDbg("fhsm_sec %u\n", opt->fhsm_second);
++ break;
++ case Opt_acl:
++ AuLabel(acl);
++ break;
++ case Opt_noacl:
++ AuLabel(noacl);
++ break;
+ default:
+ BUG();
+ }
+ goto out;
+
+ err = -EINVAL;
-+ if (unlikely(file->f_dentry->d_sb == sb)) {
++ if (unlikely(file->f_path.dentry->d_sb == sb)) {
+ fput(file);
+ pr_err("%s must be outside\n", args[0].from);
+ goto out;
+ case Opt_notrunc_xib:
+ case Opt_shwh:
+ case Opt_noshwh:
++ case Opt_dirperm1:
++ case Opt_nodirperm1:
+ case Opt_plink:
+ case Opt_noplink:
+ case Opt_list_plink:
+ case Opt_wsum:
+ case Opt_rdblk_def:
+ case Opt_rdhash_def:
++ case Opt_acl:
++ case Opt_noacl:
+ err = 0;
+ opt->type = token;
+ break;
+ pr_err("wrong value, %s\n", opt_str);
+ break;
+
++ case Opt_fhsm_sec:
++ if (unlikely(match_int(&a->args[0], &n)
++ || n < 0)) {
++ pr_err("bad integer in %s\n", opt_str);
++ break;
++ }
++ if (sysaufs_brs) {
++ opt->fhsm_second = n;
++ opt->type = token;
++ } else
++ pr_warn("ignored %s\n", opt_str);
++ err = 0;
++ break;
++
+ case Opt_ignore:
+ pr_warn("ignored %s\n", opt_str);
+ /*FALLTHROUGH*/
+ switch (create->wbr_create) {
+ case AuWbrCreate_MFSRRV:
+ case AuWbrCreate_MFSRR:
++ case AuWbrCreate_PMFSRR:
++ case AuWbrCreate_PMFSRRV:
+ sbinfo->si_wbr_mfs.mfsrr_watermark = create->mfsrr_watermark;
+ /*FALLTHROUGH*/
+ case AuWbrCreate_MFS:
+ au_fset_opts(opts->flags, REFRESH_DYAOP);
+ break;
+
++ case Opt_fhsm_sec:
++ au_fhsm_set(sbinfo, opt->fhsm_second);
++ break;
++
+ case Opt_diropq_a:
+ au_opt_set(sbinfo->si_mntflags, ALWAYS_DIROPQ);
+ break;
+ au_opt_clr(sbinfo->si_mntflags, SHWH);
+ break;
+
++ case Opt_dirperm1:
++ au_opt_set(sbinfo->si_mntflags, DIRPERM1);
++ break;
++ case Opt_nodirperm1:
++ au_opt_clr(sbinfo->si_mntflags, DIRPERM1);
++ break;
++
+ case Opt_trunc_xino:
+ au_opt_set(sbinfo->si_mntflags, TRUNC_XINO);
+ break;
+ au_fclr_opts(opts->flags, TRUNC_XIB);
+ break;
+
++ case Opt_acl:
++ sb->s_flags |= MS_POSIXACL;
++ break;
++ case Opt_noacl:
++ sb->s_flags &= ~MS_POSIXACL;
++ break;
++
+ default:
+ err = 0;
+ break;
+ goto add;
+ case Opt_prepend:
+ opt->add.bindex = 0;
-+ add:
++ add: /* indented label */
+ case Opt_add:
+ err = au_br_add(sb, &opt->add,
+ au_ftest_opts(opts->flags, REMOUNT));
+ au_xino_brid_set(sb, -1);
+
+ /* safe d_parent access */
-+ parent = opt->xino.file->f_dentry->d_parent;
++ parent = opt->xino.file->f_path.dentry->d_parent;
+ root = sb->s_root;
+ bend = au_sbend(sb);
+ for (bindex = 0; bindex <= bend; bindex++) {
+int au_opts_verify(struct super_block *sb, unsigned long sb_flags,
+ unsigned int pending)
+{
-+ int err;
++ int err, fhsm;
+ aufs_bindex_t bindex, bend;
+ unsigned char do_plink, skip, do_free;
+ struct au_branch *br;
+ && !au_opt_test(sbinfo->si_mntflags, XINO))
+ pr_warn("udba=*notify requires xino\n");
+
++ if (au_opt_test(sbinfo->si_mntflags, DIRPERM1))
++ pr_warn("dirperm1 breaks the protection"
++ " by the permission bits on the lower branch\n");
++
+ err = 0;
++ fhsm = 0;
+ root = sb->s_root;
+ dir = root->d_inode;
+ do_plink = !!au_opt_test(sbinfo->si_mntflags, PLINK);
+ skip = 0;
+ h_dir = au_h_iptr(dir, bindex);
+ br = au_sbr(sb, bindex);
-+ do_free = 0;
+
++ if ((br->br_perm & AuBrAttr_ICEX)
++ && !h_dir->i_op->listxattr)
++ br->br_perm &= ~AuBrAttr_ICEX;
++#if 0
++ if ((br->br_perm & AuBrAttr_ICEX_SEC)
++ && (au_br_sb(br)->s_flags & MS_NOSEC))
++ br->br_perm &= ~AuBrAttr_ICEX_SEC;
++#endif
++
++ do_free = 0;
+ wbr = br->br_wbr;
+ if (wbr)
+ wbr_wh_read_lock(wbr);
+ if (wbr)
+ wbr_wh_read_unlock(wbr);
+
++ if (au_br_fhsm(br->br_perm)) {
++ fhsm++;
++ AuDebugOn(!br->br_fhsm);
++ }
++
+ if (skip)
+ continue;
+
+ au_hn_imtx_lock_nested(hdir, AuLsc_I_PARENT);
+ if (wbr)
+ wbr_wh_write_lock(wbr);
-+ err = au_wh_init(au_h_dptr(root, bindex), br, sb);
++ err = au_wh_init(br, sb);
+ if (wbr)
+ wbr_wh_write_unlock(wbr);
+ au_hn_imtx_unlock(hdir);
+ }
+ }
+
++ if (fhsm >= 2) {
++ au_fset_si(sbinfo, FHSM);
++ for (bindex = bend; bindex >= 0; bindex--) {
++ br = au_sbr(sb, bindex);
++ if (au_br_fhsm(br->br_perm)) {
++ au_fhsm_set_bottom(sb, bindex);
++ break;
++ }
++ }
++ } else {
++ au_fclr_si(sbinfo, FHSM);
++ au_fhsm_set_bottom(sb, -1);
++ }
++
+ return err;
+}
+
+ struct au_opt_xino *opt_xino, xino;
+ struct au_sbinfo *sbinfo;
+ struct au_branch *br;
++ struct inode *dir;
+
+ SiMustWriteLock(sb);
+
+ /* go on even if err */
+ }
+ if (au_opt_test(tmp, UDBA_HNOTIFY)) {
-+ struct inode *dir = sb->s_root->d_inode;
++ dir = sb->s_root->d_inode;
+ au_hn_reset(dir, au_hi_flags(dir, /*isdir*/1) & ~AuHi_XINO);
+ }
+
+}
diff -urN /usr/share/empty/fs/aufs/opts.h linux/fs/aufs/opts.h
--- /usr/share/empty/fs/aufs/opts.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/opts.h 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,209 @@
++++ linux/fs/aufs/opts.h 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,211 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+#define AuOpt_UDBA_HNOTIFY (1 << 4)
+#define AuOpt_SHWH (1 << 5) /* show whiteout */
+#define AuOpt_PLINK (1 << 6) /* pseudo-link */
-+#define AuOpt_DIRPERM1 (1 << 7) /* unimplemented */
++#define AuOpt_DIRPERM1 (1 << 7) /* ignore the lower dir's perm
++ bits */
+#define AuOpt_REFROF (1 << 8) /* unimplemented */
+#define AuOpt_ALWAYS_DIROPQ (1 << 9) /* policy to creating diropq */
+#define AuOpt_SUM (1 << 10) /* summation for statfs(2) */
+ AuWbrCreate_MFSRRV, /* mfs then rr with seconds */
+ AuWbrCreate_PMFS, /* parent and mfs */
+ AuWbrCreate_PMFSV, /* parent and mfs with seconds */
++ AuWbrCreate_PMFSRR, /* parent, mfs and round-robin */
++ AuWbrCreate_PMFSRRV, /* plus seconds */
+
+ AuWbrCreate_Def = AuWbrCreate_TDP
+};
+ int udba;
+ struct au_opt_wbr_create wbr_create;
+ int wbr_copyup;
++ unsigned int fhsm_second;
+ };
+};
+
+
+/* ---------------------------------------------------------------------- */
+
-+char *au_optstr_br_perm(int brperm);
++/* opts.c */
++void au_optstr_br_perm(au_br_perm_str_t *str, int perm);
+const char *au_optstr_udba(int udba);
+const char *au_optstr_wbr_copyup(int wbr_copyup);
+const char *au_optstr_wbr_create(int wbr_create);
+
+unsigned int au_opt_udba(struct super_block *sb);
+
-+/* ---------------------------------------------------------------------- */
-+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_OPTS_H__ */
diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c
--- /usr/share/empty/fs/aufs/plink.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/plink.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,511 @@
++++ linux/fs/aufs/plink.c 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,532 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+
+/* ---------------------------------------------------------------------- */
+
-+struct pseudo_link {
-+ union {
-+ struct list_head list;
-+ struct rcu_head rcu;
-+ };
-+ struct inode *inode;
-+};
-+
+#ifdef CONFIG_AUFS_DEBUG
+void au_plink_list(struct super_block *sb)
+{
++ int i;
+ struct au_sbinfo *sbinfo;
-+ struct list_head *plink_list;
++ struct hlist_head *plink_hlist;
+ struct pseudo_link *plink;
+
+ SiMustAnyLock(sb);
+ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK));
+ AuDebugOn(au_plink_maint(sb, AuLock_NOPLM));
+
-+ plink_list = &sbinfo->si_plink.head;
-+ rcu_read_lock();
-+ list_for_each_entry_rcu(plink, plink_list, list)
-+ AuDbg("%lu\n", plink->inode->i_ino);
-+ rcu_read_unlock();
++ for (i = 0; i < AuPlink_NHASH; i++) {
++ plink_hlist = &sbinfo->si_plink[i].head;
++ rcu_read_lock();
++ hlist_for_each_entry_rcu(plink, plink_hlist, hlist)
++ AuDbg("%lu\n", plink->inode->i_ino);
++ rcu_read_unlock();
++ }
+}
+#endif
+
+/* is the inode pseudo-linked? */
+int au_plink_test(struct inode *inode)
+{
-+ int found;
++ int found, i;
+ struct au_sbinfo *sbinfo;
-+ struct list_head *plink_list;
++ struct hlist_head *plink_hlist;
+ struct pseudo_link *plink;
+
+ sbinfo = au_sbi(inode->i_sb);
+ AuDebugOn(au_plink_maint(inode->i_sb, AuLock_NOPLM));
+
+ found = 0;
-+ plink_list = &sbinfo->si_plink.head;
++ i = au_plink_hash(inode->i_ino);
++ plink_hlist = &sbinfo->si_plink[i].head;
+ rcu_read_lock();
-+ list_for_each_entry_rcu(plink, plink_list, list)
++ hlist_for_each_entry_rcu(plink, plink_hlist, hlist)
+ if (plink->inode == inode) {
+ found = 1;
+ break;
+{
+ int err;
+ struct path h_path = {
-+ .mnt = br->br_mnt
++ .mnt = au_br_mnt(br)
+ };
-+ struct inode *h_dir;
++ struct inode *h_dir, *delegated;
+
+ h_dir = h_parent->d_inode;
+ mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_CHILD2);
+ /* todo: is it really safe? */
+ if (h_path.dentry->d_inode
+ && h_path.dentry->d_inode != h_dentry->d_inode) {
-+ err = vfsub_unlink(h_dir, &h_path, /*force*/0);
++ delegated = NULL;
++ err = vfsub_unlink(h_dir, &h_path, &delegated, /*force*/0);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
++ }
+ dput(h_path.dentry);
+ h_path.dentry = NULL;
+ if (!err)
+ goto again;
+ }
-+ if (!err && !h_path.dentry->d_inode)
-+ err = vfsub_link(h_dentry, h_dir, &h_path);
++ if (!err && !h_path.dentry->d_inode) {
++ delegated = NULL;
++ err = vfsub_link(h_dentry, h_dir, &h_path, &delegated);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal link\n");
++ iput(delegated);
++ }
++ }
+ dput(h_path.dentry);
+
+out:
+static void do_put_plink(struct pseudo_link *plink, int do_del)
+{
+ if (do_del)
-+ list_del(&plink->list);
++ hlist_del(&plink->hlist);
+ iput(plink->inode);
+ kfree(plink);
+}
+{
+ struct super_block *sb;
+ struct au_sbinfo *sbinfo;
-+ struct list_head *plink_list;
++ struct hlist_head *plink_hlist;
+ struct pseudo_link *plink, *tmp;
-+ int found, err, cnt;
++ struct au_sphlhead *sphl;
++ int found, err, cnt, i;
+
+ sb = inode->i_sb;
+ sbinfo = au_sbi(sb);
+ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK));
+ AuDebugOn(au_plink_maint(sb, AuLock_NOPLM));
+
-+ cnt = 0;
-+ found = 0;
-+ plink_list = &sbinfo->si_plink.head;
-+ rcu_read_lock();
-+ list_for_each_entry_rcu(plink, plink_list, list) {
-+ cnt++;
-+ if (plink->inode == inode) {
-+ found = 1;
-+ break;
-+ }
-+ }
-+ rcu_read_unlock();
++ found = au_plink_test(inode);
+ if (found)
+ return;
+
++ i = au_plink_hash(inode->i_ino);
++ sphl = sbinfo->si_plink + i;
++ plink_hlist = &sphl->head;
+ tmp = kmalloc(sizeof(*plink), GFP_NOFS);
+ if (tmp)
+ tmp->inode = au_igrab(inode);
+ goto out;
+ }
+
-+ spin_lock(&sbinfo->si_plink.spin);
-+ list_for_each_entry(plink, plink_list, list) {
++ spin_lock(&sphl->spin);
++ hlist_for_each_entry(plink, plink_hlist, hlist) {
+ if (plink->inode == inode) {
+ found = 1;
+ break;
+ }
+ }
+ if (!found)
-+ list_add_rcu(&tmp->list, plink_list);
-+ spin_unlock(&sbinfo->si_plink.spin);
++ hlist_add_head_rcu(&tmp->hlist, plink_hlist);
++ spin_unlock(&sphl->spin);
+ if (!found) {
-+ cnt++;
-+ WARN_ONCE(cnt > AUFS_PLINK_WARN,
-+ "unexpectedly many pseudo links, %d\n", cnt);
++ cnt = au_sphl_count(sphl);
++#define msg "unexpectedly unblanced or too many pseudo-links"
++ if (cnt > AUFS_PLINK_WARN)
++ AuWarn1(msg ", %d\n", cnt);
++#undef msg
+ err = whplink(h_dentry, inode, bindex, au_sbr(sb, bindex));
+ } else {
+ do_put_plink(tmp, 0);
+ if (unlikely(err)) {
+ pr_warn("err %d, damaged pseudo link.\n", err);
+ if (tmp) {
-+ au_spl_del_rcu(&tmp->list, &sbinfo->si_plink);
++ au_sphl_del_rcu(&tmp->hlist, sphl);
+ call_rcu(&tmp->rcu, do_put_plink_rcu);
+ }
+ }
+/* free all plinks */
+void au_plink_put(struct super_block *sb, int verbose)
+{
++ int i, warned;
+ struct au_sbinfo *sbinfo;
-+ struct list_head *plink_list;
-+ struct pseudo_link *plink, *tmp;
++ struct hlist_head *plink_hlist;
++ struct hlist_node *tmp;
++ struct pseudo_link *plink;
+
+ SiMustWriteLock(sb);
+
+ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK));
+ AuDebugOn(au_plink_maint(sb, AuLock_NOPLM));
+
-+ plink_list = &sbinfo->si_plink.head;
+ /* no spin_lock since sbinfo is write-locked */
-+ WARN(verbose && !list_empty(plink_list), "pseudo-link is not flushed");
-+ list_for_each_entry_safe(plink, tmp, plink_list, list)
-+ do_put_plink(plink, 0);
-+ INIT_LIST_HEAD(plink_list);
++ warned = 0;
++ for (i = 0; i < AuPlink_NHASH; i++) {
++ plink_hlist = &sbinfo->si_plink[i].head;
++ if (!warned && verbose && !hlist_empty(plink_hlist)) {
++ pr_warn("pseudo-link is not flushed");
++ warned = 1;
++ }
++ hlist_for_each_entry_safe(plink, tmp, plink_hlist, hlist)
++ do_put_plink(plink, 0);
++ INIT_HLIST_HEAD(plink_hlist);
++ }
+}
+
+void au_plink_clean(struct super_block *sb, int verbose)
+ aufs_write_unlock(root);
+}
+
++static int au_plink_do_half_refresh(struct inode *inode, aufs_bindex_t br_id)
++{
++ int do_put;
++ aufs_bindex_t bstart, bend, bindex;
++
++ do_put = 0;
++ bstart = au_ibstart(inode);
++ bend = au_ibend(inode);
++ if (bstart >= 0) {
++ for (bindex = bstart; bindex <= bend; bindex++) {
++ if (!au_h_iptr(inode, bindex)
++ || au_ii_br_id(inode, bindex) != br_id)
++ continue;
++ au_set_h_iptr(inode, bindex, NULL, 0);
++ do_put = 1;
++ break;
++ }
++ if (do_put)
++ for (bindex = bstart; bindex <= bend; bindex++)
++ if (au_h_iptr(inode, bindex)) {
++ do_put = 0;
++ break;
++ }
++ } else
++ do_put = 1;
++
++ return do_put;
++}
++
+/* free the plinks on a branch specified by @br_id */
+void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id)
+{
+ struct au_sbinfo *sbinfo;
-+ struct list_head *plink_list;
-+ struct pseudo_link *plink, *tmp;
++ struct hlist_head *plink_hlist;
++ struct hlist_node *tmp;
++ struct pseudo_link *plink;
+ struct inode *inode;
-+ aufs_bindex_t bstart, bend, bindex;
-+ unsigned char do_put;
++ int i, do_put;
+
+ SiMustWriteLock(sb);
+
+ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK));
+ AuDebugOn(au_plink_maint(sb, AuLock_NOPLM));
+
-+ plink_list = &sbinfo->si_plink.head;
+ /* no spin_lock since sbinfo is write-locked */
-+ list_for_each_entry_safe(plink, tmp, plink_list, list) {
-+ do_put = 0;
-+ inode = au_igrab(plink->inode);
-+ ii_write_lock_child(inode);
-+ bstart = au_ibstart(inode);
-+ bend = au_ibend(inode);
-+ if (bstart >= 0) {
-+ for (bindex = bstart; bindex <= bend; bindex++) {
-+ if (!au_h_iptr(inode, bindex)
-+ || au_ii_br_id(inode, bindex) != br_id)
-+ continue;
-+ au_set_h_iptr(inode, bindex, NULL, 0);
-+ do_put = 1;
-+ break;
-+ }
-+ } else
-+ do_put_plink(plink, 1);
-+
-+ if (do_put) {
-+ for (bindex = bstart; bindex <= bend; bindex++)
-+ if (au_h_iptr(inode, bindex)) {
-+ do_put = 0;
-+ break;
-+ }
++ for (i = 0; i < AuPlink_NHASH; i++) {
++ plink_hlist = &sbinfo->si_plink[i].head;
++ hlist_for_each_entry_safe(plink, tmp, plink_hlist, hlist) {
++ inode = au_igrab(plink->inode);
++ ii_write_lock_child(inode);
++ do_put = au_plink_do_half_refresh(inode, br_id);
+ if (do_put)
+ do_put_plink(plink, 1);
++ ii_write_unlock(inode);
++ iput(inode);
+ }
-+ ii_write_unlock(inode);
-+ iput(inode);
+ }
+}
diff -urN /usr/share/empty/fs/aufs/poll.c linux/fs/aufs/poll.c
--- /usr/share/empty/fs/aufs/poll.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/poll.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,56 @@
++++ linux/fs/aufs/poll.c 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,52 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
++ */
++
++/*
++ * poll operation
++ * There is only one filesystem which implements ->poll operation, currently.
++ */
++
++#include "aufs.h"
++
++unsigned int aufs_poll(struct file *file, poll_table *wait)
++{
++ unsigned int mask;
++ int err;
++ struct file *h_file;
++ struct super_block *sb;
++
++ /* We should pretend an error happened. */
++ mask = POLLERR /* | POLLIN | POLLOUT */;
++ sb = file->f_path.dentry->d_sb;
++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
++
++ h_file = au_read_pre(file, /*keep_fi*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
++
++ /* it is not an error if h_file has no operation */
++ mask = DEFAULT_POLLMASK;
++ if (h_file->f_op->poll)
++ mask = h_file->f_op->poll(h_file, wait);
++ fput(h_file); /* instead of au_read_post() */
++
++out:
++ si_read_unlock(sb);
++ AuTraceErr((int)mask);
++ return mask;
++}
+diff -urN /usr/share/empty/fs/aufs/posix_acl.c linux/fs/aufs/posix_acl.c
+--- /usr/share/empty/fs/aufs/posix_acl.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/posix_acl.c 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,99 @@
++/*
++ * Copyright (C) 2014-2015 Junjiro R. Okajima
++ *
++ * This program, aufs is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ *
++ * This program is distributed in the hope that it will be useful,
++ * but WITHOUT ANY WARRANTY; without even the implied warranty of
++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++ * GNU General Public License for more details.
++ *
++ * You should have received a copy of the GNU General Public License
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
++ */
++
++/*
++ * posix acl operations
+ */
+
-+/*
-+ * poll operation
-+ * There is only one filesystem which implements ->poll operation, currently.
-+ */
++#include <linux/fs.h>
++#include <linux/posix_acl.h>
++#include "aufs.h"
++
++struct posix_acl *aufs_get_acl(struct inode *inode, int type)
++{
++ struct posix_acl *acl;
++ int err;
++ aufs_bindex_t bindex;
++ struct inode *h_inode;
++ struct super_block *sb;
++
++ acl = NULL;
++ sb = inode->i_sb;
++ si_read_lock(sb, AuLock_FLUSH);
++ ii_read_lock_child(inode);
++ if (!(sb->s_flags & MS_POSIXACL))
++ goto out;
++
++ bindex = au_ibstart(inode);
++ h_inode = au_h_iptr(inode, bindex);
++ if (unlikely(!h_inode
++ || ((h_inode->i_mode & S_IFMT)
++ != (inode->i_mode & S_IFMT)))) {
++ err = au_busy_or_stale();
++ acl = ERR_PTR(err);
++ goto out;
++ }
+
-+#include "aufs.h"
++ /* always topmost only */
++ acl = get_acl(h_inode, type);
+
-+unsigned int aufs_poll(struct file *file, poll_table *wait)
++out:
++ ii_read_unlock(inode);
++ si_read_unlock(sb);
++
++ AuTraceErrPtr(acl);
++ return acl;
++}
++
++int aufs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
-+ unsigned int mask;
+ int err;
-+ struct file *h_file;
++ ssize_t ssz;
+ struct dentry *dentry;
-+ struct super_block *sb;
-+
-+ /* We should pretend an error happened. */
-+ mask = POLLERR /* | POLLIN | POLLOUT */;
-+ dentry = file->f_dentry;
-+ sb = dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0);
-+ if (unlikely(err))
-+ goto out;
++ struct au_srxattr arg = {
++ .type = AU_ACL_SET,
++ .u.acl_set = {
++ .acl = acl,
++ .type = type
++ },
++ };
+
-+ /* it is not an error if h_file has no operation */
-+ mask = DEFAULT_POLLMASK;
-+ h_file = au_hf_top(file);
-+ if (h_file->f_op && h_file->f_op->poll)
-+ mask = h_file->f_op->poll(h_file, wait);
++ mutex_lock(&inode->i_mutex);
++ if (inode->i_ino == AUFS_ROOT_INO)
++ dentry = dget(inode->i_sb->s_root);
++ else {
++ dentry = d_find_alias(inode);
++ if (!dentry)
++ dentry = d_find_any_alias(inode);
++ if (!dentry) {
++ pr_warn("cannot handle this inode, "
++ "please report to aufs-users ML\n");
++ err = -ENOENT;
++ goto out;
++ }
++ }
+
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_read_unlock(file);
++ ssz = au_srxattr(dentry, &arg);
++ dput(dentry);
++ err = ssz;
++ if (ssz >= 0)
++ err = 0;
+
+out:
-+ si_read_unlock(sb);
-+ AuTraceErr((int)mask);
-+ return mask;
++ mutex_unlock(&inode->i_mutex);
++ return err;
+}
diff -urN /usr/share/empty/fs/aufs/procfs.c linux/fs/aufs/procfs.c
--- /usr/share/empty/fs/aufs/procfs.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/procfs.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,170 @@
++++ linux/fs/aufs/procfs.c 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,169 @@
+/*
-+ * Copyright (C) 2010-2013 Junjiro R. Okajima
++ * Copyright (C) 2010-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+}
diff -urN /usr/share/empty/fs/aufs/rdu.c linux/fs/aufs/rdu.c
--- /usr/share/empty/fs/aufs/rdu.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/rdu.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,384 @@
++++ linux/fs/aufs/rdu.c 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,388 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ do { (flags) &= ~AuRdu_##name; } while (0)
+
+struct au_rdu_arg {
++ struct dir_context ctx;
+ struct aufs_rdu *rdu;
+ union au_rdu_ent_ul ent;
+ unsigned long end;
+ int err;
+};
+
-+static int au_rdu_fill(void *__arg, const char *name, int nlen,
++static int au_rdu_fill(struct dir_context *ctx, const char *name, int nlen,
+ loff_t offset, u64 h_ino, unsigned int d_type)
+{
+ int err, len;
-+ struct au_rdu_arg *arg = __arg;
++ struct au_rdu_arg *arg = container_of(ctx, struct au_rdu_arg, ctx);
+ struct aufs_rdu *rdu = arg->rdu;
+ struct au_rdu_ent ent;
+
+ arg->err = 0;
+ au_fclr_rdu(cookie->flags, CALLED);
+ /* smp_mb(); */
-+ err = vfsub_readdir(h_file, au_rdu_fill, arg);
++ err = vfsub_iterate_dir(h_file, &arg->ctx);
+ if (err >= 0)
+ err = arg->err;
+ } while (!err
+{
+ int err;
+ aufs_bindex_t bend;
-+ struct au_rdu_arg arg;
++ struct au_rdu_arg arg = {
++ .ctx = {
++ .actor = au_rdu_fill
++ }
++ };
+ struct dentry *dentry;
+ struct inode *inode;
+ struct file *h_file;
+ arg.end += rdu->sz;
+
+ err = -ENOTDIR;
-+ if (unlikely(!file->f_op || !file->f_op->readdir))
++ if (unlikely(!file->f_op->iterate))
+ goto out;
+
+ err = security_file_permission(file, MAY_READ);
+ if (unlikely(err))
+ goto out;
+
-+ dentry = file->f_dentry;
++ dentry = file->f_path.dentry;
+ inode = dentry->d_inode;
+#if 1
+ mutex_lock(&inode->i_mutex);
+ err = 0;
+ nent = rdu->nent;
+ u = &rdu->ent;
-+ sb = file->f_dentry->d_sb;
++ sb = file->f_path.dentry->d_sb;
+ si_read_lock(sb, AuLock_FLUSH);
+ while (nent-- > 0) {
+ /* unnecessary to support mmap_sem since this is a dir */
+#endif
diff -urN /usr/share/empty/fs/aufs/rwsem.h linux/fs/aufs/rwsem.h
--- /usr/share/empty/fs/aufs/rwsem.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/rwsem.h 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,188 @@
++++ linux/fs/aufs/rwsem.h 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,191 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+/* why is not _nested version defined */
+static inline int au_rw_read_trylock(struct au_rwsem *rw)
+{
-+ int ret = down_read_trylock(&rw->rwsem);
++ int ret;
++
++ ret = down_read_trylock(&rw->rwsem);
+ if (ret)
+ AuDbgRcntInc(rw);
+ return ret;
+
+static inline int au_rw_write_trylock(struct au_rwsem *rw)
+{
-+ int ret = down_write_trylock(&rw->rwsem);
++ int ret;
++
++ ret = down_write_trylock(&rw->rwsem);
+ if (ret)
+ AuDbgWcntInc(rw);
+ return ret;
+#endif /* __AUFS_RWSEM_H__ */
diff -urN /usr/share/empty/fs/aufs/sbinfo.c linux/fs/aufs/sbinfo.c
--- /usr/share/empty/fs/aufs/sbinfo.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/sbinfo.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,343 @@
++++ linux/fs/aufs/sbinfo.c 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,354 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ */
+void au_si_free(struct kobject *kobj)
+{
++ int i;
+ struct au_sbinfo *sbinfo;
+ char *locked __maybe_unused; /* debug only */
+
+ sbinfo = container_of(kobj, struct au_sbinfo, si_kobj);
-+ AuDebugOn(!list_empty(&sbinfo->si_plink.head));
++ for (i = 0; i < AuPlink_NHASH; i++)
++ AuDebugOn(!hlist_empty(&sbinfo->si_plink[i].head));
+ AuDebugOn(atomic_read(&sbinfo->si_nowait.nw_len));
+
+ au_rw_write_lock(&sbinfo->si_rwsem);
+
+int au_si_alloc(struct super_block *sb)
+{
-+ int err;
++ int err, i;
+ struct au_sbinfo *sbinfo;
+ static struct lock_class_key aufs_si;
+
+ atomic_long_set(&sbinfo->si_nfiles, 0);
+
+ sbinfo->si_bend = -1;
++ sbinfo->si_last_br_id = AUFS_BRANCH_MAX / 2;
+
+ sbinfo->si_wbr_copyup = AuWbrCopyup_Def;
+ sbinfo->si_wbr_create = AuWbrCreate_Def;
+ sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + sbinfo->si_wbr_copyup;
+ sbinfo->si_wbr_create_ops = au_wbr_create_ops + sbinfo->si_wbr_create;
+
++ au_fhsm_init(sbinfo);
++
+ sbinfo->si_mntflags = au_opts_plink(AuOpt_Def);
+
++ sbinfo->si_xino_jiffy = jiffies;
++ sbinfo->si_xino_expire
++ = msecs_to_jiffies(AUFS_XINO_DEF_SEC * MSEC_PER_SEC);
+ mutex_init(&sbinfo->si_xib_mtx);
+ sbinfo->si_xino_brid = -1;
+ /* leave si_xib_last_pindex and si_xib_next_bit */
+
++ au_sphl_init(&sbinfo->si_aopen);
++
+ sbinfo->si_rdcache = msecs_to_jiffies(AUFS_RDCACHE_DEF * MSEC_PER_SEC);
+ sbinfo->si_rdblk = AUFS_RDBLK_DEF;
+ sbinfo->si_rdhash = AUFS_RDHASH_DEF;
+ sbinfo->si_dirwh = AUFS_DIRWH_DEF;
+
-+ au_spl_init(&sbinfo->si_plink);
++ for (i = 0; i < AuPlink_NHASH; i++)
++ au_sphl_init(sbinfo->si_plink + i);
+ init_waitqueue_head(&sbinfo->si_plink_wq);
+ spin_lock_init(&sbinfo->si_plink_maint_lock);
+
++ au_sphl_init(&sbinfo->si_files);
++
+ /* leave other members for sysaufs and si_mnt. */
+ sbinfo->si_sb = sb;
+ sb->s_fs_info = sbinfo;
+ si_pid_set(sb);
-+ au_debug_sbinfo_init(sbinfo);
+ return 0; /* success */
+
+out_br:
+}
diff -urN /usr/share/empty/fs/aufs/spl.h linux/fs/aufs/spl.h
--- /usr/share/empty/fs/aufs/spl.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/spl.h 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,62 @@
++++ linux/fs/aufs/spl.h 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,111 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ spin_unlock(&spl->spin);
+}
+
++/* ---------------------------------------------------------------------- */
++
++struct au_sphlhead {
++ spinlock_t spin;
++ struct hlist_head head;
++};
++
++static inline void au_sphl_init(struct au_sphlhead *sphl)
++{
++ spin_lock_init(&sphl->spin);
++ INIT_HLIST_HEAD(&sphl->head);
++}
++
++static inline void au_sphl_add(struct hlist_node *hlist,
++ struct au_sphlhead *sphl)
++{
++ spin_lock(&sphl->spin);
++ hlist_add_head(hlist, &sphl->head);
++ spin_unlock(&sphl->spin);
++}
++
++static inline void au_sphl_del(struct hlist_node *hlist,
++ struct au_sphlhead *sphl)
++{
++ spin_lock(&sphl->spin);
++ hlist_del(hlist);
++ spin_unlock(&sphl->spin);
++}
++
++static inline void au_sphl_del_rcu(struct hlist_node *hlist,
++ struct au_sphlhead *sphl)
++{
++ spin_lock(&sphl->spin);
++ hlist_del_rcu(hlist);
++ spin_unlock(&sphl->spin);
++}
++
++static inline unsigned long au_sphl_count(struct au_sphlhead *sphl)
++{
++ unsigned long cnt;
++ struct hlist_node *pos;
++
++ cnt = 0;
++ spin_lock(&sphl->spin);
++ hlist_for_each(pos, &sphl->head)
++ cnt++;
++ spin_unlock(&sphl->spin);
++ return cnt;
++}
++
+#endif /* __KERNEL__ */
+#endif /* __AUFS_SPL_H__ */
diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c
--- /usr/share/empty/fs/aufs/super.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/super.c 2013-03-14 20:07:41.221457313 +0100
-@@ -0,0 +1,993 @@
++++ linux/fs/aufs/super.c 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,1007 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ */
+
+#include <linux/mm.h>
-+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/statfs.h>
+#include <linux/vmalloc.h>
-+#include <linux/writeback.h>
+#include "aufs.h"
+
+/*
+ struct path path;
+ struct au_hdentry *hdp;
+ struct au_branch *br;
-+ char *perm;
++ au_br_perm_str_t perm;
+
+ err = 0;
+ bend = au_sbend(sb);
+ hdp = au_di(sb->s_root)->di_hdentry;
+ for (bindex = 0; !err && bindex <= bend; bindex++) {
+ br = au_sbr(sb, bindex);
-+ path.mnt = br->br_mnt;
++ path.mnt = au_br_mnt(br);
+ path.dentry = hdp[bindex].hd_dentry;
+ err = au_seq_path(seq, &path);
+ if (err > 0) {
-+ perm = au_optstr_br_perm(br->br_perm);
-+ if (perm) {
-+ err = seq_printf(seq, "=%s", perm);
-+ kfree(perm);
-+ if (err == -1)
-+ err = -E2BIG;
-+ } else
-+ err = -ENOMEM;
++ au_optstr_br_perm(&perm, br->br_perm);
++ err = seq_printf(seq, "=%s", perm.a);
++ if (err == -1)
++ err = -E2BIG;
+ }
+ if (!err && bindex != bend)
+ err = seq_putc(seq, ':');
+
+ AuRwMustAnyLock(&sbinfo->si_rwsem);
+
-+ seq_printf(m, ",create=");
++ seq_puts(m, ",create=");
+ pat = au_optstr_wbr_create(v);
+ switch (v) {
+ case AuWbrCreate_TDP:
+ case AuWbrCreate_RR:
+ case AuWbrCreate_MFS:
+ case AuWbrCreate_PMFS:
-+ seq_printf(m, pat);
++ seq_puts(m, pat);
+ break;
+ case AuWbrCreate_MFSV:
+ seq_printf(m, /*pat*/"mfs:%lu",
+ jiffies_to_msecs(sbinfo->si_wbr_mfs.mfs_expire)
+ / MSEC_PER_SEC);
+ break;
++ case AuWbrCreate_PMFSRR:
++ seq_printf(m, /*pat*/"pmfsrr:%llu",
++ sbinfo->si_wbr_mfs.mfsrr_watermark);
++ break;
++ case AuWbrCreate_PMFSRRV:
++ seq_printf(m, /*pat*/"pmfsrr:%llu:%lu",
++ sbinfo->si_wbr_mfs.mfsrr_watermark,
++ jiffies_to_msecs(sbinfo->si_wbr_mfs.mfs_expire)
++ / MSEC_PER_SEC);
++ break;
+ }
+}
+
+ hdp = au_di(sb->s_root)->di_hdentry;
+ h_root = hdp[0 + bindex].hd_dentry;
+ }
-+ d = f->f_dentry;
++ d = f->f_path.dentry;
+ name = &d->d_name;
+ /* safe ->d_parent because the file is unlinked */
+ if (d->d_parent == h_root
+ seq_printf(m, "," #str "=%u", val); \
+} while (0)
+
-+ /* lock free root dinfo */
+ sb = dentry->d_sb;
++ if (sb->s_flags & MS_POSIXACL)
++ seq_puts(m, ",acl");
++
++ /* lock free root dinfo */
+ si_noflush_read_lock(sb);
+ sbinfo = au_sbi(sb);
+ seq_printf(m, ",si=%lx", sysaufs_si_id(sbinfo));
+ AuBool(SHWH, shwh);
+ AuBool(PLINK, plink);
+ AuBool(DIO, dio);
-+ /* AuBool(DIRPERM1, dirperm1); */
++ AuBool(DIRPERM1, dirperm1);
+ /* AuBool(REFROF, refrof); */
+
+ v = sbinfo->si_wbr_create;
+ AuUInt(RDBLK, rdblk, sbinfo->si_rdblk);
+ AuUInt(RDHASH, rdhash, sbinfo->si_rdhash);
+
++ au_fhsm_show(m, sbinfo);
++
+ AuBool(SUM, sum);
+ /* AuBool(SUM_W, wsum); */
+ AuBool(WARN_PERM, warn_perm);
+void *au_array_alloc(unsigned long long *hint, au_arraycb_t cb, void *arg)
+{
+ void *array;
-+ unsigned long long n;
++ unsigned long long n, sz;
+
+ array = NULL;
+ n = 0;
+ goto out;
+ }
+
-+ array = kmalloc(sizeof(array) * *hint, GFP_NOFS);
++ sz = sizeof(array) * *hint;
++ array = kzalloc(sz, GFP_NOFS);
+ if (unlikely(!array))
-+ array = vmalloc(sizeof(array) * *hint);
++ array = vzalloc(sz);
+ if (unlikely(!array)) {
+ array = ERR_PTR(-ENOMEM);
+ goto out;
+ sigen = au_sigen(sb);
+ for (ull = 0; ull < max; ull++) {
+ inode = array[ull];
++ if (unlikely(!inode))
++ break;
+ if (au_iigen(inode, NULL) != sigen) {
+ ii_write_lock_child(inode);
+ e = au_refresh_hinode_self(inode);
+ au_dy_arefresh(do_dx);
+ }
+
++ au_fhsm_wrote_all(sb, /*force*/1); /* ?? */
+ aufs_write_unlock(root);
+
+out_mtx:
+ sb->s_d_op = &aufs_dop;
+ sb->s_magic = AUFS_SUPER_MAGIC;
+ sb->s_maxbytes = 0;
++ sb->s_stack_depth = 1;
+ au_export_init(sb);
++ /* au_xattr_init(sb); */
+
+ err = alloc_root(sb);
+ if (unlikely(err)) {
+ if (sbinfo) {
+ au_sbilist_del(sb);
+ aufs_write_lock(sb->s_root);
++ au_fhsm_fin(sb);
+ if (sbinfo->si_wbr_create_ops->fin)
+ sbinfo->si_wbr_create_ops->fin(sb);
+ if (au_opt_test(sbinfo->si_mntflags, UDBA_HNOTIFY)) {
+ aufs_write_unlock(sb->s_root);
+ au_nwt_flush(&sbinfo->si_nowait);
+ }
-+ generic_shutdown_super(sb);
++ kill_anon_super(sb);
+}
+
+struct file_system_type aufs_fs_type = {
+ .name = AUFS_FSTYPE,
-+ .fs_flags =
-+ FS_RENAME_DOES_D_MOVE /* a race between rename and others */
-+ | FS_REVAL_DOT, /* for NFS branch and udba */
++ /* a race between rename and others */
++ .fs_flags = FS_RENAME_DOES_D_MOVE,
+ .mount = aufs_mount,
+ .kill_sb = aufs_kill_sb,
+ /* no need to __module_get() and module_put(). */
+};
diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h
--- /usr/share/empty/fs/aufs/super.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/super.h 2013-03-14 20:07:18.764260309 +0100
-@@ -0,0 +1,538 @@
++++ linux/fs/aufs/super.h 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,638 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ int (*copyup)(struct dentry *dentry);
+};
+
++#define AuWbr_DIR 1 /* target is a dir */
++#define AuWbr_PARENT (1 << 1) /* always require a parent */
++
++#define au_ftest_wbr(flags, name) ((flags) & AuWbr_##name)
++#define au_fset_wbr(flags, name) { (flags) |= AuWbr_##name; }
++#define au_fclr_wbr(flags, name) { (flags) &= ~AuWbr_##name; }
++
+struct au_wbr_create_operations {
-+ int (*create)(struct dentry *dentry, int isdir);
++ int (*create)(struct dentry *dentry, unsigned int flags);
+ int (*init)(struct super_block *sb);
+ int (*fin)(struct super_block *sb);
+};
+ unsigned long long mfsrr_watermark;
+};
+
++struct pseudo_link {
++ union {
++ struct hlist_node hlist;
++ struct rcu_head rcu;
++ };
++ struct inode *inode;
++};
++
++#define AuPlink_NHASH 100
++static inline int au_plink_hash(ino_t ino)
++{
++ return ino % AuPlink_NHASH;
++}
++
++/* File-based Hierarchical Storage Management */
++struct au_fhsm {
++#ifdef CONFIG_AUFS_FHSM
++ /* allow only one process who can receive the notification */
++ spinlock_t fhsm_spin;
++ pid_t fhsm_pid;
++ wait_queue_head_t fhsm_wqh;
++ atomic_t fhsm_readable;
++
++ /* these are protected by si_rwsem */
++ unsigned long fhsm_expire;
++ aufs_bindex_t fhsm_bottom;
++#endif
++};
++
+struct au_branch;
+struct au_sbinfo {
+ /* nowait tasks in the system-wide workqueue */
+ } au_si_pid;
+
+ /*
-+ * dirty approach to protect sb->sb_inodes and ->s_files from remount.
++ * dirty approach to protect sb->sb_inodes and ->s_files (gone) from
++ * remount.
+ */
+ atomic_long_t si_ninodes, si_nfiles;
+
+ /* branch management */
+ unsigned int si_generation;
+
-+ /* see above flags */
++ /* see AuSi_ flags */
+ unsigned char au_si_status;
+
+ aufs_bindex_t si_bend;
+ /* most free space */
+ struct au_wbr_mfs si_wbr_mfs;
+
++ /* File-based Hierarchical Storage Management */
++ struct au_fhsm si_fhsm;
++
+ /* mount flags */
+ /* include/asm-ia64/siginfo.h defines a macro named si_flags */
+ unsigned int si_mntflags;
+ unsigned long si_xib_last_pindex;
+ int si_xib_next_bit;
+ aufs_bindex_t si_xino_brid;
++ unsigned long si_xino_jiffy;
++ unsigned long si_xino_expire;
+ /* reserved for future use */
+ /* unsigned long long si_xib_limit; */ /* Max xib file size */
+
+ atomic_t si_xigen_next;
+#endif
+
++ /* dirty trick to suppoer atomic_open */
++ struct au_sphlhead si_aopen;
++
+ /* vdir parameters */
+ unsigned long si_rdcache; /* max cache time in jiffies */
+ unsigned int si_rdblk; /* deblk size */
+ */
+ unsigned int si_dirwh;
+
-+ /*
-+ * rename(2) a directory with all children.
-+ */
-+ /* reserved for future use */
-+ /* int si_rendir; */
-+
+ /* pseudo_link list */
-+ struct au_splhead si_plink;
++ struct au_sphlhead si_plink[AuPlink_NHASH];
+ wait_queue_head_t si_plink_wq;
+ spinlock_t si_plink_maint_lock;
+ pid_t si_plink_maint_pid;
+
++ /* file list */
++ struct au_sphlhead si_files;
++
+ /*
+ * sysfs and lifetime management.
+ * this is not a small structure and it may be a waste of memory in case
+ */
+ struct kobject si_kobj;
+#ifdef CONFIG_DEBUG_FS
-+ struct dentry *si_dbgaufs, *si_dbgaufs_xib;
++ struct dentry *si_dbgaufs;
++ struct dentry *si_dbgaufs_plink;
++ struct dentry *si_dbgaufs_xib;
+#ifdef CONFIG_AUFS_EXPORT
+ struct dentry *si_dbgaufs_xigen;
+#endif
+ * if it is false, refreshing dirs at access time is unnecesary
+ */
+#define AuSi_FAILED_REFRESH_DIR 1
++
++#define AuSi_FHSM (1 << 1) /* fhsm is active now */
++
++#ifndef CONFIG_AUFS_FHSM
++#undef AuSi_FHSM
++#define AuSi_FHSM 0
++#endif
++
+static inline unsigned char au_do_ftest_si(struct au_sbinfo *sbi,
+ unsigned int flag)
+{
+extern struct au_wbr_copyup_operations au_wbr_copyup_ops[];
+extern struct au_wbr_create_operations au_wbr_create_ops[];
+int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst);
++int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex);
++int au_wbr_do_copyup_bu(struct dentry *dentry, aufs_bindex_t bstart);
++
++/* mvdown.c */
++int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *arg);
++
++#ifdef CONFIG_AUFS_FHSM
++/* fhsm.c */
++
++static inline pid_t au_fhsm_pid(struct au_fhsm *fhsm)
++{
++ pid_t pid;
++
++ spin_lock(&fhsm->fhsm_spin);
++ pid = fhsm->fhsm_pid;
++ spin_unlock(&fhsm->fhsm_spin);
++
++ return pid;
++}
++
++void au_fhsm_wrote(struct super_block *sb, aufs_bindex_t bindex, int force);
++void au_fhsm_wrote_all(struct super_block *sb, int force);
++int au_fhsm_fd(struct super_block *sb, int oflags);
++int au_fhsm_br_alloc(struct au_branch *br);
++void au_fhsm_set_bottom(struct super_block *sb, aufs_bindex_t bindex);
++void au_fhsm_fin(struct super_block *sb);
++void au_fhsm_init(struct au_sbinfo *sbinfo);
++void au_fhsm_set(struct au_sbinfo *sbinfo, unsigned int sec);
++void au_fhsm_show(struct seq_file *seq, struct au_sbinfo *sbinfo);
++#else
++AuStubVoid(au_fhsm_wrote, struct super_block *sb, aufs_bindex_t bindex,
++ int force)
++AuStubVoid(au_fhsm_wrote_all, struct super_block *sb, int force)
++AuStub(int, au_fhsm_fd, return -EOPNOTSUPP, struct super_block *sb, int oflags)
++AuStub(pid_t, au_fhsm_pid, return 0, struct au_fhsm *fhsm)
++AuStubInt0(au_fhsm_br_alloc, struct au_branch *br)
++AuStubVoid(au_fhsm_set_bottom, struct super_block *sb, aufs_bindex_t bindex)
++AuStubVoid(au_fhsm_fin, struct super_block *sb)
++AuStubVoid(au_fhsm_init, struct au_sbinfo *sbinfo)
++AuStubVoid(au_fhsm_set, struct au_sbinfo *sbinfo, unsigned int sec)
++AuStubVoid(au_fhsm_show, struct seq_file *seq, struct au_sbinfo *sbinfo)
++#endif
+
+/* ---------------------------------------------------------------------- */
+
+AuStubInt0(au_xigen_new, struct inode *inode)
+AuStubInt0(au_xigen_set, struct super_block *sb, struct file *base)
+AuStubVoid(au_xigen_clr, struct super_block *sb)
-+static inline int au_busy_or_stale(void)
-+{
-+ return -EBUSY;
-+}
++AuStub(int, au_busy_or_stale, return -EBUSY, void)
+#endif /* CONFIG_AUFS_EXPORT */
+
+/* ---------------------------------------------------------------------- */
+#endif /* CONFIG_AUFS_MAGIC_SYSRQ */
+#else
+AuStubVoid(au_sbilist_init, void)
-+AuStubVoid(au_sbilist_add, struct super_block*)
-+AuStubVoid(au_sbilist_del, struct super_block*)
++AuStubVoid(au_sbilist_add, struct super_block *sb)
++AuStubVoid(au_sbilist_del, struct super_block *sb)
+AuStubVoid(au_sbilist_lock, void)
+AuStubVoid(au_sbilist_unlock, void)
+#define AuGFP_SBILIST GFP_NOFS
+static inline void dbgaufs_si_null(struct au_sbinfo *sbinfo)
+{
+ /*
-+ * This function is a dynamic '__init' fucntion actually,
++ * This function is a dynamic '__init' function actually,
+ * so the tiny check for si_rwsem is unnecessary.
+ */
+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
+#ifdef CONFIG_DEBUG_FS
+ sbinfo->si_dbgaufs = NULL;
++ sbinfo->si_dbgaufs_plink = NULL;
+ sbinfo->si_dbgaufs_xib = NULL;
+#ifdef CONFIG_AUFS_EXPORT
+ sbinfo->si_dbgaufs_xigen = NULL;
+
+static inline int si_pid_test(struct super_block *sb)
+{
-+ pid_t bit = si_pid_bit();
++ pid_t bit;
++
++ bit = si_pid_bit();
+ if (bit < PID_MAX_DEFAULT)
+ return test_bit(bit, au_sbi(sb)->au_si_pid.bitmap);
-+ else
-+ return si_pid_test_slow(sb);
++ return si_pid_test_slow(sb);
+}
+
+static inline void si_pid_set(struct super_block *sb)
+{
-+ pid_t bit = si_pid_bit();
++ pid_t bit;
++
++ bit = si_pid_bit();
+ if (bit < PID_MAX_DEFAULT) {
+ AuDebugOn(test_bit(bit, au_sbi(sb)->au_si_pid.bitmap));
+ set_bit(bit, au_sbi(sb)->au_si_pid.bitmap);
+
+static inline void si_pid_clr(struct super_block *sb)
+{
-+ pid_t bit = si_pid_bit();
++ pid_t bit;
++
++ bit = si_pid_bit();
+ if (bit < PID_MAX_DEFAULT) {
+ AuDebugOn(!test_bit(bit, au_sbi(sb)->au_si_pid.bitmap));
+ clear_bit(bit, au_sbi(sb)->au_si_pid.bitmap);
+
+static inline int si_noflush_read_trylock(struct super_block *sb)
+{
-+ int locked = __si_read_trylock(sb);
++ int locked;
++
++ locked = __si_read_trylock(sb);
+ if (locked)
+ si_pid_set(sb);
+ return locked;
+
+static inline int si_noflush_write_trylock(struct super_block *sb)
+{
-+ int locked = __si_write_trylock(sb);
++ int locked;
++
++ locked = __si_write_trylock(sb);
+ if (locked)
+ si_pid_set(sb);
+ return locked;
+}
+
-+#if 0 /* unused */
++#if 0 /* reserved */
+static inline int si_read_trylock(struct super_block *sb, int flags)
+{
+ if (au_ftest_lock(flags, FLUSH))
+ __si_read_unlock(sb);
+}
+
-+#if 0 /* unused */
++#if 0 /* reserved */
+static inline int si_write_trylock(struct super_block *sb, int flags)
+{
+ if (au_ftest_lock(flags, FLUSH))
+ __si_write_unlock(sb);
+}
+
-+#if 0 /* unused */
++#if 0 /* reserved */
+static inline void si_downgrade_lock(struct super_block *sb)
+{
+ __si_downgrade_lock(sb);
+#endif /* __AUFS_SUPER_H__ */
diff -urN /usr/share/empty/fs/aufs/sysaufs.c linux/fs/aufs/sysaufs.c
--- /usr/share/empty/fs/aufs/sysaufs.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/sysaufs.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,105 @@
++++ linux/fs/aufs/sysaufs.c 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,104 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+}
diff -urN /usr/share/empty/fs/aufs/sysaufs.h linux/fs/aufs/sysaufs.h
--- /usr/share/empty/fs/aufs/sysaufs.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/sysaufs.h 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,104 @@
++++ linux/fs/aufs/sysaufs.h 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,101 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+int sysaufs_si_xi_path(struct seq_file *seq, struct super_block *sb);
+ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr,
+ char *buf);
++long au_brinfo_ioctl(struct file *file, unsigned long arg);
++#ifdef CONFIG_COMPAT
++long au_brinfo_compat_ioctl(struct file *file, unsigned long arg);
++#endif
+
+void sysaufs_br_init(struct au_branch *br);
+void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex);
+#define sysaufs_attr_group NULL
+
+AuStubInt0(sysaufs_si_xi_path, struct seq_file *seq, struct super_block *sb)
-+
-+static inline
-+ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr,
-+ char *buf)
-+{
-+ return 0;
-+}
-+
++AuStub(ssize_t, sysaufs_si_show, return 0, struct kobject *kobj,
++ struct attribute *attr, char *buf)
+AuStubVoid(sysaufs_br_init, struct au_branch *br)
+AuStubVoid(sysaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex)
+AuStubVoid(sysaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex)
+#endif /* __SYSAUFS_H__ */
diff -urN /usr/share/empty/fs/aufs/sysfs.c linux/fs/aufs/sysfs.c
--- /usr/share/empty/fs/aufs/sysfs.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/sysfs.c 2013-02-19 08:40:03.950226347 +0100
-@@ -0,0 +1,257 @@
++++ linux/fs/aufs/sysfs.c 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,372 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * sysfs interface
+ */
+
++#include <linux/compat.h>
+#include <linux/seq_file.h>
+#include "aufs.h"
+
+ * unlinked.
+ */
+static int sysaufs_si_br(struct seq_file *seq, struct super_block *sb,
-+ aufs_bindex_t bindex)
++ aufs_bindex_t bindex, int idx)
+{
+ int err;
+ struct path path;
+ struct dentry *root;
+ struct au_branch *br;
-+ char *perm;
++ au_br_perm_str_t perm;
+
+ AuDbg("b%d\n", bindex);
+
+ 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);
++
++ switch (idx) {
++ case AuBrSysfs_BR:
++ path.mnt = au_br_mnt(br);
++ path.dentry = au_h_dptr(root, bindex);
++ au_seq_path(seq, &path);
++ au_optstr_br_perm(&perm, br->br_perm);
++ err = seq_printf(seq, "=%s\n", perm.a);
++ break;
++ case AuBrSysfs_BRID:
++ err = seq_printf(seq, "%d\n", br->br_id);
++ break;
++ }
+ di_read_unlock(root, !AuLock_IR);
-+ perm = au_optstr_br_perm(br->br_perm);
-+ if (perm) {
-+ err = seq_printf(seq, "=%s\n", perm);
-+ kfree(perm);
-+ if (err == -1)
-+ err = -E2BIG;
-+ } else
-+ err = -ENOMEM;
++ if (err == -1)
++ err = -E2BIG;
++
+ return err;
+}
+
+ return seq;
+}
+
-+#define SysaufsBr_PREFIX "br"
++#define SysaufsBr_PREFIX "br"
++#define SysaufsBrid_PREFIX "brid"
+
+/* todo: file size may exceed PAGE_SIZE */
+ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ ssize_t err;
++ int idx;
+ long l;
+ aufs_bindex_t bend;
+ struct au_sbinfo *sbinfo;
+ cattr++;
+ }
+
-+ bend = au_sbend(sb);
-+ if (!strncmp(name, SysaufsBr_PREFIX, sizeof(SysaufsBr_PREFIX) - 1)) {
++ if (!strncmp(name, SysaufsBrid_PREFIX,
++ sizeof(SysaufsBrid_PREFIX) - 1)) {
++ idx = AuBrSysfs_BRID;
++ name += sizeof(SysaufsBrid_PREFIX) - 1;
++ } else if (!strncmp(name, SysaufsBr_PREFIX,
++ sizeof(SysaufsBr_PREFIX) - 1)) {
++ idx = AuBrSysfs_BR;
+ name += sizeof(SysaufsBr_PREFIX) - 1;
-+ err = kstrtol(name, 10, &l);
-+ if (!err) {
-+ if (l <= bend)
-+ err = sysaufs_si_br(seq, sb, (aufs_bindex_t)l);
-+ else
-+ err = -ENOENT;
++ } else
++ BUG();
++
++ err = kstrtol(name, 10, &l);
++ if (!err) {
++ bend = au_sbend(sb);
++ if (l <= bend)
++ err = sysaufs_si_br(seq, sb, (aufs_bindex_t)l, idx);
++ else
++ err = -ENOENT;
++ }
++
++out_seq:
++ if (!err) {
++ err = seq->count;
++ /* sysfs limit */
++ if (unlikely(err == PAGE_SIZE))
++ err = -EFBIG;
++ }
++ kfree(seq);
++out_unlock:
++ si_read_unlock(sb);
++out:
++ return err;
++}
++
++/* ---------------------------------------------------------------------- */
++
++static int au_brinfo(struct super_block *sb, union aufs_brinfo __user *arg)
++{
++ int err;
++ int16_t brid;
++ aufs_bindex_t bindex, bend;
++ size_t sz;
++ char *buf;
++ struct seq_file *seq;
++ struct au_branch *br;
++
++ si_read_lock(sb, AuLock_FLUSH);
++ bend = au_sbend(sb);
++ err = bend + 1;
++ if (!arg)
++ goto out;
++
++ err = -ENOMEM;
++ buf = (void *)__get_free_page(GFP_NOFS);
++ if (unlikely(!buf))
++ goto out;
++
++ seq = au_seq(buf, PAGE_SIZE);
++ err = PTR_ERR(seq);
++ if (IS_ERR(seq))
++ goto out_buf;
++
++ sz = sizeof(*arg) - offsetof(union aufs_brinfo, path);
++ for (bindex = 0; bindex <= bend; bindex++, arg++) {
++ err = !access_ok(VERIFY_WRITE, arg, sizeof(*arg));
++ if (unlikely(err))
++ break;
++
++ br = au_sbr(sb, bindex);
++ brid = br->br_id;
++ BUILD_BUG_ON(sizeof(brid) != sizeof(arg->id));
++ err = __put_user(brid, &arg->id);
++ if (unlikely(err))
++ break;
++
++ BUILD_BUG_ON(sizeof(br->br_perm) != sizeof(arg->perm));
++ err = __put_user(br->br_perm, &arg->perm);
++ if (unlikely(err))
++ break;
++
++ au_seq_path(seq, &br->br_path);
++ err = seq_putc(seq, '\0');
++ if (!err && seq->count <= sz) {
++ err = copy_to_user(arg->path, seq->buf, seq->count);
++ seq->count = 0;
++ if (unlikely(err))
++ break;
++ } else {
++ err = -E2BIG;
++ goto out_seq;
+ }
-+ goto out_seq;
+ }
-+ BUG();
++ if (unlikely(err))
++ err = -EFAULT;
+
+out_seq:
-+ if (!err) {
-+ err = seq->count;
-+ /* sysfs limit */
-+ if (unlikely(err == PAGE_SIZE))
-+ err = -EFBIG;
-+ }
+ kfree(seq);
-+out_unlock:
-+ si_read_unlock(sb);
++out_buf:
++ free_page((unsigned long)buf);
+out:
++ si_read_unlock(sb);
+ return err;
+}
+
++long au_brinfo_ioctl(struct file *file, unsigned long arg)
++{
++ return au_brinfo(file->f_path.dentry->d_sb, (void __user *)arg);
++}
++
++#ifdef CONFIG_COMPAT
++long au_brinfo_compat_ioctl(struct file *file, unsigned long arg)
++{
++ return au_brinfo(file->f_path.dentry->d_sb, compat_ptr(arg));
++}
++#endif
++
+/* ---------------------------------------------------------------------- */
+
+void sysaufs_br_init(struct au_branch *br)
+{
-+ struct attribute *attr = &br->br_attr;
++ int i;
++ struct au_brsysfs *br_sysfs;
++ struct attribute *attr;
+
-+ sysfs_attr_init(attr);
-+ attr->name = br->br_name;
-+ attr->mode = S_IRUGO;
++ br_sysfs = br->br_sysfs;
++ for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) {
++ attr = &br_sysfs->attr;
++ sysfs_attr_init(attr);
++ attr->name = br_sysfs->name;
++ attr->mode = S_IRUGO;
++ br_sysfs++;
++ }
+}
+
+void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex)
+{
+ struct au_branch *br;
+ struct kobject *kobj;
++ struct au_brsysfs *br_sysfs;
++ int i;
+ aufs_bindex_t bend;
+
+ dbgaufs_brs_del(sb, bindex);
+ bend = au_sbend(sb);
+ for (; bindex <= bend; bindex++) {
+ br = au_sbr(sb, bindex);
-+ sysfs_remove_file(kobj, &br->br_attr);
++ br_sysfs = br->br_sysfs;
++ for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) {
++ sysfs_remove_file(kobj, &br_sysfs->attr);
++ br_sysfs++;
++ }
+ }
+}
+
+void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex)
+{
-+ int err;
++ int err, i;
+ aufs_bindex_t bend;
+ struct kobject *kobj;
+ struct au_branch *br;
++ struct au_brsysfs *br_sysfs;
+
+ dbgaufs_brs_add(sb, bindex);
+
+ 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))
-+ pr_warn("failed %s under sysfs(%d)\n",
-+ br->br_name, err);
++ br_sysfs = br->br_sysfs;
++ snprintf(br_sysfs[AuBrSysfs_BR].name, sizeof(br_sysfs->name),
++ SysaufsBr_PREFIX "%d", bindex);
++ snprintf(br_sysfs[AuBrSysfs_BRID].name, sizeof(br_sysfs->name),
++ SysaufsBrid_PREFIX "%d", bindex);
++ for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) {
++ err = sysfs_create_file(kobj, &br_sysfs->attr);
++ if (unlikely(err))
++ pr_warn("failed %s under sysfs(%d)\n",
++ br_sysfs->name, err);
++ br_sysfs++;
++ }
+ }
+}
diff -urN /usr/share/empty/fs/aufs/sysrq.c linux/fs/aufs/sysrq.c
--- /usr/share/empty/fs/aufs/sysrq.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/sysrq.c 2013-03-14 20:07:41.221457313 +0100
-@@ -0,0 +1,148 @@
++++ linux/fs/aufs/sysrq.c 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,157 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ char *plevel;
+ struct au_sbinfo *sbinfo;
+ struct file *file;
++ struct au_sphlhead *files;
++ struct au_finfo *finfo;
+
+ plevel = au_plevel;
+ au_plevel = KERN_WARNING;
+
-+ sbinfo = au_sbi(sb);
+ /* since we define pr_fmt, call printk directly */
++#define pr(str) printk(KERN_WARNING AUFS_NAME ": " str)
++
++ sbinfo = au_sbi(sb);
+ printk(KERN_WARNING "si=%lx\n", sysaufs_si_id(sbinfo));
-+ printk(KERN_WARNING AUFS_NAME ": superblock\n");
++ pr("superblock\n");
+ au_dpri_sb(sb);
+
+#if 0
-+ printk(KERN_WARNING AUFS_NAME ": root dentry\n");
++ pr("root dentry\n");
+ au_dpri_dentry(sb->s_root);
-+ printk(KERN_WARNING AUFS_NAME ": root inode\n");
++ pr("root inode\n");
+ au_dpri_inode(sb->s_root->d_inode);
+#endif
+
+#if 1
+ {
+ struct inode *i;
-+ printk(KERN_WARNING AUFS_NAME ": isolated inode\n");
++
++ pr("isolated inode\n");
+ spin_lock(&inode_sb_list_lock);
+ list_for_each_entry(i, &sb->s_inodes, i_sb_list) {
+ spin_lock(&i->i_lock);
+ spin_unlock(&inode_sb_list_lock);
+ }
+#endif
-+ printk(KERN_WARNING AUFS_NAME ": files\n");
-+ lg_global_lock(&files_lglock);
-+ do_file_list_for_each_entry(sb, file) {
++ pr("files\n");
++ files = &au_sbi(sb)->si_files;
++ spin_lock(&files->spin);
++ hlist_for_each_entry(finfo, &files->head, fi_hlist) {
+ umode_t mode;
-+ mode = file->f_dentry->d_inode->i_mode;
-+ if (!special_file(mode) || au_special_file(mode))
++
++ file = finfo->fi_file;
++ mode = file_inode(file)->i_mode;
++ if (!special_file(mode))
+ au_dpri_file(file);
-+ } while_file_list_for_each_entry;
-+ lg_global_unlock(&files_lglock);
-+ printk(KERN_WARNING AUFS_NAME ": done\n");
++ }
++ spin_unlock(&files->spin);
++ pr("done\n");
+
++#undef pr
+ au_plevel = plevel;
+}
+
+void au_sysrq_fin(void)
+{
+ int err;
++
+ err = unregister_sysrq_key(*aufs_sysrq_key, &au_sysrq_op);
+ if (unlikely(err))
+ pr_err("err %d (ignored)\n", err);
+}
diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c
--- /usr/share/empty/fs/aufs/vdir.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/vdir.c 2013-03-14 20:07:41.221457313 +0100
-@@ -0,0 +1,885 @@
++++ linux/fs/aufs/vdir.c 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,888 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+{
+ struct hlist_head *head;
+ unsigned int u;
++ size_t sz;
+
-+ head = kmalloc(sizeof(*nhash->nh_head) * num_hash, gfp);
++ sz = sizeof(*nhash->nh_head) * num_hash;
++ head = kmalloc(sz, gfp);
+ if (head) {
+ nhash->nh_num = num_hash;
+ nhash->nh_head = head;
+
+static void au_nhash_wh_do_free(struct hlist_head *head)
+{
-+ struct au_vdir_wh *tpos;
-+ struct hlist_node *pos, *node;
++ struct au_vdir_wh *pos;
++ struct hlist_node *node;
+
-+ hlist_for_each_entry_safe(tpos, pos, node, head, wh_hash) {
-+ /* hlist_del(pos); */
-+ kfree(tpos);
-+ }
++ hlist_for_each_entry_safe(pos, node, head, wh_hash)
++ kfree(pos);
+}
+
+static void au_nhash_de_do_free(struct hlist_head *head)
+{
-+ struct au_vdir_dehstr *tpos;
-+ struct hlist_node *pos, *node;
++ struct au_vdir_dehstr *pos;
++ struct hlist_node *node;
+
-+ hlist_for_each_entry_safe(tpos, pos, node, head, hash) {
-+ /* hlist_del(pos); */
-+ au_cache_free_vdir_dehstr(tpos);
-+ }
++ hlist_for_each_entry_safe(pos, node, head, hash)
++ au_cache_free_vdir_dehstr(pos);
+}
+
+static void au_nhash_do_free(struct au_nhash *nhash,
+ int num;
+ unsigned int u, n;
+ struct hlist_head *head;
-+ struct au_vdir_wh *tpos;
-+ struct hlist_node *pos;
++ struct au_vdir_wh *pos;
+
+ num = 0;
+ n = whlist->nh_num;
+ head = whlist->nh_head;
+ for (u = 0; u < n; u++, head++)
-+ hlist_for_each_entry(tpos, pos, head, wh_hash)
-+ if (tpos->wh_bindex == btgt && ++num > limit)
++ hlist_for_each_entry(pos, head, wh_hash)
++ if (pos->wh_bindex == btgt && ++num > limit)
+ return 1;
+ return 0;
+}
+int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen)
+{
+ struct hlist_head *head;
-+ struct au_vdir_wh *tpos;
-+ struct hlist_node *pos;
++ struct au_vdir_wh *pos;
+ struct au_vdir_destr *str;
+
+ head = au_name_hash(whlist, name, nlen);
-+ hlist_for_each_entry(tpos, pos, head, wh_hash) {
-+ str = &tpos->wh_str;
++ hlist_for_each_entry(pos, head, wh_hash) {
++ str = &pos->wh_str;
+ AuDbg("%.*s\n", str->len, str->name);
+ if (au_nhash_test_name(str, name, nlen))
+ return 1;
+static int test_known(struct au_nhash *delist, char *name, int nlen)
+{
+ struct hlist_head *head;
-+ struct au_vdir_dehstr *tpos;
-+ struct hlist_node *pos;
++ struct au_vdir_dehstr *pos;
+ struct au_vdir_destr *str;
+
+ head = au_name_hash(delist, name, nlen);
-+ hlist_for_each_entry(tpos, pos, head, hash) {
-+ str = tpos->str;
++ hlist_for_each_entry(pos, head, hash) {
++ str = pos->str;
+ AuDbg("%.*s\n", str->len, str->name);
+ if (au_nhash_test_name(str, name, nlen))
+ return 1;
+ struct super_block *sb;
+ int err;
+
-+ sb = file->f_dentry->d_sb;
++ sb = file->f_path.dentry->d_sb;
+ SiMustAnyLock(sb);
+
+ err = -ENOMEM;
+#endif
+
+struct fillvdir_arg {
++ struct dir_context ctx;
+ struct file *file;
+ struct au_vdir *vdir;
+ struct au_nhash delist;
+ int err;
+};
+
-+static int fillvdir(void *__arg, const char *__name, int nlen,
++static int fillvdir(struct dir_context *ctx, const char *__name, int nlen,
+ loff_t offset __maybe_unused, u64 h_ino,
+ unsigned int d_type)
+{
-+ struct fillvdir_arg *arg = __arg;
++ struct fillvdir_arg *arg = container_of(ctx, struct fillvdir_arg, ctx);
+ char *name = (void *)__name;
+ struct super_block *sb;
+ ino_t ino;
+ const unsigned char shwh = !!au_ftest_fillvdir(arg->flags, SHWH);
+
+ arg->err = 0;
-+ sb = arg->file->f_dentry->d_sb;
++ sb = arg->file->f_path.dentry->d_sb;
+ au_fset_fillvdir(arg->flags, CALLED);
+ /* smp_mb(); */
+ if (nlen <= AUFS_WH_PFX_LEN
+ || au_nhash_test_known_wh(&arg->whlist, name, nlen))
+ goto out; /* already exists or whiteouted */
+
-+ sb = arg->file->f_dentry->d_sb;
+ arg->err = au_ino(sb, arg->bindex, h_ino, d_type, &ino);
+ if (!arg->err) {
+ if (unlikely(nlen > AUFS_MAX_NAMELEN))
+ int err;
+ unsigned int nh, u;
+ struct hlist_head *head;
-+ struct au_vdir_wh *tpos;
-+ struct hlist_node *pos, *n;
++ struct au_vdir_wh *pos;
++ struct hlist_node *n;
+ char *p, *o;
+ struct au_vdir_destr *destr;
+
+ p += AUFS_WH_PFX_LEN;
+ for (u = 0; u < nh; u++) {
+ head = whlist->nh_head + u;
-+ hlist_for_each_entry_safe(tpos, pos, n, head, wh_hash) {
-+ destr = &tpos->wh_str;
++ hlist_for_each_entry_safe(pos, n, head, wh_hash) {
++ destr = &pos->wh_str;
+ memcpy(p, destr->name, destr->len);
+ err = append_de(vdir, o, destr->len + AUFS_WH_PFX_LEN,
-+ tpos->wh_ino, tpos->wh_type, delist);
++ pos->wh_ino, pos->wh_type, delist);
+ if (unlikely(err))
+ break;
+ }
+ struct super_block *sb;
+
+ file = arg->file;
-+ sb = file->f_dentry->d_sb;
++ sb = file->f_path.dentry->d_sb;
+ SiMustAnyLock(sb);
+
+ rdhash = au_sbi(sb)->si_rdhash;
+ arg->err = 0;
+ au_fclr_fillvdir(arg->flags, CALLED);
+ /* smp_mb(); */
-+ err = vfsub_readdir(hf, fillvdir, arg);
++ err = vfsub_iterate_dir(hf, &arg->ctx);
+ if (err >= 0)
+ err = arg->err;
+ } while (!err && au_ftest_fillvdir(arg->flags, CALLED));
++
++ /*
++ * dir_relax() may be good for concurrency, but aufs should not
++ * use it since it will cause a lockdep problem.
++ */
+ }
+
+ if (!err && shwh)
+ int err;
+ unsigned long expire;
+ unsigned char do_read;
-+ struct fillvdir_arg arg;
++ struct fillvdir_arg arg = {
++ .ctx = {
++ .actor = fillvdir
++ }
++ };
+ struct inode *inode;
+ struct au_vdir *vdir, *allocated;
+
+ err = 0;
-+ inode = file->f_dentry->d_inode;
++ inode = file_inode(file);
+ IMustLock(inode);
+ SiMustAnyLock(inode->i_sb);
+
+ arg.vdir = vdir;
+ err = au_do_read_vdir(&arg);
+ if (!err) {
-+ /* file->f_pos = 0; */
++ /* file->f_pos = 0; */ /* todo: ctx->pos? */
+ vdir->vd_version = inode->i_version;
+ vdir->vd_last.ul = 0;
+ vdir->vd_last.p.deblk = vdir->vd_deblk[0];
+ struct inode *inode;
+ struct au_vdir *vdir_cache, *allocated;
+
++ /* test file->f_pos here instead of ctx->pos */
+ err = read_vdir(file, !file->f_pos);
+ if (unlikely(err))
+ goto out;
+ goto out;
+ allocated = vdir_cache;
+ } else if (!file->f_pos && vdir_cache->vd_version != file->f_version) {
++ /* test file->f_pos here instead of ctx->pos */
+ err = reinit_vdir(vdir_cache);
+ if (unlikely(err))
+ goto out;
+ } else
+ return 0; /* success */
+
-+ inode = file->f_dentry->d_inode;
++ inode = file_inode(file);
+ err = copy_vdir(vdir_cache, au_ivdir(inode));
+ if (!err) {
+ file->f_version = inode->i_version;
+}
+
+/* returns true or false */
-+static int seek_vdir(struct file *file)
++static int seek_vdir(struct file *file, struct dir_context *ctx)
+{
+ int valid;
+ unsigned int deblk_sz;
+ vdir_cache = au_fvdir_cache(file);
+ offset = calc_offset(vdir_cache);
+ AuDbg("offset %lld\n", offset);
-+ if (file->f_pos == offset)
++ if (ctx->pos == offset)
+ goto out;
+
+ vdir_cache->vd_last.ul = 0;
+ vdir_cache->vd_last.p.deblk = vdir_cache->vd_deblk[0];
-+ if (!file->f_pos)
++ if (!ctx->pos)
+ goto out;
+
+ valid = 0;
+ deblk_sz = vdir_cache->vd_deblk_sz;
-+ ul = div64_u64(file->f_pos, deblk_sz);
++ ul = div64_u64(ctx->pos, deblk_sz);
+ AuDbg("ul %lu\n", ul);
+ if (ul >= vdir_cache->vd_nblk)
+ goto out;
+ deblk_end.deblk = p.deblk + deblk_sz;
+ offset = ul;
+ offset *= deblk_sz;
-+ while (!is_deblk_end(&p, &deblk_end) && offset < file->f_pos) {
++ while (!is_deblk_end(&p, &deblk_end) && offset < ctx->pos) {
+ unsigned int l;
+
+ l = calc_size(p.de->de_str.len);
+ return valid;
+}
+
-+int au_vdir_fill_de(struct file *file, void *dirent, filldir_t filldir)
++int au_vdir_fill_de(struct file *file, struct dir_context *ctx)
+{
-+ int err;
+ unsigned int l, deblk_sz;
+ union au_vdir_deblk_p deblk_end;
+ struct au_vdir *vdir_cache;
+ struct au_vdir_de *de;
+
+ vdir_cache = au_fvdir_cache(file);
-+ if (!seek_vdir(file))
++ if (!seek_vdir(file, ctx))
+ return 0;
+
+ deblk_sz = vdir_cache->vd_deblk_sz;
+ 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,
++ de->de_str.len, de->de_str.name, ctx->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);
++ if (unlikely(!dir_emit(ctx, de->de_str.name,
++ de->de_str.len, de->de_ino,
++ de->de_type))) {
+ /* todo: ignore the error caused by udba? */
+ /* return err; */
+ return 0;
+
+ l = calc_size(de->de_str.len);
+ vdir_cache->vd_last.p.deblk += l;
-+ file->f_pos += l;
++ ctx->pos += l;
+ }
+ if (vdir_cache->vd_last.ul < vdir_cache->vd_nblk - 1) {
+ vdir_cache->vd_last.ul++;
+ vdir_cache->vd_last.p.deblk
+ = vdir_cache->vd_deblk[vdir_cache->vd_last.ul];
-+ file->f_pos = deblk_sz * vdir_cache->vd_last.ul;
++ ctx->pos = deblk_sz * vdir_cache->vd_last.ul;
+ continue;
+ }
+ break;
+}
diff -urN /usr/share/empty/fs/aufs/vfsub.c linux/fs/aufs/vfsub.c
--- /usr/share/empty/fs/aufs/vfsub.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/vfsub.c 2013-03-14 20:07:41.221457313 +0100
-@@ -0,0 +1,777 @@
++++ linux/fs/aufs/vfsub.c 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,846 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * sub-routines for VFS
+ */
+
-+#include <linux/ima.h>
+#include <linux/namei.h>
+#include <linux/security.h>
+#include <linux/splice.h>
+ h_sb = h_path->dentry->d_sb;
+ *did = (!au_test_fs_remote(h_sb) && au_test_fs_refresh_iattr(h_sb));
+ if (*did)
-+ err = vfs_getattr(h_path->mnt, h_path->dentry, &st);
++ err = vfs_getattr(h_path, &st);
+
+ return err;
+}
+ return file;
+}
+
++/*
++ * Ideally this function should call VFS:do_last() in order to keep all its
++ * checkings. But it is very hard for aufs to regenerate several VFS internal
++ * structure such as nameidata. This is a second (or third) best approach.
++ * cf. linux/fs/namei.c:do_last(), lookup_open() and atomic_open().
++ */
++int vfsub_atomic_open(struct inode *dir, struct dentry *dentry,
++ struct vfsub_aopen_args *args, struct au_branch *br)
++{
++ int err;
++ struct file *file = args->file;
++ /* copied from linux/fs/namei.c:atomic_open() */
++ struct dentry *const DENTRY_NOT_SET = (void *)-1UL;
++
++ IMustLock(dir);
++ AuDebugOn(!dir->i_op->atomic_open);
++
++ err = au_br_test_oflag(args->open_flag, br);
++ if (unlikely(err))
++ goto out;
++
++ args->file->f_path.dentry = DENTRY_NOT_SET;
++ args->file->f_path.mnt = au_br_mnt(br);
++ err = dir->i_op->atomic_open(dir, dentry, file, args->open_flag,
++ args->create_mode, args->opened);
++ if (err >= 0) {
++ /* some filesystems don't set FILE_CREATED while succeeded? */
++ if (*args->opened & FILE_CREATED)
++ fsnotify_create(dir, dentry);
++ } else
++ goto out;
++
++
++ if (!err) {
++ /* todo: call VFS:may_open() here */
++ err = open_check_o_direct(file);
++ /* todo: ima_file_check() too? */
++ if (!err && (args->open_flag & __FMODE_EXEC))
++ err = deny_write_access(file);
++ if (unlikely(err))
++ /* note that the file is created and still opened */
++ goto out;
++ }
++
++ atomic_inc(&br->br_count);
++ fsnotify_open(file);
++
++out:
++ return err;
++}
++
+int vfsub_kern_path(const char *name, unsigned int flags, struct path *path)
+{
+ int err;
+ if (unlikely(err))
+ goto out;
+
++ lockdep_off();
+ err = vfs_create(dir, path->dentry, mode, want_excl);
++ lockdep_on();
+ if (!err) {
+ struct path tmp = *path;
+ int did;
+ if (unlikely(err))
+ goto out;
+
++ lockdep_off();
+ err = vfs_symlink(dir, path->dentry, symname);
++ lockdep_on();
+ if (!err) {
+ struct path tmp = *path;
+ int did;
+ if (unlikely(err))
+ goto out;
+
++ lockdep_off();
+ err = vfs_mknod(dir, path->dentry, mode, dev);
++ lockdep_on();
+ if (!err) {
+ struct path tmp = *path;
+ int did;
+ return -EMLINK;
+}
+
-+int vfsub_link(struct dentry *src_dentry, struct inode *dir, struct path *path)
++int vfsub_link(struct dentry *src_dentry, struct inode *dir, struct path *path,
++ struct inode **delegated_inode)
+{
+ int err;
+ struct dentry *d;
+ goto out;
+
+ lockdep_off();
-+ err = vfs_link(src_dentry, dir, path->dentry);
++ err = vfs_link(src_dentry, dir, path->dentry, delegated_inode);
+ lockdep_on();
+ if (!err) {
+ struct path tmp = *path;
+}
+
+int vfsub_rename(struct inode *src_dir, struct dentry *src_dentry,
-+ struct inode *dir, struct path *path)
++ struct inode *dir, struct path *path,
++ struct inode **delegated_inode)
+{
+ int err;
+ struct path tmp = {
+ d = path->dentry;
+ path->dentry = d->d_parent;
+ tmp.dentry = src_dentry->d_parent;
-+ err = security_path_rename(&tmp, src_dentry, path, d);
++ err = security_path_rename(&tmp, src_dentry, path, d, /*flags*/0);
+ path->dentry = d;
+ if (unlikely(err))
+ goto out;
+
+ lockdep_off();
-+ err = vfs_rename(src_dir, src_dentry, dir, path->dentry);
++ err = vfs_rename(src_dir, src_dentry, dir, path->dentry,
++ delegated_inode, /*flags*/0);
+ lockdep_on();
+ if (!err) {
+ int did;
+ if (unlikely(err))
+ goto out;
+
++ lockdep_off();
+ err = vfs_mkdir(dir, path->dentry, mode);
++ lockdep_on();
+ if (!err) {
+ struct path tmp = *path;
+ int did;
+ int err;
+
+ err = 0;
-+ if (file->f_op && file->f_op->flush) {
-+ if (!au_test_nfs(file->f_dentry->d_sb))
++ if (file->f_op->flush) {
++ if (!au_test_nfs(file->f_path.dentry->d_sb))
+ err = file->f_op->flush(file, id);
+ else {
+ lockdep_off();
+ return err;
+}
+
-+int vfsub_readdir(struct file *file, filldir_t filldir, void *arg)
++int vfsub_iterate_dir(struct file *file, struct dir_context *ctx)
+{
+ int err;
+
++ AuDbg("%pD, ctx{%pf, %llu}\n", file, ctx->actor, ctx->pos);
++
+ lockdep_off();
-+ err = vfs_readdir(file, filldir, arg);
++ err = iterate_dir(file, ctx);
+ lockdep_on();
+ if (err >= 0)
+ vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/
+{
+ int err;
+ struct inode *h_inode;
++ struct super_block *h_sb;
+
-+ h_inode = h_path->dentry->d_inode;
+ if (!h_file) {
-+ err = vfsub_mnt_want_write(h_path->mnt);
-+ if (err)
-+ goto out;
-+ err = inode_permission(h_inode, MAY_WRITE);
-+ if (err)
-+ goto out_mnt;
-+ err = get_write_access(h_inode);
-+ if (err)
-+ goto out_mnt;
-+ err = break_lease(h_inode, O_WRONLY);
-+ if (err)
-+ goto out_inode;
++ err = vfsub_truncate(h_path, length);
++ goto out;
+ }
+
++ h_inode = h_path->dentry->d_inode;
++ h_sb = h_inode->i_sb;
++ lockdep_off();
++ sb_start_write(h_sb);
++ lockdep_on();
+ err = locks_verify_truncate(h_inode, h_file, length);
+ if (!err)
+ err = security_path_truncate(h_path);
+ err = do_truncate(h_path->dentry, length, attr, h_file);
+ lockdep_on();
+ }
++ lockdep_off();
++ sb_end_write(h_sb);
++ lockdep_on();
+
-+out_inode:
-+ if (!h_file)
-+ put_write_access(h_inode);
-+out_mnt:
-+ if (!h_file)
-+ vfsub_mnt_drop_write(h_path->mnt);
+out:
+ return err;
+}
+ int err, do_sio, wkq_err;
+
+ do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE);
-+ if (!do_sio)
++ if (!do_sio) {
++ lockdep_off();
+ err = vfsub_mkdir(dir, path, mode);
-+ else {
++ lockdep_on();
++ } else {
+ struct au_vfsub_mkdir_args args = {
+ .errp = &err,
+ .dir = dir,
+ int err, do_sio, wkq_err;
+
+ do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE);
-+ if (!do_sio)
++ if (!do_sio) {
++ lockdep_off();
+ err = vfsub_rmdir(dir, path);
-+ else {
++ lockdep_on();
++ } else {
+ struct au_vfsub_rmdir_args args = {
+ .errp = &err,
+ .dir = dir,
+ int *errp;
+ struct path *path;
+ struct iattr *ia;
++ struct inode **delegated_inode;
+};
+
+static void call_notify_change(void *args)
+
+ *a->errp = -EPERM;
+ if (!IS_IMMUTABLE(h_inode) && !IS_APPEND(h_inode)) {
-+ *a->errp = notify_change(a->path->dentry, a->ia);
++ lockdep_off();
++ *a->errp = notify_change(a->path->dentry, a->ia,
++ a->delegated_inode);
++ lockdep_on();
+ if (!*a->errp)
+ vfsub_update_h_iattr(a->path, /*did*/NULL); /*ignore*/
+ }
+ AuTraceErr(*a->errp);
+}
+
-+int vfsub_notify_change(struct path *path, struct iattr *ia)
++int vfsub_notify_change(struct path *path, struct iattr *ia,
++ struct inode **delegated_inode)
+{
+ int err;
+ struct notify_change_args args = {
-+ .errp = &err,
-+ .path = path,
-+ .ia = ia
++ .errp = &err,
++ .path = path,
++ .ia = ia,
++ .delegated_inode = delegated_inode
+ };
+
+ call_notify_change(&args);
+ return err;
+}
+
-+int vfsub_sio_notify_change(struct path *path, struct iattr *ia)
++int vfsub_sio_notify_change(struct path *path, struct iattr *ia,
++ struct inode **delegated_inode)
+{
+ int err, wkq_err;
+ struct notify_change_args args = {
-+ .errp = &err,
-+ .path = path,
-+ .ia = ia
++ .errp = &err,
++ .path = path,
++ .ia = ia,
++ .delegated_inode = delegated_inode
+ };
+
+ wkq_err = au_wkq_wait(call_notify_change, &args);
+ int *errp;
+ struct inode *dir;
+ struct path *path;
++ struct inode **delegated_inode;
+};
+
+static void call_unlink(void *args)
+ struct dentry *d = a->path->dentry;
+ struct inode *h_inode;
+ const int stop_sillyrename = (au_test_nfs(d->d_sb)
-+ && d->d_count == 1);
++ && au_dcount(d) == 1);
+
+ IMustLock(a->dir);
+
+ ihold(h_inode);
+
+ lockdep_off();
-+ *a->errp = vfs_unlink(a->dir, d);
++ *a->errp = vfs_unlink(a->dir, d, a->delegated_inode);
+ lockdep_on();
+ if (!*a->errp) {
+ struct path tmp = {
+ * @dir: must be locked.
+ * @dentry: target dentry.
+ */
-+int vfsub_unlink(struct inode *dir, struct path *path, int force)
++int vfsub_unlink(struct inode *dir, struct path *path,
++ struct inode **delegated_inode, int force)
+{
+ int err;
+ struct unlink_args args = {
-+ .errp = &err,
-+ .dir = dir,
-+ .path = path
++ .errp = &err,
++ .dir = dir,
++ .path = path,
++ .delegated_inode = delegated_inode
+ };
+
+ if (!force)
+}
diff -urN /usr/share/empty/fs/aufs/vfsub.h linux/fs/aufs/vfsub.h
--- /usr/share/empty/fs/aufs/vfsub.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/vfsub.h 2013-03-14 20:07:41.224790724 +0100
-@@ -0,0 +1,284 @@
++++ linux/fs/aufs/vfsub.h 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,286 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
-+#include <linux/lglock.h>
+#include <linux/mount.h>
++#include <linux/xattr.h>
+#include "debug.h"
+
+/* copied from linux/fs/internal.h */
+/* todo: BAD approach!! */
-+extern struct lglock vfsmount_lock;
++extern void __mnt_drop_write(struct vfsmount *);
+extern spinlock_t inode_sb_list_lock;
-+
-+/* copied from linux/fs/file_table.c */
-+extern struct lglock files_lglock;
-+#ifdef CONFIG_SMP
-+/*
-+ * These macros iterate all files on all CPUs for a given superblock.
-+ * files_lglock must be held globally.
-+ */
-+#define do_file_list_for_each_entry(__sb, __file) \
-+{ \
-+ int i; \
-+ for_each_possible_cpu(i) { \
-+ struct list_head *list; \
-+ list = per_cpu_ptr((__sb)->s_files, i); \
-+ list_for_each_entry((__file), list, f_u.fu_list)
-+
-+#define while_file_list_for_each_entry \
-+ } \
-+}
-+
-+#else
-+
-+#define do_file_list_for_each_entry(__sb, __file) \
-+{ \
-+ struct list_head *list; \
-+ list = &(sb)->s_files; \
-+ list_for_each_entry((__file), list, f_u.fu_list)
-+
-+#define while_file_list_for_each_entry \
-+}
-+#endif
++extern int open_check_o_direct(struct file *f);
+
+/* ---------------------------------------------------------------------- */
+
+/* default MAX_LOCKDEP_SUBCLASSES(8) is not enough */
+/* reduce? gave up. */
+enum {
-+ AuLsc_I_Begin = I_MUTEX_QUOTA, /* 4 */
++ AuLsc_I_Begin = I_MUTEX_PARENT2, /* 5 */
+ AuLsc_I_PARENT, /* lower inode, parent first */
+ AuLsc_I_PARENT2, /* copyup dirs */
+ AuLsc_I_PARENT3, /* copyup wh */
+ clear_nlink(inode);
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+/* cf. i_[ug]id_read() in linux/include/fs.h */
-+static inline uid_t vfsub_ia_uid(struct iattr *ia)
-+{
-+ return from_kuid(&init_user_ns, ia->ia_uid);
-+}
-+
-+static inline gid_t vfsub_ia_gid(struct iattr *ia)
++static inline int vfsub_native_ro(struct inode *inode)
+{
-+ return from_kgid(&init_user_ns, ia->ia_gid);
++ return (inode->i_sb->s_flags & MS_RDONLY)
++ || IS_RDONLY(inode)
++ /* || IS_APPEND(inode) */
++ || IS_IMMUTABLE(inode);
+}
+
+/* ---------------------------------------------------------------------- */
+int vfsub_update_h_iattr(struct path *h_path, int *did);
+struct file *vfsub_dentry_open(struct path *path, int flags);
+struct file *vfsub_filp_open(const char *path, int oflags, int mode);
++struct vfsub_aopen_args {
++ struct file *file;
++ unsigned int open_flag;
++ umode_t create_mode;
++ int *opened;
++};
++struct au_branch;
++int vfsub_atomic_open(struct inode *dir, struct dentry *dentry,
++ struct vfsub_aopen_args *args, struct au_branch *br);
+int vfsub_kern_path(const char *name, unsigned int flags, struct path *path);
+
+struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent,
+static inline int vfsub_mnt_want_write(struct vfsmount *mnt)
+{
+ int err;
++
+ lockdep_off();
+ err = mnt_want_write(mnt);
+ lockdep_on();
+ lockdep_on();
+}
+
++#if 0 /* reserved */
++static inline void vfsub_mnt_drop_write_file(struct file *file)
++{
++ lockdep_off();
++ mnt_drop_write_file(file);
++ lockdep_on();
++}
++#endif
++
+/* ---------------------------------------------------------------------- */
+
+struct au_hinode;
+ const char *symname);
+int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev);
+int vfsub_link(struct dentry *src_dentry, struct inode *dir,
-+ struct path *path);
++ struct path *path, struct inode **delegated_inode);
+int vfsub_rename(struct inode *src_hdir, struct dentry *src_dentry,
-+ struct inode *hdir, struct path *path);
++ struct inode *hdir, struct path *path,
++ struct inode **delegated_inode);
+int vfsub_mkdir(struct inode *dir, struct path *path, int mode);
+int vfsub_rmdir(struct inode *dir, struct path *path);
+
+ssize_t vfsub_write_k(struct file *file, void *kbuf, size_t count,
+ loff_t *ppos);
+int vfsub_flush(struct file *file, fl_owner_t id);
-+int vfsub_readdir(struct file *file, filldir_t filldir, void *arg);
++int vfsub_iterate_dir(struct file *file, struct dir_context *ctx);
++
++static inline loff_t vfsub_f_size_read(struct file *file)
++{
++ return i_size_read(file_inode(file));
++}
+
+static inline unsigned int vfsub_file_flags(struct file *file)
+{
+ return flags;
+}
+
++#if 0 /* reserved */
+static inline void vfsub_file_accessed(struct file *h_file)
+{
+ file_accessed(h_file);
+ vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL); /*ignore*/
+}
++#endif
+
+static inline void vfsub_touch_atime(struct vfsmount *h_mnt,
+ struct dentry *h_dentry)
+static inline int vfsub_update_time(struct inode *h_inode, struct timespec *ts,
+ int flags)
+{
-+ return update_time(h_inode, ts, flags);
++ return generic_update_time(h_inode, ts, flags);
+ /* no vfsub_update_h_iattr() since we don't have struct path */
+}
+
+ unsigned int flags);
+long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out,
+ loff_t *ppos, size_t len, unsigned int flags);
++
++static inline long vfsub_truncate(struct path *path, loff_t length)
++{
++ long err;
++
++ lockdep_off();
++ err = vfs_truncate(path, length);
++ lockdep_on();
++ return err;
++}
++
+int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr,
+ struct file *h_file);
+int vfsub_fsync(struct file *file, struct path *path, int datasync);
+
+/* ---------------------------------------------------------------------- */
+
-+/* dirty workaround for strict type of fmode_t */
-+union vfsub_fmu {
-+ fmode_t fm;
-+ unsigned int ui;
-+};
++int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode);
++int vfsub_sio_rmdir(struct inode *dir, struct path *path);
++int vfsub_sio_notify_change(struct path *path, struct iattr *ia,
++ struct inode **delegated_inode);
++int vfsub_notify_change(struct path *path, struct iattr *ia,
++ struct inode **delegated_inode);
++int vfsub_unlink(struct inode *dir, struct path *path,
++ struct inode **delegated_inode, int force);
+
-+static inline unsigned int vfsub_fmode_to_uint(fmode_t fm)
++/* ---------------------------------------------------------------------- */
++
++static inline int vfsub_setxattr(struct dentry *dentry, const char *name,
++ const void *value, size_t size, int flags)
+{
-+ union vfsub_fmu u = {
-+ .fm = fm
-+ };
++ int err;
+
-+ BUILD_BUG_ON(sizeof(u.fm) != sizeof(u.ui));
++ lockdep_off();
++ err = vfs_setxattr(dentry, name, value, size, flags);
++ lockdep_on();
+
-+ return u.ui;
++ return err;
+}
+
-+static inline fmode_t vfsub_uint_to_fmode(unsigned int ui)
++static inline int vfsub_removexattr(struct dentry *dentry, const char *name)
+{
-+ union vfsub_fmu u = {
-+ .ui = ui
-+ };
-+
-+ return u.fm;
-+}
++ int err;
+
-+/* ---------------------------------------------------------------------- */
++ lockdep_off();
++ err = vfs_removexattr(dentry, name);
++ lockdep_on();
+
-+int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode);
-+int vfsub_sio_rmdir(struct inode *dir, struct path *path);
-+int vfsub_sio_notify_change(struct path *path, struct iattr *ia);
-+int vfsub_notify_change(struct path *path, struct iattr *ia);
-+int vfsub_unlink(struct inode *dir, struct path *path, int force);
++ return err;
++}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_VFSUB_H__ */
diff -urN /usr/share/empty/fs/aufs/wbr_policy.c linux/fs/aufs/wbr_policy.c
--- /usr/share/empty/fs/aufs/wbr_policy.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/wbr_policy.c 2013-02-19 08:40:03.953559833 +0100
-@@ -0,0 +1,700 @@
++++ linux/fs/aufs/wbr_policy.c 2015-06-22 08:27:37.887501948 +0200
+@@ -0,0 +1,765 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ ia.ia_uid = h_isrc->i_uid;
+ ia.ia_gid = h_isrc->i_gid;
+ sbits = !!(ia.ia_mode & (S_ISUID | S_ISGID));
-+ au_cpup_attr_flags(h_path->dentry->d_inode, h_isrc);
-+ err = vfsub_sio_notify_change(h_path, &ia);
++ au_cpup_attr_flags(h_path->dentry->d_inode, h_isrc->i_flags);
++ /* no delegation since it is just created */
++ err = vfsub_sio_notify_change(h_path, &ia, /*delegated*/NULL);
+
+ /* 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_sio_notify_change(h_path, &ia);
++ err = vfsub_sio_notify_change(h_path, &ia, /*delegated*/NULL);
+ }
+
+ return err;
+#define au_fclr_cpdown(flags, name) \
+ do { (flags) &= ~AuCpdown_##name; } while (0)
+
-+struct au_cpdown_dir_args {
-+ struct dentry *parent;
-+ unsigned int flags;
-+};
-+
+static int au_cpdown_dir_opq(struct dentry *dentry, aufs_bindex_t bdst,
-+ struct au_cpdown_dir_args *a)
++ unsigned int *flags)
+{
+ int err;
+ struct dentry *opq_dentry;
+ if (IS_ERR(opq_dentry))
+ goto out;
+ dput(opq_dentry);
-+ au_fset_cpdown(a->flags, DIROPQ);
++ au_fset_cpdown(*flags, DIROPQ);
+
+out:
+ return err;
+
+ err = 0;
+ if (h_path.dentry->d_inode) {
-+ h_path.mnt = br->br_mnt;
++ h_path.mnt = au_br_mnt(br);
+ err = au_wh_unlink_dentry(au_h_iptr(dir, bdst), &h_path,
+ dentry);
+ }
+}
+
+static int au_cpdown_dir(struct dentry *dentry, aufs_bindex_t bdst,
++ struct au_pin *pin,
+ struct dentry *h_parent, void *arg)
+{
+ int err, rerr;
+ struct path h_path;
+ struct dentry *parent;
+ struct inode *h_dir, *h_inode, *inode, *dir;
-+ struct au_cpdown_dir_args *args = arg;
++ unsigned int *flags = arg;
+
+ bstart = au_dbstart(dentry);
+ /* dentry is di-locked */
+ AuDebugOn(h_dir != au_h_iptr(dir, bdst));
+ IMustLock(h_dir);
+
-+ err = au_lkup_neg(dentry, bdst);
++ err = au_lkup_neg(dentry, bdst, /*wh*/0);
+ if (unlikely(err < 0))
+ goto out;
+ h_path.dentry = au_h_dptr(dentry, bdst);
+ S_IRWXU | S_IRUGO | S_IXUGO);
+ if (unlikely(err))
+ goto out_put;
-+ au_fset_cpdown(args->flags, MADE_DIR);
++ au_fset_cpdown(*flags, MADE_DIR);
+
+ bopq = au_dbdiropq(dentry);
-+ au_fclr_cpdown(args->flags, WHED);
-+ au_fclr_cpdown(args->flags, DIROPQ);
++ au_fclr_cpdown(*flags, WHED);
++ au_fclr_cpdown(*flags, DIROPQ);
+ if (au_dbwh(dentry) == bdst)
-+ au_fset_cpdown(args->flags, WHED);
-+ if (!au_ftest_cpdown(args->flags, PARENT_OPQ) && bopq <= bdst)
-+ au_fset_cpdown(args->flags, PARENT_OPQ);
++ au_fset_cpdown(*flags, WHED);
++ if (!au_ftest_cpdown(*flags, PARENT_OPQ) && bopq <= bdst)
++ au_fset_cpdown(*flags, PARENT_OPQ);
+ h_inode = h_path.dentry->d_inode;
+ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
-+ if (au_ftest_cpdown(args->flags, WHED)) {
-+ err = au_cpdown_dir_opq(dentry, bdst, args);
++ if (au_ftest_cpdown(*flags, WHED)) {
++ err = au_cpdown_dir_opq(dentry, bdst, flags);
+ if (unlikely(err)) {
+ mutex_unlock(&h_inode->i_mutex);
+ goto out_dir;
+ if (unlikely(err))
+ goto out_opq;
+
-+ if (au_ftest_cpdown(args->flags, WHED)) {
++ if (au_ftest_cpdown(*flags, WHED)) {
+ err = au_cpdown_dir_wh(dentry, h_parent, dir, bdst);
+ if (unlikely(err))
+ goto out_opq;
+ au_set_ibend(inode, bdst);
+ au_set_h_iptr(inode, bdst, au_igrab(h_inode),
+ au_hi_flags(inode, /*isdir*/1));
++ au_fhsm_wrote(dentry->d_sb, bdst, /*force*/0);
+ goto out; /* success */
+
+ /* revert */
+out_opq:
-+ if (au_ftest_cpdown(args->flags, DIROPQ)) {
++ if (au_ftest_cpdown(*flags, DIROPQ)) {
+ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
+ rerr = au_diropq_remove(dentry, bdst);
+ mutex_unlock(&h_inode->i_mutex);
+ if (unlikely(rerr)) {
-+ AuIOErr("failed removing diropq for %.*s b%d (%d)\n",
-+ AuDLNPair(dentry), bdst, rerr);
++ AuIOErr("failed removing diropq for %pd b%d (%d)\n",
++ dentry, bdst, rerr);
+ err = -EIO;
+ goto out;
+ }
+ }
+out_dir:
-+ if (au_ftest_cpdown(args->flags, MADE_DIR)) {
++ if (au_ftest_cpdown(*flags, MADE_DIR)) {
+ rerr = vfsub_sio_rmdir(au_h_iptr(dir, bdst), &h_path);
+ if (unlikely(rerr)) {
-+ AuIOErr("failed removing %.*s b%d (%d)\n",
-+ AuDLNPair(dentry), bdst, rerr);
++ AuIOErr("failed removing %pd b%d (%d)\n",
++ dentry, bdst, rerr);
+ err = -EIO;
+ }
+ }
+int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst)
+{
+ int err;
-+ struct au_cpdown_dir_args args = {
-+ .parent = dget_parent(dentry),
-+ .flags = 0
-+ };
++ unsigned int flags;
+
-+ err = au_cp_dirs(dentry, bdst, au_cpdown_dir, &args);
-+ dput(args.parent);
++ flags = 0;
++ err = au_cp_dirs(dentry, bdst, au_cpdown_dir, &flags);
+
+ return err;
+}
+
+/* policies for create */
+
-+static int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex)
++int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex)
+{
+ int err, i, j, ndentry;
+ aufs_bindex_t bopq;
+}
+
+/* top down parent */
-+static int au_wbr_create_tdp(struct dentry *dentry, int isdir __maybe_unused)
++static int au_wbr_create_tdp(struct dentry *dentry,
++ unsigned int flags __maybe_unused)
+{
+ int err;
+ aufs_bindex_t bstart, bindex;
+ return err;
+}
+
-+static int au_wbr_create_rr(struct dentry *dentry, int isdir)
++static int au_wbr_create_rr(struct dentry *dentry, unsigned int flags)
+{
+ int err, nbr;
+ unsigned int u;
+ bend = au_sbend(sb);
+ nbr = bend + 1;
+ for (bindex = 0; bindex <= bend; bindex++) {
-+ if (!isdir) {
++ if (!au_ftest_wbr(flags, DIR)) {
+ err = atomic_dec_return(next) + 1;
+ /* modulo for 0 is meaningless */
+ if (unlikely(!err))
+/* ---------------------------------------------------------------------- */
+
+/* most free space */
-+static void au_mfs(struct dentry *dentry)
++static void au_mfs(struct dentry *dentry, struct dentry *parent)
+{
+ struct super_block *sb;
+ struct au_branch *br;
+ struct au_wbr_mfs *mfs;
++ struct dentry *h_parent;
+ aufs_bindex_t bindex, bend;
+ int err;
+ unsigned long long b, bavail;
+ MtxMustLock(&mfs->mfs_lock);
+ mfs->mfs_bindex = -EROFS;
+ mfs->mfsrr_bytes = 0;
-+ bend = au_sbend(sb);
-+ for (bindex = 0; bindex <= bend; bindex++) {
++ if (!parent) {
++ bindex = 0;
++ bend = au_sbend(sb);
++ } else {
++ bindex = au_dbstart(parent);
++ bend = au_dbtaildir(parent);
++ }
++
++ for (; bindex <= bend; bindex++) {
++ if (parent) {
++ h_parent = au_h_dptr(parent, bindex);
++ if (!h_parent || !h_parent->d_inode)
++ continue;
++ }
+ br = au_sbr(sb, bindex);
+ if (au_br_rdonly(br))
+ continue;
+
+ /* sb->s_root for NFS is unreliable */
-+ h_path.mnt = br->br_mnt;
++ h_path.mnt = au_br_mnt(br);
+ h_path.dentry = h_path.mnt->mnt_root;
+ err = vfs_statfs(&h_path, st);
+ if (unlikely(err)) {
+ kfree(st);
+}
+
-+static int au_wbr_create_mfs(struct dentry *dentry, int isdir __maybe_unused)
++static int au_wbr_create_mfs(struct dentry *dentry, unsigned int flags)
+{
+ int err;
++ struct dentry *parent;
+ struct super_block *sb;
+ struct au_wbr_mfs *mfs;
+
+ goto out;
+
+ sb = dentry->d_sb;
++ parent = NULL;
++ if (au_ftest_wbr(flags, PARENT))
++ parent = dget_parent(dentry);
+ mfs = &au_sbi(sb)->si_wbr_mfs;
+ mutex_lock(&mfs->mfs_lock);
+ if (time_after(jiffies, mfs->mfs_jiffy + mfs->mfs_expire)
+ || mfs->mfs_bindex < 0
+ || au_br_rdonly(au_sbr(sb, mfs->mfs_bindex)))
-+ au_mfs(dentry);
++ au_mfs(dentry, parent);
+ mutex_unlock(&mfs->mfs_lock);
+ err = mfs->mfs_bindex;
++ dput(parent);
+
+ if (err >= 0)
+ err = au_wbr_nonopq(dentry, err);
+/* ---------------------------------------------------------------------- */
+
+/* most free space and then round robin */
-+static int au_wbr_create_mfsrr(struct dentry *dentry, int isdir)
++static int au_wbr_create_mfsrr(struct dentry *dentry, unsigned int flags)
+{
+ int err;
+ struct au_wbr_mfs *mfs;
+
-+ err = au_wbr_create_mfs(dentry, isdir);
++ err = au_wbr_create_mfs(dentry, flags);
+ if (err >= 0) {
+ mfs = &au_sbi(dentry->d_sb)->si_wbr_mfs;
+ mutex_lock(&mfs->mfs_lock);
+ if (mfs->mfsrr_bytes < mfs->mfsrr_watermark)
-+ err = au_wbr_create_rr(dentry, isdir);
++ err = au_wbr_create_rr(dentry, flags);
+ mutex_unlock(&mfs->mfs_lock);
+ }
+
+/* ---------------------------------------------------------------------- */
+
+/* top down parent and most free space */
-+static int au_wbr_create_pmfs(struct dentry *dentry, int isdir)
++static int au_wbr_create_pmfs(struct dentry *dentry, unsigned int flags)
+{
+ int err, e2;
+ unsigned long long b;
+ struct dentry *parent, *h_parent;
+ struct au_branch *br;
+
-+ err = au_wbr_create_tdp(dentry, isdir);
++ err = au_wbr_create_tdp(dentry, flags);
+ if (unlikely(err < 0))
+ goto out;
+ parent = dget_parent(dentry);
+ if (bstart == bend)
+ goto out_parent; /* success */
+
-+ e2 = au_wbr_create_mfs(dentry, isdir);
++ e2 = au_wbr_create_mfs(dentry, flags);
+ if (e2 < 0)
+ goto out_parent; /* success */
+
+
+/* ---------------------------------------------------------------------- */
+
++/*
++ * - top down parent
++ * - most free space with parent
++ * - most free space round-robin regardless parent
++ */
++static int au_wbr_create_pmfsrr(struct dentry *dentry, unsigned int flags)
++{
++ int err;
++ unsigned long long watermark;
++ struct super_block *sb;
++ struct au_branch *br;
++ struct au_wbr_mfs *mfs;
++
++ err = au_wbr_create_pmfs(dentry, flags | AuWbr_PARENT);
++ if (unlikely(err < 0))
++ goto out;
++
++ sb = dentry->d_sb;
++ br = au_sbr(sb, err);
++ mfs = &au_sbi(sb)->si_wbr_mfs;
++ mutex_lock(&mfs->mfs_lock);
++ watermark = mfs->mfsrr_watermark;
++ mutex_unlock(&mfs->mfs_lock);
++ if (br->br_wbr->wbr_bytes < watermark)
++ /* regardless the parent dir */
++ err = au_wbr_create_mfsrr(dentry, flags);
++
++out:
++ AuDbg("b%d\n", err);
++ return err;
++}
++
++/* ---------------------------------------------------------------------- */
++
+/* policies for copyup */
+
+/* top down parent */
+static int au_wbr_copyup_tdp(struct dentry *dentry)
+{
-+ return au_wbr_create_tdp(dentry, /*isdir, anything is ok*/0);
++ return au_wbr_create_tdp(dentry, /*flags, anything is ok*/0);
+}
+
+/* bottom up parent */
+}
+
+/* bottom up */
-+static int au_wbr_copyup_bu(struct dentry *dentry)
++int au_wbr_do_copyup_bu(struct dentry *dentry, aufs_bindex_t bstart)
+{
+ int err;
-+ aufs_bindex_t bstart;
+
-+ bstart = au_dbstart(dentry);
+ err = au_wbr_bu(dentry->d_sb, bstart);
+ AuDbg("b%d\n", err);
+ if (err > bstart)
+ return err;
+}
+
++static int au_wbr_copyup_bu(struct dentry *dentry)
++{
++ int err;
++ aufs_bindex_t bstart;
++
++ bstart = au_dbstart(dentry);
++ err = au_wbr_do_copyup_bu(dentry, bstart);
++ return err;
++}
++
+/* ---------------------------------------------------------------------- */
+
+struct au_wbr_copyup_operations au_wbr_copyup_ops[] = {
+ .create = au_wbr_create_pmfs,
+ .init = au_wbr_create_init_mfs,
+ .fin = au_wbr_create_fin_mfs
++ },
++ [AuWbrCreate_PMFSRR] = {
++ .create = au_wbr_create_pmfsrr,
++ .init = au_wbr_create_init_mfsrr,
++ .fin = au_wbr_create_fin_mfs
++ },
++ [AuWbrCreate_PMFSRRV] = {
++ .create = au_wbr_create_pmfsrr,
++ .init = au_wbr_create_init_mfsrr,
++ .fin = au_wbr_create_fin_mfs
+ }
+};
diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c
--- /usr/share/empty/fs/aufs/whout.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/whout.c 2013-03-14 20:07:41.224790724 +0100
-@@ -0,0 +1,1042 @@
++++ linux/fs/aufs/whout.c 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,1064 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * 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 au_wh_test(struct dentry *h_parent, struct qstr *wh_name, int try_sio)
+{
+ int err;
+ struct dentry *wh_dentry;
+ if (!try_sio)
+ wh_dentry = vfsub_lkup_one(wh_name, h_parent);
+ else
-+ wh_dentry = au_sio_lkup_one(wh_name, h_parent, br);
++ wh_dentry = au_sio_lkup_one(wh_name, h_parent);
+ err = PTR_ERR(wh_dentry);
-+ if (IS_ERR(wh_dentry))
++ if (IS_ERR(wh_dentry)) {
++ if (err == -ENAMETOOLONG)
++ err = 0;
+ goto out;
++ }
+
+ err = 0;
+ if (!wh_dentry->d_inode)
+ goto out_wh; /* success */
+
+ err = 1;
-+ if (S_ISREG(wh_dentry->d_inode->i_mode))
++ if (d_is_reg(wh_dentry))
+ goto out_wh; /* success */
+
+ err = -EIO;
-+ AuIOErr("%.*s Invalid whiteout entry type 0%o.\n",
-+ AuDLNPair(wh_dentry), wh_dentry->d_inode->i_mode);
++ AuIOErr("%pd Invalid whiteout entry type 0%o.\n",
++ wh_dentry, wh_dentry->d_inode->i_mode);
+
+out_wh:
+ dput(wh_dentry);
+/*
+ * test if the @h_dentry sets opaque or not.
+ */
-+int au_diropq_test(struct dentry *h_dentry, struct au_branch *br)
++int au_diropq_test(struct dentry *h_dentry)
+{
+ int err;
+ struct inode *h_dir;
+
+ h_dir = h_dentry->d_inode;
-+ err = au_wh_test(h_dentry, &diropq_name, br,
++ err = au_wh_test(h_dentry, &diropq_name,
+ au_test_h_perm_sio(h_dir, MAY_EXEC));
+ return err;
+}
+ qs.name = name;
+ for (i = 0; i < 3; i++) {
+ sprintf(p, "%.*x", AUFS_WH_TMP_LEN, cnt++);
-+ dentry = au_sio_lkup_one(&qs, h_parent, br);
++ dentry = au_sio_lkup_one(&qs, h_parent);
+ if (IS_ERR(dentry) || !dentry->d_inode)
+ goto out_name;
+ dput(dentry);
+{
+ int err;
+ struct path h_path = {
-+ .mnt = br->br_mnt
++ .mnt = au_br_mnt(br)
+ };
-+ struct inode *h_dir;
++ struct inode *h_dir, *delegated;
+ struct dentry *h_parent;
+
+ h_parent = h_dentry->d_parent; /* dir inode is locked */
+ goto out;
+
+ /* under the same dir, no need to lock_rename() */
-+ err = vfsub_rename(h_dir, h_dentry, h_dir, &h_path);
++ delegated = NULL;
++ err = vfsub_rename(h_dir, h_dentry, h_dir, &h_path, &delegated);
+ AuTraceErr(err);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal rename\n");
++ iput(delegated);
++ }
+ dput(h_path.dentry);
+
+out:
+
+static int do_unlink_wh(struct inode *h_dir, struct path *h_path)
+{
-+ int force;
++ int err, force;
++ struct inode *delegated;
+
+ /*
+ * forces superio when the dir has a sticky bit.
+ */
+ force = (h_dir->i_mode & S_ISVTX)
+ && !uid_eq(current_fsuid(), h_path->dentry->d_inode->i_uid);
-+ return vfsub_unlink(h_dir, h_path, force);
++ delegated = NULL;
++ err = vfsub_unlink(h_dir, h_path, &delegated, force);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
++ }
++ return err;
+}
+
+int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path,
+{
+ int err;
+ struct path h_path = {
-+ .mnt = br->br_mnt
++ .mnt = au_br_mnt(br)
+ };
+
+ err = 0;
+ err = PTR_ERR(h_path.dentry);
+ else {
+ if (h_path.dentry->d_inode
-+ && S_ISREG(h_path.dentry->d_inode->i_mode))
++ && d_is_reg(h_path.dentry))
+ err = do_unlink_wh(h_parent->d_inode, &h_path);
+ dput(h_path.dentry);
+ }
+ const int isdir)
+{
+ int err;
++ struct inode *delegated;
+
+ if (!whpath->dentry->d_inode)
+ return;
+
-+ err = vfsub_mnt_want_write(whpath->mnt);
-+ if (!err) {
-+ if (isdir)
-+ err = vfsub_rmdir(h_dir, whpath);
-+ else
-+ err = vfsub_unlink(h_dir, whpath, /*force*/0);
-+ vfsub_mnt_drop_write(whpath->mnt);
++ if (isdir)
++ err = vfsub_rmdir(h_dir, whpath);
++ else {
++ delegated = NULL;
++ err = vfsub_unlink(h_dir, whpath, &delegated, /*force*/0);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
++ }
+ }
+ if (unlikely(err))
-+ pr_warn("failed removing %.*s (%d), ignored.\n",
-+ AuDLNPair(whpath->dentry), err);
++ pr_warn("failed removing %pd (%d), ignored.\n",
++ whpath->dentry, err);
+}
+
+static int test_linkable(struct dentry *h_root)
+ if (h_dir->i_op->link)
+ return 0;
+
-+ pr_err("%.*s (%s) doesn't support link(2), use noplink and rw+nolwh\n",
-+ AuDLNPair(h_root), au_sbtype(h_root->d_sb));
++ pr_err("%pd (%s) doesn't support link(2), use noplink and rw+nolwh\n",
++ h_root, au_sbtype(h_root->d_sb));
+ return -ENOSYS;
+}
+
+
+ if (au_test_nfs(path->dentry->d_sb))
+ mode |= S_IXUGO;
-+ err = vfsub_mnt_want_write(path->mnt);
-+ if (!err) {
-+ err = vfsub_mkdir(h_dir, path, mode);
-+ vfsub_mnt_drop_write(path->mnt);
-+ }
-+ } else if (S_ISDIR(path->dentry->d_inode->i_mode))
++ err = vfsub_mkdir(h_dir, path, mode);
++ } else if (d_is_dir(path->dentry))
+ err = 0;
+ else
-+ pr_err("unknown %.*s exists\n", AuDLNPair(path->dentry));
++ pr_err("unknown %pd exists\n", path->dentry);
+
+ return err;
+}
+
+/*
+ * returns tri-state,
-+ * minus: error, caller should print the mesage
++ * minus: error, caller should print the message
+ * zero: succuess
-+ * plus: error, caller should NOT print the mesage
++ * plus: error, caller should NOT print the message
+ */
+static int au_wh_init_rw_nolink(struct dentry *h_root, struct au_wbr *wbr,
+ int do_plink, struct au_wh_base base[],
+ err = -EEXIST;
+ h_dir = h_root->d_inode;
+ if (!base[AuBrWh_BASE].dentry->d_inode) {
-+ err = vfsub_mnt_want_write(h_path->mnt);
-+ if (!err) {
-+ h_path->dentry = base[AuBrWh_BASE].dentry;
-+ err = vfsub_create(h_dir, h_path, WH_MASK,
-+ /*want_excl*/true);
-+ vfsub_mnt_drop_write(h_path->mnt);
-+ }
-+ } else if (S_ISREG(base[AuBrWh_BASE].dentry->d_inode->i_mode))
++ h_path->dentry = base[AuBrWh_BASE].dentry;
++ err = vfsub_create(h_dir, h_path, WH_MASK, /*want_excl*/true);
++ } else if (d_is_reg(base[AuBrWh_BASE].dentry))
+ err = 0;
+ else
-+ pr_err("unknown %.*s/%.*s exists\n",
-+ AuDLNPair(h_root), AuDLNPair(base[AuBrWh_BASE].dentry));
++ pr_err("unknown %pd2 exists\n", base[AuBrWh_BASE].dentry);
+ if (unlikely(err))
+ goto out;
+
+/*
+ * 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 au_wh_init(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 path path = br->br_path;
++ struct dentry *h_root = path.dentry;
+ struct au_wbr *wbr = br->br_wbr;
+ static const struct qstr base_name[] = {
+ [AuBrWh_BASE] = QSTR_INIT(AUFS_BASE_NAME,
+ goto out; /* success */
+
+out_err:
-+ pr_err("an error(%d) on the writable branch %.*s(%s)\n",
-+ err, AuDLNPair(h_root), au_sbtype(h_root->d_sb));
++ pr_err("an error(%d) on the writable branch %pd(%s)\n",
++ err, h_root, au_sbtype(h_root->d_sb));
+out:
+ for (i = 0; i < AuBrWh_Last; i++)
+ dput(base[i].dentry);
+ struct path h_path;
+ struct reinit_br_wh *a = arg;
+ struct au_wbr *wbr;
-+ struct inode *dir;
++ struct inode *dir, *delegated;
+ struct dentry *h_root;
+ struct au_hinode *hdir;
+
+ dir = a->sb->s_root->d_inode;
+ hdir = au_hi(dir, bindex);
+ h_root = au_h_dptr(a->sb->s_root, bindex);
++ AuDebugOn(h_root != au_br_dentry(a->br));
+
+ au_hn_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 = vfsub_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);
-+ vfsub_mnt_drop_write(a->br->br_mnt);
++ h_path.dentry = wbr->wbr_whbase;
++ h_path.mnt = au_br_mnt(a->br);
++ delegated = NULL;
++ err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated,
++ /*force*/0);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
+ }
+ } else {
-+ pr_warn("%.*s is moved, ignored\n",
-+ AuDLNPair(wbr->wbr_whbase));
++ pr_warn("%pd is moved, ignored\n", 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);
++ err = au_wh_init(a->br, a->sb);
+ wbr_wh_write_unlock(wbr);
+ au_hn_imtx_unlock(hdir);
+ di_read_unlock(a->sb->s_root, AuLock_IR);
++ if (!err)
++ au_fhsm_wrote(a->sb, bindex, /*force*/0);
+
+out:
+ if (wbr)
+ struct au_branch *br;
+ struct au_wbr *wbr;
+ struct dentry *h_parent;
-+ struct inode *h_dir;
++ struct inode *h_dir, *delegated;
+
+ 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;
++ h_path.mnt = au_br_mnt(br);
+ wbr = br->br_wbr;
+ wbr_wh_read_lock(wbr);
+ if (wbr->wbr_whbase) {
-+ err = vfsub_link(wbr->wbr_whbase, h_dir, &h_path);
++ delegated = NULL;
++ err = vfsub_link(wbr->wbr_whbase, h_dir, &h_path, &delegated);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal link\n");
++ iput(delegated);
++ }
+ if (!err || err != -EMLINK)
+ goto out;
+
+
+ /* return this error in this context */
+ err = vfsub_create(h_dir, &h_path, WH_MASK, /*want_excl*/true);
++ if (!err)
++ au_fhsm_wrote(sb, bindex, /*force*/0);
+
+out:
+ wbr_wh_read_unlock(wbr);
+ } else {
+ struct path tmp = {
+ .dentry = opq_dentry,
-+ .mnt = br->br_mnt
++ .mnt = au_br_mnt(br)
+ };
+ err = do_unlink_wh(au_h_iptr(dentry->d_inode, bindex), &tmp);
+ if (!err)
+ 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)
++ if (!err) {
+ au_set_dbwh(dentry, bindex);
-+ else {
++ au_fhsm_wrote(sb, bindex, /*force*/0);
++ } else {
+ dput(wh_dentry);
+ wh_dentry = ERR_PTR(err);
+ }
+ struct qstr wh_name;
+ char *p;
+ struct hlist_head *head;
-+ struct au_vdir_wh *tpos;
-+ struct hlist_node *pos;
++ struct au_vdir_wh *pos;
+ struct au_vdir_destr *str;
+
+ err = -ENOMEM;
+ n = whlist->nh_num;
+ head = whlist->nh_head;
+ for (ul = 0; !err && ul < n; ul++, head++) {
-+ hlist_for_each_entry(tpos, pos, head, wh_hash) {
-+ if (tpos->wh_bindex != bindex)
++ hlist_for_each_entry(pos, head, wh_hash) {
++ if (pos->wh_bindex != bindex)
+ continue;
+
-+ str = &tpos->wh_str;
++ str = &pos->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;
+ struct dentry *wh_dentry, struct au_nhash *whlist)
+{
+ int err;
++ unsigned int h_nlink;
+ struct path h_tmp;
+ struct inode *wh_inode, *h_dir;
+ struct au_branch *br;
+
+ if (!err) {
+ h_tmp.dentry = wh_dentry;
-+ h_tmp.mnt = br->br_mnt;
++ h_tmp.mnt = au_br_mnt(br);
++ h_nlink = h_dir->i_nlink;
+ err = vfsub_rmdir(h_dir, &h_tmp);
++ /* some fs doesn't change the parent nlink in some cases */
++ h_nlink -= h_dir->i_nlink;
+ }
+
+ if (!err) {
+ if (au_ibstart(dir) == bindex) {
+ /* todo: dir->i_mutex is necessary */
+ au_cpup_attr_timesizes(dir);
-+ vfsub_drop_nlink(dir);
++ if (h_nlink)
++ vfsub_drop_nlink(dir);
+ }
+ return 0; /* success */
+ }
+
-+ pr_warn("failed removing %.*s(%d), ignored\n",
-+ AuDLNPair(wh_dentry), err);
++ pr_warn("failed removing %pd(%d), ignored\n", wh_dentry, err);
+ return err;
+}
+
+ h_parent = dget_parent(a->wh_dentry);
+ h_dir = h_parent->d_inode;
+ hdir = au_hi(a->dir, bindex);
++ err = vfsub_mnt_want_write(au_br_mnt(a->br));
++ if (unlikely(err))
++ goto out_mnt;
+ au_hn_imtx_lock_nested(hdir, AuLsc_I_PARENT);
+ err = au_h_verify(a->wh_dentry, au_opt_udba(sb), h_dir, h_parent,
+ a->br);
-+ if (!err) {
-+ err = vfsub_mnt_want_write(a->br->br_mnt);
-+ if (!err) {
-+ err = au_whtmp_rmdir(a->dir, bindex, a->wh_dentry,
-+ &a->whlist);
-+ vfsub_mnt_drop_write(a->br->br_mnt);
-+ }
-+ }
++ if (!err)
++ err = au_whtmp_rmdir(a->dir, bindex, a->wh_dentry, &a->whlist);
+ au_hn_imtx_unlock(hdir);
++ vfsub_mnt_drop_write(au_br_mnt(a->br));
++
++out_mnt:
+ dput(h_parent);
+ ii_write_unlock(a->dir);
-+
+out:
+ /* mutex_unlock(&a->dir->i_mutex); */
+ au_whtmp_rmdir_free(a);
+ args->wh_dentry = dget(wh_dentry);
+ wkq_err = au_wkq_nowait(call_rmdir_whtmp, args, sb, /*flags*/0);
+ if (unlikely(wkq_err)) {
-+ pr_warn("rmdir error %.*s (%d), ignored\n",
-+ AuDLNPair(wh_dentry), wkq_err);
++ pr_warn("rmdir error %pd (%d), ignored\n", wh_dentry, wkq_err);
+ au_whtmp_rmdir_free(args);
+ }
+}
diff -urN /usr/share/empty/fs/aufs/whout.h linux/fs/aufs/whout.h
--- /usr/share/empty/fs/aufs/whout.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/whout.h 2013-02-19 08:40:03.953559833 +0100
-@@ -0,0 +1,88 @@
++++ linux/fs/aufs/whout.h 2015-06-22 08:27:37.890835363 +0200
+@@ -0,0 +1,85 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+
+/* whout.c */
+int au_wh_name_alloc(struct qstr *wh, const struct qstr *name);
++int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, int try_sio);
++int au_diropq_test(struct dentry *h_dentry);
+struct au_branch;
-+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);
++int au_wh_init(struct au_branch *br, struct super_block *sb);
+
+/* diropq flags */
+#define AuDiropq_CREATE 1
+#endif /* __AUFS_WHOUT_H__ */
diff -urN /usr/share/empty/fs/aufs/wkq.c linux/fs/aufs/wkq.c
--- /usr/share/empty/fs/aufs/wkq.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/wkq.c 2013-02-19 08:40:03.953559833 +0100
-@@ -0,0 +1,214 @@
++++ linux/fs/aufs/wkq.c 2015-06-22 08:27:37.890835363 +0200
+@@ -0,0 +1,213 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+/*
+ * Since struct completion is large, try allocating it dynamically.
+ */
-+#if defined(CONFIG_4KSTACKS) || defined(AuTest4KSTACKS)
++#if 1 /* 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)
+{
+ if (au_ftest_wkq(wkinfo->flags, NEST)) {
+ if (au_wkq_test()) {
-+ AuWarn1("wkq from wkq, due to a dead dir by UDBA?\n");
++ AuWarn1("wkq from wkq, unless silly-rename on NFS,"
++ " due to a dead dir by UDBA?\n");
+ AuDebugOn(au_ftest_wkq(wkinfo->flags, WAIT));
+ }
+ } else
+ kobject_get(wkinfo->kobj);
+ __module_get(THIS_MODULE); /* todo: ?? */
+
-+ au_wkq_run(wkinfo);
-+ } else {
-+ err = -ENOMEM;
-+ au_nwt_done(&au_sbi(sb)->si_nowait);
++ au_wkq_run(wkinfo);
++ } else {
++ err = -ENOMEM;
++ au_nwt_done(&au_sbi(sb)->si_nowait);
++ }
++
++ 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)
++{
++ destroy_workqueue(au_wkq);
++}
++
++int __init au_wkq_init(void)
++{
++ int err;
++
++ err = 0;
++ au_wkq = alloc_workqueue(AUFS_WKQ_NAME, 0, WQ_DFL_ACTIVE);
++ if (IS_ERR(au_wkq))
++ err = PTR_ERR(au_wkq);
++ else if (!au_wkq)
++ err = -ENOMEM;
++
++ return err;
++}
+diff -urN /usr/share/empty/fs/aufs/wkq.h linux/fs/aufs/wkq.h
+--- /usr/share/empty/fs/aufs/wkq.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/wkq.h 2015-06-22 08:27:37.890835363 +0200
+@@ -0,0 +1,91 @@
++/*
++ * Copyright (C) 2005-2015 Junjiro R. Okajima
++ *
++ * This program, aufs is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ *
++ * This program is distributed in the hope that it will be useful,
++ * but WITHOUT ANY WARRANTY; without even the implied warranty of
++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++ * GNU General Public License for more details.
++ *
++ * You should have received a copy of the GNU General Public License
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
++ */
++
++/*
++ * workqueue for asynchronous/super-io operations
++ * todo: try new credentials management scheme
++ */
++
++#ifndef __AUFS_WKQ_H__
++#define __AUFS_WKQ_H__
++
++#ifdef __KERNEL__
++
++struct super_block;
++
++/* ---------------------------------------------------------------------- */
++
++/*
++ * 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 AuWkq_NEST (1 << 1)
++#define au_ftest_wkq(flags, name) ((flags) & AuWkq_##name)
++#define au_fset_wkq(flags, name) \
++ do { (flags) |= AuWkq_##name; } while (0)
++#define au_fclr_wkq(flags, name) \
++ do { (flags) &= ~AuWkq_##name; } while (0)
++
++#ifndef CONFIG_AUFS_HNOTIFY
++#undef AuWkq_NEST
++#define AuWkq_NEST 0
++#endif
++
++/* wkq.c */
++int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args);
++int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb,
++ unsigned int flags);
++void au_nwt_init(struct au_nowait_tasks *nwt);
++int __init au_wkq_init(void);
++void au_wkq_fin(void);
++
++/* ---------------------------------------------------------------------- */
++
++static inline int au_wkq_test(void)
++{
++ return current->flags & PF_WQ_WORKER;
++}
++
++static inline int au_wkq_wait(au_wkq_func_t func, void *args)
++{
++ return au_wkq_do_wait(AuWkq_WAIT, func, args);
++}
++
++static inline void au_nwt_done(struct au_nowait_tasks *nwt)
++{
++ if (atomic_dec_and_test(&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__ */
+diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c
+--- /usr/share/empty/fs/aufs/xattr.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/xattr.c 2015-06-22 08:27:37.890835363 +0200
+@@ -0,0 +1,344 @@
++/*
++ * Copyright (C) 2014-2015 Junjiro R. Okajima
++ *
++ * This program, aufs is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ *
++ * This program is distributed in the hope that it will be useful,
++ * but WITHOUT ANY WARRANTY; without even the implied warranty of
++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++ * GNU General Public License for more details.
++ *
++ * You should have received a copy of the GNU General Public License
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
++ */
++
++/*
++ * handling xattr functions
++ */
++
++#include <linux/xattr.h>
++#include "aufs.h"
++
++static int au_xattr_ignore(int err, char *name, unsigned int ignore_flags)
++{
++ if (!ignore_flags)
++ goto out;
++ switch (err) {
++ case -ENOMEM:
++ case -EDQUOT:
++ goto out;
++ }
++
++ if ((ignore_flags & AuBrAttr_ICEX) == AuBrAttr_ICEX) {
++ err = 0;
++ goto out;
++ }
++
++#define cmp(brattr, prefix) do { \
++ if (!strncmp(name, XATTR_##prefix##_PREFIX, \
++ XATTR_##prefix##_PREFIX_LEN)) { \
++ if (ignore_flags & AuBrAttr_ICEX_##brattr) \
++ err = 0; \
++ goto out; \
++ } \
++ } while (0)
++
++ cmp(SEC, SECURITY);
++ cmp(SYS, SYSTEM);
++ cmp(TR, TRUSTED);
++ cmp(USR, USER);
++#undef cmp
++
++ if (ignore_flags & AuBrAttr_ICEX_OTH)
++ err = 0;
++
++out:
++ return err;
++}
++
++static const int au_xattr_out_of_list = AuBrAttr_ICEX_OTH << 1;
++
++static int au_do_cpup_xattr(struct dentry *h_dst, struct dentry *h_src,
++ char *name, char **buf, unsigned int ignore_flags,
++ unsigned int verbose)
++{
++ int err;
++ ssize_t ssz;
++ struct inode *h_idst;
++
++ ssz = vfs_getxattr_alloc(h_src, name, buf, 0, GFP_NOFS);
++ err = ssz;
++ if (unlikely(err <= 0)) {
++ if (err == -ENODATA
++ || (err == -EOPNOTSUPP
++ && ((ignore_flags & au_xattr_out_of_list)
++ || (au_test_nfs_noacl(h_src->d_inode)
++ && (!strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS)
++ || !strcmp(name,
++ XATTR_NAME_POSIX_ACL_DEFAULT))))
++ ))
++ err = 0;
++ if (err && (verbose || au_debug_test()))
++ pr_err("%s, err %d\n", name, err);
++ goto out;
++ }
++
++ /* unlock it temporary */
++ h_idst = h_dst->d_inode;
++ mutex_unlock(&h_idst->i_mutex);
++ err = vfsub_setxattr(h_dst, name, *buf, ssz, /*flags*/0);
++ mutex_lock_nested(&h_idst->i_mutex, AuLsc_I_CHILD2);
++ if (unlikely(err)) {
++ if (verbose || au_debug_test())
++ pr_err("%s, err %d\n", name, err);
++ err = au_xattr_ignore(err, name, ignore_flags);
++ }
++
++out:
++ return err;
++}
++
++int au_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, int ignore_flags,
++ unsigned int verbose)
++{
++ int err, unlocked, acl_access, acl_default;
++ ssize_t ssz;
++ struct inode *h_isrc, *h_idst;
++ char *value, *p, *o, *e;
++
++ /* try stopping to update the source inode while we are referencing */
++ /* there should not be the parent-child relationship between them */
++ h_isrc = h_src->d_inode;
++ h_idst = h_dst->d_inode;
++ mutex_unlock(&h_idst->i_mutex);
++ mutex_lock_nested(&h_isrc->i_mutex, AuLsc_I_CHILD);
++ mutex_lock_nested(&h_idst->i_mutex, AuLsc_I_CHILD2);
++ unlocked = 0;
++
++ /* some filesystems don't list POSIX ACL, for example tmpfs */
++ ssz = vfs_listxattr(h_src, NULL, 0);
++ err = ssz;
++ if (unlikely(err < 0)) {
++ AuTraceErr(err);
++ if (err == -ENODATA
++ || err == -EOPNOTSUPP)
++ err = 0; /* ignore */
++ goto out;
++ }
++
++ err = 0;
++ p = NULL;
++ o = NULL;
++ if (ssz) {
++ err = -ENOMEM;
++ p = kmalloc(ssz, GFP_NOFS);
++ o = p;
++ if (unlikely(!p))
++ goto out;
++ err = vfs_listxattr(h_src, p, ssz);
++ }
++ mutex_unlock(&h_isrc->i_mutex);
++ unlocked = 1;
++ AuDbg("err %d, ssz %zd\n", err, ssz);
++ if (unlikely(err < 0))
++ goto out_free;
++
++ err = 0;
++ e = p + ssz;
++ value = NULL;
++ acl_access = 0;
++ acl_default = 0;
++ while (!err && p < e) {
++ acl_access |= !strncmp(p, XATTR_NAME_POSIX_ACL_ACCESS,
++ sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1);
++ acl_default |= !strncmp(p, XATTR_NAME_POSIX_ACL_DEFAULT,
++ sizeof(XATTR_NAME_POSIX_ACL_DEFAULT)
++ - 1);
++ err = au_do_cpup_xattr(h_dst, h_src, p, &value, ignore_flags,
++ verbose);
++ p += strlen(p) + 1;
++ }
++ AuTraceErr(err);
++ ignore_flags |= au_xattr_out_of_list;
++ if (!err && !acl_access) {
++ err = au_do_cpup_xattr(h_dst, h_src,
++ XATTR_NAME_POSIX_ACL_ACCESS, &value,
++ ignore_flags, verbose);
++ AuTraceErr(err);
++ }
++ if (!err && !acl_default) {
++ err = au_do_cpup_xattr(h_dst, h_src,
++ XATTR_NAME_POSIX_ACL_DEFAULT, &value,
++ ignore_flags, verbose);
++ AuTraceErr(err);
++ }
++
++ kfree(value);
++
++out_free:
++ kfree(o);
++out:
++ if (!unlocked)
++ mutex_unlock(&h_isrc->i_mutex);
++ AuTraceErr(err);
++ return err;
++}
++
++/* ---------------------------------------------------------------------- */
++
++enum {
++ AU_XATTR_LIST,
++ AU_XATTR_GET
++};
++
++struct au_lgxattr {
++ int type;
++ union {
++ struct {
++ char *list;
++ size_t size;
++ } list;
++ struct {
++ const char *name;
++ void *value;
++ size_t size;
++ } get;
++ } u;
++};
++
++static ssize_t au_lgxattr(struct dentry *dentry, struct au_lgxattr *arg)
++{
++ ssize_t err;
++ struct path h_path;
++ struct super_block *sb;
++
++ sb = dentry->d_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (unlikely(err))
++ goto out;
++ err = au_h_path_getattr(dentry, /*force*/1, &h_path);
++ if (unlikely(err))
++ goto out_si;
++ if (unlikely(!h_path.dentry))
++ /* illegally overlapped or something */
++ goto out_di; /* pretending success */
++
++ /* always topmost entry only */
++ switch (arg->type) {
++ case AU_XATTR_LIST:
++ err = vfs_listxattr(h_path.dentry,
++ arg->u.list.list, arg->u.list.size);
++ break;
++ case AU_XATTR_GET:
++ err = vfs_getxattr(h_path.dentry,
++ arg->u.get.name, arg->u.get.value,
++ arg->u.get.size);
++ break;
+ }
+
++out_di:
++ di_read_unlock(dentry, AuLock_IR);
++out_si:
++ si_read_unlock(sb);
++out:
++ AuTraceErr(err);
+ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+void au_nwt_init(struct au_nowait_tasks *nwt)
++ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size)
+{
-+ atomic_set(&nwt->nw_len, 0);
-+ /* smp_mb(); */ /* atomic_set */
-+ init_waitqueue_head(&nwt->nw_wq);
-+}
++ struct au_lgxattr arg = {
++ .type = AU_XATTR_LIST,
++ .u.list = {
++ .list = list,
++ .size = size
++ },
++ };
+
-+void au_wkq_fin(void)
-+{
-+ destroy_workqueue(au_wkq);
++ return au_lgxattr(dentry, &arg);
+}
+
-+int __init au_wkq_init(void)
++ssize_t aufs_getxattr(struct dentry *dentry, const char *name, void *value,
++ size_t size)
+{
-+ int err;
-+
-+ err = 0;
-+ BUILD_BUG_ON(!WQ_RESCUER);
-+ au_wkq = alloc_workqueue(AUFS_WKQ_NAME, !WQ_RESCUER, WQ_DFL_ACTIVE);
-+ if (IS_ERR(au_wkq))
-+ err = PTR_ERR(au_wkq);
-+ else if (!au_wkq)
-+ err = -ENOMEM;
++ struct au_lgxattr arg = {
++ .type = AU_XATTR_GET,
++ .u.get = {
++ .name = name,
++ .value = value,
++ .size = size
++ },
++ };
+
-+ return err;
++ return au_lgxattr(dentry, &arg);
+}
-diff -urN /usr/share/empty/fs/aufs/wkq.h linux/fs/aufs/wkq.h
---- /usr/share/empty/fs/aufs/wkq.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/wkq.h 2013-02-19 08:40:03.953559833 +0100
-@@ -0,0 +1,92 @@
-+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-+ */
-+
-+/*
-+ * workqueue for asynchronous/super-io operations
-+ * todo: try new credentials management scheme
-+ */
-+
-+#ifndef __AUFS_WKQ_H__
-+#define __AUFS_WKQ_H__
-+
-+#ifdef __KERNEL__
-+
-+struct super_block;
-+
-+/* ---------------------------------------------------------------------- */
+
-+/*
-+ * 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);
++int aufs_setxattr(struct dentry *dentry, const char *name, const void *value,
++ size_t size, int flags)
++{
++ struct au_srxattr arg = {
++ .type = AU_XATTR_SET,
++ .u.set = {
++ .name = name,
++ .value = value,
++ .size = size,
++ .flags = flags
++ },
++ };
+
-+/* wkq flags */
-+#define AuWkq_WAIT 1
-+#define AuWkq_NEST (1 << 1)
-+#define au_ftest_wkq(flags, name) ((flags) & AuWkq_##name)
-+#define au_fset_wkq(flags, name) \
-+ do { (flags) |= AuWkq_##name; } while (0)
-+#define au_fclr_wkq(flags, name) \
-+ do { (flags) &= ~AuWkq_##name; } while (0)
++ return au_srxattr(dentry, &arg);
++}
+
-+#ifndef CONFIG_AUFS_HNOTIFY
-+#undef AuWkq_NEST
-+#define AuWkq_NEST 0
-+#endif
++int aufs_removexattr(struct dentry *dentry, const char *name)
++{
++ struct au_srxattr arg = {
++ .type = AU_XATTR_REMOVE,
++ .u.remove = {
++ .name = name
++ },
++ };
+
-+/* wkq.c */
-+int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args);
-+int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb,
-+ unsigned int flags);
-+void au_nwt_init(struct au_nowait_tasks *nwt);
-+int __init au_wkq_init(void);
-+void au_wkq_fin(void);
++ return au_srxattr(dentry, &arg);
++}
+
+/* ---------------------------------------------------------------------- */
+
-+static inline int au_wkq_test(void)
++#if 0
++static size_t au_xattr_list(struct dentry *dentry, char *list, size_t list_size,
++ const char *name, size_t name_len, int type)
+{
-+ return current->flags & PF_WQ_WORKER;
++ return aufs_listxattr(dentry, list, list_size);
+}
+
-+static inline int au_wkq_wait(au_wkq_func_t func, void *args)
++static int au_xattr_get(struct dentry *dentry, const char *name, void *buffer,
++ size_t size, int type)
+{
-+ return au_wkq_do_wait(AuWkq_WAIT, func, args);
++ return aufs_getxattr(dentry, name, buffer, size);
+}
+
-+static inline void au_nwt_done(struct au_nowait_tasks *nwt)
++static int au_xattr_set(struct dentry *dentry, const char *name,
++ const void *value, size_t size, int flags, int type)
+{
-+ if (atomic_dec_and_test(&nwt->nw_len))
-+ wake_up_all(&nwt->nw_wq);
++ return aufs_setxattr(dentry, name, value, size, flags);
+}
+
-+static inline int au_nwt_flush(struct au_nowait_tasks *nwt)
++static const struct xattr_handler au_xattr_handler = {
++ /* no prefix, no flags */
++ .list = au_xattr_list,
++ .get = au_xattr_get,
++ .set = au_xattr_set
++ /* why no remove? */
++};
++
++static const struct xattr_handler *au_xattr_handlers[] = {
++ &au_xattr_handler
++};
++
++void au_xattr_init(struct super_block *sb)
+{
-+ wait_event(nwt->nw_wq, !atomic_read(&nwt->nw_len));
-+ return 0;
++ /* sb->s_xattr = au_xattr_handlers; */
+}
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_WKQ_H__ */
++#endif
diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c
--- /usr/share/empty/fs/aufs/xino.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux/fs/aufs/xino.c 2013-03-14 20:07:41.224790724 +0100
-@@ -0,0 +1,1265 @@
++++ linux/fs/aufs/xino.c 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,1322 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ */
+
+#include <linux/seq_file.h>
++#include <linux/statfs.h>
+#include "aufs.h"
+
+/* todo: unnecessary to support mmap_sem since kernel-space? */
+
+#if 0 /* reserved for future use */
+ if (err > 0)
-+ fsnotify_access(file->f_dentry);
++ fsnotify_access(file->f_path.dentry);
+#endif
+
+ return err;
+
+#if 0 /* reserved for future use */
+ if (err > 0)
-+ fsnotify_modify(file->f_dentry);
++ fsnotify_modify(file->f_path.dentry);
+#endif
+
+ return err;
+{
+ struct file *file;
+ struct dentry *base, *parent;
-+ struct inode *dir;
++ struct inode *dir, *delegated;
+ struct qstr *name;
+ struct path path;
+ int err;
+
-+ base = base_file->f_dentry;
++ base = base_file->f_path.dentry;
+ parent = base->d_parent; /* dir inode is locked */
+ dir = parent->d_inode;
+ IMustLock(dir);
+ path.dentry = vfsub_lookup_one_len(name->name, parent, name->len);
+ if (IS_ERR(path.dentry)) {
+ file = (void *)path.dentry;
-+ pr_err("%.*s lookup err %ld\n",
-+ AuLNPair(name), PTR_ERR(path.dentry));
++ pr_err("%pd lookup err %ld\n",
++ base, PTR_ERR(path.dentry));
+ goto out;
+ }
+
+ err = vfs_create(dir, path.dentry, S_IRUGO | S_IWUGO, NULL);
+ if (unlikely(err)) {
+ file = ERR_PTR(err);
-+ pr_err("%.*s create err %d\n", AuLNPair(name), err);
++ pr_err("%pd create err %d\n", base, err);
+ goto out_dput;
+ }
+
-+ path.mnt = base_file->f_vfsmnt;
++ path.mnt = base_file->f_path.mnt;
+ file = vfsub_dentry_open(&path,
+ O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE
+ /* | __FMODE_NONOTIFY */);
+ if (IS_ERR(file)) {
-+ pr_err("%.*s open err %ld\n", AuLNPair(name), PTR_ERR(file));
++ pr_err("%pd open err %ld\n", base, PTR_ERR(file));
+ goto out_dput;
+ }
+
-+ err = vfsub_unlink(dir, &file->f_path, /*force*/0);
++ delegated = NULL;
++ err = vfsub_unlink(dir, &file->f_path, &delegated, /*force*/0);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
++ }
+ if (unlikely(err)) {
-+ pr_err("%.*s unlink err %d\n", AuLNPair(name), err);
++ pr_err("%pd unlink err %d\n", base, err);
+ goto out_fput;
+ }
+
+ if (copy_src) {
+ /* no one can touch copy_src xino */
-+ err = au_copy_file(file, copy_src,
-+ i_size_read(copy_src->f_dentry->d_inode));
++ err = au_copy_file(file, copy_src, vfsub_f_size_read(copy_src));
+ if (unlikely(err)) {
-+ pr_err("%.*s copy err %d\n", AuLNPair(name), err);
++ pr_err("%pd copy err %d\n", base, err);
+ goto out_fput;
+ }
+ }
+ ldir->hdir = au_hi(sb->s_root->d_inode, bindex);
+ au_hn_imtx_lock_nested(ldir->hdir, AuLsc_I_PARENT);
+ } else {
-+ ldir->parent = dget_parent(xino->f_dentry);
++ ldir->parent = dget_parent(xino->f_path.dentry);
+ ldir->mtx = &ldir->parent->d_inode->i_mutex;
+ mutex_lock_nested(ldir->mtx, AuLsc_I_PARENT);
+ }
+int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex)
+{
+ int err;
++ unsigned long jiffy;
++ blkcnt_t blocks;
+ aufs_bindex_t bi, bend;
++ struct kstatfs *st;
+ struct au_branch *br;
+ struct file *new_xino, *file;
+ struct super_block *h_sb;
+ struct au_xino_lock_dir ldir;
+
++ err = -ENOMEM;
++ st = kzalloc(sizeof(*st), GFP_NOFS);
++ if (unlikely(!st))
++ goto out;
++
+ err = -EINVAL;
+ bend = au_sbend(sb);
+ if (unlikely(bindex < 0 || bend < bindex))
-+ goto out;
++ goto out_st;
+ br = au_sbr(sb, bindex);
+ file = br->br_xino.xi_file;
+ if (!file)
-+ goto out;
++ goto out_st;
++
++ err = vfs_statfs(&file->f_path, st);
++ if (unlikely(err))
++ AuErr1("statfs err %d, ignored\n", err);
++ jiffy = jiffies;
++ blocks = file_inode(file)->i_blocks;
++ pr_info("begin truncating xino(b%d), ib%llu, %llu/%llu free blks\n",
++ bindex, (u64)blocks, st->f_bfree, st->f_blocks);
+
+ au_xino_lock_dir(sb, file, &ldir);
+ /* mnt_want_write() is unnecessary here */
+ new_xino = au_xino_create2(file, file);
+ au_xino_unlock_dir(&ldir);
+ err = PTR_ERR(new_xino);
-+ if (IS_ERR(new_xino))
-+ goto out;
++ if (IS_ERR(new_xino)) {
++ pr_err("err %d, ignored\n", err);
++ goto out_st;
++ }
+ err = 0;
+ fput(file);
+ br->br_xino.xi_file = new_xino;
+
-+ h_sb = br->br_mnt->mnt_sb;
++ h_sb = au_br_sb(br);
+ for (bi = 0; bi <= bend; bi++) {
+ if (unlikely(bi == bindex))
+ continue;
+ br = au_sbr(sb, bi);
-+ if (br->br_mnt->mnt_sb != h_sb)
++ if (au_br_sb(br) != h_sb)
+ continue;
+
+ fput(br->br_xino.xi_file);
+ get_file(new_xino);
+ }
+
++ err = vfs_statfs(&new_xino->f_path, st);
++ if (!err) {
++ pr_info("end truncating xino(b%d), ib%llu, %llu/%llu free blks\n",
++ bindex, (u64)file_inode(new_xino)->i_blocks,
++ st->f_bfree, st->f_blocks);
++ if (file_inode(new_xino)->i_blocks < blocks)
++ au_sbi(sb)->si_xino_jiffy = jiffy;
++ } else
++ AuErr1("statfs err %d, ignored\n", err);
++
++out_st:
++ kfree(st);
+out:
+ return err;
+}
+ ii_read_lock_parent(dir);
+ bindex = au_br_index(sb, br->br_id);
+ err = au_xino_trunc(sb, bindex);
-+ if (!err
-+ && br->br_xino.xi_file->f_dentry->d_inode->i_blocks
-+ >= br->br_xino_upper)
-+ br->br_xino_upper += AUFS_XINO_TRUNC_STEP;
-+
+ ii_read_unlock(dir);
+ if (unlikely(err))
-+ pr_warn("err b%d, upper %llu, (%d)\n",
-+ bindex, (unsigned long long)br->br_xino_upper, err);
++ pr_warn("err b%d, (%d)\n", bindex, err);
+ atomic_dec(&br->br_xino_running);
+ atomic_dec(&br->br_count);
+ si_write_unlock(sb);
+ kfree(args);
+}
+
++static int xino_trunc_test(struct super_block *sb, struct au_branch *br)
++{
++ int err;
++ struct kstatfs st;
++ struct au_sbinfo *sbinfo;
++
++ /* todo: si_xino_expire and the ratio should be customizable */
++ sbinfo = au_sbi(sb);
++ if (time_before(jiffies,
++ sbinfo->si_xino_jiffy + sbinfo->si_xino_expire))
++ return 0;
++
++ /* truncation border */
++ err = vfs_statfs(&br->br_xino.xi_file->f_path, &st);
++ if (unlikely(err)) {
++ AuErr1("statfs err %d, ignored\n", err);
++ return 0;
++ }
++ if (div64_u64(st.f_bfree * 100, st.f_blocks) >= AUFS_XINO_DEF_TRUNC)
++ return 0;
++
++ return 1;
++}
++
+static void xino_try_trunc(struct super_block *sb, struct au_branch *br)
+{
+ struct xino_do_trunc_args *args;
+ int wkq_err;
+
-+ if (br->br_xino.xi_file->f_dentry->d_inode->i_blocks
-+ < br->br_xino_upper)
++ if (!xino_trunc_test(sb, br))
+ return;
+
+ if (atomic_inc_return(&br->br_xino_running) > 1)
+ h_ino, ino);
+ if (!err) {
+ if (au_opt_test(mnt_flags, TRUNC_XINO)
-+ && au_test_fs_trunc_xino(br->br_mnt->mnt_sb))
++ && au_test_fs_trunc_xino(au_br_sb(br)))
+ xino_try_trunc(sb, br);
+ return 0; /* success */
+ }
+
+ pos = pindex;
+ pos *= PAGE_SIZE;
-+ if (i_size_read(xib->f_dentry->d_inode) >= pos + PAGE_SIZE)
++ if (vfsub_f_size_read(xib) >= pos + PAGE_SIZE)
+ sz = xino_fread(sbinfo->si_xread, xib, p, PAGE_SIZE, &pos);
+ else {
+ memset(p, 0, PAGE_SIZE);
+ err = au_xino_do_write(xwrite, br->br_xino.xi_file,
+ h_inode->i_ino, /*ino*/0);
+ if (!err && try_trunc
-+ && au_test_fs_trunc_xino(br->br_mnt->mnt_sb))
++ && au_test_fs_trunc_xino(au_br_sb(br)))
+ xino_try_trunc(sb, br);
+ }
+}
+ }
+
+ file = sbinfo->si_xib;
-+ pend = i_size_read(file->f_dentry->d_inode) / PAGE_SIZE;
++ pend = vfsub_f_size_read(file) / PAGE_SIZE;
+ for (ul = pindex + 1; ul <= pend; ul++) {
+ err = xib_pindex(sb, ul);
+ if (unlikely(err))
+ pos *= sizeof(*ino);
+
+ file = au_sbr(sb, bindex)->br_xino.xi_file;
-+ if (i_size_read(file->f_dentry->d_inode) < pos + sizeof(*ino))
++ if (vfsub_f_size_read(file) < pos + sizeof(*ino))
+ return 0; /* no ino */
+
+ sz = xino_fread(sbinfo->si_xread, file, ino, sizeof(*ino), &pos);
+{
+ struct file *file;
+ struct dentry *h_parent, *d;
-+ struct inode *h_dir;
++ struct inode *h_dir, *inode;
+ int err;
+
+ /*
+ }
+
+ /* keep file count */
-+ h_parent = dget_parent(file->f_dentry);
++ err = 0;
++ inode = file_inode(file);
++ h_parent = dget_parent(file->f_path.dentry);
+ h_dir = h_parent->d_inode;
+ mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_PARENT);
+ /* mnt_want_write() is unnecessary here */
-+ err = vfsub_unlink(h_dir, &file->f_path, /*force*/0);
++ /* no delegation since it is just created */
++ if (inode->i_nlink)
++ err = vfsub_unlink(h_dir, &file->f_path, /*delegated*/NULL,
++ /*force*/0);
+ mutex_unlock(&h_dir->i_mutex);
+ dput(h_parent);
+ if (unlikely(err)) {
+ }
+
+ err = -EINVAL;
-+ d = file->f_dentry;
++ d = file->f_path.dentry;
+ if (unlikely(sb == d->d_sb)) {
+ if (!silent)
+ pr_err("%s must be outside\n", fname);
+ shared_br = NULL;
+ bend = au_sbend(sb);
+ if (do_test) {
-+ tgt_sb = br->br_mnt->mnt_sb;
++ tgt_sb = au_br_sb(br);
+ for (bindex = 0; bindex <= bend; bindex++) {
+ b = au_sbr(sb, bindex);
-+ if (tgt_sb == b->br_mnt->mnt_sb) {
++ if (tgt_sb == au_br_sb(b)) {
+ shared_br = b;
+ break;
+ }
+ MtxMustLock(&sbinfo->si_xib_mtx);
+ p = sbinfo->si_xib_buf;
+ func = sbinfo->si_xread;
-+ pend = i_size_read(file->f_dentry->d_inode);
++ pend = vfsub_f_size_read(file);
+ pos = 0;
+ while (pos < pend) {
+ sz = xino_fread(func, file, page, PAGE_SIZE, &pos);
+ goto out;
+
+ file = sbinfo->si_xib;
-+ if (i_size_read(file->f_dentry->d_inode) <= PAGE_SIZE)
++ if (vfsub_f_size_read(file) <= PAGE_SIZE)
+ goto out;
+
+ au_xino_lock_dir(sb, file, &ldir);
+{
+ const struct file_operations *fop = h_file->f_op;
+
-+ if (fop) {
-+ if (fop->read)
-+ return fop->read;
-+ if (fop->aio_read)
-+ return do_sync_read;
-+ }
++ if (fop->read)
++ return fop->read;
++ if (fop->aio_read)
++ return do_sync_read;
++ if (fop->read_iter)
++ return new_sync_read;
+ return ERR_PTR(-ENOSYS);
+}
+
+{
+ const struct file_operations *fop = h_file->f_op;
+
-+ if (fop) {
-+ if (fop->write)
-+ return fop->write;
-+ if (fop->aio_write)
-+ return do_sync_write;
-+ }
++ if (fop->write)
++ return fop->write;
++ if (fop->aio_write)
++ return do_sync_write;
++ if (fop->write_iter)
++ return new_sync_write;
+ return ERR_PTR(-ENOSYS);
+}
+
+
+ sbinfo->si_xib_last_pindex = 0;
+ sbinfo->si_xib_next_bit = 0;
-+ if (i_size_read(file->f_dentry->d_inode) < PAGE_SIZE) {
++ if (vfsub_f_size_read(file) < PAGE_SIZE) {
+ pos = 0;
+ err = xino_fwrite(sbinfo->si_xwrite, file, sbinfo->si_xib_buf,
+ PAGE_SIZE, &pos);
+
+ err = 0;
+ sbinfo = au_sbi(sb);
-+ parent = dget_parent(xino->file->f_dentry);
++ parent = dget_parent(xino->file->f_path.dentry);
+ if (remount) {
+ skip = 0;
-+ dname = &xino->file->f_dentry->d_name;
++ dname = &xino->file->f_path.dentry->d_name;
+ cur_xino = sbinfo->si_xib;
+ if (cur_xino) {
-+ cur_parent = dget_parent(cur_xino->f_dentry);
-+ cur_name = &cur_xino->f_dentry->d_name;
++ cur_parent = dget_parent(cur_xino->f_path.dentry);
++ cur_name = &cur_xino->f_path.dentry->d_name;
+ skip = (cur_parent == parent
-+ && dname->len == cur_name->len
-+ && !memcmp(dname->name, cur_name->name,
-+ dname->len));
++ && au_qstreq(dname, cur_name));
+ dput(cur_parent);
+ }
+ if (skip)
+
+ /* reset all */
+ AuIOErr("failed creating xino(%d).\n", err);
++ au_xigen_clr(sb);
++ xino_clear_xib(sb);
+
+out:
+ dput(parent);
+ for (bindex = 0; bindex <= bend; bindex++) {
+ br = au_sbr(sb, bindex);
+ if (au_br_writable(br->br_perm)
-+ && !au_test_fs_bad_xino(br->br_mnt->mnt_sb)) {
++ && !au_test_fs_bad_xino(au_br_sb(br))) {
+ bwr = bindex;
+ break;
+ }
+ page = (void *)__get_free_page(GFP_NOFS);
+ if (unlikely(!page))
+ goto out;
-+ path.mnt = br->br_mnt;
++ path.mnt = au_br_mnt(br);
+ path.dentry = au_h_dptr(sb->s_root, bwr);
+ p = d_path(&path, page, PATH_MAX - sizeof(AUFS_XINO_FNAME));
+ file = (void *)p;
+ file = au_xino_create(sb, AUFS_XINO_DEFPATH, /*silent*/0);
+ if (IS_ERR(file))
+ goto out;
-+ h_sb = file->f_dentry->d_sb;
++ h_sb = file->f_path.dentry->d_sb;
+ if (unlikely(au_test_fs_bad_xino(h_sb))) {
+ pr_err("xino doesn't support %s(%s)\n",
+ AUFS_XINO_DEFPATH, au_sbtype(h_sb));
+out:
+ return err;
+}
-diff -urN /usr/share/empty/include/linux/aufs_type.h linux/include/linux/aufs_type.h
---- /usr/share/empty/include/linux/aufs_type.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/include/linux/aufs_type.h 2013-02-19 08:40:03.953559833 +0100
-@@ -0,0 +1,19 @@
-+/*
-+ * Copyright (C) 2012-2013 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-+ */
-+
-+#include <uapi/linux/aufs_type.h>
diff -urN /usr/share/empty/include/uapi/linux/aufs_type.h linux/include/uapi/linux/aufs_type.h
--- /usr/share/empty/include/uapi/linux/aufs_type.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux/include/uapi/linux/aufs_type.h 2013-03-14 20:07:41.224790724 +0100
-@@ -0,0 +1,234 @@
++++ linux/include/uapi/linux/aufs_type.h 2015-06-22 08:29:23.710091096 +0200
+@@ -0,0 +1,419 @@
+/*
-+ * Copyright (C) 2005-2013 Junjiro R. Okajima
++ * Copyright (C) 2005-2015 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
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
++ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __AUFS_TYPE_H__
+
+#include <linux/limits.h>
+
-+#define AUFS_VERSION "3.8-20130311"
++#define AUFS_VERSION "3.x-rcN-20150622"
+
+/* todo? move this to linux-2.6.19/include/magic.h */
+#define AUFS_SUPER_MAGIC ('a' << 24 | 'u' << 16 | 'f' << 8 | 's')
+#define AUFS_WH_PFX ".wh."
+#define AUFS_WH_PFX_LEN ((int)sizeof(AUFS_WH_PFX) - 1)
+#define AUFS_WH_TMP_LEN 4
-+/* a limit for rmdir/rename a dir */
++/* a limit for rmdir/rename a dir and copyup */
+#define AUFS_MAX_NAMELEN (NAME_MAX \
+ - AUFS_WH_PFX_LEN * 2 /* doubly whiteouted */\
+ - 1 /* dot */\
+ - AUFS_WH_TMP_LEN) /* hex */
+#define AUFS_XINO_FNAME "." AUFS_NAME ".xino"
+#define AUFS_XINO_DEFPATH "/tmp/" AUFS_XINO_FNAME
-+#define AUFS_XINO_TRUNC_INIT 64 /* blocks */
-+#define AUFS_XINO_TRUNC_STEP 4 /* blocks */
++#define AUFS_XINO_DEF_SEC 30 /* seconds */
++#define AUFS_XINO_DEF_TRUNC 45 /* percentage */
+#define AUFS_DIRWH_DEF 3
+#define AUFS_RDCACHE_DEF 10 /* seconds */
+#define AUFS_RDCACHE_MAX 3600 /* seconds */
+#define AUFS_WKQ_NAME AUFS_NAME "d"
+#define AUFS_MFS_DEF_SEC 30 /* seconds */
+#define AUFS_MFS_MAX_SEC 3600 /* seconds */
-+#define AUFS_PLINK_WARN 100 /* number of plinks */
++#define AUFS_FHSM_CACHE_DEF_SEC 30 /* seconds */
++#define AUFS_PLINK_WARN 50 /* number of plinks in a single bucket */
+
+/* pseudo-link maintenace under /proc */
+#define AUFS_PLINK_MAINT_NAME "plink_maint"
+#define AUFS_BRPERM_RW "rw"
+#define AUFS_BRPERM_RO "ro"
+#define AUFS_BRPERM_RR "rr"
++#define AUFS_BRATTR_COO_REG "coo_reg"
++#define AUFS_BRATTR_COO_ALL "coo_all"
++#define AUFS_BRATTR_FHSM "fhsm"
++#define AUFS_BRATTR_UNPIN "unpin"
++#define AUFS_BRATTR_ICEX "icex"
++#define AUFS_BRATTR_ICEX_SEC "icexsec"
++#define AUFS_BRATTR_ICEX_SYS "icexsys"
++#define AUFS_BRATTR_ICEX_TR "icextr"
++#define AUFS_BRATTR_ICEX_USR "icexusr"
++#define AUFS_BRATTR_ICEX_OTH "icexoth"
+#define AUFS_BRRATTR_WH "wh"
+#define AUFS_BRWATTR_NLWH "nolwh"
++#define AUFS_BRWATTR_MOO "moo"
++
++#define AuBrPerm_RW 1 /* writable, hardlinkable wh */
++#define AuBrPerm_RO (1 << 1) /* readonly */
++#define AuBrPerm_RR (1 << 2) /* natively readonly */
++#define AuBrPerm_Mask (AuBrPerm_RW | AuBrPerm_RO | AuBrPerm_RR)
++
++#define AuBrAttr_COO_REG (1 << 3) /* copy-up on open */
++#define AuBrAttr_COO_ALL (1 << 4)
++#define AuBrAttr_COO_Mask (AuBrAttr_COO_REG | AuBrAttr_COO_ALL)
++
++#define AuBrAttr_FHSM (1 << 5) /* file-based hsm */
++#define AuBrAttr_UNPIN (1 << 6) /* rename-able top dir of
++ branch. meaningless since
++ linux-3.18-rc1 */
++
++/* ignore error in copying XATTR */
++#define AuBrAttr_ICEX_SEC (1 << 7)
++#define AuBrAttr_ICEX_SYS (1 << 8)
++#define AuBrAttr_ICEX_TR (1 << 9)
++#define AuBrAttr_ICEX_USR (1 << 10)
++#define AuBrAttr_ICEX_OTH (1 << 11)
++#define AuBrAttr_ICEX (AuBrAttr_ICEX_SEC \
++ | AuBrAttr_ICEX_SYS \
++ | AuBrAttr_ICEX_TR \
++ | AuBrAttr_ICEX_USR \
++ | AuBrAttr_ICEX_OTH)
++
++#define AuBrRAttr_WH (1 << 12) /* whiteout-able */
++#define AuBrRAttr_Mask AuBrRAttr_WH
++
++#define AuBrWAttr_NoLinkWH (1 << 13) /* un-hardlinkable whiteouts */
++#define AuBrWAttr_MOO (1 << 14) /* move-up on open */
++#define AuBrWAttr_Mask (AuBrWAttr_NoLinkWH | AuBrWAttr_MOO)
++
++#define AuBrAttr_CMOO_Mask (AuBrAttr_COO_Mask | AuBrWAttr_MOO)
++
++/* #warning test userspace */
++#ifdef __KERNEL__
++#ifndef CONFIG_AUFS_FHSM
++#undef AuBrAttr_FHSM
++#define AuBrAttr_FHSM 0
++#endif
++#ifndef CONFIG_AUFS_XATTR
++#undef AuBrAttr_ICEX
++#define AuBrAttr_ICEX 0
++#undef AuBrAttr_ICEX_SEC
++#define AuBrAttr_ICEX_SEC 0
++#undef AuBrAttr_ICEX_SYS
++#define AuBrAttr_ICEX_SYS 0
++#undef AuBrAttr_ICEX_TR
++#define AuBrAttr_ICEX_TR 0
++#undef AuBrAttr_ICEX_USR
++#define AuBrAttr_ICEX_USR 0
++#undef AuBrAttr_ICEX_OTH
++#define AuBrAttr_ICEX_OTH 0
++#endif
++#endif
++
++/* the longest combination */
++/* AUFS_BRATTR_ICEX and AUFS_BRATTR_ICEX_TR don't affect here */
++#define AuBrPermStrSz sizeof(AUFS_BRPERM_RW \
++ "+" AUFS_BRATTR_COO_REG \
++ "+" AUFS_BRATTR_FHSM \
++ "+" AUFS_BRATTR_UNPIN \
++ "+" AUFS_BRATTR_ICEX_SEC \
++ "+" AUFS_BRATTR_ICEX_SYS \
++ "+" AUFS_BRATTR_ICEX_USR \
++ "+" AUFS_BRATTR_ICEX_OTH \
++ "+" AUFS_BRWATTR_NLWH)
++
++typedef struct {
++ char a[AuBrPermStrSz];
++} au_br_perm_str_t;
++
++static inline int au_br_writable(int brperm)
++{
++ return brperm & AuBrPerm_RW;
++}
++
++static inline int au_br_whable(int brperm)
++{
++ return brperm & (AuBrPerm_RW | AuBrRAttr_WH);
++}
++
++static inline int au_br_wh_linkable(int brperm)
++{
++ return !(brperm & AuBrWAttr_NoLinkWH);
++}
++
++static inline int au_br_cmoo(int brperm)
++{
++ return brperm & AuBrAttr_CMOO_Mask;
++}
++
++static inline int au_br_fhsm(int brperm)
++{
++ return brperm & AuBrAttr_FHSM;
++}
+
+/* ---------------------------------------------------------------------- */
+
+ AuCtl_RDU,
+ AuCtl_RDU_INO,
+
-+ /* pathconf wrapper */
-+ AuCtl_WBR_FD,
-+
-+ /* busy inode */
-+ AuCtl_IBUSY
++ AuCtl_WBR_FD, /* pathconf wrapper */
++ AuCtl_IBUSY, /* busy inode */
++ AuCtl_MVDOWN, /* move-down */
++ AuCtl_BR, /* info about branches */
++ AuCtl_FHSM_FD /* connection for fhsm */
+};
+
+/* borrowed from linux/include/linux/kernel.h */
+
+/* ---------------------------------------------------------------------- */
+
++/* error code for move-down */
++/* the actual message strings are implemented in aufs-util.git */
++enum {
++ EAU_MVDOWN_OPAQUE = 1,
++ EAU_MVDOWN_WHITEOUT,
++ EAU_MVDOWN_UPPER,
++ EAU_MVDOWN_BOTTOM,
++ EAU_MVDOWN_NOUPPER,
++ EAU_MVDOWN_NOLOWERBR,
++ EAU_Last
++};
++
++/* flags for move-down */
++#define AUFS_MVDOWN_DMSG 1
++#define AUFS_MVDOWN_OWLOWER (1 << 1) /* overwrite lower */
++#define AUFS_MVDOWN_KUPPER (1 << 2) /* keep upper */
++#define AUFS_MVDOWN_ROLOWER (1 << 3) /* do even if lower is RO */
++#define AUFS_MVDOWN_ROLOWER_R (1 << 4) /* did on lower RO */
++#define AUFS_MVDOWN_ROUPPER (1 << 5) /* do even if upper is RO */
++#define AUFS_MVDOWN_ROUPPER_R (1 << 6) /* did on upper RO */
++#define AUFS_MVDOWN_BRID_UPPER (1 << 7) /* upper brid */
++#define AUFS_MVDOWN_BRID_LOWER (1 << 8) /* lower brid */
++#define AUFS_MVDOWN_FHSM_LOWER (1 << 9) /* find fhsm attr for lower */
++#define AUFS_MVDOWN_STFS (1 << 10) /* req. stfs */
++#define AUFS_MVDOWN_STFS_FAILED (1 << 11) /* output: stfs is unusable */
++#define AUFS_MVDOWN_BOTTOM (1 << 12) /* output: no more lowers */
++
++/* index for move-down */
++enum {
++ AUFS_MVDOWN_UPPER,
++ AUFS_MVDOWN_LOWER,
++ AUFS_MVDOWN_NARRAY
++};
++
++/*
++ * additional info of move-down
++ * number of free blocks and inodes.
++ * subset of struct kstatfs, but smaller and always 64bit.
++ */
++struct aufs_stfs {
++ uint64_t f_blocks;
++ uint64_t f_bavail;
++ uint64_t f_files;
++ uint64_t f_ffree;
++};
++
++struct aufs_stbr {
++ int16_t brid; /* optional input */
++ int16_t bindex; /* output */
++ struct aufs_stfs stfs; /* output when AUFS_MVDOWN_STFS set */
++} __aligned(8);
++
++struct aufs_mvdown {
++ uint32_t flags; /* input/output */
++ struct aufs_stbr stbr[AUFS_MVDOWN_NARRAY]; /* input/output */
++ int8_t au_errno; /* output */
++} __aligned(8);
++
++/* ---------------------------------------------------------------------- */
++
++union aufs_brinfo {
++ /* PATH_MAX may differ between kernel-space and user-space */
++ char _spacer[4096];
++ struct {
++ int16_t id;
++ int perm;
++ char path[0];
++ };
++} __aligned(8);
++
++/* ---------------------------------------------------------------------- */
++
+#define AuCtlType 'A'
+#define AUFS_CTL_RDU _IOWR(AuCtlType, AuCtl_RDU, struct aufs_rdu)
+#define AUFS_CTL_RDU_INO _IOWR(AuCtlType, AuCtl_RDU_INO, struct aufs_rdu)
+#define AUFS_CTL_WBR_FD _IOW(AuCtlType, AuCtl_WBR_FD, \
+ struct aufs_wbr_fd)
+#define AUFS_CTL_IBUSY _IOWR(AuCtlType, AuCtl_IBUSY, struct aufs_ibusy)
++#define AUFS_CTL_MVDOWN _IOWR(AuCtlType, AuCtl_MVDOWN, \
++ struct aufs_mvdown)
++#define AUFS_CTL_BRINFO _IOW(AuCtlType, AuCtl_BR, union aufs_brinfo)
++#define AUFS_CTL_FHSM_FD _IOW(AuCtlType, AuCtl_FHSM_FD, int)
+
+#endif /* __AUFS_TYPE_H__ */
-