diff options
Diffstat (limited to 'target/linux/generic-2.6/patches-2.6.32/230-union_mounts.patch')
| -rw-r--r-- | target/linux/generic-2.6/patches-2.6.32/230-union_mounts.patch | 5203 |
1 files changed, 5203 insertions, 0 deletions
diff --git a/target/linux/generic-2.6/patches-2.6.32/230-union_mounts.patch b/target/linux/generic-2.6/patches-2.6.32/230-union_mounts.patch new file mode 100644 index 0000000000..23236a07c6 --- /dev/null +++ b/target/linux/generic-2.6/patches-2.6.32/230-union_mounts.patch @@ -0,0 +1,5203 @@ +--- /dev/null ++++ b/Documentation/filesystems/union-mounts.txt +@@ -0,0 +1,187 @@ ++VFS based Union Mounts ++---------------------- ++ ++ 1. What are "Union Mounts" ++ 2. The Union Stack ++ 3. Whiteouts, Opaque Directories, and Fallthrus ++ 4. Copy-up ++ 5. Directory Reading ++ 6. Known Problems ++ 7. References ++ ++------------------------------------------------------------------------------- ++ ++1. What are "Union Mounts" ++========================== ++ ++Please note: this is NOT about UnionFS and it is NOT derived work! ++ ++Traditionally the mount operation is opaque, which means that the content of ++the mount point, the directory where the file system is mounted on, is hidden ++by the content of the mounted file system's root directory until the file ++system is unmounted again. Unlike the traditional UNIX mount mechanism, that ++hides the contents of the mount point, a union mount presents a view as if ++both filesystems are merged together. Although only the topmost layer of the ++mount stack can be altered, it appears as if transparent file system mounts ++allow any file to be created, modified or deleted. ++ ++Most people know the concepts and features of union mounts from other ++operating systems like Sun's Translucent Filesystem, Plan9 or BSD. For an ++in-depth review of union mounts and other unioning file systems, see: ++ ++http://lwn.net/Articles/324291/ ++http://lwn.net/Articles/325369/ ++http://lwn.net/Articles/327738/ ++ ++Here are the key features of this implementation: ++- completely VFS based ++- does not change the namespace stacking ++- directory listings have duplicate entries removed in the kernel ++- writable unions: only the topmost file system layer may be writable ++- writable unions: new whiteout filetype handled inside the kernel ++ ++------------------------------------------------------------------------------- ++ ++2. The Union Stack ++================== ++ ++The mounted file systems are organized in the "file system hierarchy" (tree of ++vfsmount structures), which keeps track about the stacking of file systems ++upon each other. The per-directory view on the file system hierarchy is called ++"mount stack" and reflects the order of file systems, which are mounted on a ++specific directory. ++ ++Union mounts present a single unified view of the contents of two or more file ++systems as if they are merged together. Since the information which file ++system objects are part of a unified view is not directly available from the ++file system hierarchy there is a need for a new structure. The file system ++objects, which are part of a unified view are ordered in a so-called "union ++stack". Only directories can be part of a unified view. ++ ++The link between two layers of the union stack is maintained using the ++union_mount structure (#include <linux/union.h>): ++ ++struct union_mount { ++ atomic_t u_count; /* reference count */ ++ struct mutex u_mutex; ++ struct list_head u_unions; /* list head for d_unions */ ++ struct hlist_node u_hash; /* list head for searching */ ++ struct hlist_node u_rhash; /* list head for reverse searching */ ++ ++ struct path u_this; /* this is me */ ++ struct path u_next; /* this is what I overlay */ ++}; ++ ++The union_mount structure holds a reference (dget,mntget) to the next lower ++layer of the union stack. Since a dentry can be part of multiple unions ++(e.g. with bind mounts) they are tied together via the d_unions field of the ++dentry structure. ++ ++All union_mount structures are cached in two hash tables, one for lookups of ++the next lower layer of the union stack and one for reverse lookups of the ++next upper layer of the union stack. The reverse lookup is necessary to ++resolve CWD relative path lookups. For calculation of the hash value, the ++(dentry,vfsmount) pair is used. The u_this field is used for the hash table ++which is used in forward lookups and the u_next field for the reverse lookups. ++ ++During every new mount (or mount propagation), a new union_mount structure is ++allocated. A reference to the mountpoint's vfsmount and dentry is taken and ++stored in the u_next field. In almost the same manner an union_mount ++structure is created during the first time lookup of a directory within a ++union mount point. In this case the lookup proceeds to all lower layers of the ++union. Therefore the complete union stack is constructed during lookups. ++ ++The union_mount structures of a dentry are destroyed when the dentry itself is ++destroyed. Therefore the dentry cache is indirectly driving the union_mount ++cache like this is done for inodes too. Please note that lower layer ++union_mount structures are kept in memory until the topmost dentry is ++destroyed. ++ ++------------------------------------------------------------------------------- ++ ++3. Whiteouts, Opaque Directories, and Fallthrus ++=========================================================== ++ ++The whiteout filetype isn't new. It has been there for quite some time now ++but Linux's VFS hasn't used it yet. With the availability of union mount code ++inside the VFS the whiteout filetype is getting important to support writable ++union mounts. For read-only union mounts, support for whiteouts or ++copy-on-open is not necessary. ++ ++The whiteout filetype has the same function as negative dentries: they ++describe a filename which isn't there. The creation of whiteouts needs ++lowlevel filesystem support. At the time of writing this, there is whiteout ++support for tmpfs, ext2 and ext3 available. The VFS is extended to make the ++whiteout handling transparent to all its users. The whiteouts are not ++visible to user-space. ++ ++What happens when we create a directory that was previously whited-out? We ++don't want the directory entries from underlying filesystems to suddenly appear ++in the newly created directory. So we mark the directory opaque (the file ++system must support storage of the opaque flag). ++ ++Fallthrus are directory entries that override the opaque flag on a directory ++for that specific directory entry name (the lookup "falls through" to the next ++layer of the union mount). Fallthrus are mainly useful for implementing ++readdir(). ++ ++------------------------------------------------------------------------------- ++ ++4. Copy-up ++=========== ++ ++Any write to an object on any layer other than the topmost triggers a copy-up ++of the object to the topmost file system. For regular files, the copy-up ++happens when it is opened in writable mode. ++ ++Directories are copied up on open, regardless of intent to write, to simplify ++copy-up of any object located below it in the namespace. Otherwise we have to ++walk the entire pathname to create intermediate directories whenever we do a ++copy-up. This is the same approach as BSD union mounts and uses a negigible ++amount of disk space. Note that the actual directory entries themselves are ++not copied-up from the lower levels until (a) the directory is written to, or ++(b) the first readdir() of the directory (more on that later). ++ ++Rename across different levels of the union is implemented as a copy-up ++operation for regular files. Rename of directories simply returns EXDEV, the ++same as if we tried to rename across different mounts. Most applications have ++to handle this case anyway. Some applications do not expect EXDEV on ++rename operations within the same directory, but these applications will also ++be broken with bind mounts. ++ ++------------------------------------------------------------------------------- ++ ++5. Directory Reading ++==================== ++ ++readdir() is somewhat difficult to implement in a unioning file system. We must ++eliminate duplicates, apply whiteouts, and start up readdir() where we left ++off, given a single f_pos value. Our solution is to copy up all the directory ++entries to the topmost directory the first time readdir() is called on a ++directory. During this copy-up, we skip duplicates and entries covered by ++whiteouts, and then create fallthru entries for each remaining visible dentry. ++Then we mark the whole directory opaque. From then on, we just use the topmost ++file system's normal readdir() operation. ++ ++------------------------------------------------------------------------------- ++ ++6. Known Problems ++================= ++ ++- copyup() for other filetypes that reg and dir (e.g. for chown() on devices) ++- symlinks are untested ++ ++------------------------------------------------------------------------------- ++ ++7. References ++============= ++ ++[1] http://marc.info/?l=linux-fsdevel&m=96035682927821&w=2 ++[2] http://marc.info/?l=linux-fsdevel&m=117681527820133&w=2 ++[3] http://marc.info/?l=linux-fsdevel&m=117913503200362&w=2 ++[4] http://marc.info/?l=linux-fsdevel&m=118231827024394&w=2 ++ ++Authors: ++Jan Blunck <jblunck@suse.de> ++Bharata B Rao <bharata@linux.vnet.ibm.com> ++Valerie Aurora <vaurora@redhat.com> +--- a/fs/autofs4/autofs_i.h ++++ b/fs/autofs4/autofs_i.h +@@ -130,6 +130,7 @@ struct autofs_sb_info { + int reghost_enabled; + int needs_reghost; + struct super_block *sb; ++ struct vfsmount *mnt; + struct mutex wq_mutex; + spinlock_t fs_lock; + struct autofs_wait_queue *queues; /* Wait queue pointer */ +--- a/fs/autofs4/init.c ++++ b/fs/autofs4/init.c +@@ -17,7 +17,16 @@ + static int autofs_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, struct vfsmount *mnt) + { +- return get_sb_nodev(fs_type, flags, data, autofs4_fill_super, mnt); ++ struct autofs_sb_info *sbi; ++ int ret; ++ ++ ret = get_sb_nodev(fs_type, flags, data, autofs4_fill_super, mnt); ++ if (ret) ++ return ret; ++ ++ sbi = autofs4_sbi(mnt->mnt_sb); ++ sbi->mnt = mnt; ++ return 0; + } + + static struct file_system_type autofs_fs_type = { +--- a/fs/autofs4/root.c ++++ b/fs/autofs4/root.c +@@ -179,6 +179,12 @@ static void *autofs4_follow_link(struct + DPRINTK("dentry=%p %.*s oz_mode=%d nd->flags=%d", + dentry, dentry->d_name.len, dentry->d_name.name, oz_mode, + nd->flags); ++ ++ dput(nd->path.dentry); ++ mntput(nd->path.mnt); ++ nd->path.mnt = mntget(sbi->mnt); ++ nd->path.dentry = dget(dentry); ++ + /* + * For an expire of a covered direct or offset mount we need + * to break out of follow_down() at the autofs mount trigger +--- a/fs/compat.c ++++ b/fs/compat.c +@@ -840,6 +840,9 @@ static int compat_fillonedir(void *__buf + struct compat_old_linux_dirent __user *dirent; + compat_ulong_t d_ino; + ++ if (d_type == DT_WHT) ++ return 0; ++ + if (buf->result) + return -EINVAL; + d_ino = ino; +@@ -911,6 +914,9 @@ static int compat_filldir(void *__buf, c + compat_ulong_t d_ino; + int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 2, sizeof(compat_long_t)); + ++ if (d_type == DT_WHT) ++ return 0; ++ + buf->error = -EINVAL; /* only used if we fail.. */ + if (reclen > buf->count) + return -EINVAL; +@@ -1000,6 +1006,9 @@ static int compat_filldir64(void * __buf + int reclen = ALIGN(jj + namlen + 1, sizeof(u64)); + u64 off; + ++ if (d_type == DT_WHT) ++ return 0; ++ + buf->error = -EINVAL; /* only used if we fail.. */ + if (reclen > buf->count) + return -EINVAL; +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -18,6 +18,7 @@ + #include <linux/string.h> + #include <linux/mm.h> + #include <linux/fs.h> ++#include <linux/union.h> + #include <linux/fsnotify.h> + #include <linux/slab.h> + #include <linux/init.h> +@@ -158,14 +159,19 @@ static void dentry_lru_del_init(struct d + } + + /** +- * d_kill - kill dentry and return parent ++ * __d_kill - kill dentry and return parent + * @dentry: dentry to kill ++ * @list: kill list ++ * @greedy: return parent instead of putting it on the kill list + * + * The dentry must already be unhashed and removed from the LRU. + * +- * If this is the root of the dentry tree, return NULL. ++ * If this is the root of the dentry tree, return NULL. If greedy is zero, we ++ * put the parent of this dentry on the kill list instead. The callers must ++ * make sure that __d_kill_final() is called on all dentries on the kill list. + */ +-static struct dentry *d_kill(struct dentry *dentry) ++static struct dentry *__d_kill(struct dentry *dentry, struct list_head *list, ++ int greedy) + __releases(dentry->d_lock) + __releases(dcache_lock) + { +@@ -173,13 +179,78 @@ static struct dentry *d_kill(struct dent + + list_del(&dentry->d_u.d_child); + dentry_stat.nr_dentry--; /* For d_free, below */ +- /*drops the locks, at that point nobody can reach this dentry */ ++ ++ /* ++ * If we are not greedy we just put this on a list for later processing ++ * (follow up to parent, releasing of inode and freeing dentry memory). ++ */ ++ if (!greedy) { ++ list_del_init(&dentry->d_alias); ++ /* at this point nobody can reach this dentry */ ++ list_add(&dentry->d_lru, list); ++ spin_unlock(&dentry->d_lock); ++ spin_unlock(&dcache_lock); ++ __shrink_d_unions(dentry, list); ++ return NULL; ++ } ++ ++ /* drops the locks, at that point nobody can reach this dentry */ + dentry_iput(dentry); ++ /* If the dentry was in an union delete them */ ++ __shrink_d_unions(dentry, list); ++ if (IS_ROOT(dentry)) ++ parent = NULL; ++ else ++ parent = dentry->d_parent; ++ d_free(dentry); ++ return parent; ++} ++ ++void __dput(struct dentry *, struct list_head *, int); ++ ++static void __d_kill_final(struct dentry *dentry, struct list_head *list) ++{ ++ struct dentry *parent; ++ struct inode *inode = dentry->d_inode; ++ ++ if (inode) { ++ dentry->d_inode = NULL; ++ if (!inode->i_nlink) ++ fsnotify_inoderemove(inode); ++ if (dentry->d_op && dentry->d_op->d_iput) ++ dentry->d_op->d_iput(dentry, inode); ++ else ++ iput(inode); ++ } ++ + if (IS_ROOT(dentry)) + parent = NULL; + else + parent = dentry->d_parent; + d_free(dentry); ++ __dput(parent, list, 1); ++} ++ ++/** ++ * d_kill - kill dentry and return parent ++ * @dentry: dentry to kill ++ * ++ * The dentry must already be unhashed and removed from the LRU. ++ * ++ * If this is the root of the dentry tree, return NULL. ++ */ ++static struct dentry *d_kill(struct dentry *dentry) ++{ ++ LIST_HEAD(mortuary); ++ struct dentry *parent; ++ ++ parent = __d_kill(dentry, &mortuary, 1); ++ while (!list_empty(&mortuary)) { ++ dentry = list_entry(mortuary.next, struct dentry, d_lru); ++ list_del(&dentry->d_lru); ++ __d_kill_final(dentry, &mortuary); ++ } ++ + return parent; + } + +@@ -200,19 +271,24 @@ static struct dentry *d_kill(struct dent + * Real recursion would eat up our stack space. + */ + +-/* +- * dput - release a dentry +- * @dentry: dentry to release ++/** ++ * __dput - release a dentry ++ * @dentry: dentry to release ++ * @list: kill list argument for __d_kill() ++ * @greedy: greedy argument for __d_kill() + * + * Release a dentry. This will drop the usage count and if appropriate + * call the dentry unlink method as well as removing it from the queues and + * releasing its resources. If the parent dentries were scheduled for release +- * they too may now get deleted. ++ * they too may now get deleted if @greedy is not zero. Otherwise parent is ++ * added to the kill list. The callers must make sure that __d_kill_final() is ++ * called on all dentries on the kill list. ++ * ++ * You probably want to use dput() instead. + * + * no dcache lock, please. + */ +- +-void dput(struct dentry *dentry) ++void __dput(struct dentry *dentry, struct list_head *list, int greedy) + { + if (!dentry) + return; +@@ -253,12 +329,35 @@ unhash_it: + kill_it: + /* if dentry was on the d_lru list delete it from there */ + dentry_lru_del(dentry); +- dentry = d_kill(dentry); ++ dentry = __d_kill(dentry, list, greedy); + if (dentry) + goto repeat; + } + + /** ++ * dput - release a dentry ++ * @dentry: dentry to release ++ * ++ * Release a dentry. This will drop the usage count and if appropriate ++ * call the dentry unlink method as well as removing it from the queues and ++ * releasing its resources. If the parent dentries were scheduled for release ++ * they too may now get deleted. ++ * ++ * no dcache lock, please. ++ */ ++void dput(struct dentry *dentry) ++{ ++ LIST_HEAD(mortuary); ++ ++ __dput(dentry, &mortuary, 1); ++ while (!list_empty(&mortuary)) { ++ dentry = list_entry(mortuary.next, struct dentry, d_lru); ++ list_del(&dentry->d_lru); ++ __d_kill_final(dentry, &mortuary); ++ } ++} ++ ++/** + * d_invalidate - invalidate a dentry + * @dentry: dentry to invalidate + * +@@ -690,6 +789,7 @@ static void shrink_dcache_for_umount_sub + iput(inode); + } + ++ shrink_d_unions(dentry); + d_free(dentry); + + /* finished when we fall off the top of the tree, +@@ -952,6 +1052,10 @@ struct dentry *d_alloc(struct dentry * p + INIT_LIST_HEAD(&dentry->d_lru); + INIT_LIST_HEAD(&dentry->d_subdirs); + INIT_LIST_HEAD(&dentry->d_alias); ++#ifdef CONFIG_UNION_MOUNT ++ INIT_LIST_HEAD(&dentry->d_unions); ++ dentry->d_unionized = 0; ++#endif + + if (parent) { + dentry->d_parent = dget(parent); +@@ -982,8 +1086,10 @@ struct dentry *d_alloc_name(struct dentr + /* the caller must hold dcache_lock */ + static void __d_instantiate(struct dentry *dentry, struct inode *inode) + { +- if (inode) ++ if (inode) { ++ dentry->d_flags &= ~(DCACHE_WHITEOUT|DCACHE_FALLTHRU); + list_add(&dentry->d_alias, &inode->i_dentry); ++ } + dentry->d_inode = inode; + fsnotify_d_instantiate(dentry, inode); + } +@@ -1514,7 +1620,9 @@ void d_delete(struct dentry * dentry) + spin_lock(&dentry->d_lock); + isdir = S_ISDIR(dentry->d_inode->i_mode); + if (atomic_read(&dentry->d_count) == 1) { ++ __d_drop_unions(dentry); + dentry_iput(dentry); ++ shrink_d_unions(dentry); + fsnotify_nameremove(dentry, isdir); + return; + } +@@ -1525,14 +1633,14 @@ void d_delete(struct dentry * dentry) + spin_unlock(&dentry->d_lock); + spin_unlock(&dcache_lock); + ++ shrink_d_unions(dentry); + fsnotify_nameremove(dentry, isdir); + } + + static void __d_rehash(struct dentry * entry, struct hlist_head *list) + { +- +- entry->d_flags &= ~DCACHE_UNHASHED; +- hlist_add_head_rcu(&entry->d_hash, list); ++ entry->d_flags &= ~DCACHE_UNHASHED; ++ hlist_add_head_rcu(&entry->d_hash, list); + } + + static void _d_rehash(struct dentry * entry) +@@ -1551,6 +1659,7 @@ void d_rehash(struct dentry * entry) + { + spin_lock(&dcache_lock); + spin_lock(&entry->d_lock); ++ BUG_ON(!d_unhashed(entry)); + _d_rehash(entry); + spin_unlock(&entry->d_lock); + spin_unlock(&dcache_lock); +@@ -2183,7 +2292,9 @@ resume: + struct list_head *tmp = next; + struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); + next = tmp->next; +- if (d_unhashed(dentry)||!dentry->d_inode) ++ if (d_unhashed(dentry)||(!dentry->d_inode && ++ !d_is_whiteout(dentry) && ++ !d_is_fallthru(dentry))) + continue; + if (!list_empty(&dentry->d_subdirs)) { + this_parent = dentry; +--- a/fs/ext2/dir.c ++++ b/fs/ext2/dir.c +@@ -219,7 +219,8 @@ static inline int ext2_match (int len, c + { + if (len != de->name_len) + return 0; +- if (!de->inode) ++ if (!de->inode && ((de->file_type != EXT2_FT_WHT) && ++ (de->file_type != EXT2_FT_FALLTHRU))) + return 0; + return !memcmp(name, de->name, len); + } +@@ -255,6 +256,8 @@ static unsigned char ext2_filetype_table + [EXT2_FT_FIFO] = DT_FIFO, + [EXT2_FT_SOCK] = DT_SOCK, + [EXT2_FT_SYMLINK] = DT_LNK, ++ [EXT2_FT_WHT] = DT_WHT, ++ [EXT2_FT_FALLTHRU] = DT_UNKNOWN, + }; + + #define S_SHIFT 12 +@@ -341,6 +344,18 @@ ext2_readdir (struct file * filp, void * + ext2_put_page(page); + return 0; + } ++ } else if (de->file_type == EXT2_FT_FALLTHRU) { ++ int over; ++ unsigned char d_type = DT_UNKNOWN; ++ ++ offset = (char *)de - kaddr; ++ over = filldir(dirent, de->name, de->name_len, ++ (n<<PAGE_CACHE_SHIFT) | offset, ++ 123, d_type); ++ if (over) { ++ ext2_put_page(page); ++ return 0; ++ } + } + filp->f_pos += ext2_rec_len_from_disk(de->rec_len); + } +@@ -448,6 +463,30 @@ ino_t ext2_inode_by_name(struct inode *d + return res; + } + ++/* Special version for filetype based whiteout support */ ++ino_t ext2_inode_by_dentry(struct inode *dir, struct dentry *dentry) ++{ ++ ino_t res = 0; ++ struct ext2_dir_entry_2 *de; ++ struct page *page; ++ ++ de = ext2_find_entry (dir, &dentry->d_name, &page); ++ if (de) { ++ res = le32_to_cpu(de->inode); ++ if (!res && de->file_type == EXT2_FT_WHT) { ++ spin_lock(&dentry->d_lock); ++ dentry->d_flags |= DCACHE_WHITEOUT; ++ spin_unlock(&dentry->d_lock); ++ } else if(!res && de->file_type == EXT2_FT_FALLTHRU) { ++ spin_lock(&dentry->d_lock); ++ dentry->d_flags |= DCACHE_FALLTHRU; ++ spin_unlock(&dentry->d_lock); ++ } ++ ext2_put_page(page); ++ } ++ return res; ++} ++ + /* Releases the page */ + void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, + struct page *page, struct inode *inode, int update_times) +@@ -472,9 +511,10 @@ void ext2_set_link(struct inode *dir, st + } + + /* +- * Parent is locked. ++ * Find or append a given dentry to the parent directory + */ +-int ext2_add_link (struct dentry *dentry, struct inode *inode) ++static ext2_dirent * ext2_append_entry(struct dentry * dentry, ++ struct page ** page) + { + struct inode *dir = dentry->d_parent->d_inode; + const char *name = dentry->d_name.name; +@@ -482,13 +522,10 @@ int ext2_add_link (struct dentry *dentry + unsigned chunk_size = ext2_chunk_size(dir); + unsigned reclen = EXT2_DIR_REC_LEN(namelen); + unsigned short rec_len, name_len; +- struct page *page = NULL; +- ext2_dirent * de; ++ ext2_dirent * de = NULL; + unsigned long npages = dir_pages(dir); + unsigned long n; + char *kaddr; +- loff_t pos; +- int err; + + /* + * We take care of directory expansion in the same loop. +@@ -498,55 +535,97 @@ int ext2_add_link (struct dentry *dentry + for (n = 0; n <= npages; n++) { + char *dir_end; + +- page = ext2_get_page(dir, n, 0); +- err = PTR_ERR(page); +- if (IS_ERR(page)) ++ *page = ext2_get_page(dir, n, 0); ++ de = ERR_PTR(PTR_ERR(*page)); ++ if (IS_ERR(*page)) + goto out; +- lock_page(page); +- kaddr = page_address(page); ++ lock_page(*page); ++ kaddr = page_address(*page); + dir_end = kaddr + ext2_last_byte(dir, n); + de = (ext2_dirent *)kaddr; + kaddr += PAGE_CACHE_SIZE - reclen; + while ((char *)de <= kaddr) { + if ((char *)de == dir_end) { + /* We hit i_size */ +- name_len = 0; +- rec_len = chunk_size; ++ de->name_len = 0; + de->rec_len = ext2_rec_len_to_disk(chunk_size); + de->inode = 0; ++ de->file_type = 0; + goto got_it; + } + if (de->rec_len == 0) { + ext2_error(dir->i_sb, __func__, + "zero-length directory entry"); +- err = -EIO; ++ de = ERR_PTR(-EIO); + goto out_unlock; + } +- err = -EEXIST; + if (ext2_match (namelen, name, de)) +- goto out_unlock; ++ goto got_it; + name_len = EXT2_DIR_REC_LEN(de->name_len); + rec_len = ext2_rec_len_from_disk(de->rec_len); +- if (!de->inode && rec_len >= reclen) ++ if (!de->inode && (de->file_type != EXT2_FT_WHT) && ++ (de->file_type != EXT2_FT_FALLTHRU) && ++ (rec_len >= reclen)) + goto got_it; + if (rec_len >= name_len + reclen) + goto got_it; + de = (ext2_dirent *) ((char *) de + rec_len); + } +- unlock_page(page); +- ext2_put_page(page); ++ unlock_page(*page); ++ ext2_put_page(*page); + } ++ + BUG(); +- return -EINVAL; + + got_it: ++ return de; ++ /* OFFSET_CACHE */ ++out_unlock: ++ unlock_page(*page); ++ ext2_put_page(*page); ++out: ++ return de; ++} ++ ++/* ++ * Parent is locked. ++ */ ++int ext2_add_link (struct dentry *dentry, struct inode *inode) ++{ ++ struct inode *dir = dentry->d_parent->d_inode; ++ const char *name = dentry->d_name.name; ++ int namelen = dentry->d_name.len; ++ unsigned short rec_len, name_len; ++ ext2_dirent * de; ++ struct page *page; ++ loff_t pos; ++ int err; ++ ++ de = ext2_append_entry(dentry, &page); ++ if (IS_ERR(de)) ++ return PTR_ERR(de); ++ ++ err = -EEXIST; ++ if (ext2_match (namelen, name, de)) { ++ if ((de->file_type == EXT2_FT_WHT) || ++ (de->file_type == EXT2_FT_FALLTHRU)) ++ goto got_it; ++ goto out_unlock; ++ } ++ ++got_it: ++ name_len = EXT2_DIR_REC_LEN(de->name_len); ++ rec_len = ext2_rec_len_from_disk(de->rec_len); ++ + pos = page_offset(page) + + (char*)de - (char*)page_address(page); + err = __ext2_write_begin(NULL, page->mapping, pos, rec_len, 0, + &page, NULL); + if (err) + goto out_unlock; +- if (de->inode) { ++ if (de->inode || (((de->file_type == EXT2_FT_WHT) || ++ (de->file_type == EXT2_FT_FALLTHRU)) && ++ !ext2_match (namelen, name, de))) { + ext2_dirent *de1 = (ext2_dirent *) ((char *) de + name_len); + de1->rec_len = ext2_rec_len_to_disk(rec_len - name_len); + de->rec_len = ext2_rec_len_to_disk(name_len); +@@ -563,7 +642,60 @@ got_it: + /* OFFSET_CACHE */ + out_put: + ext2_put_page(page); +-out: ++ return err; ++out_unlock: ++ unlock_page(page); ++ goto out_put; ++} ++ ++/* ++ * Create a fallthru entry. ++ */ ++int ext2_fallthru_entry (struct inode *dir, struct dentry *dentry) ++{ ++ const char *name = dentry->d_name.name; ++ int namelen = dentry->d_name.len; ++ unsigned short rec_len, name_len; ++ ext2_dirent * de; ++ struct page *page; ++ loff_t pos; ++ int err; ++ ++ de = ext2_append_entry(dentry, &page); ++ if (IS_ERR(de)) ++ return PTR_ERR(de); ++ ++ err = -EEXIST; ++ if (ext2_match (namelen, name, de)) ++ goto out_unlock; ++ ++ name_len = EXT2_DIR_REC_LEN(de->name_len); ++ rec_len = ext2_rec_len_from_disk(de->rec_len); ++ ++ pos = page_offset(page) + ++ (char*)de - (char*)page_address(page); ++ err = __ext2_write_begin(NULL, page->mapping, pos, rec_len, 0, ++ &page, NULL); ++ if (err) ++ goto out_unlock; ++ if (de->inode || (de->file_type == EXT2_FT_WHT) || ++ (de->file_type == EXT2_FT_FALLTHRU)) { ++ ext2_dirent *de1 = (ext2_dirent *) ((char *) de + name_len); ++ de1->rec_len = ext2_rec_len_to_disk(rec_len - name_len); ++ de->rec_len = ext2_rec_len_to_disk(name_len); ++ de = de1; ++ } ++ de->name_len = namelen; ++ memcpy(de->name, name, namelen); ++ de->inode = 0; ++ de->file_type = EXT2_FT_FALLTHRU; ++ err = ext2_commit_chunk(page, pos, rec_len); ++ dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; ++ EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL; ++ mark_inode_dirty(dir); ++ /* OFFSET_CACHE */ ++out_put: ++ ext2_put_page(page); + return err; + out_unlock: + unlock_page(page); +@@ -616,6 +748,70 @@ out: + return err; + } + ++int ext2_whiteout_entry (struct inode * dir, struct dentry * dentry, ++ struct ext2_dir_entry_2 * de, struct page * page) ++{ ++ const char *name = dentry->d_name.name; ++ int namelen = dentry->d_name.len; ++ unsigned short rec_len, name_len; ++ loff_t pos; ++ int err; ++ ++ if (!de) { ++ de = ext2_append_entry(dentry, &page); ++ BUG_ON(!de); ++ } ++ ++ err = -EEXIST; ++ if (ext2_match (namelen, name, de) && ++ (de->file_type == EXT2_FT_WHT)) { ++ ext2_error(dir->i_sb, __func__, ++ "entry is already a whiteout in directory #%lu", ++ dir->i_ino); ++ goto out_unlock; ++ } ++ ++ name_len = EXT2_DIR_REC_LEN(de->name_len); ++ rec_len = ext2_rec_len_from_disk(de->rec_len); ++ ++ pos = page_offset(page) + ++ (char*)de - (char*)page_address(page); ++ err = __ext2_write_begin(NULL, page->mapping, pos, rec_len, 0, ++ &page, NULL); ++ if (err) ++ goto out_unlock; ++ /* ++ * We whiteout an existing entry. Do what ext2_delete_entry() would do, ++ * except that we don't need to merge with the previous entry since ++ * we are going to reuse it. ++ */ ++ if (ext2_match (namelen, name, de)) ++ de->inode = 0; ++ if (de->inode || (((de->file_type == EXT2_FT_WHT) || ++ (de->file_type == EXT2_FT_FALLTHRU)) && ++ !ext2_match (namelen, name, de))) { ++ ext2_dirent *de1 = (ext2_dirent *) ((char *) de + name_len); ++ de1->rec_len = ext2_rec_len_to_disk(rec_len - name_len); ++ de->rec_len = ext2_rec_len_to_disk(name_len); ++ de = de1; ++ } ++ de->name_len = namelen; ++ memcpy(de->name, name, namelen); ++ de->inode = 0; ++ de->file_type = EXT2_FT_WHT; ++ err = ext2_commit_chunk(page, pos, rec_len); ++ dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; ++ EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL; ++ mark_inode_dirty(dir); ++ /* OFFSET_CACHE */ ++out_put: ++ ext2_put_page(page); ++ return err; ++out_unlock: ++ unlock_page(page); ++ goto out_put; ++} ++ + /* + * Set the first fragment of directory. + */ +--- a/fs/ext2/ext2.h ++++ b/fs/ext2/ext2.h +@@ -102,9 +102,13 @@ extern void ext2_rsv_window_add(struct s + /* dir.c */ + extern int ext2_add_link (struct dentry *, struct inode *); + extern ino_t ext2_inode_by_name(struct inode *, struct qstr *); ++extern ino_t ext2_inode_by_dentry(struct inode *, struct dentry *); + extern int ext2_make_empty(struct inode *, struct inode *); + extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,struct qstr *, struct page **); + extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *); ++extern int ext2_whiteout_entry (struct inode *, struct dentry *, ++ struct ext2_dir_entry_2 *, struct page *); ++extern int ext2_fallthru_entry (struct inode *, struct dentry *); + extern int ext2_empty_dir (struct inode *); + extern struct ext2_dir_entry_2 * ext2_dotdot (struct inode *, struct page **); + extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, struct inode *, int); +--- a/fs/ext2/inode.c ++++ b/fs/ext2/inode.c +@@ -1178,7 +1178,8 @@ void ext2_set_inode_flags(struct inode * + { + unsigned int flags = EXT2_I(inode)->i_flags; + +- inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); ++ inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC| ++ S_OPAQUE); + if (flags & EXT2_SYNC_FL) + inode->i_flags |= S_SYNC; + if (flags & EXT2_APPEND_FL) +@@ -1189,6 +1190,8 @@ void ext2_set_inode_flags(struct inode * + inode->i_flags |= S_NOATIME; + if (flags & EXT2_DIRSYNC_FL) + inode->i_flags |= S_DIRSYNC; ++ if (flags & EXT2_OPAQUE_FL) ++ inode->i_flags |= S_OPAQUE; + } + + /* Propagate flags from i_flags to EXT2_I(inode)->i_flags */ +@@ -1196,8 +1199,8 @@ void ext2_get_inode_flags(struct ext2_in + { + unsigned int flags = ei->vfs_inode.i_flags; + +- ei->i_flags &= ~(EXT2_SYNC_FL|EXT2_APPEND_FL| +- EXT2_IMMUTABLE_FL|EXT2_NOATIME_FL|EXT2_DIRSYNC_FL); ++ ei->i_flags &= ~(EXT2_SYNC_FL|EXT2_APPEND_FL|EXT2_IMMUTABLE_FL| ++ EXT2_NOATIME_FL|EXT2_DIRSYNC_FL|EXT2_OPAQUE_FL); + if (flags & S_SYNC) + ei->i_flags |= EXT2_SYNC_FL; + if (flags & S_APPEND) +@@ -1208,6 +1211,8 @@ void ext2_get_inode_flags(struct ext2_in + ei->i_flags |= EXT2_NOATIME_FL; + if (flags & S_DIRSYNC) + ei->i_flags |= EXT2_DIRSYNC_FL; ++ if (flags & S_OPAQUE) ++ ei->i_flags |= EXT2_OPAQUE_FL; + } + + struct inode *ext2_iget (struct super_block *sb, unsigned long ino) +--- a/fs/ext2/namei.c ++++ b/fs/ext2/namei.c +@@ -54,15 +54,16 @@ static inline int ext2_add_nondir(struct + * Methods themselves. + */ + +-static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) ++static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, ++ struct nameidata *nd) + { + struct inode * inode; + ino_t ino; +- ++ + if (dentry->d_name.len > EXT2_NAME_LEN) + return ERR_PTR(-ENAMETOOLONG); + +- ino = ext2_inode_by_name(dir, &dentry->d_name); ++ ino = ext2_inode_by_dentry(dir, dentry); + inode = NULL; + if (ino) { + inode = ext2_iget(dir->i_sb, ino); +@@ -230,6 +231,10 @@ static int ext2_mkdir(struct inode * dir + else + inode->i_mapping->a_ops = &ext2_aops; + ++ /* if we call mkdir on a whiteout create an opaque directory */ ++ if (dentry->d_flags & DCACHE_WHITEOUT) ++ inode->i_flags |= S_OPAQUE; ++ + inode_inc_link_count(inode); + + err = ext2_make_empty(inode, dir); +@@ -293,6 +298,78 @@ static int ext2_rmdir (struct inode * di + return err; + } + ++/* ++ * Create a whiteout for the dentry ++ */ ++static int ext2_whiteout(struct inode *dir, struct dentry *dentry, ++ struct dentry *new_dentry) ++{ ++ struct inode * inode = dentry->d_inode; ++ struct ext2_dir_entry_2 * de = NULL; ++ struct page * page; ++ int err = -ENOTEMPTY; ++ ++ if (!EXT2_HAS_INCOMPAT_FEATURE(dir->i_sb, ++ EXT2_FEATURE_INCOMPAT_FILETYPE)) { ++ ext2_error (dir->i_sb, "ext2_whiteout", ++ "can't set whiteout filetype"); ++ err = -EPERM; ++ goto out; ++ } ++ ++ if (inode) { ++ if (S_ISDIR(inode->i_mode) && !ext2_empty_dir(inode)) ++ goto out; ++ ++ err = -ENOENT; ++ de = ext2_find_entry (dir, &dentry->d_name, &page); ++ if (!de) ++ goto out; ++ lock_page(page); ++ } ++ ++ err = ext2_whiteout_entry (dir, dentry, de, page); ++ if (err) ++ goto out; ++ ++ spin_lock(&new_dentry->d_lock); ++ new_dentry->d_flags &= ~DCACHE_FALLTHRU; ++ new_dentry->d_flags |= DCACHE_WHITEOUT; ++ spin_unlock(&new_dentry->d_lock); ++ d_add(new_dentry, NULL); ++ ++ if (inode) { ++ inode->i_ctime = dir->i_ctime; ++ inode_dec_link_count(inode); ++ if (S_ISDIR(inode->i_mode)) { ++ inode->i_size = 0; ++ inode_dec_link_count(inode); ++ inode_dec_link_count(dir); ++ } ++ } ++ err = 0; ++out: ++ return err; ++} ++ ++/* ++ * Create a fallthru entry. ++ */ ++static int ext2_fallthru (struct inode *dir, struct dentry *dentry) ++{ ++ int err; ++ ++ err = ext2_fallthru_entry(dir, dentry); ++ if (err) ++ return err; ++ ++ d_instantiate(dentry, NULL); ++ spin_lock(&dentry->d_lock); ++ dentry->d_flags |= DCACHE_FALLTHRU; ++ spin_unlock(&dentry->d_lock); ++ return 0; ++} ++ + static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, + struct inode * new_dir, struct dentry * new_dentry ) + { +@@ -392,6 +469,8 @@ const struct inode_operations ext2_dir_i + .mkdir = ext2_mkdir, + .rmdir = ext2_rmdir, + .mknod = ext2_mknod, ++ .whiteout = ext2_whiteout, ++ .fallthru = ext2_fallthru, + .rename = ext2_rename, + #ifdef CONFIG_EXT2_FS_XATTR + .setxattr = generic_setxattr, +--- a/fs/ext2/super.c ++++ b/fs/ext2/super.c +@@ -1062,6 +1062,13 @@ static int ext2_fill_super(struct super_ + if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL)) + ext2_warning(sb, __func__, + "mounting ext3 filesystem as ext2"); ++ ++ /* ++ * Whiteouts (and fallthrus) require explicit whiteout support. ++ */ ++ if (EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_WHITEOUT)) ++ sb->s_flags |= MS_WHITEOUT; ++ + ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY); + return 0; + +--- a/fs/Kconfig ++++ b/fs/Kconfig +@@ -59,6 +59,14 @@ source "fs/notify/Kconfig" + + source "fs/quota/Kconfig" + ++config UNION_MOUNT ++ bool "Union mount support (EXPERIMENTAL)" ++ depends on EXPERIMENTAL ++ ---help--- ++ If you say Y here, you will be able to mount file systems as ++ union mount stacks. This is a VFS based implementation and ++ should work with all file systems. If unsure, say N. ++ + source "fs/autofs/Kconfig" + source "fs/autofs4/Kconfig" + source "fs/fuse/Kconfig" +--- a/fs/libfs.c ++++ b/fs/libfs.c +@@ -133,6 +133,7 @@ int dcache_readdir(struct file * filp, v + struct dentry *cursor = filp->private_data; + struct list_head *p, *q = &cursor->d_u.d_child; + ino_t ino; ++ int d_type; + int i = filp->f_pos; + + switch (i) { +@@ -158,14 +159,25 @@ int dcache_readdir(struct file * filp, v + for (p=q->next; p != &dentry->d_subdirs; p=p->next) { + struct dentry *next; + next = list_entry(p, struct dentry, d_u.d_child); +- if (d_unhashed(next) || !next->d_inode) ++ if (d_unhashed(next) || (!next->d_inode && !d_is_fallthru(next))) + continue; + ++ if (d_is_fallthru(next)) { ++ /* XXX Make up things we can ++ * only get out of the inode. ++ * Should probably really do a ++ * lookup instead. */ ++ ino = 100; /* XXX Made up number of no significance */ ++ d_type = DT_UNKNOWN; ++ } else { ++ ino = next->d_inode->i_ino; ++ d_type = dt_type(next->d_inode); ++ } ++ + spin_unlock(&dcache_lock); + if (filldir(dirent, next->d_name.name, + next->d_name.len, filp->f_pos, +- next->d_inode->i_ino, +- dt_type(next->d_inode)) < 0) ++ ino, d_type) < 0) + return 0; + spin_lock(&dcache_lock); + /* next is still alive */ +--- a/fs/Makefile ++++ b/fs/Makefile +@@ -52,6 +52,7 @@ obj-$(CONFIG_NFS_COMMON) += nfs_common/ + obj-$(CONFIG_GENERIC_ACL) += generic_acl.o + + obj-y += quota/ ++obj-$(CONFIG_UNION_MOUNT) += union.o + + obj-$(CONFIG_PROC_FS) += proc/ + obj-y += partitions/ +--- a/fs/namei.c ++++ b/fs/namei.c +@@ -33,6 +33,7 @@ + #include <linux/fcntl.h> + #include <linux/device_cgroup.h> + #include <linux/fs_struct.h> ++#include <linux/union.h> + #include <asm/uaccess.h> + + #define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE]) +@@ -242,16 +243,17 @@ int generic_permission(struct inode *ino + } + + /** +- * inode_permission - check for access rights to a given inode ++ * __inode_permission - check for access rights to a given inode + * @inode: inode to check permission on + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) ++ * @rofs: check for read-only fs + * + * Used to check for read/write/execute permissions on an inode. + * We use "fsuid" for this, letting us set arbitrary permissions + * for filesystem access without changing the "normal" uids which + * are used for other things. + */ +-int inode_permission(struct inode *inode, int mask) ++int __inode_permission(struct inode *inode, int mask, int rofs) + { + int retval; + +@@ -261,7 +263,7 @@ int inode_permission(struct inode *inode + /* + * Nobody gets write access to a read-only fs. + */ +- if (IS_RDONLY(inode) && ++ if ((rofs & IS_RDONLY(inode)) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) + return -EROFS; + +@@ -289,6 +291,18 @@ int inode_permission(struct inode *inode + } + + /** ++ * inode_permission - check for access rights to a given inode ++ * @inode: inode to check permission on ++ * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) ++ * ++ * This version pays attention to the MS_RDONLY flag on the fs. ++ */ ++int inode_permission(struct inode *inode, int mask) ++{ ++ return __inode_permission(inode, mask, 1); ++} ++ ++/** + * file_permission - check for additional access rights to a given file + * @file: file to check access rights for + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) +@@ -417,15 +431,10 @@ do_revalidate(struct dentry *dentry, str + * Internal lookup() using the new generic dcache. + * SMP-safe + */ +-static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd) ++static struct dentry *cache_lookup(struct dentry *parent, struct qstr *name, ++ struct nameidata *nd) + { +- struct dentry * dentry = __d_lookup(parent, name); +- +- /* lockess __d_lookup may fail due to concurrent d_move() +- * in some unrelated directory, so try with d_lookup +- */ +- if (!dentry) +- dentry = d_lookup(parent, name); ++ struct dentry *dentry = d_lookup(parent, name); + + if (dentry && dentry->d_op && dentry->d_op->d_revalidate) + dentry = do_revalidate(dentry, nd); +@@ -434,6 +443,208 @@ static struct dentry * cached_lookup(str + } + + /* ++ * Theory of operation for opaque, whiteout, and fallthru: ++ * ++ * whiteout: Unconditionally stop lookup here - ENOENT ++ * ++ * opaque: Don't lookup in directories lower in the union stack ++ * ++ * fallthru: While looking up an entry, ignore the opaque flag for the ++ * current directory only. ++ * ++ * A union stack is a linked list of directory dentries which appear ++ * in the same place in the namespace. When constructing the union ++ * stack, we include directories below opaque directories so that we ++ * can properly handle fallthrus. All non-fallthru lookups have to ++ * check for the opaque flag on the parent directory and obey it. ++ * ++ * In general, the code pattern is to lookup the the topmost entry ++ * first (either the first visible non-negative dentry or a negative ++ * dentry in the topmost layer of the union), then build the union ++ * stack for the newly looked-up entry (if it is a directory). ++ */ ++ ++/** ++ * __cache_lookup_topmost - lookup the topmost (non-)negative dentry ++ * ++ * @nd - parent's nameidata ++ * @name - pathname part to lookup ++ * @path - found dentry for pathname part ++ * ++ * This is used for union mount lookups from dcache. The first non-negative ++ * dentry is searched on all layers of the union stack. Otherwise the topmost ++ * negative dentry is returned. ++ */ ++static int __cache_lookup_topmost(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct dentry *dentry; ++ ++ dentry = d_lookup(nd->path.dentry, name); ++ if (dentry && dentry->d_op && dentry->d_op->d_revalidate) ++ dentry = do_revalidate(dentry, nd); ++ ++ /* ++ * Remember the topmost negative dentry in case we don't find anything ++ */ ++ path->dentry = dentry; ++ path->mnt = dentry ? nd->path.mnt : NULL; ++ ++ if (!dentry || (dentry->d_inode || d_is_whiteout(dentry))) ++ return !dentry; ++ ++ /* Keep going through opaque directories if we found a fallthru */ ++ if (IS_OPAQUE(nd->path.dentry->d_inode) && !d_is_fallthru(dentry)) ++ return !dentry; ++ ++ /* look for the first non-negative or whiteout dentry */ ++ ++ while (follow_union_down(&nd->path)) { ++ dentry = d_hash_and_lookup(nd->path.dentry, name); ++ ++ /* ++ * If parts of the union stack are not in the dcache we need ++ * to do a real lookup ++ */ ++ if (!dentry) ++ goto out_dput; ++ ++ /* ++ * If parts of the union don't survive the revalidation we ++ * need to do a real lookup ++ */ ++ if (dentry->d_op && dentry->d_op->d_revalidate) { ++ dentry = do_revalidate(dentry, nd); ++ if (!dentry) ++ goto out_dput; ++ } ++ ++ if (dentry->d_inode || d_is_whiteout(dentry)) ++ goto out_dput; ++ ++ /* Stop the lookup on opaque parent and non-fallthru child */ ++ if (IS_OPAQUE(nd->path.dentry->d_inode) && !d_is_fallthru(dentry)) ++ goto out_dput; ++ ++ dput(dentry); ++ } ++ ++ return !dentry; ++ ++out_dput: ++ dput(path->dentry); ++ path->dentry = dentry; ++ path->mnt = dentry ? mntget(nd->path.mnt) : NULL; ++ return !dentry; ++} ++ ++/** ++ * __cache_lookup_build_union - build the union stack for this part, ++ * cached version ++ * ++ * This is called after you have the topmost dentry in @path. ++ */ ++static int __cache_lookup_build_union(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct path last = *path; ++ struct dentry *dentry; ++ ++ while (follow_union_down(&nd->path)) { ++ dentry = d_hash_and_lookup(nd->path.dentry, name); ++ if (!dentry) ++ return 1; ++ ++ if (dentry->d_op && dentry->d_op->d_revalidate) { ++ dentry = do_revalidate(dentry, nd); ++ if (!dentry) ++ return 1; ++ } ++ ++ if (d_is_whiteout(dentry)) { ++ dput(dentry); ++ break; ++ } ++ ++ if (!dentry->d_inode) { ++ dput(dentry); ++ continue; ++ } ++ ++ /* only directories can be part of a union stack */ ++ if (!S_ISDIR(dentry->d_inode->i_mode)) { ++ dput(dentry); ++ break; ++ } ++ ++ /* Add the newly discovered dir to the union stack */ ++ append_to_union(last.mnt, last.dentry, nd->path.mnt, dentry); ++ ++ if (last.dentry != path->dentry) ++ path_put(&last); ++ last.dentry = dentry; ++ last.mnt = mntget(nd->path.mnt); ++ } ++ ++ if (last.dentry != path->dentry) ++ path_put(&last); ++ ++ return 0; ++} ++ ++/** ++ * cache_lookup_union - lookup a single pathname part from dcache ++ * ++ * This is a union mount capable version of what d_lookup() & revalidate() ++ * would do. This function returns a valid (union) dentry on success. ++ * ++ * Remember: On failure it means that parts of the union aren't cached. You ++ * should call real_lookup() afterwards to find the proper (union) dentry. ++ */ ++static int cache_lookup_union(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ int res ; ++ ++ if (!IS_MNT_UNION(nd->path.mnt)) { ++ path->dentry = cache_lookup(nd->path.dentry, name, nd); ++ path->mnt = path->dentry ? nd->path.mnt : NULL; ++ res = path->dentry ? 0 : 1; ++ } else { ++ struct path safe = { ++ .dentry = nd->path.dentry, ++ .mnt = nd->path.mnt ++ }; ++ ++ path_get(&safe); ++ res = __cache_lookup_topmost(nd, name, path); ++ if (res) ++ goto out; ++ ++ /* only directories can be part of a union stack */ ++ if (!path->dentry->d_inode || ++ !S_ISDIR(path->dentry->d_inode->i_mode)) ++ goto out; ++ ++ /* Build the union stack for this part */ ++ res = __cache_lookup_build_union(nd, name, path); ++ if (res) { ++ dput(path->dentry); ++ if (path->mnt != safe.mnt) ++ mntput(path->mnt); ++ goto out; ++ } ++ ++out: ++ path_put(&nd->path); ++ nd->path.dentry = safe.dentry; ++ nd->path.mnt = safe.mnt; ++ } ++ ++ return res; ++} ++ ++/* + * Short-cut version of permission(), for calling by + * path_walk(), when dcache lock is held. Combines parts + * of permission() and generic_permission(), and tests ONLY for +@@ -473,10 +684,11 @@ ok: + * make sure that nobody added the entry to the dcache in the meantime.. + * SMP-safe + */ +-static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd) ++static int real_lookup(struct nameidata *nd, struct qstr *name, ++ struct path *path) + { +- struct dentry * result; +- struct inode *dir = parent->d_inode; ++ struct inode *dir = nd->path.dentry->d_inode; ++ int res = 0; + + mutex_lock(&dir->i_mutex); + /* +@@ -493,27 +705,36 @@ static struct dentry * real_lookup(struc + * + * so doing d_lookup() (with seqlock), instead of lockfree __d_lookup + */ +- result = d_lookup(parent, name); +- if (!result) { ++ path->dentry = d_lookup(nd->path.dentry, name); ++ path->mnt = nd->path.mnt; ++ if (!path->dentry) { + struct dentry *dentry; + + /* Don't create child dentry for a dead directory. */ +- result = ERR_PTR(-ENOENT); +- if (IS_DEADDIR(dir)) ++ if (IS_DEADDIR(dir)) { ++ res = -ENOENT; + goto out_unlock; ++ } + +- dentry = d_alloc(parent, name); +- result = ERR_PTR(-ENOMEM); ++ dentry = d_alloc(nd->path.dentry, name); + if (dentry) { +- result = dir->i_op->lookup(dir, dentry, nd); +- if (result) ++ path->dentry = dir->i_op->lookup(dir, dentry, nd); ++ if (path->dentry) { + dput(dentry); +- else +- result = dentry; ++ if (IS_ERR(path->dentry)) { ++ res = PTR_ERR(path->dentry); ++ path->dentry = NULL; ++ path->mnt = NULL; ++ } ++ } else ++ path->dentry = dentry; ++ } else { ++ res = -ENOMEM; ++ path->mnt = NULL; + } + out_unlock: + mutex_unlock(&dir->i_mutex); +- return result; ++ return res; + } + + /* +@@ -521,12 +742,170 @@ out_unlock: + * we waited on the semaphore. Need to revalidate. + */ + mutex_unlock(&dir->i_mutex); +- if (result->d_op && result->d_op->d_revalidate) { +- result = do_revalidate(result, nd); +- if (!result) +- result = ERR_PTR(-ENOENT); ++ if (path->dentry->d_op && path->dentry->d_op->d_revalidate) { ++ path->dentry = do_revalidate(path->dentry, nd); ++ if (!path->dentry) { ++ res = -ENOENT; ++ path->mnt = NULL; ++ } ++ if (IS_ERR(path->dentry)) { ++ res = PTR_ERR(path->dentry); ++ path->dentry = NULL; ++ path->mnt = NULL; ++ } + } +- return result; ++ ++ return res; ++} ++ ++/** ++ * __real_lookup_topmost - lookup topmost dentry, non-cached version ++ * ++ * If we reach a dentry with restricted access, we just stop the lookup ++ * because we shouldn't see through that dentry. Same thing for dentry ++ * type mismatch and whiteouts. ++ * ++ * FIXME: ++ * - handle union stacks in use ++ * - handle union stacks mounted upon union stacks ++ * - avoid unnecessary allocations of union locks ++ */ ++static int __real_lookup_topmost(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct path next; ++ int err; ++ ++ err = real_lookup(nd, name, path); ++ if (err) ++ return err; ++ ++ if (path->dentry->d_inode || d_is_whiteout(path->dentry)) ++ return 0; ++ ++ if (IS_OPAQUE(nd->path.dentry->d_inode) && !d_is_fallthru(path->dentry)) ++ return 0; ++ ++ while (follow_union_down(&nd->path)) { ++ name->hash = full_name_hash(name->name, name->len); ++ if (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) { ++ err = nd->path.dentry->d_op->d_hash(nd->path.dentry, ++ name); ++ if (err < 0) ++ goto out; ++ } ++ ++ err = real_lookup(nd, name, &next); ++ if (err) ++ goto out; ++ ++ if (next.dentry->d_inode || d_is_whiteout(next.dentry)) { ++ dput(path->dentry); ++ mntget(next.mnt); ++ *path = next; ++ goto out; ++ } ++ ++ if (IS_OPAQUE(nd->path.dentry->d_inode) && !d_is_fallthru(next.dentry)) ++ goto out; ++ ++ dput(next.dentry); ++ } ++out: ++ if (err) ++ dput(path->dentry); ++ return err; ++} ++ ++/** ++ * __real_lookup_build_union: build the union stack for this pathname ++ * part, non-cached version ++ * ++ * Called when not all parts of the union stack are in cache ++ */ ++ ++static int __real_lookup_build_union(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct path last = *path; ++ struct path next; ++ int err = 0; ++ ++ while (follow_union_down(&nd->path)) { ++ /* We need to recompute the hash for lower layer lookups */ ++ name->hash = full_name_hash(name->name, name->len); ++ if (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) { ++ err = nd->path.dentry->d_op->d_hash(nd->path.dentry, ++ name); ++ if (err < 0) ++ goto out; ++ } ++ ++ err = real_lookup(nd, name, &next); ++ if (err) ++ goto out; ++ ++ if (d_is_whiteout(next.dentry)) { ++ dput(next.dentry); ++ break; ++ } ++ ++ if (!next.dentry->d_inode) { ++ dput(next.dentry); ++ continue; ++ } ++ ++ /* only directories can be part of a union stack */ ++ if (!S_ISDIR(next.dentry->d_inode->i_mode)) { ++ dput(next.dentry); ++ break; ++ } ++ ++ /* now we know we found something "real" */ ++ append_to_union(last.mnt, last.dentry, next.mnt, next.dentry); ++ ++ if (last.dentry != path->dentry) ++ path_put(&last); ++ last.dentry = next.dentry; ++ last.mnt = mntget(next.mnt); ++ } ++ ++ if (last.dentry != path->dentry) ++ path_put(&last); ++out: ++ return err; ++} ++ ++static int real_lookup_union(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct path safe = { .dentry = nd->path.dentry, .mnt = nd->path.mnt }; ++ int res ; ++ ++ path_get(&safe); ++ res = __real_lookup_topmost(nd, name, path); ++ if (res) ++ goto out; ++ ++ /* only directories can be part of a union stack */ ++ if (!path->dentry->d_inode || ++ !S_ISDIR(path->dentry->d_inode->i_mode)) ++ goto out; ++ ++ /* Build the union stack for this part */ ++ res = __real_lookup_build_union(nd, name, path); ++ if (res) { ++ dput(path->dentry); ++ if (path->mnt != safe.mnt) ++ mntput(path->mnt); ++ goto out; ++ } ++ ++out: ++ path_put(&nd->path); ++ nd->path.dentry = safe.dentry; ++ nd->path.mnt = safe.mnt; ++ return res; + } + + /* +@@ -629,11 +1008,8 @@ static __always_inline int __do_follow_l + touch_atime(path->mnt, dentry); + nd_set_link(nd, NULL); + +- if (path->mnt != nd->path.mnt) { +- path_to_nameidata(path, nd); +- dget(dentry); +- } +- mntget(path->mnt); ++ if (path->mnt == nd->path.mnt) ++ mntget(nd->path.mnt); + cookie = dentry->d_inode->i_op->follow_link(dentry, nd); + error = PTR_ERR(cookie); + if (!IS_ERR(cookie)) { +@@ -721,7 +1097,7 @@ static int __follow_mount(struct path *p + return res; + } + +-static void follow_mount(struct path *path) ++void follow_mount(struct path *path) + { + while (d_mountpoint(path->dentry)) { + struct vfsmount *mounted = lookup_mnt(path); +@@ -786,6 +1162,7 @@ static __always_inline void follow_dotdo + nd->path.mnt = parent; + } + follow_mount(&nd->path); ++ follow_union_mount(&nd->path); + } + + /* +@@ -796,35 +1173,55 @@ static __always_inline void follow_dotdo + static int do_lookup(struct nameidata *nd, struct qstr *name, + struct path *path) + { +- struct vfsmount *mnt = nd->path.mnt; +- struct dentry *dentry = __d_lookup(nd->path.dentry, name); ++ int err; ++ ++ if (IS_MNT_UNION(nd->path.mnt)) ++ goto need_union_lookup; + +- if (!dentry) ++ path->dentry = __d_lookup(nd->path.dentry, name); ++ path->mnt = nd->path.mnt; ++ if (!path->dentry) + goto need_lookup; +- if (dentry->d_op && dentry->d_op->d_revalidate) ++ if (path->dentry->d_op && path->dentry->d_op->d_revalidate) + goto need_revalidate; ++ + done: +- path->mnt = mnt; +- path->dentry = dentry; +- __follow_mount(path); ++ if (nd->path.mnt != path->mnt) { ++ nd->um_flags |= LAST_LOWLEVEL; ++ follow_mount(path); ++ } else ++ __follow_mount(path); ++ follow_union_mount(path); + return 0; + + need_lookup: +- dentry = real_lookup(nd->path.dentry, name, nd); +- if (IS_ERR(dentry)) ++ err = real_lookup(nd, name, path); ++ if (err) ++ goto fail; ++ goto done; ++ ++need_union_lookup: ++ err = cache_lookup_union(nd, name, path); ++ if (!err && path->dentry) ++ goto done; ++ ++ err = real_lookup_union(nd, name, path); ++ if (err) + goto fail; + goto done; + + need_revalidate: +- dentry = do_revalidate(dentry, nd); +- if (!dentry) ++ path->dentry = do_revalidate(path->dentry, nd); ++ if (!path->dentry) + goto need_lookup; +- if (IS_ERR(dentry)) ++ if (IS_ERR(path->dentry)) { ++ err = PTR_ERR(path->dentry); + goto fail; ++ } + goto done; + + fail: +- return PTR_ERR(dentry); ++ return err; + } + + /* +@@ -851,6 +1248,8 @@ static int __link_path_walk(const char * + if (nd->depth) + lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE); + ++ follow_union_mount(&nd->path); ++ + /* At this point we know we have a real path component. */ + for(;;) { + unsigned long hash; +@@ -913,6 +1312,44 @@ static int __link_path_walk(const char * + if (err) + break; + ++ /* ++ * We want to create this element on the top level ++ * file system in two cases: ++ * ++ * - We are specifically told to - LOOKUP_TOPMOST. ++ * - This is a directory, and it does not yet exist on ++ * the top level. Various tricks only work if ++ * directories always exist on the top level. ++ * ++ * In either case, only create this element on the top ++ * level if the last element is located on the lower ++ * level. If the last element is located on the top ++ * level, then every single element in the path ++ * already exists on the top level. ++ * ++ * Note that we can assume that the parent is on the ++ * top level since we always create the directory on ++ * the top level. ++ */ ++ ++ if ((nd->um_flags & LAST_LOWLEVEL) && ++ ((next.dentry->d_inode && ++ S_ISDIR(next.dentry->d_inode->i_mode) && ++ (nd->path.mnt != next.mnt)) || ++ (nd->flags & LOOKUP_TOPMOST))) { ++ struct dentry *dentry; ++ ++ dentry = union_create_topmost(nd, &this, &next); ++ if (IS_ERR(dentry)) { ++ err = PTR_ERR(dentry); ++ goto out_dput; ++ } ++ path_put_conditional(&next, nd); ++ next.mnt = nd->path.mnt; ++ next.dentry = dentry; ++ nd->um_flags &= ~LAST_LOWLEVEL; ++ } ++ + err = -ENOENT; + inode = next.dentry->d_inode; + if (!inode) +@@ -962,6 +1399,25 @@ last_component: + err = do_lookup(nd, &this, &next); + if (err) + break; ++ ++ if ((nd->um_flags & LAST_LOWLEVEL) && ++ ((next.dentry->d_inode && ++ S_ISDIR(next.dentry->d_inode->i_mode) && ++ (nd->path.mnt != next.mnt)) || ++ (nd->flags & LOOKUP_TOPMOST))) { ++ struct dentry *dentry; ++ ++ dentry = union_create_topmost(nd, &this, &next); ++ if (IS_ERR(dentry)) { ++ err = PTR_ERR(dentry); ++ goto out_dput; ++ } ++ path_put_conditional(&next, nd); ++ next.mnt = nd->path.mnt; ++ next.dentry = dentry; ++ nd->um_flags &= ~LAST_LOWLEVEL; ++ } ++ + inode = next.dentry->d_inode; + if ((lookup_flags & LOOKUP_FOLLOW) + && inode && inode->i_op->follow_link) { +@@ -1029,6 +1485,7 @@ static int path_init(int dfd, const char + + nd->last_type = LAST_ROOT; /* if there are only slashes... */ + nd->flags = flags; ++ nd->um_flags = 0; + nd->depth = 0; + nd->root.mnt = NULL; + +@@ -1172,61 +1629,437 @@ static int path_lookup_open(int dfd, con + } + + static struct dentry *__lookup_hash(struct qstr *name, +- struct dentry *base, struct nameidata *nd) ++ struct dentry *base, struct nameidata *nd) ++{ ++ struct dentry *dentry; ++ struct inode *inode; ++ int err; ++ ++ inode = base->d_inode; ++ ++ /* ++ * See if the low-level filesystem might want ++ * to use its own hash.. ++ */ ++ if (base->d_op && base->d_op->d_hash) { ++ err = base->d_op->d_hash(base, name); ++ dentry = ERR_PTR(err); ++ if (err < 0) ++ goto out; ++ } ++ ++ dentry = cache_lookup(base, name, nd); ++ if (!dentry) { ++ struct dentry *new; ++ ++ /* Don't create child dentry for a dead directory. */ ++ dentry = ERR_PTR(-ENOENT); ++ if (IS_DEADDIR(inode)) ++ goto out; ++ ++ new = d_alloc(base, name); ++ dentry = ERR_PTR(-ENOMEM); ++ if (!new) ++ goto out; ++ dentry = inode->i_op->lookup(inode, new, nd); ++ if (!dentry) ++ dentry = new; ++ else ++ dput(new); ++ } ++out: ++ return dentry; ++} ++ ++/* ++ * Restricted form of lookup. Doesn't follow links, single-component only, ++ * needs parent already locked. Doesn't follow mounts. ++ * SMP-safe. ++ */ ++static int lookup_hash(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ int err; ++ ++ err = inode_permission(nd->path.dentry->d_inode, MAY_EXEC); ++ if (err) ++ return err; ++ path->mnt = nd->path.mnt; ++ path->dentry = __lookup_hash(name, nd->path.dentry, nd); ++ if (IS_ERR(path->dentry)) { ++ err = PTR_ERR(path->dentry); ++ path->dentry = NULL; ++ path->mnt = NULL; ++ } ++ return err; ++} ++ ++static int __hash_lookup_topmost(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct path next; ++ int err; ++ ++ err = lookup_hash(nd, name, path); ++ if (err) ++ return err; ++ ++ if (path->dentry->d_inode || d_is_whiteout(path->dentry)) ++ return 0; ++ ++ if (IS_OPAQUE(nd->path.dentry->d_inode) && !d_is_fallthru(path->dentry)) ++ return 0; ++ ++ while (follow_union_down(&nd->path)) { ++ name->hash = full_name_hash(name->name, name->len); ++ if (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) { ++ err = nd->path.dentry->d_op->d_hash(nd->path.dentry, ++ name); ++ if (err < 0) ++ goto out; ++ } ++ ++ mutex_lock(&nd->path.dentry->d_inode->i_mutex); ++ err = lookup_hash(nd, name, &next); ++ mutex_unlock(&nd->path.dentry->d_inode->i_mutex); ++ if (err) ++ goto out; ++ ++ if (next.dentry->d_inode || d_is_whiteout(next.dentry)) { ++ dput(path->dentry); ++ mntget(next.mnt); ++ *path = next; ++ goto out; ++ } ++ ++ if (IS_OPAQUE(nd->path.dentry->d_inode) && !d_is_fallthru(next.dentry)) ++ goto out; ++ ++ dput(next.dentry); ++ } ++out: ++ if (err) ++ dput(path->dentry); ++ return err; ++} ++ ++static int __hash_lookup_build_union(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct path last = *path; ++ struct path next; ++ int err = 0; ++ ++ while (follow_union_down(&nd->path)) { ++ /* We need to recompute the hash for lower layer lookups */ ++ name->hash = full_name_hash(name->name, name->len); ++ if (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) { ++ err = nd->path.dentry->d_op->d_hash(nd->path.dentry, ++ name); ++ if (err < 0) ++ goto out; ++ } ++ ++ mutex_lock(&nd->path.dentry->d_inode->i_mutex); ++ err = lookup_hash(nd, name, &next); ++ mutex_unlock(&nd->path.dentry->d_inode->i_mutex); ++ if (err) ++ goto out; ++ ++ if (d_is_whiteout(next.dentry)) { ++ dput(next.dentry); ++ break; ++ } ++ ++ if (!next.dentry->d_inode) { ++ dput(next.dentry); ++ continue; ++ } ++ ++ /* only directories can be part of a union stack */ ++ if (!S_ISDIR(next.dentry->d_inode->i_mode)) { ++ dput(next.dentry); ++ break; ++ } ++ ++ /* now we know we found something "real" */ ++ append_to_union(last.mnt, last.dentry, next.mnt, next.dentry); ++ ++ if (last.dentry != path->dentry) ++ path_put(&last); ++ last.dentry = next.dentry; ++ last.mnt = mntget(next.mnt); ++ } ++ ++ if (last.dentry != path->dentry) ++ path_put(&last); ++out: ++ return err; ++} ++ ++int hash_lookup_union(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct path safe = { .dentry = nd->path.dentry, .mnt = nd->path.mnt }; ++ int res ; ++ ++ path_get(&safe); ++ res = __hash_lookup_topmost(nd, name, path); ++ if (res) ++ goto out; ++ ++ /* only directories can be part of a union stack */ ++ if (!path->dentry->d_inode || ++ !S_ISDIR(path->dentry->d_inode->i_mode)) ++ goto out; ++ ++ /* Build the union stack for this part */ ++ res = __hash_lookup_build_union(nd, name, path); ++ if (res) { ++ dput(path->dentry); ++ if (path->mnt != safe.mnt) ++ mntput(path->mnt); ++ goto out; ++ } ++ ++out: ++ path_put(&nd->path); ++ nd->path.dentry = safe.dentry; ++ nd->path.mnt = safe.mnt; ++ return res; ++} ++ ++/** ++ * do_union_hash_lookup() - walk down the union stack and lookup_hash() ++ * @nd: nameidata of parent to lookup from ++ * @name: pathname component to lookup ++ * @path: path to store result of lookup in ++ * ++ * Walk down the union stack and search for single pathname component name. It ++ * is assumed that the caller already did a lookup_hash() in the topmost parent ++ * that gave negative lookup result. Therefore this does call lookup_hash() in ++ * every lower layer (!) of the union stack. If a directory is found the union ++ * stack for that is assembled as well. ++ * ++ * Note: ++ * The caller needs to take care of holding a valid reference to the topmost ++ * parent. ++ * On error we leave @path untouched as well as when we don't find anything. ++ */ ++static int do_union_hash_lookup(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct path next; ++ int err = 0; ++ ++ while (follow_union_down(&nd->path)) { ++ /* rehash because of d_op->d_hash() by the previous layer */ ++ name->hash = full_name_hash(name->name, name->len); ++ ++ mutex_lock(&nd->path.dentry->d_inode->i_mutex); ++ err = lookup_hash(nd, name, &next); ++ mutex_unlock(&nd->path.dentry->d_inode->i_mutex); ++ ++ if (err) ++ break; ++ ++ if (next.dentry->d_inode) { ++ mntget(next.mnt); ++ if (!S_ISDIR(next.dentry->d_inode->i_mode)) { ++ *path = next; ++ break; ++ } ++ err = __hash_lookup_build_union(nd, name, &next); ++ if (err) ++ path_put(&next); ++ else ++ *path = next; ++ break; ++ } ++ ++ path_put_conditional(&next, nd); ++ ++ if ((IS_OPAQUE(nd->path.dentry->d_inode) && ++ !d_is_fallthru(next.dentry)) || ++ d_is_whiteout(next.dentry)) ++ break; ++ } ++ ++ return err; ++} ++ ++/** ++ * _hash_lookup_union() - lookup single pathname component ++ * @nd: nameidata of parent to lookup from ++ * @name: pathname component to lookup ++ * @path: path to store result of lookup in ++ * ++ * Returns the topmost parent locked and the target dentry found in the union ++ * or the topmost negative target dentry otherwise. ++ * ++ * Note: ++ * Returns topmost parent locked even on error. ++ */ ++static int _hash_lookup_union(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct path parent = nd->path; ++ struct path topmost; ++ int err; ++ ++ mutex_lock(&nd->path.dentry->d_inode->i_mutex); ++ err = lookup_hash(nd, name, path); ++ if (err) ++ return err; ++ ++ /* return if we found something and it isn't a directory we are done */ ++ if (path->dentry->d_inode && !S_ISDIR(path->dentry->d_inode->i_mode)) ++ return 0; ++ ++ /* stop lookup if the parent directory is marked opaque */ ++ if ((IS_OPAQUE(nd->path.dentry->d_inode) && ++ !d_is_fallthru(path->dentry)) || ++ d_is_whiteout(path->dentry)) ++ return 0; ++ ++ if (!strcmp(path->mnt->mnt_sb->s_type->name, "proc") || ++ !strcmp(path->mnt->mnt_sb->s_type->name, "sysfs")) ++ return 0; ++ ++ mutex_unlock(&nd->path.dentry->d_inode->i_mutex); ++ ++ /* ++ * safe a reference to the topmost parent for walking the union stack ++ */ ++ path_get(&parent); ++ topmost = *path; ++ ++ if (path->dentry->d_inode && S_ISDIR(path->dentry->d_inode->i_mode)) { ++ err = __hash_lookup_build_union(nd, name, path); ++ if (err) ++ goto err_lock_parent; ++ goto out_lock_and_revalidate_parent; ++ } ++ ++ err = do_union_hash_lookup(nd, name, path); ++ if (err) ++ goto err_lock_parent; ++ ++out_lock_and_revalidate_parent: ++ /* seems that we haven't found anything, so return the topmost */ ++ path_to_nameidata(&parent, nd); ++ mutex_lock(&nd->path.dentry->d_inode->i_mutex); ++ ++ if (topmost.dentry == path->dentry) { ++ spin_lock(&path->dentry->d_lock); ++ if (nd->path.dentry != path->dentry->d_parent) { ++ spin_unlock(&path->dentry->d_lock); ++ dput(path->dentry); ++ name->hash = full_name_hash(name->name, name->len); ++ err = lookup_hash(nd, name, path); ++ if (err) ++ return err; ++ /* FIXME: What if we find a directory here ... */ ++ return err; ++ } ++ spin_unlock(&path->dentry->d_lock); ++ } else ++ dput(topmost.dentry); ++ ++ return 0; ++ ++err_lock_parent: ++ path_to_nameidata(&parent, nd); ++ path_put_conditional(path, nd); ++ mutex_lock(&nd->path.dentry->d_inode->i_mutex); ++ return err; ++} ++ ++/** ++ * lookup_rename_source() - lookup the source used by rename ++ * ++ * This is a special version of _hash_lookup_union() which becomes necessary ++ * for finding the source of a rename on union mounts. ++ * ++ * See comment for _hash_lookup_union() above. ++ */ ++static int lookup_rename_source(struct nameidata *oldnd, ++ struct nameidata *newnd, ++ struct dentry **trap, struct qstr *name, ++ struct path *old) + { +- struct dentry *dentry; +- struct inode *inode; ++ struct path parent = oldnd->path; ++ struct path topmost; + int err; + +- inode = base->d_inode; ++ err = lookup_hash(oldnd, name, old); ++ if (err) ++ return err; ++ ++ /* return if we found something and it isn't a directory we are done */ ++ if (old->dentry->d_inode && !S_ISDIR(old->dentry->d_inode->i_mode)) ++ return 0; ++ ++ /* stop lookup if the parent directory is marked opaque */ ++ if ((IS_OPAQUE(oldnd->path.dentry->d_inode) && ++ !d_is_fallthru(old->dentry)) || ++ d_is_whiteout(old->dentry)) ++ return 0; ++ ++ if (!strcmp(old->mnt->mnt_sb->s_type->name, "proc") || ++ !strcmp(old->mnt->mnt_sb->s_type->name, "sysfs")) ++ return 0; ++ ++ unlock_rename(oldnd->path.dentry, newnd->path.dentry); + + /* +- * See if the low-level filesystem might want +- * to use its own hash.. ++ * safe a reference to the topmost parent for walking the union stack + */ +- if (base->d_op && base->d_op->d_hash) { +- err = base->d_op->d_hash(base, name); +- dentry = ERR_PTR(err); +- if (err < 0) +- goto out; ++ path_get(&parent); ++ topmost = *old; ++ ++ if (old->dentry->d_inode && S_ISDIR(old->dentry->d_inode->i_mode)) { ++ err = __hash_lookup_build_union(oldnd, name, old); ++ if (err) ++ goto err_lock; ++ goto out_lock_and_revalidate_parent; + } + +- dentry = cached_lookup(base, name, nd); +- if (!dentry) { +- struct dentry *new; ++ err = do_union_hash_lookup(oldnd, name, old); ++ if (err) ++ goto err_lock; + +- /* Don't create child dentry for a dead directory. */ +- dentry = ERR_PTR(-ENOENT); +- if (IS_DEADDIR(inode)) +- goto out; ++out_lock_and_revalidate_parent: ++ path_to_nameidata(&parent, oldnd); ++ *trap = lock_rename(oldnd->path.dentry, newnd->path.dentry); + +- new = d_alloc(base, name); +- dentry = ERR_PTR(-ENOMEM); +- if (!new) +- goto out; +- dentry = inode->i_op->lookup(inode, new, nd); +- if (!dentry) +- dentry = new; +- else +- dput(new); +- } +-out: +- return dentry; +-} ++ /* ++ * If we return the topmost dentry we have to make sure that it has not ++ * been moved away while we gave up the topmost parents i_mutex lock. ++ */ ++ if (topmost.dentry == old->dentry) { ++ spin_lock(&old->dentry->d_lock); ++ if (oldnd->path.dentry != old->dentry->d_parent) { ++ spin_unlock(&old->dentry->d_lock); ++ dput(old->dentry); ++ name->hash = full_name_hash(name->name, name->len); ++ err = lookup_hash(oldnd, name, old); ++ if (err) ++ return err; ++ /* FIXME: What if we find a directory here ... */ ++ return err; ++ } ++ spin_unlock(&old->dentry->d_lock); ++ } else ++ dput(topmost.dentry); + +-/* +- * Restricted form of lookup. Doesn't follow links, single-component only, +- * needs parent already locked. Doesn't follow mounts. +- * SMP-safe. +- */ +-static struct dentry *lookup_hash(struct nameidata *nd) +-{ +- int err; ++ return 0; + +- err = inode_permission(nd->path.dentry->d_inode, MAY_EXEC); +- if (err) +- return ERR_PTR(err); +- return __lookup_hash(&nd->last, nd->path.dentry, nd); ++err_lock: ++ path_to_nameidata(&parent, oldnd); ++ path_put_conditional(old, oldnd); ++ *trap = lock_rename(oldnd->path.dentry, newnd->path.dentry); ++ return err; + } + + static int __lookup_one_len(const char *name, struct qstr *this, +@@ -1502,8 +2335,9 @@ int vfs_create(struct inode *dir, struct + return error; + } + +-int may_open(struct path *path, int acc_mode, int flag) ++int may_open(struct nameidata *nd, int acc_mode, int flag) + { ++ struct path *path = &nd->path; + struct dentry *dentry = path->dentry; + struct inode *inode = dentry->d_inode; + int error; +@@ -1529,7 +2363,7 @@ int may_open(struct path *path, int acc_ + break; + } + +- error = inode_permission(inode, acc_mode); ++ error = union_permission(path, acc_mode); + if (error) + return error; + +@@ -1577,6 +2411,9 @@ int may_open(struct path *path, int acc_ + if (!error) + error = security_path_truncate(path, 0, + ATTR_MTIME|ATTR_CTIME|ATTR_OPEN); ++ /* XXX don't copy up file data */ ++ if (is_unionized(path->dentry, path->mnt)) ++ error = union_copyup(nd, flag /* XXX not used */); + if (!error) { + vfs_dq_init(inode); + +@@ -1623,7 +2460,7 @@ out_unlock: + if (error) + return error; + /* Don't check for write permission, don't truncate */ +- return may_open(&nd->path, 0, flag & ~O_TRUNC); ++ return may_open(nd, 0, flag & ~O_TRUNC); + } + + /* +@@ -1738,12 +2575,10 @@ struct file *do_filp_open(int dfd, const + if (flag & O_EXCL) + nd.flags |= LOOKUP_EXCL; + mutex_lock(&dir->d_inode->i_mutex); +- path.dentry = lookup_hash(&nd); +- path.mnt = nd.path.mnt; ++ error = hash_lookup_union(&nd, &nd.last, &path); + + do_last: +- error = PTR_ERR(path.dentry); +- if (IS_ERR(path.dentry)) { ++ if (error) { + mutex_unlock(&dir->d_inode->i_mutex); + goto exit; + } +@@ -1803,10 +2638,23 @@ do_last: + if (path.dentry->d_inode->i_op->follow_link) + goto do_link; + +- path_to_nameidata(&path, &nd); + error = -EISDIR; + if (path.dentry->d_inode && S_ISDIR(path.dentry->d_inode->i_mode)) +- goto exit; ++ goto exit_dput; ++ ++ /* ++ * If this file is on a lower layer of the union stack, copy it to the ++ * topmost layer before opening it ++ */ ++ if (path.dentry->d_inode && ++ (path.dentry->d_parent != dir) && ++ S_ISREG(path.dentry->d_inode->i_mode)) { ++ error = __union_copyup(&path, &nd, &path); ++ if (error) ++ goto exit_dput; ++ } ++ ++ path_to_nameidata(&path, &nd); + ok: + /* + * Consider: +@@ -1824,12 +2672,18 @@ ok: + if (error) + goto exit; + } +- error = may_open(&nd.path, acc_mode, flag); ++ error = may_open(&nd, acc_mode, flag); + if (error) { + if (will_write) + mnt_drop_write(nd.path.mnt); + goto exit; + } ++ /* Okay, all permissions go, now copy up */ ++ if (!(flag & O_CREAT) && (flag & FMODE_WRITE)) { ++ error = union_copyup(&nd, flag /* XXX not used */); ++ if (error) ++ goto exit; ++ } + filp = nameidata_to_filp(&nd, open_flag); + if (IS_ERR(filp)) + ima_counts_put(&nd.path, +@@ -1904,8 +2758,7 @@ do_link: + } + dir = nd.path.dentry; + mutex_lock(&dir->d_inode->i_mutex); +- path.dentry = lookup_hash(&nd); +- path.mnt = nd.path.mnt; ++ error = hash_lookup_union(&nd, &nd.last, &path); + __putname(nd.last.name); + goto do_last; + } +@@ -1939,7 +2792,8 @@ EXPORT_SYMBOL(filp_open); + */ + struct dentry *lookup_create(struct nameidata *nd, int is_dir) + { +- struct dentry *dentry = ERR_PTR(-EEXIST); ++ struct path path = { .dentry = ERR_PTR(-EEXIST) } ; ++ int err; + + mutex_lock_nested(&nd->path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); + /* +@@ -1955,11 +2809,13 @@ struct dentry *lookup_create(struct name + /* + * Do the final lookup. + */ +- dentry = lookup_hash(nd); +- if (IS_ERR(dentry)) ++ err = hash_lookup_union(nd, &nd->last, &path); ++ if (err) { ++ path.dentry = ERR_PTR(err); + goto fail; ++ } + +- if (dentry->d_inode) ++ if (path.dentry->d_inode) + goto eexist; + /* + * Special case - lookup gave negative, but... we had foo/bar/ +@@ -1968,15 +2824,17 @@ struct dentry *lookup_create(struct name + * been asking for (non-existent) directory. -ENOENT for you. + */ + if (unlikely(!is_dir && nd->last.name[nd->last.len])) { +- dput(dentry); +- dentry = ERR_PTR(-ENOENT); ++ path_put_conditional(&path, nd); ++ path.dentry = ERR_PTR(-ENOENT); + } +- return dentry; ++ if (nd->path.mnt != path.mnt) ++ mntput(path.mnt); ++ return path.dentry; + eexist: +- dput(dentry); +- dentry = ERR_PTR(-EEXIST); ++ path_put_conditional(&path, nd); ++ path.dentry = ERR_PTR(-EEXIST); + fail: +- return dentry; ++ return path.dentry; + } + EXPORT_SYMBOL_GPL(lookup_create); + +@@ -2088,6 +2946,7 @@ SYSCALL_DEFINE3(mknod, const char __user + int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) + { + int error = may_create(dir, dentry); ++ int opaque = 0; + + if (error) + return error; +@@ -2101,9 +2960,18 @@ int vfs_mkdir(struct inode *dir, struct + return error; + + vfs_dq_init(dir); ++ ++ if (d_is_whiteout(dentry)) ++ opaque = 1; ++ + error = dir->i_op->mkdir(dir, dentry, mode); +- if (!error) ++ if (!error) { + fsnotify_mkdir(dir, dentry); ++ if (opaque) { ++ dentry->d_inode->i_flags |= S_OPAQUE; ++ mark_inode_dirty(dentry->d_inode); ++ } ++ } + return error; + } + +@@ -2149,6 +3017,212 @@ SYSCALL_DEFINE2(mkdir, const char __user + return sys_mkdirat(AT_FDCWD, pathname, mode); + } + ++ ++/* Checks on the victim for whiteout */ ++static inline int may_whiteout(struct inode *dir, struct dentry *victim, ++ int isdir) ++{ ++ int err; ++ ++ /* from may_create() */ ++ if (IS_DEADDIR(dir)) ++ return -ENOENT; ++ err = inode_permission(dir, MAY_WRITE | MAY_EXEC); ++ if (err) ++ return err; ++ ++ /* from may_delete() */ ++ if (IS_APPEND(dir)) ++ return -EPERM; ++ if (!victim->d_inode) ++ return 0; ++ if (check_sticky(dir, victim->d_inode) || ++ IS_APPEND(victim->d_inode) || ++ IS_IMMUTABLE(victim->d_inode)) ++ return -EPERM; ++ if (isdir) { ++ if (!S_ISDIR(victim->d_inode->i_mode)) ++ return -ENOTDIR; ++ if (IS_ROOT(victim)) ++ return -EBUSY; ++ } else if (S_ISDIR(victim->d_inode->i_mode)) ++ return -EISDIR; ++ if (victim->d_flags & DCACHE_NFSFS_RENAMED) ++ return -EBUSY; ++ return 0; ++} ++ ++/** ++ * vfs_whiteout: creates a white-out for the given directory entry ++ * @dir: parent inode ++ * @dentry: directory entry to white-out ++ * ++ * Simply white-out a given directory entry. This functionality is usually used ++ * in the sense of unlink. Therefore the given dentry can still be in-use and ++ * contains an in-use inode. The filesystem has to do what unlink or rmdir ++ * would in that case. Since the dentry still might be in-use we have to ++ * provide a fresh unhashed dentry that whiteout can fill the new inode into. ++ * In that case the given dentry is dropped and the fresh dentry containing the ++ * whiteout is rehashed instead. If the given dentry is unused, the whiteout ++ * inode is instantiated into it instead. ++ * ++ * After this returns with success, don't make any assumptions about the inode. ++ * Just dput() it dentry. ++ */ ++static int vfs_whiteout(struct inode *dir, struct dentry *dentry, int isdir) ++{ ++ int err; ++ struct inode *old_inode = dentry->d_inode; ++ struct dentry *parent, *whiteout; ++ ++ err = may_whiteout(dir, dentry, isdir); ++ if (err) ++ return err; ++ ++ BUG_ON(dentry->d_parent->d_inode != dir); ++ ++ if (!dir->i_op || !dir->i_op->whiteout) ++ return -EOPNOTSUPP; ++ ++ if (old_inode) { ++ vfs_dq_init(dir); ++ ++ mutex_lock(&old_inode->i_mutex); ++ if (isdir) ++ dentry_unhash(dentry); ++ if (d_mountpoint(dentry)) ++ err = -EBUSY; ++ else { ++ if (isdir) ++ err = security_inode_rmdir(dir, dentry); ++ else ++ err = security_inode_unlink(dir, dentry); ++ } ++ } ++ ++ parent = dget_parent(dentry); ++ whiteout = d_alloc_name(parent, dentry->d_name.name); ++ ++ if (!err) ++ err = dir->i_op->whiteout(dir, dentry, whiteout); ++ ++ if (old_inode) { ++ mutex_unlock(&old_inode->i_mutex); ++ if (!err) { ++ fsnotify_link_count(old_inode); ++ d_delete(dentry); ++ } ++ if (isdir) ++ dput(dentry); ++ } ++ ++ dput(whiteout); ++ dput(parent); ++ return err; ++} ++ ++int path_whiteout(struct path *dir_path, struct dentry *dentry, int isdir) ++{ ++ int error = mnt_want_write(dir_path->mnt); ++ ++ if (!error) { ++ error = vfs_whiteout(dir_path->dentry->d_inode, dentry, isdir); ++ mnt_drop_write(dir_path->mnt); ++ } ++ ++ return error; ++} ++EXPORT_SYMBOL(path_whiteout); ++ ++/* ++ * This is abusing readdir to check if a union directory is logically empty. ++ * Al Viro barfed when he saw this, but Val said: "Well, at this point I'm ++ * aiming for working, pretty can come later" ++ */ ++static int filldir_is_empty(void *__buf, const char *name, int namlen, ++ loff_t offset, u64 ino, unsigned int d_type) ++{ ++ int *is_empty = (int *)__buf; ++ ++ switch (namlen) { ++ case 2: ++ if (name[1] != '.') ++ break; ++ case 1: ++ if (name[0] != '.') ++ break; ++ return 0; ++ } ++ ++ if (d_type == DT_WHT) ++ return 0; ++ ++ (*is_empty) = 0; ++ return 0; ++} ++ ++static int directory_is_empty(struct dentry *dentry, struct vfsmount *mnt) ++{ ++ struct file *file; ++ int err; ++ int is_empty = 1; ++ ++ BUG_ON(!S_ISDIR(dentry->d_inode->i_mode)); ++ ++ /* references for the file pointer */ ++ dget(dentry); ++ mntget(mnt); ++ ++ file = dentry_open(dentry, mnt, O_RDONLY, current_cred()); ++ if (IS_ERR(file)) ++ return 0; ++ ++ err = vfs_readdir(file, filldir_is_empty, &is_empty); ++ ++ fput(file); ++ return is_empty; ++} ++ ++static int do_whiteout(struct nameidata *nd, struct path *path, int isdir) ++{ ++ struct path safe = { .dentry = dget(nd->path.dentry), ++ .mnt = mntget(nd->path.mnt) }; ++ struct dentry *dentry = path->dentry; ++ int err; ++ ++ err = may_whiteout(nd->path.dentry->d_inode, dentry, isdir); ++ if (err) ++ goto out; ++ ++ err = -ENOENT; ++ if (!dentry->d_inode) ++ goto out; ++ ++ err = -ENOTEMPTY; ++ if (isdir && !directory_is_empty(path->dentry, path->mnt)) ++ goto out; ++ ++ if (nd->path.dentry != dentry->d_parent) { ++ dentry = __lookup_hash(&path->dentry->d_name, nd->path.dentry, ++ nd); ++ err = PTR_ERR(dentry); ++ if (IS_ERR(dentry)) ++ goto out; ++ ++ dput(path->dentry); ++ if (path->mnt != safe.mnt) ++ mntput(path->mnt); ++ path->mnt = nd->path.mnt; ++ path->dentry = dentry; ++ } ++ ++ err = vfs_whiteout(nd->path.dentry->d_inode, dentry, isdir); ++ ++out: ++ path_put(&safe); ++ return err; ++} ++ + /* + * We try to drop the dentry early: we should have + * a usage count of 2 if we're the only user of this +@@ -2213,7 +3287,7 @@ static long do_rmdir(int dfd, const char + { + int error = 0; + char * name; +- struct dentry *dentry; ++ struct path path; + struct nameidata nd; + + error = user_path_parent(dfd, pathname, &nd, &name); +@@ -2235,21 +3309,24 @@ static long do_rmdir(int dfd, const char + nd.flags &= ~LOOKUP_PARENT; + + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); +- dentry = lookup_hash(&nd); +- error = PTR_ERR(dentry); +- if (IS_ERR(dentry)) ++ error = hash_lookup_union(&nd, &nd.last, &path); ++ if (error) + goto exit2; ++ if (is_unionized(nd.path.dentry, nd.path.mnt)) { ++ error = do_whiteout(&nd, &path, 1); ++ goto exit3; ++ } + error = mnt_want_write(nd.path.mnt); + if (error) + goto exit3; +- error = security_path_rmdir(&nd.path, dentry); ++ error = security_path_rmdir(&nd.path, path.dentry); + if (error) + goto exit4; +- error = vfs_rmdir(nd.path.dentry->d_inode, dentry); ++ error = vfs_rmdir(nd.path.dentry->d_inode, path.dentry); + exit4: + mnt_drop_write(nd.path.mnt); + exit3: +- dput(dentry); ++ path_put_conditional(&path, &nd); + exit2: + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + exit1: +@@ -2304,7 +3381,7 @@ static long do_unlinkat(int dfd, const c + { + int error; + char *name; +- struct dentry *dentry; ++ struct path path; + struct nameidata nd; + struct inode *inode = NULL; + +@@ -2319,26 +3396,29 @@ static long do_unlinkat(int dfd, const c + nd.flags &= ~LOOKUP_PARENT; + + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); +- dentry = lookup_hash(&nd); +- error = PTR_ERR(dentry); +- if (!IS_ERR(dentry)) { ++ error = hash_lookup_union(&nd, &nd.last, &path); ++ if (!error) { + /* Why not before? Because we want correct error value */ + if (nd.last.name[nd.last.len]) + goto slashes; +- inode = dentry->d_inode; ++ inode = path.dentry->d_inode; + if (inode) + atomic_inc(&inode->i_count); ++ if (is_unionized(nd.path.dentry, nd.path.mnt)) { ++ error = do_whiteout(&nd, &path, 0); ++ goto exit2; ++ } + error = mnt_want_write(nd.path.mnt); + if (error) + goto exit2; +- error = security_path_unlink(&nd.path, dentry); ++ error = security_path_unlink(&nd.path, path.dentry); + if (error) + goto exit3; +- error = vfs_unlink(nd.path.dentry->d_inode, dentry); ++ error = vfs_unlink(nd.path.dentry->d_inode, path.dentry); + exit3: + mnt_drop_write(nd.path.mnt); + exit2: +- dput(dentry); ++ path_put_conditional(&path, &nd); + } + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + if (inode) +@@ -2349,8 +3429,8 @@ exit1: + return error; + + slashes: +- error = !dentry->d_inode ? -ENOENT : +- S_ISDIR(dentry->d_inode->i_mode) ? -EISDIR : -ENOTDIR; ++ error = !path.dentry->d_inode ? -ENOENT : ++ S_ISDIR(path.dentry->d_inode->i_mode) ? -EISDIR : -ENOTDIR; + goto exit2; + } + +@@ -2686,11 +3766,96 @@ int vfs_rename(struct inode *old_dir, st + return error; + } + ++static int vfs_rename_union(struct nameidata *oldnd, struct path *old, ++ struct nameidata *newnd, struct path *new) ++{ ++ struct inode *old_dir = oldnd->path.dentry->d_inode; ++ struct inode *new_dir = newnd->path.dentry->d_inode; ++ struct qstr old_name; ++ char *name; ++ struct dentry *dentry; ++ int error; ++ ++ if (old->dentry->d_inode == new->dentry->d_inode) ++ return 0; ++ error = may_whiteout(old_dir, old->dentry, 0); ++ if (error) ++ return error; ++ if (!old_dir->i_op || !old_dir->i_op->whiteout) ++ return -EPERM; ++ ++ if (!new->dentry->d_inode) ++ error = may_create(new_dir, new->dentry); ++ else ++ error = may_delete(new_dir, new->dentry, 0); ++ if (error) ++ return error; ++ ++ vfs_dq_init(old_dir); ++ vfs_dq_init(new_dir); ++ ++ error = -EBUSY; ++ if (d_mountpoint(old->dentry) || d_mountpoint(new->dentry)) ++ return error; ++ ++ error = -ENOMEM; ++ name = kmalloc(old->dentry->d_name.len, GFP_KERNEL); ++ if (!name) ++ return error; ++ strncpy(name, old->dentry->d_name.name, old->dentry->d_name.len); ++ name[old->dentry->d_name.len] = 0; ++ old_name.len = old->dentry->d_name.len; ++ old_name.hash = old->dentry->d_name.hash; ++ old_name.name = name; ++ ++ /* possibly delete the existing new file */ ++ if ((newnd->path.dentry == new->dentry->d_parent) && ++ new->dentry->d_inode) { ++ /* FIXME: inode may be truncated while we hold a lock */ ++ error = vfs_unlink(new_dir, new->dentry); ++ if (error) ++ goto freename; ++ ++ dentry = __lookup_hash(&new->dentry->d_name, ++ newnd->path.dentry, newnd); ++ if (IS_ERR(dentry)) ++ goto freename; ++ ++ dput(new->dentry); ++ new->dentry = dentry; ++ } ++ ++ /* copyup to the new file */ ++ error = __union_copyup(old, newnd, new); ++ if (error) ++ goto freename; ++ ++ /* whiteout the old file */ ++ dentry = __lookup_hash(&old_name, oldnd->path.dentry, oldnd); ++ error = PTR_ERR(dentry); ++ if (IS_ERR(dentry)) ++ goto freename; ++ error = vfs_whiteout(old_dir, dentry, 0); ++ dput(dentry); ++ ++ /* FIXME: This is acutally unlink() && create() ... */ ++/* ++ if (!error) { ++ const char *new_name = old_dentry->d_name.name; ++ fsnotify_move(old_dir, new_dir, old_name.name, new_name, 0, ++ new_dentry->d_inode, old_dentry->d_inode); ++ } ++*/ ++freename: ++ kfree(old_name.name); ++ return error; ++} ++ + SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, + int, newdfd, const char __user *, newname) + { + struct dentry *old_dir, *new_dir; +- struct dentry *old_dentry, *new_dentry; ++ struct path old, new; + struct dentry *trap; + struct nameidata oldnd, newnd; + char *from; +@@ -2724,16 +3889,28 @@ SYSCALL_DEFINE4(renameat, int, olddfd, c + + trap = lock_rename(new_dir, old_dir); + +- old_dentry = lookup_hash(&oldnd); +- error = PTR_ERR(old_dentry); +- if (IS_ERR(old_dentry)) ++ /* ++ * For union mounts we need to call a giant lookup_rename_source() ++ * instead. ++ * First lock_rename() and look on the topmost fs like you would do in ++ * the normal rename, if you find something which is not a directory, ++ * go ahead and lookup target and do normal rename. ++ * If you find a negative dentry, unlock_rename() and continue as ++ * _hash_lookup_union() would do without locking the topmost parent ++ * at the end. After that do lock_rename() of the source parent and the ++ * target parent and do a copyup with additional whiteout creation at ++ * the end. ++ */ ++// error = hash_lookup_union(&oldnd, &oldnd.last, &old); ++ error = lookup_rename_source(&oldnd, &newnd, &trap, &oldnd.last, &old); ++ if (error) + goto exit3; + /* source must exist */ + error = -ENOENT; +- if (!old_dentry->d_inode) ++ if (!old.dentry->d_inode) + goto exit4; + /* unless the source is a directory trailing slashes give -ENOTDIR */ +- if (!S_ISDIR(old_dentry->d_inode->i_mode)) { ++ if (!S_ISDIR(old.dentry->d_inode->i_mode)) { + error = -ENOTDIR; + if (oldnd.last.name[oldnd.last.len]) + goto exit4; +@@ -2742,32 +3919,44 @@ SYSCALL_DEFINE4(renameat, int, olddfd, c + } + /* source should not be ancestor of target */ + error = -EINVAL; +- if (old_dentry == trap) ++ if (old.dentry == trap) + goto exit4; +- new_dentry = lookup_hash(&newnd); +- error = PTR_ERR(new_dentry); +- if (IS_ERR(new_dentry)) ++ /* target is always on topmost fs, even with unions */ ++ error = lookup_hash(&newnd, &newnd.last, &new); ++ if (error) + goto exit4; + /* target should not be an ancestor of source */ + error = -ENOTEMPTY; +- if (new_dentry == trap) ++ if (new.dentry == trap) ++ goto exit5; ++ /* renaming of directories on unions is done by the user-space */ ++ error = -EXDEV; ++ if (is_unionized(oldnd.path.dentry, oldnd.path.mnt) && ++ S_ISDIR(old.dentry->d_inode->i_mode)) + goto exit5; ++// if (is_unionized(newnd.path.dentry, newnd.path.mnt)) ++// goto exit5; + + error = mnt_want_write(oldnd.path.mnt); + if (error) + goto exit5; +- error = security_path_rename(&oldnd.path, old_dentry, +- &newnd.path, new_dentry); ++ error = security_path_rename(&oldnd.path, old.dentry, ++ &newnd.path, new.dentry); + if (error) + goto exit6; +- error = vfs_rename(old_dir->d_inode, old_dentry, +- new_dir->d_inode, new_dentry); ++ if (is_unionized(oldnd.path.dentry, oldnd.path.mnt) && ++ (old.dentry->d_parent != oldnd.path.dentry)) { ++ error = vfs_rename_union(&oldnd, &old, &newnd, &new); ++ goto exit6; ++ } ++ error = vfs_rename(old_dir->d_inode, old.dentry, ++ new_dir->d_inode, new.dentry); + exit6: + mnt_drop_write(oldnd.path.mnt); + exit5: +- dput(new_dentry); ++ path_put_conditional(&new, &newnd); + exit4: +- dput(old_dentry); ++ path_put_conditional(&old, &oldnd); + exit3: + unlock_rename(new_dir, old_dir); + exit2: +--- a/fs/namespace.c ++++ b/fs/namespace.c +@@ -29,6 +29,7 @@ + #include <linux/log2.h> + #include <linux/idr.h> + #include <linux/fs_struct.h> ++#include <linux/union.h> + #include <asm/uaccess.h> + #include <asm/unistd.h> + #include "pnode.h" +@@ -150,6 +151,9 @@ struct vfsmount *alloc_vfsmnt(const char + INIT_LIST_HEAD(&mnt->mnt_share); + INIT_LIST_HEAD(&mnt->mnt_slave_list); + INIT_LIST_HEAD(&mnt->mnt_slave); ++#ifdef CONFIG_UNION_MOUNT ++ INIT_LIST_HEAD(&mnt->mnt_unions); ++#endif + #ifdef CONFIG_SMP + mnt->mnt_writers = alloc_percpu(int); + if (!mnt->mnt_writers) +@@ -469,6 +473,7 @@ static void __touch_mnt_namespace(struct + + static void detach_mnt(struct vfsmount *mnt, struct path *old_path) + { ++ detach_mnt_union(mnt); + old_path->dentry = mnt->mnt_mountpoint; + old_path->mnt = mnt->mnt_parent; + mnt->mnt_parent = mnt; +@@ -492,6 +497,7 @@ static void attach_mnt(struct vfsmount * + list_add_tail(&mnt->mnt_hash, mount_hashtable + + hash(path->mnt, path->dentry)); + list_add_tail(&mnt->mnt_child, &path->mnt->mnt_mounts); ++ attach_mnt_union(mnt, path->mnt, path->dentry); + } + + /* +@@ -514,6 +520,7 @@ static void commit_tree(struct vfsmount + list_add_tail(&mnt->mnt_hash, mount_hashtable + + hash(parent, mnt->mnt_mountpoint)); + list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); ++ attach_mnt_union(mnt, mnt->mnt_parent, mnt->mnt_mountpoint); + touch_mnt_namespace(n); + } + +@@ -770,6 +777,7 @@ static void show_mnt_opts(struct seq_fil + { MNT_NODIRATIME, ",nodiratime" }, + { MNT_RELATIME, ",relatime" }, + { MNT_STRICTATIME, ",strictatime" }, ++ { MNT_UNION, ",union" }, + { 0, NULL } + }; + const struct proc_fs_info *fs_infop; +@@ -984,6 +992,7 @@ void release_mounts(struct list_head *he + struct dentry *dentry; + struct vfsmount *m; + spin_lock(&vfsmount_lock); ++ detach_mnt_union(mnt); + dentry = mnt->mnt_mountpoint; + m = mnt->mnt_parent; + mnt->mnt_mountpoint = mnt->mnt_root; +@@ -1102,6 +1111,11 @@ static int do_umount(struct vfsmount *mn + spin_unlock(&vfsmount_lock); + if (retval) + security_sb_umount_busy(mnt); ++ /* If this was a union mount, we are no longer a read-only ++ * user on the underlying mount */ ++ if (mnt->mnt_flags & MNT_UNION) ++ mnt->mnt_parent->mnt_sb->s_readonly_users--; ++ + up_write(&namespace_sem); + release_mounts(&umount_list); + return retval; +@@ -1426,6 +1440,10 @@ static int do_change_type(struct path *p + if (path->dentry != path->mnt->mnt_root) + return -EINVAL; + ++ /* Don't change the type of union mounts */ ++ if (IS_MNT_UNION(path->mnt)) ++ return -EINVAL; ++ + down_write(&namespace_sem); + if (type == MS_SHARED) { + err = invent_group_ids(mnt, recurse); +@@ -1444,10 +1462,65 @@ static int do_change_type(struct path *p + } + + /* ++ * Mount-time check of upper and lower layer file systems to see if we ++ * can union mount one on the other. ++ * ++ * Union mounts must follow these rules: ++ * ++ * - The lower layer must be read-only. This avoids lots of nasty ++ * unsolvable races where file system structures disappear suddenly. ++ * XXX - Checking the vfsmnt for read-only is a temporary hack; the ++ * file system could be mounted read-write elsewhere. We need to ++ * enforce read-only at the superblock level (patches coming). ++ * ++ * - The upper layer must be writable. This isn't an absolute ++ * requirement; right now we need it to make readdir() work since we ++ * copy up directory entries to the top level. A possible ++ * workaround is to mount a tmpfs file system transparently over the ++ * top. ++ * ++ * - The upper layer must support whiteouts and fallthrus (if it is ++ * writeable). ++ * ++ * - The lower layer must not also be a union mount. This is just to ++ * make life simpler for now, there is no inherent limitation on the ++ * number of layers. ++ * ++ * XXX - Check other mount flags for incompatibilities - I'm sure ++ * there are some. ++ */ ++ ++static int ++check_union_mnt(struct path *mntpnt, struct vfsmount *top_mnt, int mnt_flags) ++{ ++ struct vfsmount *lower_mnt = mntpnt->mnt; ++ ++ /* Is this even a union mount? */ ++ if (!(mnt_flags & MNT_UNION)) ++ return 0; ++ ++ /* Lower layer must be read-only and not a union mount */ ++ if (!(lower_mnt->mnt_sb->s_flags & MS_RDONLY) || ++ (lower_mnt->mnt_flags & MNT_UNION)) ++ return -EBUSY; ++ ++ /* Upper layer must be writable */ ++ if (mnt_flags & MNT_READONLY) ++ return -EROFS; ++ ++ /* Upper layer must support whiteouts and fallthrus */ ++ if (!(top_mnt->mnt_sb->s_flags & MS_WHITEOUT)) ++ return -EINVAL; ++ ++ /* All good! */ ++ return 0; ++} ++ ++/* + * do loopback mount. + */ +-static int do_loopback(struct path *path, char *old_name, +- int recurse) ++static int do_loopback(struct path *path, char *old_name, int recurse, ++ int mnt_flags) + { + struct path old_path; + struct vfsmount *mnt = NULL; +@@ -1477,6 +1550,13 @@ static int do_loopback(struct path *path + if (!mnt) + goto out; + ++ err = check_union_mnt(&old_path, mnt, mnt_flags); ++ if (err) ++ goto out; ++ ++ if (mnt_flags & MNT_UNION) ++ mnt->mnt_flags |= MNT_UNION; ++ + err = graft_tree(mnt, path); + if (err) { + LIST_HEAD(umount_list); +@@ -1486,6 +1566,10 @@ static int do_loopback(struct path *path + release_mounts(&umount_list); + } + ++ /* If this is a union mount, add ourselves to the readonly users */ ++ if (mnt_flags & MNT_UNION) ++ mnt->mnt_parent->mnt_sb->s_readonly_users++; ++ + out: + up_write(&namespace_sem); + path_put(&old_path); +@@ -1570,6 +1654,13 @@ static int do_move_mount(struct path *pa + if (err) + return err; + ++ /* moving to or from a union mount is not supported */ ++ err = -EINVAL; ++ if (IS_MNT_UNION(path->mnt)) ++ goto exit; ++ if (IS_MNT_UNION(old_path.mnt)) ++ goto exit; ++ + down_write(&namespace_sem); + while (d_mountpoint(path->dentry) && + follow_down(path)) +@@ -1627,6 +1718,7 @@ out: + up_write(&namespace_sem); + if (!err) + path_put(&parent_path); ++exit: + path_put(&old_path); + return err; + } +@@ -1684,10 +1776,18 @@ int do_add_mount(struct vfsmount *newmnt + if (S_ISLNK(newmnt->mnt_root->d_inode->i_mode)) + goto unlock; + ++ err = check_union_mnt(path, newmnt, mnt_flags); ++ if (err) ++ goto unlock; ++ + newmnt->mnt_flags = mnt_flags; + if ((err = graft_tree(newmnt, path))) + goto unlock; + ++ /* If this is a union mount, add ourselves to the readonly users */ ++ if (mnt_flags & MNT_UNION) ++ newmnt->mnt_parent->mnt_sb->s_readonly_users++; ++ + if (fslist) /* add to the specified expiration list */ + list_add_tail(&newmnt->mnt_expire, fslist); + +@@ -1940,10 +2040,12 @@ long do_mount(char *dev_name, char *dir_ + mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); + if (flags & MS_RDONLY) + mnt_flags |= MNT_READONLY; ++ if (flags & MS_UNION) ++ mnt_flags |= MNT_UNION; + + flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | + MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | +- MS_STRICTATIME); ++ MS_STRICTATIME | MS_UNION); + + /* ... and get the mountpoint */ + retval = kern_path(dir_name, LOOKUP_FOLLOW, &path); +@@ -1959,7 +2061,8 @@ long do_mount(char *dev_name, char *dir_ + retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags, + data_page); + else if (flags & MS_BIND) +- retval = do_loopback(&path, dev_name, flags & MS_REC); ++ retval = do_loopback(&path, dev_name, flags & MS_REC, ++ mnt_flags); + else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) + retval = do_change_type(&path, flags); + else if (flags & MS_MOVE) +@@ -2196,6 +2299,8 @@ SYSCALL_DEFINE2(pivot_root, const char _ + if (d_unlinked(old.dentry)) + goto out2; + error = -EBUSY; ++ follow_union_down(&new); ++ follow_union_down(&root); + if (new.mnt == root.mnt || + old.mnt == root.mnt) + goto out2; /* loop, on the same file system */ +--- a/fs/nfsctl.c ++++ b/fs/nfsctl.c +@@ -38,10 +38,10 @@ static struct file *do_open(char *name, + return ERR_PTR(error); + + if (flags == O_RDWR) +- error = may_open(&nd.path, MAY_READ|MAY_WRITE, +- FMODE_READ|FMODE_WRITE); ++ error = may_open(&nd, MAY_READ|MAY_WRITE, ++ FMODE_READ|FMODE_WRITE); + else +- error = may_open(&nd.path, MAY_WRITE, FMODE_WRITE); ++ error = may_open(&nd, MAY_WRITE, FMODE_WRITE); + + if (!error) + return dentry_open(nd.path.dentry, nd.path.mnt, flags, +--- a/fs/nfsd/nfs3xdr.c ++++ b/fs/nfsd/nfs3xdr.c +@@ -898,6 +898,11 @@ encode_entry(struct readdir_cd *ccd, con + int elen; /* estimated entry length in words */ + int num_entry_words = 0; /* actual number of words */ + ++ if (d_type == DT_WHT) { ++ cd->common.err = nfs_ok; ++ return 0; ++ } ++ + if (cd->offset) { + u64 offset64 = offset; + +--- a/fs/nfsd/nfs4xdr.c ++++ b/fs/nfsd/nfs4xdr.c +@@ -2261,7 +2261,7 @@ nfsd4_encode_dirent(void *ccdv, const ch + __be32 nfserr = nfserr_toosmall; + + /* In nfsv4, "." and ".." never make it onto the wire.. */ +- if (name && isdotent(name, namlen)) { ++ if (d_type == DT_WHT || (name && isdotent(name, namlen))) { + cd->common.err = nfs_ok; + return 0; + } +--- a/fs/nfsd/nfsxdr.c ++++ b/fs/nfsd/nfsxdr.c +@@ -513,6 +513,10 @@ nfssvc_encode_entry(void *ccdv, const ch + namlen, name, offset, ino); + */ + ++ if (d_type == DT_WHT) { ++ cd->common.err = nfs_ok; ++ return 0; ++ } + if (offset > ~((u32) 0)) { + cd->common.err = nfserr_fbig; + return -EINVAL; +--- a/fs/open.c ++++ b/fs/open.c +@@ -30,6 +30,7 @@ + #include <linux/audit.h> + #include <linux/falloc.h> + #include <linux/fs_struct.h> ++#include <linux/union.h> + + int vfs_statfs(struct dentry *dentry, struct kstatfs *buf) + { +@@ -224,69 +225,69 @@ int do_truncate(struct dentry *dentry, l + return ret; + } + +-static long do_sys_truncate(const char __user *pathname, loff_t length) ++static int __do_ftruncate(struct file *file, unsigned long length, int small) + { +- struct path path; +- struct inode *inode; ++ struct inode * inode; ++ struct dentry *dentry; + int error; + + error = -EINVAL; +- if (length < 0) /* sorry, but loff_t says... */ ++ if (length < 0) + goto out; ++ /* explicitly opened as large or we are on 64-bit box */ ++ if (file->f_flags & O_LARGEFILE) ++ small = 0; + +- error = user_path(pathname, &path); +- if (error) ++ dentry = file->f_path.dentry; ++ inode = dentry->d_inode; ++ error = -EINVAL; ++ if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE)) + goto out; +- inode = path.dentry->d_inode; +- +- /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ +- error = -EISDIR; +- if (S_ISDIR(inode->i_mode)) +- goto dput_and_out; + + error = -EINVAL; +- if (!S_ISREG(inode->i_mode)) +- goto dput_and_out; +- +- error = mnt_want_write(path.mnt); +- if (error) +- goto dput_and_out; ++ /* Cannot ftruncate over 2^31 bytes without large file support */ ++ if (small && length > MAX_NON_LFS) + +- error = inode_permission(inode, MAY_WRITE); +- if (error) +- goto mnt_drop_write_and_out; ++ goto out; + + error = -EPERM; + if (IS_APPEND(inode)) +- goto mnt_drop_write_and_out; ++ goto out; + +- error = get_write_access(inode); +- if (error) +- goto mnt_drop_write_and_out; ++ error = locks_verify_truncate(inode, file, length); ++ if (!error) ++ error = security_path_truncate(&file->f_path, length, ++ ATTR_MTIME|ATTR_CTIME); ++ if (!error) ++ /* Already copied up for union, opened with write */ ++ error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file); ++out: ++ return error; ++} + +- /* +- * Make sure that there are no leases. get_write_access() protects +- * against the truncate racing with a lease-granting setlease(). +- */ +- error = break_lease(inode, FMODE_WRITE); +- if (error) +- goto put_write_and_out; ++static long do_sys_truncate(const char __user *pathname, loff_t length) ++{ ++ struct file *file; ++ char *tmp; ++ int error; + +- error = locks_verify_truncate(inode, NULL, length); +- if (!error) +- error = security_path_truncate(&path, length, 0); +- if (!error) { +- vfs_dq_init(inode); +- error = do_truncate(path.dentry, length, 0, NULL); +- } ++ error = -EINVAL; ++ if (length < 0) /* sorry, but loff_t says... */ ++ return error; + +-put_write_and_out: +- put_write_access(inode); +-mnt_drop_write_and_out: +- mnt_drop_write(path.mnt); +-dput_and_out: +- path_put(&path); +-out: ++ tmp = getname(pathname); ++ if (IS_ERR(tmp)) ++ return PTR_ERR(tmp); ++ ++ file = filp_open(tmp, O_RDWR | O_LARGEFILE, 0); ++ putname(tmp); ++ ++ if (IS_ERR(file)) ++ return PTR_ERR(file); ++ ++ error = __do_ftruncate(file, length, 0); ++ ++ fput(file); + return error; + } + +@@ -297,45 +298,16 @@ SYSCALL_DEFINE2(truncate, const char __u + + static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) + { +- struct inode * inode; +- struct dentry *dentry; + struct file * file; + int error; + +- error = -EINVAL; +- if (length < 0) +- goto out; + error = -EBADF; + file = fget(fd); + if (!file) + goto out; + +- /* explicitly opened as large or we are on 64-bit box */ +- if (file->f_flags & O_LARGEFILE) +- small = 0; +- +- dentry = file->f_path.dentry; +- inode = dentry->d_inode; +- error = -EINVAL; +- if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE)) +- goto out_putf; +- +- error = -EINVAL; +- /* Cannot ftruncate over 2^31 bytes without large file support */ +- if (small && length > MAX_NON_LFS) +- goto out_putf; ++ error = __do_ftruncate(file, length, small); + +- error = -EPERM; +- if (IS_APPEND(inode)) +- goto out_putf; +- +- error = locks_verify_truncate(inode, file, length); +- if (!error) +- error = security_path_truncate(&file->f_path, length, +- ATTR_MTIME|ATTR_CTIME); +- if (!error) +- error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file); +-out_putf: + fput(file); + out: + return error; +@@ -494,7 +466,8 @@ SYSCALL_DEFINE3(faccessat, int, dfd, con + goto out_path_release; + } + +- res = inode_permission(inode, mode | MAY_ACCESS); ++ res = union_permission(&path, mode | MAY_ACCESS); ++ + /* SuS v2 requires we report a read only fs too */ + if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) + goto out_path_release; +@@ -508,7 +481,8 @@ SYSCALL_DEFINE3(faccessat, int, dfd, con + * inherently racy and know that the fs may change + * state before we even see this result. + */ +- if (__mnt_is_readonly(path.mnt)) ++ if ((!is_unionized(path.dentry, path.mnt) && ++ (__mnt_is_readonly(path.mnt)))) + res = -EROFS; + + out_path_release: +@@ -554,20 +528,19 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd + error = -EBADF; + file = fget(fd); + if (!file) +- goto out; ++ return error; + + inode = file->f_path.dentry->d_inode; + + error = -ENOTDIR; + if (!S_ISDIR(inode->i_mode)) +- goto out_putf; ++ goto out; + + error = inode_permission(inode, MAY_EXEC | MAY_ACCESS); + if (!error) + set_fs_pwd(current->fs, &file->f_path); +-out_putf: +- fput(file); + out: ++ fput(file); + return error; + } + +--- a/fs/readdir.c ++++ b/fs/readdir.c +@@ -16,6 +16,7 @@ + #include <linux/security.h> + #include <linux/syscalls.h> + #include <linux/unistd.h> ++#include <linux/union.h> + + #include <asm/uaccess.h> + +@@ -36,9 +37,24 @@ int vfs_readdir(struct file *file, filld + + res = -ENOENT; + if (!IS_DEADDIR(inode)) { ++ /* ++ * XXX Think harder about locking for ++ * union_copyup_dir. Currently we lock the topmost ++ * directory and hold that lock while sequentially ++ * acquiring and dropping locks for the directories ++ * below this one in the union stack. ++ */ ++ if (is_unionized(file->f_path.dentry, file->f_path.mnt) && ++ !IS_OPAQUE(inode)) { ++ res = union_copyup_dir(&file->f_path); ++ if (res) ++ goto out_unlock; ++ } ++ + res = file->f_op->readdir(file, buf, filler); + file_accessed(file); + } ++out_unlock: + mutex_unlock(&inode->i_mutex); + out: + return res; +@@ -77,6 +93,9 @@ static int fillonedir(void * __buf, cons + struct old_linux_dirent __user * dirent; + unsigned long d_ino; + ++ if (d_type == DT_WHT) ++ return 0; ++ + if (buf->result) + return -EINVAL; + d_ino = ino; +@@ -154,6 +173,9 @@ static int filldir(void * __buf, const c + unsigned long d_ino; + int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 2, sizeof(long)); + ++ if (d_type == DT_WHT) ++ return 0; ++ + buf->error = -EINVAL; /* only used if we fail.. */ + if (reclen > buf->count) + return -EINVAL; +@@ -239,6 +261,9 @@ static int filldir64(void * __buf, const + struct getdents_callback64 * buf = (struct getdents_callback64 *) __buf; + int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 1, sizeof(u64)); + ++ if (d_type == DT_WHT) ++ return 0; ++ + buf->error = -EINVAL; /* only used if we fail.. */ + if (reclen > buf->count) + return -EINVAL; +--- a/fs/super.c ++++ b/fs/super.c +@@ -596,6 +596,15 @@ int do_remount_sb(struct super_block *sb + } + remount_rw = !(flags & MS_RDONLY) && (sb->s_flags & MS_RDONLY); + ++ /* If we are remounting read/write, make sure that none of the ++ users require read-only for correct operation (such as ++ union mounts). */ ++ if (remount_rw && sb->s_readonly_users) { ++ printk(KERN_INFO "%s: In use by %d read-only user(s)\n", ++ sb->s_id, sb->s_readonly_users); ++ return -EROFS; ++ } ++ + if (sb->s_op->remount_fs) { + retval = sb->s_op->remount_fs(sb, &flags, data); + if (retval) +@@ -953,6 +962,11 @@ vfs_kern_mount(struct file_system_type * + WARN((mnt->mnt_sb->s_maxbytes < 0), "%s set sb->s_maxbytes to " + "negative value (%lld)\n", type->name, mnt->mnt_sb->s_maxbytes); + ++ error = -EROFS; ++ if (!(flags & MS_RDONLY) && ++ (mnt->mnt_sb->s_readonly_users)) ++ goto out_sb; ++ + mnt->mnt_mountpoint = mnt->mnt_root; + mnt->mnt_parent = mnt; + up_write(&mnt->mnt_sb->s_umount); +--- /dev/null ++++ b/fs/union.c +@@ -0,0 +1,981 @@ ++/* ++ * VFS based union mount for Linux ++ * ++ * Copyright (C) 2004-2007 IBM Corporation, IBM Deutschland Entwicklung GmbH. ++ * Copyright (C) 2007-2009 Novell Inc. ++ * ++ * Author(s): Jan Blunck (j.blunck@tu-harburg.de) ++ * Valerie Aurora <vaurora@redhat.com> ++ * ++ * 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. ++ */ ++ ++#include <linux/bootmem.h> ++#include <linux/init.h> ++#include <linux/module.h> ++#include <linux/types.h> ++#include <linux/hash.h> ++#include <linux/fs.h> ++#include <linux/mount.h> ++#include <linux/fs_struct.h> ++#include <linux/union.h> ++#include <linux/namei.h> ++#include <linux/file.h> ++#include <linux/mm.h> ++#include <linux/quotaops.h> ++#include <linux/dnotify.h> ++#include <linux/security.h> ++#include <linux/pipe_fs_i.h> ++#include <linux/splice.h> ++ ++/* ++ * This is borrowed from fs/inode.c. The hashtable for lookups. Somebody ++ * should try to make this good - I've just made it work. ++ */ ++static unsigned int union_hash_mask __read_mostly; ++static unsigned int union_hash_shift __read_mostly; ++static struct hlist_head *union_hashtable __read_mostly; ++static unsigned int union_rhash_mask __read_mostly; ++static unsigned int union_rhash_shift __read_mostly; ++static struct hlist_head *union_rhashtable __read_mostly; ++ ++/* ++ * Locking Rules: ++ * - dcache_lock (for union_rlookup() only) ++ * - union_lock ++ */ ++DEFINE_SPINLOCK(union_lock); ++ ++static struct kmem_cache *union_cache __read_mostly; ++ ++static unsigned long hash(struct dentry *dentry, struct vfsmount *mnt) ++{ ++ unsigned long tmp; ++ ++ tmp = ((unsigned long)mnt * (unsigned long)dentry) ^ ++ (GOLDEN_RATIO_PRIME + (unsigned long)mnt) / L1_CACHE_BYTES; ++ tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> union_hash_shift); ++ return tmp & union_hash_mask; ++} ++ ++static __initdata unsigned long union_hash_entries; ++ ++static int __init set_union_hash_entries(char *str) ++{ ++ if (!str) ++ return 0; ++ union_hash_entries = simple_strtoul(str, &str, 0); ++ return 1; ++} ++ ++__setup("union_hash_entries=", set_union_hash_entries); ++ ++static int __init init_union(void) ++{ ++ int loop; ++ ++ union_cache = KMEM_CACHE(union_mount, SLAB_PANIC | SLAB_MEM_SPREAD); ++ union_hashtable = alloc_large_system_hash("Union-cache", ++ sizeof(struct hlist_head), ++ union_hash_entries, ++ 14, ++ 0, ++ &union_hash_shift, ++ &union_hash_mask, ++ 0); ++ ++ for (loop = 0; loop < (1 << union_hash_shift); loop++) ++ INIT_HLIST_HEAD(&union_hashtable[loop]); ++ ++ ++ union_rhashtable = alloc_large_system_hash("rUnion-cache", ++ sizeof(struct hlist_head), ++ union_hash_entries, ++ 14, ++ 0, ++ &union_rhash_shift, ++ &union_rhash_mask, ++ 0); ++ ++ for (loop = 0; loop < (1 << union_rhash_shift); loop++) ++ INIT_HLIST_HEAD(&union_rhashtable[loop]); ++ ++ return 0; ++} ++ ++fs_initcall(init_union); ++ ++struct union_mount *union_alloc(struct dentry *this, struct vfsmount *this_mnt, ++ struct dentry *next, struct vfsmount *next_mnt) ++{ ++ struct union_mount *um; ++ ++ BUG_ON(!S_ISDIR(this->d_inode->i_mode)); ++ BUG_ON(!S_ISDIR(next->d_inode->i_mode)); ++ ++ um = kmem_cache_alloc(union_cache, GFP_ATOMIC); ++ if (!um) ++ return NULL; ++ ++ atomic_set(&um->u_count, 1); ++ INIT_LIST_HEAD(&um->u_unions); ++ INIT_LIST_HEAD(&um->u_list); ++ INIT_HLIST_NODE(&um->u_hash); ++ INIT_HLIST_NODE(&um->u_rhash); ++ ++ um->u_this.mnt = this_mnt; ++ um->u_this.dentry = this; ++ um->u_next.mnt = mntget(next_mnt); ++ um->u_next.dentry = dget(next); ++ ++ return um; ++} ++ ++struct union_mount *union_get(struct union_mount *um) ++{ ++ BUG_ON(!atomic_read(&um->u_count)); ++ atomic_inc(&um->u_count); ++ return um; ++} ++ ++static int __union_put(struct union_mount *um) ++{ ++ if (!atomic_dec_and_test(&um->u_count)) ++ return 0; ++ ++ BUG_ON(!hlist_unhashed(&um->u_hash)); ++ BUG_ON(!hlist_unhashed(&um->u_rhash)); ++ ++ kmem_cache_free(union_cache, um); ++ return 1; ++} ++ ++void union_put(struct union_mount *um) ++{ ++ struct path tmp = um->u_next; ++ ++ if (__union_put(um)) ++ path_put(&tmp); ++} ++ ++static void __union_hash(struct union_mount *um) ++{ ++ hlist_add_head(&um->u_hash, union_hashtable + ++ hash(um->u_this.dentry, um->u_this.mnt)); ++ hlist_add_head(&um->u_rhash, union_rhashtable + ++ hash(um->u_next.dentry, um->u_next.mnt)); ++} ++ ++static void __union_unhash(struct union_mount *um) ++{ ++ hlist_del_init(&um->u_hash); ++ hlist_del_init(&um->u_rhash); ++} ++ ++struct union_mount *union_lookup(struct dentry *dentry, struct vfsmount *mnt) ++{ ++ struct hlist_head *head = union_hashtable + hash(dentry, mnt); ++ struct hlist_node *node; ++ struct union_mount *um; ++ ++ hlist_for_each_entry(um, node, head, u_hash) { ++ if ((um->u_this.dentry == dentry) && ++ (um->u_this.mnt == mnt)) ++ return um; ++ } ++ ++ return NULL; ++} ++ ++struct union_mount *union_rlookup(struct dentry *dentry, struct vfsmount *mnt) ++{ ++ struct hlist_head *head = union_rhashtable + hash(dentry, mnt); ++ struct hlist_node *node; ++ struct union_mount *um; ++ ++ hlist_for_each_entry(um, node, head, u_rhash) { ++ if ((um->u_next.dentry == dentry) && ++ (um->u_next.mnt == mnt)) ++ return um; ++ } ++ ++ return NULL; ++} ++ ++/* ++ * is_unionized - check if a dentry lives on a union mounted file system ++ * ++ * This tests if a dentry is living on an union mounted file system by walking ++ * the file system hierarchy. ++ */ ++int is_unionized(struct dentry *dentry, struct vfsmount *mnt) ++{ ++ struct path this = { .mnt = mntget(mnt), ++ .dentry = dget(dentry) }; ++ struct vfsmount *tmp; ++ ++ do { ++ /* check if there is an union mounted on top of us */ ++ spin_lock(&vfsmount_lock); ++ list_for_each_entry(tmp, &this.mnt->mnt_mounts, mnt_child) { ++ if (!(tmp->mnt_flags & MNT_UNION)) ++ continue; ++ /* Isn't this a bug? */ ++ if (this.dentry->d_sb != tmp->mnt_mountpoint->d_sb) ++ continue; ++ if (is_subdir(this.dentry, tmp->mnt_mountpoint)) { ++ spin_unlock(&vfsmount_lock); ++ path_put(&this); ++ return 1; ++ } ++ } ++ spin_unlock(&vfsmount_lock); ++ ++ /* check our mountpoint next */ ++ tmp = mntget(this.mnt->mnt_parent); ++ dput(this.dentry); ++ this.dentry = dget(this.mnt->mnt_mountpoint); ++ mntput(this.mnt); ++ this.mnt = tmp; ++ } while (this.mnt != this.mnt->mnt_parent); ++ ++ path_put(&this); ++ return 0; ++} ++ ++int append_to_union(struct vfsmount *mnt, struct dentry *dentry, ++ struct vfsmount *dest_mnt, struct dentry *dest_dentry) ++{ ++ struct union_mount *this, *um; ++ ++ BUG_ON(!IS_MNT_UNION(mnt)); ++ ++ this = union_alloc(dentry, mnt, dest_dentry, dest_mnt); ++ if (!this) ++ return -ENOMEM; ++ ++ spin_lock(&union_lock); ++ um = union_lookup(dentry, mnt); ++ if (um) { ++ BUG_ON((um->u_next.dentry != dest_dentry) || ++ (um->u_next.mnt != dest_mnt)); ++ spin_unlock(&union_lock); ++ union_put(this); ++ return 0; ++ } ++ list_add(&this->u_list, &mnt->mnt_unions); ++ list_add(&this->u_unions, &dentry->d_unions); ++ dest_dentry->d_unionized++; ++ __union_hash(this); ++ spin_unlock(&union_lock); ++ return 0; ++} ++ ++/* ++ * follow_union_down - follow the union stack one layer down ++ * ++ * This is called to traverse the union stack from one layer to the next ++ * overlayed one. follow_union_down() is called by various lookup functions ++ * that are aware of union mounts. ++ * ++ * Returns non-zero if followed to the next layer, zero otherwise. ++ */ ++int follow_union_down(struct path *path) ++{ ++ struct union_mount *um; ++ ++ if (!IS_MNT_UNION(path->mnt)) ++ return 0; ++ ++ spin_lock(&union_lock); ++ um = union_lookup(path->dentry, path->mnt); ++ spin_unlock(&union_lock); ++ if (um) { ++ path_get(&um->u_next); ++ dput(path->dentry); ++ path->dentry = um->u_next.dentry; ++ mntput(path->mnt); ++ path->mnt = um->u_next.mnt; ++ return 1; ++ } ++ return 0; ++} ++ ++/* ++ * follow_union_mount - follow the union stack to the topmost layer ++ * ++ * This is called to traverse the union stack to the topmost layer. This is ++ * necessary for following parent pointers in an union mount. ++ * ++ * Returns none zero if followed to the topmost layer, zero otherwise. ++ */ ++int follow_union_mount(struct path *path) ++{ ++ struct union_mount *um; ++ int res = 0; ++ ++ while (IS_UNION(path->dentry)) { ++ spin_lock(&dcache_lock); ++ spin_lock(&union_lock); ++ um = union_rlookup(path->dentry, path->mnt); ++ if (um) ++ path_get(&um->u_this); ++ spin_unlock(&union_lock); ++ spin_unlock(&dcache_lock); ++ ++ /* ++ * Q: Aaargh, how do I validate the topmost dentry pointer? ++ * A: Eeeeasy! We took the dcache_lock and union_lock. Since ++ * this protects from any dput'ng going on, we know that the ++ * dentry is valid since the union is unhashed under ++ * dcache_lock too. ++ */ ++ if (!um) ++ break; ++ dput(path->dentry); ++ path->dentry = um->u_this.dentry; ++ mntput(path->mnt); ++ path->mnt = um->u_this.mnt; ++ res = 1; ++ } ++ ++ return res; ++} ++ ++/* ++ * Union mount copyup support ++ */ ++ ++extern int hash_lookup_union(struct nameidata *, struct qstr *, struct path *); ++extern void follow_mount(struct path *); ++ ++/* ++ * union_relookup_topmost - lookup and create the topmost path to dentry ++ * @nd: pointer to nameidata ++ * @flags: lookup flags ++ */ ++static int union_relookup_topmost(struct nameidata *nd, int flags) ++{ ++ int err; ++ char *kbuf, *name; ++ struct nameidata this; ++ ++ kbuf = (char *)__get_free_page(GFP_KERNEL); ++ if (!kbuf) ++ return -ENOMEM; ++ ++ name = d_path(&nd->path, kbuf, PAGE_SIZE); ++ err = PTR_ERR(name); ++ if (IS_ERR(name)) ++ goto free_page; ++ ++ err = path_lookup(name, flags|LOOKUP_CREATE|LOOKUP_TOPMOST, &this); ++ if (err) ++ goto free_page; ++ ++ path_put(&nd->path); ++ nd->path.dentry = this.path.dentry; ++ nd->path.mnt = this.path.mnt; ++ ++ /* ++ * the nd->flags should be unchanged ++ */ ++ BUG_ON(this.um_flags & LAST_LOWLEVEL); ++ nd->um_flags &= ~LAST_LOWLEVEL; ++ free_page: ++ free_page((unsigned long)kbuf); ++ return err; ++} ++ ++static void __update_fs_pwd(struct path *path, struct dentry *dentry, ++ struct vfsmount *mnt) ++{ ++ struct path old = { NULL, NULL }; ++ ++ write_lock(¤t->fs->lock); ++ if (current->fs->pwd.dentry == path->dentry) { ++ old = current->fs->pwd; ++ path_get(¤t->fs->pwd); ++ } ++ write_unlock(¤t->fs->lock); ++ ++ if (old.dentry) ++ path_put(&old); ++ ++ return; ++} ++ ++/** ++ * union_permission - check for access rights to a given inode ++ * @inode: inode to check permission on ++ * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) ++ * ++ * In a union mount, the top layer is always read-write and the bottom ++ * is always read-only. Ignore the read-only flag on the lower fs. ++ * ++ * Only need for certain activities, like checking to see if write ++ * access is ok. ++ */ ++ ++int union_permission(struct path *path, int mask) ++{ ++ struct inode *inode = path->dentry->d_inode; ++ ++ if (!is_unionized(path->dentry, path->mnt)) ++ return inode_permission(inode, mask); ++ ++ /* Tell __inode_permission to ignore MS_RDONLY */ ++ return __inode_permission(inode, mask, 0); ++} ++ ++/* ++ * union_create_topmost - create the topmost path component ++ * @nd: pointer to nameidata of the base directory ++ * @name: pointer to file name ++ * @path: pointer to path of the overlaid file ++ * ++ * This is called by __link_path_walk() to create the directories on a path ++ * when it is called with LOOKUP_TOPMOST. ++ */ ++struct dentry *union_create_topmost(struct nameidata *nd, struct qstr *name, ++ struct path *path) ++{ ++ struct dentry *dentry, *parent = nd->path.dentry; ++ int res, mode = path->dentry->d_inode->i_mode; ++ ++ if (parent->d_sb == path->dentry->d_sb) ++ return ERR_PTR(-EEXIST); ++ ++ mutex_lock(&parent->d_inode->i_mutex); ++ dentry = lookup_one_len(name->name, nd->path.dentry, name->len); ++ if (IS_ERR(dentry)) ++ goto out_unlock; ++ ++ switch (mode & S_IFMT) { ++ case S_IFREG: ++ /* ++ * FIXME: Does this make any sense in this case? ++ * Special case - lookup gave negative, but... we had foo/bar/ ++ * From the vfs_mknod() POV we just have a negative dentry - ++ * all is fine. Let's be bastards - you had / on the end,you've ++ * been asking for (non-existent) directory. -ENOENT for you. ++ */ ++ if (name->name[name->len] && !dentry->d_inode) { ++ dput(dentry); ++ dentry = ERR_PTR(-ENOENT); ++ goto out_unlock; ++ } ++ ++ res = vfs_create(parent->d_inode, dentry, mode, nd); ++ if (res) { ++ dput(dentry); ++ dentry = ERR_PTR(res); ++ goto out_unlock; ++ } ++ break; ++ case S_IFDIR: ++ res = vfs_mkdir(parent->d_inode, dentry, mode); ++ if (res) { ++ dput(dentry); ++ dentry = ERR_PTR(res); ++ goto out_unlock; ++ } ++ ++ res = append_to_union(nd->path.mnt, dentry, path->mnt, ++ path->dentry); ++ if (res) { ++ dput(dentry); ++ dentry = ERR_PTR(res); ++ goto out_unlock; ++ } ++ break; ++ default: ++ dput(dentry); ++ dentry = ERR_PTR(-EINVAL); ++ goto out_unlock; ++ } ++ ++ /* FIXME: Really necessary ??? */ ++/* __update_fs_pwd(path, dentry, nd->path.mnt); */ ++ ++ out_unlock: ++ mutex_unlock(&parent->d_inode->i_mutex); ++ return dentry; ++} ++ ++static int union_copy_file(struct dentry *old_dentry, struct vfsmount *old_mnt, ++ struct dentry *new_dentry, struct vfsmount *new_mnt) ++{ ++ int ret; ++ size_t size; ++ loff_t offset; ++ struct file *old_file, *new_file; ++ const struct cred *cred = current_cred(); ++ ++ dget(old_dentry); ++ mntget(old_mnt); ++ old_file = dentry_open(old_dentry, old_mnt, O_RDONLY, cred); ++ if (IS_ERR(old_file)) ++ return PTR_ERR(old_file); ++ ++ dget(new_dentry); ++ mntget(new_mnt); ++ new_file = dentry_open(new_dentry, new_mnt, O_WRONLY, cred); ++ ret = PTR_ERR(new_file); ++ if (IS_ERR(new_file)) ++ goto fput_old; ++ ++ /* XXX be smart by using a length param, which indicates max ++ * data we'll want (e.g., we are about to truncate to 0 or 10 ++ * bytes or something */ ++ size = i_size_read(old_file->f_path.dentry->d_inode); ++ if (((size_t)size != size) || ((ssize_t)size != size)) { ++ ret = -EFBIG; ++ goto fput_new; ++ } ++ ++ offset = 0; ++ ret = do_splice_direct(old_file, &offset, new_file, size, ++ SPLICE_F_MOVE); ++ if (ret >= 0) ++ ret = 0; ++ fput_new: ++ fput(new_file); ++ fput_old: ++ fput(old_file); ++ return ret; ++} ++ ++/** ++ * __union_copyup - copy a file to the topmost directory ++ * @old: pointer to path of the old file name ++ * @new_nd: pointer to nameidata of the topmost directory ++ * @new: pointer to path of the new file name ++ * ++ * The topmost directory @new_nd must already be locked. Creates the topmost ++ * file if it doesn't exist yet. ++ */ ++int __union_copyup(struct path *old, struct nameidata *new_nd, ++ struct path *new) ++{ ++ struct dentry *dentry; ++ int error; ++ ++ /* Maybe this should be -EINVAL */ ++ if (S_ISDIR(old->dentry->d_inode->i_mode)) ++ return -EISDIR; ++ ++ if (new_nd->path.dentry != new->dentry->d_parent) { ++ mutex_lock(&new_nd->path.dentry->d_inode->i_mutex); ++ dentry = lookup_one_len(new->dentry->d_name.name, ++ new_nd->path.dentry, ++ new->dentry->d_name.len); ++ mutex_unlock(&new_nd->path.dentry->d_inode->i_mutex); ++ if (IS_ERR(dentry)) ++ return PTR_ERR(dentry); ++ error = -EEXIST; ++ if (dentry->d_inode) ++ goto out_dput; ++ } else ++ dentry = dget(new->dentry); ++ ++ if (!dentry->d_inode) { ++ error = vfs_create(new_nd->path.dentry->d_inode, dentry, ++ old->dentry->d_inode->i_mode, new_nd); ++ if (error) ++ goto out_dput; ++ } ++ ++ BUG_ON(!S_ISREG(old->dentry->d_inode->i_mode)); ++ error = union_copy_file(old->dentry, old->mnt, dentry, ++ new_nd->path.mnt); ++ if (error) { ++ /* FIXME: are there return value we should not ++ * BUG() on ? */ ++ BUG_ON(vfs_unlink(new_nd->path.dentry->d_inode, ++ dentry)); ++ goto out_dput; ++ } ++ ++ dput(new->dentry); ++ new->dentry = dentry; ++ if (new->mnt != new_nd->path.mnt) ++ mntput(new->mnt); ++ new->mnt = new_nd->path.mnt; ++ return error; ++ ++out_dput: ++ dput(dentry); ++ return error; ++} ++ ++/* ++ * union_copyup - copy a file to the topmost layer of the union stack ++ * @nd: nameidata pointer to the file ++ * @flags: flags given to open_namei ++ */ ++int union_copyup(struct nameidata *nd, int flags /* XXX not used */) ++{ ++ struct qstr this; ++ char *name; ++ struct dentry *dir; ++ struct path path; ++ int err; ++ ++ if (!is_unionized(nd->path.dentry, nd->path.mnt)) ++ return 0; ++ if (!S_ISREG(nd->path.dentry->d_inode->i_mode)) ++ return 0; ++ ++ /* safe the name for hash_lookup_union() */ ++ this.len = nd->path.dentry->d_name.len; ++ this.hash = nd->path.dentry->d_name.hash; ++ name = kmalloc(this.len + 1, GFP_KERNEL); ++ if (!name) ++ return -ENOMEM; ++ this.name = name; ++ memcpy(name, nd->path.dentry->d_name.name, nd->path.dentry->d_name.len); ++ name[this.len] = 0; ++ ++ err = union_relookup_topmost(nd, nd->flags|LOOKUP_PARENT); ++ if (err) { ++ kfree(name); ++ return err; ++ } ++ nd->flags &= ~LOOKUP_PARENT; ++ ++ dir = nd->path.dentry; ++ mutex_lock(&dir->d_inode->i_mutex); ++ err = hash_lookup_union(nd, &this, &path); ++ mutex_unlock(&dir->d_inode->i_mutex); ++ kfree(name); ++ if (err) ++ return err; ++ ++ err = -ENOENT; ++ if (!path.dentry->d_inode) ++ goto exit_dput; ++ ++ /* Necessary?! I guess not ... */ ++ follow_mount(&path); ++ ++ err = -ENOENT; ++ if (!path.dentry->d_inode) ++ goto exit_dput; ++ ++ err = -EISDIR; ++ if (!S_ISREG(path.dentry->d_inode->i_mode)) ++ goto exit_dput; ++ ++ if (path.dentry->d_parent != nd->path.dentry) { ++ err = __union_copyup(&path, nd, &path); ++ if (err) ++ goto exit_dput; ++ } ++ ++ dput(nd->path.dentry); ++ if (nd->path.mnt != path.mnt) ++ mntput(nd->path.mnt); ++ nd->path = path; ++ return 0; ++ ++exit_dput: ++ dput(path.dentry); ++ if (path.mnt != nd->path.mnt) ++ mntput(path.mnt); ++ return err; ++} ++ ++/* ++ * This must be called when unhashing a dentry. This is called with dcache_lock ++ * and unhashes all unions this dentry is in. ++ */ ++void __d_drop_unions(struct dentry *dentry) ++{ ++ struct union_mount *this, *next; ++ ++ spin_lock(&union_lock); ++ list_for_each_entry_safe(this, next, &dentry->d_unions, u_unions) ++ __union_unhash(this); ++ spin_unlock(&union_lock); ++} ++EXPORT_SYMBOL_GPL(__d_drop_unions); ++ ++/* ++ * This must be called after __d_drop_unions() without holding any locks. ++ * Note: The dentry might still be reachable via a lookup but at that time it ++ * already a negative dentry. Otherwise it would be unhashed. The union_mount ++ * structure itself is still reachable through mnt->mnt_unions (which we ++ * protect against with union_lock). ++ */ ++void shrink_d_unions(struct dentry *dentry) ++{ ++ struct union_mount *this, *next; ++ ++repeat: ++ spin_lock(&union_lock); ++ list_for_each_entry_safe(this, next, &dentry->d_unions, u_unions) { ++ BUG_ON(!hlist_unhashed(&this->u_hash)); ++ BUG_ON(!hlist_unhashed(&this->u_rhash)); ++ list_del(&this->u_list); ++ list_del(&this->u_unions); ++ this->u_next.dentry->d_unionized--; ++ spin_unlock(&union_lock); ++ union_put(this); ++ goto repeat; ++ } ++ spin_unlock(&union_lock); ++} ++ ++extern void __dput(struct dentry *, struct list_head *, int); ++ ++/* ++ * This is the special variant for use in dput() only. ++ */ ++void __shrink_d_unions(struct dentry *dentry, struct list_head *list) ++{ ++ struct union_mount *this, *next; ++ ++ BUG_ON(!d_unhashed(dentry)); ++ ++repeat: ++ spin_lock(&union_lock); ++ list_for_each_entry_safe(this, next, &dentry->d_unions, u_unions) { ++ struct dentry *n_dentry = this->u_next.dentry; ++ struct vfsmount *n_mnt = this->u_next.mnt; ++ ++ BUG_ON(!hlist_unhashed(&this->u_hash)); ++ BUG_ON(!hlist_unhashed(&this->u_rhash)); ++ list_del(&this->u_list); ++ list_del(&this->u_unions); ++ this->u_next.dentry->d_unionized--; ++ spin_unlock(&union_lock); ++ if (__union_put(this)) { ++ __dput(n_dentry, list, 0); ++ mntput(n_mnt); ++ } ++ goto repeat; ++ } ++ spin_unlock(&union_lock); ++} ++ ++/* ++ * Remove all union_mounts structures belonging to this vfsmount from the ++ * union lookup hashtable and so on ... ++ */ ++void shrink_mnt_unions(struct vfsmount *mnt) ++{ ++ struct union_mount *this, *next; ++ ++repeat: ++ spin_lock(&union_lock); ++ list_for_each_entry_safe(this, next, &mnt->mnt_unions, u_list) { ++ if (this->u_this.dentry == mnt->mnt_root) ++ continue; ++ __union_unhash(this); ++ list_del(&this->u_list); ++ list_del(&this->u_unions); ++ this->u_next.dentry->d_unionized--; ++ spin_unlock(&union_lock); ++ union_put(this); ++ goto repeat; ++ } ++ spin_unlock(&union_lock); ++} ++ ++int attach_mnt_union(struct vfsmount *mnt, struct vfsmount *dest_mnt, ++ struct dentry *dest_dentry) ++{ ++ if (!IS_MNT_UNION(mnt)) ++ return 0; ++ ++ return append_to_union(mnt, mnt->mnt_root, dest_mnt, dest_dentry); ++} ++ ++void detach_mnt_union(struct vfsmount *mnt) ++{ ++ struct union_mount *um; ++ ++ if (!IS_MNT_UNION(mnt)) ++ return; ++ ++ shrink_mnt_unions(mnt); ++ ++ spin_lock(&union_lock); ++ um = union_lookup(mnt->mnt_root, mnt); ++ __union_unhash(um); ++ list_del(&um->u_list); ++ list_del(&um->u_unions); ++ um->u_next.dentry->d_unionized--; ++ spin_unlock(&union_lock); ++ union_put(um); ++ return; ++} ++ ++/** ++ * union_copyup_dir_one - copy up a single directory entry ++ * ++ * Individual directory entry copyup function for union_copyup_dir. ++ * We get the entries from higher level layers first. ++ */ ++ ++static int union_copyup_dir_one(void *buf, const char *name, int namlen, ++ loff_t offset, u64 ino, unsigned int d_type) ++{ ++ struct dentry *topmost_dentry = (struct dentry *) buf; ++ struct dentry *dentry; ++ int err = 0; ++ ++ switch (namlen) { ++ case 2: ++ if (name[1] != '.') ++ break; ++ case 1: ++ if (name[0] != '.') ++ break; ++ return 0; ++ } ++ ++ /* Lookup this entry in the topmost directory */ ++ dentry = lookup_one_len(name, topmost_dentry, namlen); ++ ++ if (IS_ERR(dentry)) { ++ printk(KERN_INFO "error looking up %s\n", dentry->d_name.name); ++ goto out; ++ } ++ ++ /* ++ * If the entry already exists, one of the following is true: ++ * it was already copied up (due to an earlier lookup), an ++ * entry with the same name already exists on the topmost file ++ * system, it is a whiteout, or it is a fallthru. In each ++ * case, the top level entry masks any entries from lower file ++ * systems, so don't copy up this entry. ++ */ ++ if (dentry->d_inode || d_is_whiteout(dentry) || ++ d_is_fallthru(dentry)) { ++ printk(KERN_INFO "skipping copy of %s\n", dentry->d_name.name); ++ goto out_dput; ++ } ++ ++ /* ++ * If the entry doesn't exist, create a fallthru entry in the ++ * topmost file system. All possible directory types are ++ * used, so each file system must implement its own way of ++ * storing a fallthru entry. ++ */ ++ printk(KERN_INFO "creating fallthru for %s\n", dentry->d_name.name); ++ err = topmost_dentry->d_inode->i_op->fallthru(topmost_dentry->d_inode, ++ dentry); ++ /* FIXME */ ++ BUG_ON(err); ++ /* ++ * At this point, we have a negative dentry marked as fallthru ++ * in the cache. We could potentially lookup the entry lower ++ * level file system and turn this into a positive dentry ++ * right now, but it is not clear that would be a performance ++ * win and adds more opportunities to fail. ++ */ ++out_dput: ++ dput(dentry); ++out: ++ return 0; ++} ++ ++/** ++ * union_copyup_dir - copy up low-level directory entries to topmost dir ++ * ++ * readdir() is difficult to support on union file systems for two ++ * reasons: We must eliminate duplicates and apply whiteouts, and we ++ * must return something in f_pos that lets us restart in the same ++ * place when we return. Our solution is to, on first readdir() of ++ * the directory, copy up all visible entries from the low-level file ++ * systems and mark the entries that refer to low-level file system ++ * objects as "fallthru" entries. ++ */ ++ ++int union_copyup_dir(struct path *topmost_path) ++{ ++ struct dentry *topmost_dentry = topmost_path->dentry; ++ struct path path = *topmost_path; ++ int res = 0; ++ ++ /* ++ * Skip opaque dirs. ++ */ ++ if (IS_OPAQUE(topmost_dentry->d_inode)) ++ return 0; ++ ++ /* ++ * Mark this dir opaque to show that we have already copied up ++ * the lower entries. Only fallthru entries pass through to ++ * the underlying file system. ++ * ++ * XXX Deal with the lower file system changing. This could ++ * be through running a tool over the top level file system to ++ * make directories transparent again, or we could check the ++ * mtime of the underlying directory. ++ */ ++ ++ topmost_dentry->d_inode->i_flags |= S_OPAQUE; ++ mark_inode_dirty(topmost_dentry->d_inode); ++ ++ /* ++ * Loop through each dir on each level copying up the entries ++ * to the topmost. ++ */ ++ ++ /* Don't drop the caller's reference to the topmost path */ ++ path_get(&path); ++ while (follow_union_down(&path)) { ++ struct file * ftmp; ++ struct inode * inode; ++ ++ /* XXX Permit fallthrus on lower-level? Would need to ++ * pass in opaque flag to union_copyup_dir_one() and ++ * only copy up fallthru entries there. We allow ++ * fallthrus in lower level opaque directories on ++ * lookup, so for consistency we should do one or the ++ * other in both places. */ ++ if (IS_OPAQUE(path.dentry->d_inode)) ++ break; ++ ++ /* dentry_open() doesn't get a path reference itself */ ++ path_get(&path); ++ ftmp = dentry_open(path.dentry, path.mnt, ++ O_RDONLY | O_DIRECTORY | O_NOATIME, ++ current_cred()); ++ if (IS_ERR(ftmp)) { ++ printk (KERN_ERR "unable to open dir %s for " ++ "directory copyup: %ld\n", ++ path.dentry->d_name.name, PTR_ERR(ftmp)); ++ continue; ++ } ++ ++ inode = path.dentry->d_inode; ++ mutex_lock(&inode->i_mutex); ++ ++ res = -ENOENT; ++ if (IS_DEADDIR(inode)) ++ goto out_fput; ++ /* ++ * Read the whole directory, calling our directory ++ * entry copyup function on each entry. Pass in the ++ * topmost dentry as our private data so we can create ++ * new entries in the topmost directory. ++ */ ++ res = ftmp->f_op->readdir(ftmp, topmost_dentry, ++ union_copyup_dir_one); ++out_fput: ++ mutex_unlock(&inode->i_mutex); ++ fput(ftmp); ++ ++ if (res) ++ break; ++ } ++ path_put(&path); ++ return res; ++} +--- a/include/linux/dcache.h ++++ b/include/linux/dcache.h +@@ -101,6 +101,15 @@ struct dentry { + struct dentry *d_parent; /* parent directory */ + struct qstr d_name; + ++#ifdef CONFIG_UNION_MOUNT ++ /* ++ * The following fields are used by the VFS based union mount ++ * implementation. Both are protected by union_lock! ++ */ ++ struct list_head d_unions; /* list of union_mount's */ ++ unsigned int d_unionized; /* unions referencing this dentry */ ++#endif ++ + struct list_head d_lru; /* LRU list */ + /* + * d_child and d_rcu can share memory +@@ -186,6 +195,9 @@ d_iput: no no no yes + + #define DCACHE_FSNOTIFY_PARENT_WATCHED 0x0080 /* Parent inode is watched by some fsnotify listener */ + ++#define DCACHE_WHITEOUT 0x0100 /* This negative dentry is a whiteout */ ++#define DCACHE_FALLTHRU 0x0200 /* Keep looking in the file system below */ ++ + extern spinlock_t dcache_lock; + extern seqlock_t rename_lock; + +@@ -205,12 +217,20 @@ extern seqlock_t rename_lock; + * __d_drop requires dentry->d_lock. + */ + ++#ifdef CONFIG_UNION_MOUNT ++extern void __d_drop_unions(struct dentry *); ++#endif ++ + static inline void __d_drop(struct dentry *dentry) + { + if (!(dentry->d_flags & DCACHE_UNHASHED)) { + dentry->d_flags |= DCACHE_UNHASHED; + hlist_del_rcu(&dentry->d_hash); + } ++#ifdef CONFIG_UNION_MOUNT ++ /* remove dentry from the union hashtable */ ++ __d_drop_unions(dentry); ++#endif + } + + static inline void d_drop(struct dentry *dentry) +@@ -358,6 +378,16 @@ static inline int d_unlinked(struct dent + return d_unhashed(dentry) && !IS_ROOT(dentry); + } + ++static inline int d_is_whiteout(struct dentry *dentry) ++{ ++ return (dentry->d_flags & DCACHE_WHITEOUT); ++} ++ ++static inline int d_is_fallthru(struct dentry *dentry) ++{ ++ return (dentry->d_flags & DCACHE_FALLTHRU); ++} ++ + static inline struct dentry *dget_parent(struct dentry *dentry) + { + struct dentry *ret; +--- a/include/linux/ext2_fs.h ++++ b/include/linux/ext2_fs.h +@@ -189,6 +189,7 @@ struct ext2_group_desc + #define EXT2_NOTAIL_FL FS_NOTAIL_FL /* file tail should not be merged */ + #define EXT2_DIRSYNC_FL FS_DIRSYNC_FL /* dirsync behaviour (directories only) */ + #define EXT2_TOPDIR_FL FS_TOPDIR_FL /* Top of directory hierarchies*/ ++#define EXT2_OPAQUE_FL 0x00040000 + #define EXT2_RESERVED_FL FS_RESERVED_FL /* reserved for ext2 lib */ + + #define EXT2_FL_USER_VISIBLE FS_FL_USER_VISIBLE /* User visible flags */ +@@ -503,10 +504,12 @@ struct ext2_super_block { + #define EXT3_FEATURE_INCOMPAT_RECOVER 0x0004 + #define EXT3_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 + #define EXT2_FEATURE_INCOMPAT_META_BG 0x0010 ++#define EXT2_FEATURE_INCOMPAT_WHITEOUT 0x0020 + #define EXT2_FEATURE_INCOMPAT_ANY 0xffffffff + + #define EXT2_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR + #define EXT2_FEATURE_INCOMPAT_SUPP (EXT2_FEATURE_INCOMPAT_FILETYPE| \ ++ EXT2_FEATURE_INCOMPAT_WHITEOUT| \ + EXT2_FEATURE_INCOMPAT_META_BG) + #define EXT2_FEATURE_RO_COMPAT_SUPP (EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER| \ + EXT2_FEATURE_RO_COMPAT_LARGE_FILE| \ +@@ -573,6 +576,8 @@ enum { + EXT2_FT_FIFO, + EXT2_FT_SOCK, + EXT2_FT_SYMLINK, ++ EXT2_FT_WHT, ++ EXT2_FT_FALLTHRU, + EXT2_FT_MAX + }; + +--- a/include/linux/fs.h ++++ b/include/linux/fs.h +@@ -188,6 +188,7 @@ struct inodes_stat_t { + #define MS_REMOUNT 32 /* Alter flags of a mounted FS */ + #define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ + #define MS_DIRSYNC 128 /* Directory modifications are synchronous */ ++#define MS_UNION 256 + #define MS_NOATIME 1024 /* Do not update access times. */ + #define MS_NODIRATIME 2048 /* Do not update directory access times */ + #define MS_BIND 4096 +@@ -205,6 +206,7 @@ struct inodes_stat_t { + #define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ + #define MS_I_VERSION (1<<23) /* Update inode I_version field */ + #define MS_STRICTATIME (1<<24) /* Always perform atime updates */ ++#define MS_WHITEOUT (1<<26) /* fs does support white-out filetype */ + #define MS_ACTIVE (1<<30) + #define MS_NOUSER (1<<31) + +@@ -231,6 +233,7 @@ struct inodes_stat_t { + #define S_NOCMTIME 128 /* Do not update file c/mtime */ + #define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */ + #define S_PRIVATE 512 /* Inode is fs-internal */ ++#define S_OPAQUE 1024 /* Directory is opaque */ + + /* + * Note that nosuid etc flags are inode-specific: setting some file-system +@@ -266,6 +269,8 @@ struct inodes_stat_t { + #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) + #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) + ++#define IS_OPAQUE(inode) ((inode)->i_flags & S_OPAQUE) ++ + /* the read-only stuff doesn't really belong here, but any other place is + probably as bad and I don't want to create yet another include file. */ + +@@ -1380,6 +1385,11 @@ struct super_block { + * generic_show_options() + */ + char *s_options; ++ ++ /* ++ * Users who require read-only access - e.g., union mounts ++ */ ++ int s_readonly_users; + }; + + extern struct timespec current_fs_time(struct super_block *sb); +@@ -1517,6 +1527,8 @@ struct inode_operations { + int (*mkdir) (struct inode *,struct dentry *,int); + int (*rmdir) (struct inode *,struct dentry *); + int (*mknod) (struct inode *,struct dentry *,int,dev_t); ++ int (*whiteout) (struct inode *, struct dentry *, struct dentry *); ++ int (*fallthru) (struct inode *, struct dentry *); + int (*rename) (struct inode *, struct dentry *, + struct inode *, struct dentry *); + int (*readlink) (struct dentry *, char __user *,int); +@@ -2108,6 +2120,7 @@ extern void emergency_remount(void); + extern sector_t bmap(struct inode *, sector_t); + #endif + extern int notify_change(struct dentry *, struct iattr *); ++extern int __inode_permission(struct inode *inode, int mask, int rofs); + extern int inode_permission(struct inode *, int); + extern int generic_permission(struct inode *, int, + int (*check_acl)(struct inode *, int)); +@@ -2135,7 +2148,7 @@ extern void free_write_pipe(struct file + + extern struct file *do_filp_open(int dfd, const char *pathname, + int open_flag, int mode, int acc_mode); +-extern int may_open(struct path *, int, int); ++extern int may_open(struct nameidata *, int, int); + + extern int kernel_read(struct file *, loff_t, char *, unsigned long); + extern struct file * open_exec(const char *); +--- a/include/linux/mount.h ++++ b/include/linux/mount.h +@@ -35,6 +35,7 @@ struct mnt_namespace; + #define MNT_SHARED 0x1000 /* if the vfsmount is a shared mount */ + #define MNT_UNBINDABLE 0x2000 /* if the vfsmount is a unbindable mount */ + #define MNT_PNODE_MASK 0x3000 /* propagation flag mask */ ++#define MNT_UNION 0x4000 /* if the vfsmount is a union mount */ + + struct vfsmount { + struct list_head mnt_hash; +@@ -53,6 +54,9 @@ struct vfsmount { + struct list_head mnt_slave_list;/* list of slave mounts */ + struct list_head mnt_slave; /* slave list entry */ + struct vfsmount *mnt_master; /* slave is on master->mnt_slave_list */ ++#ifdef CONFIG_UNION_MOUNT ++ struct list_head mnt_unions; /* list of union_mount structures */ ++#endif + struct mnt_namespace *mnt_ns; /* containing namespace */ + int mnt_id; /* mount identifier */ + int mnt_group_id; /* peer group identifier */ +--- a/include/linux/namei.h ++++ b/include/linux/namei.h +@@ -20,6 +20,7 @@ struct nameidata { + struct qstr last; + struct path root; + unsigned int flags; ++ unsigned int um_flags; + int last_type; + unsigned depth; + char *saved_names[MAX_NESTED_LINKS + 1]; +@@ -35,6 +36,9 @@ struct nameidata { + */ + enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; + ++#define LAST_UNION 0x01 ++#define LAST_LOWLEVEL 0x02 ++ + /* + * The bitmask for a lookup event: + * - follow links at the end +@@ -49,6 +53,8 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LA + #define LOOKUP_CONTINUE 4 + #define LOOKUP_PARENT 16 + #define LOOKUP_REVAL 64 ++#define LOOKUP_TOPMOST 128 ++ + /* + * Intent data + */ +--- /dev/null ++++ b/include/linux/union.h +@@ -0,0 +1,84 @@ ++/* ++ * VFS based union mount for Linux ++ * ++ * Copyright (C) 2004-2007 IBM Corporation, IBM Deutschland Entwicklung GmbH. ++ * Copyright (C) 2007 Novell Inc. ++ * Author(s): Jan Blunck (j.blunck@tu-harburg.de) ++ * ++ * 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. ++ * ++ */ ++#ifndef __LINUX_UNION_H ++#define __LINUX_UNION_H ++#ifdef __KERNEL__ ++ ++#include <linux/list.h> ++#include <asm/atomic.h> ++ ++struct dentry; ++struct vfsmount; ++ ++#ifdef CONFIG_UNION_MOUNT ++ ++/* ++ * The new union mount structure. ++ */ ++struct union_mount { ++ atomic_t u_count; /* reference count */ ++ struct mutex u_mutex; ++ struct list_head u_unions; /* list head for d_unions */ ++ struct list_head u_list; /* list head for mnt_unions */ ++ struct hlist_node u_hash; /* list head for seaching */ ++ struct hlist_node u_rhash; /* list head for reverse seaching */ ++ ++ struct path u_this; /* this is me */ ++ struct path u_next; /* this is what I overlay */ ++}; ++ ++#define IS_UNION(dentry) (!list_empty(&(dentry)->d_unions) || \ ++ (dentry)->d_unionized) ++#define IS_MNT_UNION(mnt) ((mnt)->mnt_flags & MNT_UNION) ++ ++extern int is_unionized(struct dentry *, struct vfsmount *); ++extern int append_to_union(struct vfsmount *, struct dentry *, ++ struct vfsmount *, struct dentry *); ++extern int follow_union_down(struct path *); ++extern int follow_union_mount(struct path *); ++extern void __d_drop_unions(struct dentry *); ++extern void shrink_d_unions(struct dentry *); ++extern void __shrink_d_unions(struct dentry *, struct list_head *); ++extern int attach_mnt_union(struct vfsmount *, struct vfsmount *, ++ struct dentry *); ++extern void detach_mnt_union(struct vfsmount *); ++extern struct dentry *union_create_topmost(struct nameidata *, struct qstr *, ++ struct path *); ++extern int __union_copyup(struct path *, struct nameidata *, struct path *); ++extern int union_copyup(struct nameidata *, int); ++extern int union_copyup_dir(struct path *path); ++extern int union_permission(struct path *, int); ++ ++#else /* CONFIG_UNION_MOUNT */ ++ ++#define IS_UNION(x) (0) ++#define IS_MNT_UNION(x) (0) ++#define is_unionized(x, y) (0) ++#define append_to_union(x1, y1, x2, y2) ({ BUG(); (0); }) ++#define follow_union_down(x) ({ (0); }) ++#define follow_union_mount(x) ({ (0); }) ++#define __d_drop_unions(x) do { } while (0) ++#define shrink_d_unions(x) do { } while (0) ++#define __shrink_d_unions(x,y) do { } while (0) ++#define attach_mnt_union(x, y, z) do { } while (0) ++#define detach_mnt_union(x) do { } while (0) ++#define union_create_topmost(x, y, z) ({ BUG(); (NULL); }) ++#define __union_copyup(x, y, z) ({ BUG(); (0); }) ++#define union_copyup(x, y) ({ (0); }) ++#define union_copyup_dir(x) ({ BUG(); (0); }) ++#define union_permission(x, y) inode_permission(x->dentry->d_inode, y) ++ ++#endif /* CONFIG_UNION_MOUNT */ ++#endif /* __KERNEL__ */ ++#endif /* __LINUX_UNION_H */ +--- a/mm/shmem.c ++++ b/mm/shmem.c +@@ -1798,6 +1798,118 @@ static int shmem_statfs(struct dentry *d + return 0; + } + ++static int shmem_rmdir(struct inode *dir, struct dentry *dentry); ++static int shmem_unlink(struct inode *dir, struct dentry *dentry); ++ ++/* ++ * Create a dentry to signify a whiteout. ++ */ ++static int shmem_whiteout(struct inode *dir, struct dentry *old_dentry, ++ struct dentry *new_dentry) ++{ ++ struct shmem_sb_info *sbinfo = SHMEM_SB(dir->i_sb); ++ struct dentry *dentry; ++ ++ if (!(dir->i_sb->s_flags & MS_WHITEOUT)) ++ return -EPERM; ++ ++ /* This gives us a proper initialized negative dentry */ ++ dentry = simple_lookup(dir, new_dentry, NULL); ++ if (dentry && IS_ERR(dentry)) ++ return PTR_ERR(dentry); ++ ++ /* ++ * No ordinary (disk based) filesystem counts whiteouts as inodes; ++ * but each new link needs a new dentry, pinning lowmem, and ++ * tmpfs dentries cannot be pruned until they are unlinked. ++ */ ++ if (sbinfo->max_inodes) { ++ spin_lock(&sbinfo->stat_lock); ++ if (!sbinfo->free_inodes) { ++ spin_unlock(&sbinfo->stat_lock); ++ return -ENOSPC; ++ } ++ sbinfo->free_inodes--; ++ spin_unlock(&sbinfo->stat_lock); ++ } ++ ++ if (old_dentry->d_inode || d_is_fallthru(old_dentry)) { ++ if (old_dentry->d_inode && S_ISDIR(old_dentry->d_inode->i_mode)) ++ shmem_rmdir(dir, old_dentry); ++ else ++ shmem_unlink(dir, old_dentry); ++ } ++ ++ dir->i_size += BOGO_DIRENT_SIZE; ++ dir->i_ctime = dir->i_mtime = CURRENT_TIME; ++ /* Extra pinning count for the created dentry */ ++ dget(new_dentry); ++ spin_lock(&new_dentry->d_lock); ++ new_dentry->d_flags |= DCACHE_WHITEOUT; ++ spin_unlock(&new_dentry->d_lock); ++ return 0; ++} ++ ++static void shmem_d_instantiate(struct inode *dir, struct dentry *dentry, ++ struct inode *inode); ++ ++/* ++ * Create a dentry to signify a fallthru. A fallthru lets us read the ++ * low-level dentries into the dcache once on the first readdir() and ++ * then ++ */ ++static int shmem_fallthru(struct inode *dir, struct dentry *dentry) ++{ ++ struct shmem_sb_info *sbinfo = SHMEM_SB(dir->i_sb); ++ ++ /* FIXME: this is stupid */ ++ if (!(dir->i_sb->s_flags & MS_WHITEOUT)) ++ return -EPERM; ++ ++ if (dentry->d_inode || d_is_fallthru(dentry) || d_is_whiteout(dentry)) ++ return -EEXIST; ++ ++ /* ++ * Each new link needs a new dentry, pinning lowmem, and tmpfs ++ * dentries cannot be pruned until they are unlinked. ++ */ ++ if (sbinfo->max_inodes) { ++ spin_lock(&sbinfo->stat_lock); ++ if (!sbinfo->free_inodes) { ++ spin_unlock(&sbinfo->stat_lock); ++ return -ENOSPC; ++ } ++ sbinfo->free_inodes--; ++ spin_unlock(&sbinfo->stat_lock); ++ } ++ ++ shmem_d_instantiate(dir, dentry, NULL); ++ dir->i_ctime = dir->i_mtime = CURRENT_TIME; ++ ++ spin_lock(&dentry->d_lock); ++ dentry->d_flags |= DCACHE_FALLTHRU; ++ spin_unlock(&dentry->d_lock); ++ return 0; ++} ++ ++static void shmem_d_instantiate(struct inode *dir, struct dentry *dentry, ++ struct inode *inode) ++{ ++ if (d_is_whiteout(dentry)) { ++ /* Re-using an existing whiteout */ ++ shmem_free_inode(dir->i_sb); ++ if (S_ISDIR(inode->i_mode)) ++ inode->i_mode |= S_OPAQUE; ++ } else if (d_is_fallthru(dentry)) { ++ shmem_free_inode(dir->i_sb); ++ } else { ++ /* New dentry */ ++ dir->i_size += BOGO_DIRENT_SIZE; ++ dget(dentry); /* Extra count - pin the dentry in core */ ++ } ++ /* Will clear DCACHE_WHITEOUT and DCACHE_FALLTHRU flags */ ++ d_instantiate(dentry, inode); ++} + /* + * File creation. Allocate an inode, and we're done.. + */ +@@ -1822,15 +1934,16 @@ shmem_mknod(struct inode *dir, struct de + iput(inode); + return error; + } ++ + if (dir->i_mode & S_ISGID) { + inode->i_gid = dir->i_gid; + if (S_ISDIR(mode)) + inode->i_mode |= S_ISGID; + } +- dir->i_size += BOGO_DIRENT_SIZE; ++ ++ shmem_d_instantiate(dir, dentry, inode); ++ + dir->i_ctime = dir->i_mtime = CURRENT_TIME; +- d_instantiate(dentry, inode); +- dget(dentry); /* Extra count - pin the dentry in core */ + } + return error; + } +@@ -1868,12 +1981,11 @@ static int shmem_link(struct dentry *old + if (ret) + goto out; + +- dir->i_size += BOGO_DIRENT_SIZE; ++ shmem_d_instantiate(dir, dentry, inode); ++ + inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; + inc_nlink(inode); + atomic_inc(&inode->i_count); /* New dentry reference */ +- dget(dentry); /* Extra pinning count for the created dentry */ +- d_instantiate(dentry, inode); + out: + return ret; + } +@@ -1882,21 +1994,63 @@ static int shmem_unlink(struct inode *di + { + struct inode *inode = dentry->d_inode; + +- if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) +- shmem_free_inode(inode->i_sb); ++ if (d_is_whiteout(dentry) || d_is_fallthru(dentry) || ++ (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode))) ++ shmem_free_inode(dir->i_sb); + ++ if (inode) { ++ inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; ++ drop_nlink(inode); ++ } + dir->i_size -= BOGO_DIRENT_SIZE; +- inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; +- drop_nlink(inode); + dput(dentry); /* Undo the count from "create" - this does all the work */ + return 0; + } + ++static void shmem_dir_unlink_whiteouts(struct inode *dir, struct dentry *dentry) ++{ ++ if (!dentry->d_inode) ++ return; ++ ++ /* Remove whiteouts from logical empty directory */ ++ if (S_ISDIR(dentry->d_inode->i_mode) && ++ dentry->d_inode->i_sb->s_flags & MS_WHITEOUT) { ++ struct dentry *child, *next; ++ LIST_HEAD(list); ++ ++ spin_lock(&dcache_lock); ++ list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) { ++ spin_lock(&child->d_lock); ++ /* Unlink fallthrus too */ ++ if (d_is_whiteout(child) || d_is_fallthru(child)) { ++ __d_drop(child); ++ if (!list_empty(&child->d_lru)) { ++ list_del(&child->d_lru); ++ dentry_stat.nr_unused--; ++ } ++ list_add(&child->d_lru, &list); ++ } ++ spin_unlock(&child->d_lock); ++ } ++ spin_unlock(&dcache_lock); ++ ++ list_for_each_entry_safe(child, next, &list, d_lru) { ++ spin_lock(&child->d_lock); ++ list_del_init(&child->d_lru); ++ spin_unlock(&child->d_lock); ++ ++ shmem_unlink(dentry->d_inode, child); ++ } ++ } ++} ++ + static int shmem_rmdir(struct inode *dir, struct dentry *dentry) + { + if (!simple_empty(dentry)) + return -ENOTEMPTY; + ++ /* Remove whiteouts from logical empty directory */ ++ shmem_dir_unlink_whiteouts(dir, dentry); + drop_nlink(dentry->d_inode); + drop_nlink(dir); + return shmem_unlink(dir, dentry); +@@ -1905,7 +2059,7 @@ static int shmem_rmdir(struct inode *dir + /* + * The VFS layer already does all the dentry stuff for rename, + * we just have to decrement the usage count for the target if +- * it exists so that the VFS layer correctly free's it when it ++ * it exists so that the VFS layer correctly frees it when it + * gets overwritten. + */ + static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) +@@ -1916,7 +2070,12 @@ static int shmem_rename(struct inode *ol + if (!simple_empty(new_dentry)) + return -ENOTEMPTY; + ++ if (d_is_whiteout(new_dentry)) ++ shmem_unlink(new_dir, new_dentry); ++ + if (new_dentry->d_inode) { ++ /* Remove whiteouts from logical empty directory */ ++ shmem_dir_unlink_whiteouts(new_dir, new_dentry); + (void) shmem_unlink(new_dir, new_dentry); + if (they_are_dirs) + drop_nlink(old_dir); +@@ -1981,12 +2140,12 @@ static int shmem_symlink(struct inode *d + unlock_page(page); + page_cache_release(page); + } ++ ++ shmem_d_instantiate(dir, dentry, inode); ++ + if (dir->i_mode & S_ISGID) + inode->i_gid = dir->i_gid; +- dir->i_size += BOGO_DIRENT_SIZE; + dir->i_ctime = dir->i_mtime = CURRENT_TIME; +- d_instantiate(dentry, inode); +- dget(dentry); + return 0; + } + +@@ -2363,6 +2522,12 @@ int shmem_fill_super(struct super_block + if (!root) + goto failed_iput; + sb->s_root = root; ++ ++#ifdef CONFIG_TMPFS ++ if (!(sb->s_flags & MS_NOUSER)) ++ sb->s_flags |= MS_WHITEOUT; ++#endif ++ + return 0; + + failed_iput: +@@ -2463,6 +2628,8 @@ static const struct inode_operations shm + .rmdir = shmem_rmdir, + .mknod = shmem_mknod, + .rename = shmem_rename, ++ .whiteout = shmem_whiteout, ++ .fallthru = shmem_fallthru, + #endif + #ifdef CONFIG_TMPFS_POSIX_ACL + .setattr = shmem_notify_change, |