diff options
Diffstat (limited to 'fs/kernfs')
| -rw-r--r-- | fs/kernfs/dir.c | 224 | ||||
| -rw-r--r-- | fs/kernfs/file.c | 92 | ||||
| -rw-r--r-- | fs/kernfs/kernfs-internal.h | 2 | ||||
| -rw-r--r-- | fs/kernfs/mount.c | 87 |
4 files changed, 348 insertions, 57 deletions
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 91e004518237..e5499c5f63da 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -44,28 +44,116 @@ static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen) return strlcpy(buf, kn->parent ? kn->name : "/", buflen); } -static char * __must_check kernfs_path_locked(struct kernfs_node *kn, char *buf, - size_t buflen) +/* kernfs_node_depth - compute depth from @from to @to */ +static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to) { - char *p = buf + buflen; - int len; + size_t depth = 0; - *--p = '\0'; + while (to->parent && to != from) { + depth++; + to = to->parent; + } + return depth; +} - do { - len = strlen(kn->name); - if (p - buf < len + 1) { - buf[0] = '\0'; - p = NULL; - break; - } - p -= len; - memcpy(p, kn->name, len); - *--p = '/'; - kn = kn->parent; - } while (kn && kn->parent); +static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, + struct kernfs_node *b) +{ + size_t da, db; + struct kernfs_root *ra = kernfs_root(a), *rb = kernfs_root(b); + + if (ra != rb) + return NULL; + + da = kernfs_depth(ra->kn, a); + db = kernfs_depth(rb->kn, b); + + while (da > db) { + a = a->parent; + da--; + } + while (db > da) { + b = b->parent; + db--; + } + + /* worst case b and a will be the same at root */ + while (b != a) { + b = b->parent; + a = a->parent; + } + + return a; +} + +/** + * kernfs_path_from_node_locked - find a pseudo-absolute path to @kn_to, + * where kn_from is treated as root of the path. + * @kn_from: kernfs node which should be treated as root for the path + * @kn_to: kernfs node to which path is needed + * @buf: buffer to copy the path into + * @buflen: size of @buf + * + * We need to handle couple of scenarios here: + * [1] when @kn_from is an ancestor of @kn_to at some level + * kn_from: /n1/n2/n3 + * kn_to: /n1/n2/n3/n4/n5 + * result: /n4/n5 + * + * [2] when @kn_from is on a different hierarchy and we need to find common + * ancestor between @kn_from and @kn_to. + * kn_from: /n1/n2/n3/n4 + * kn_to: /n1/n2/n5 + * result: /../../n5 + * OR + * kn_from: /n1/n2/n3/n4/n5 [depth=5] + * kn_to: /n1/n2/n3 [depth=3] + * result: /../.. + * + * Returns the length of the full path. If the full length is equal to or + * greater than @buflen, @buf contains the truncated path with the trailing + * '\0'. On error, -errno is returned. + */ +static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, + struct kernfs_node *kn_from, + char *buf, size_t buflen) +{ + struct kernfs_node *kn, *common; + const char parent_str[] = "/.."; + size_t depth_from, depth_to, len = 0; + int i, j; + + if (!kn_from) + kn_from = kernfs_root(kn_to)->kn; + + if (kn_from == kn_to) + return strlcpy(buf, "/", buflen); + + common = kernfs_common_ancestor(kn_from, kn_to); + if (WARN_ON(!common)) + return -EINVAL; - return p; + depth_to = kernfs_depth(common, kn_to); + depth_from = kernfs_depth(common, kn_from); + + if (buf) + buf[0] = '\0'; + + for (i = 0; i < depth_from; i++) + len += strlcpy(buf + len, parent_str, + len < buflen ? buflen - len : 0); + + /* Calculate how many bytes we need for the rest */ + for (i = depth_to - 1; i >= 0; i--) { + for (kn = kn_to, j = 0; j < i; j++) + kn = kn->parent; + len += strlcpy(buf + len, "/", + len < buflen ? buflen - len : 0); + len += strlcpy(buf + len, kn->name, + len < buflen ? buflen - len : 0); + } + + return len; } /** @@ -115,27 +203,33 @@ size_t kernfs_path_len(struct kernfs_node *kn) } /** - * kernfs_path - build full path of a given node - * @kn: kernfs_node of interest - * @buf: buffer to copy @kn's name into + * kernfs_path_from_node - build path of node @to relative to @from. + * @from: parent kernfs_node relative to which we need to build the path + * @to: kernfs_node of interest + * @buf: buffer to copy @to's path into * @buflen: size of @buf * - * Builds and returns the full path of @kn in @buf of @buflen bytes. The - * path is built from the end of @buf so the returned pointer usually - * doesn't match @buf. If @buf isn't long enough, @buf is nul terminated - * and %NULL is returned. + * Builds @to's path relative to @from in @buf. @from and @to must + * be on the same kernfs-root. If @from is not parent of @to, then a relative + * path (which includes '..'s) as needed to reach from @from to @to is + * returned. + * + * Returns the length of the full path. If the full length is equal to or + * greater than @buflen, @buf contains the truncated path with the trailing + * '\0'. On error, -errno is returned. */ -char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) +int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, + char *buf, size_t buflen) { unsigned long flags; - char *p; + int ret; spin_lock_irqsave(&kernfs_rename_lock, flags); - p = kernfs_path_locked(kn, buf, buflen); + ret = kernfs_path_from_node_locked(to, from, buf, buflen); spin_unlock_irqrestore(&kernfs_rename_lock, flags); - return p; + return ret; } -EXPORT_SYMBOL_GPL(kernfs_path); +EXPORT_SYMBOL_GPL(kernfs_path_from_node); /** * pr_cont_kernfs_name - pr_cont name of a kernfs_node @@ -164,17 +258,25 @@ void pr_cont_kernfs_name(struct kernfs_node *kn) void pr_cont_kernfs_path(struct kernfs_node *kn) { unsigned long flags; - char *p; + int sz; spin_lock_irqsave(&kernfs_rename_lock, flags); - p = kernfs_path_locked(kn, kernfs_pr_cont_buf, - sizeof(kernfs_pr_cont_buf)); - if (p) - pr_cont("%s", p); - else - pr_cont("<name too long>"); + sz = kernfs_path_from_node_locked(kn, NULL, kernfs_pr_cont_buf, + sizeof(kernfs_pr_cont_buf)); + if (sz < 0) { + pr_cont("(error)"); + goto out; + } + + if (sz >= sizeof(kernfs_pr_cont_buf)) { + pr_cont("(name too long)"); + goto out; + } + pr_cont("%s", kernfs_pr_cont_buf); + +out: spin_unlock_irqrestore(&kernfs_rename_lock, flags); } @@ -389,7 +491,7 @@ static void kernfs_drain(struct kernfs_node *kn) rwsem_release(&kn->dep_map, 1, _RET_IP_); } - kernfs_unmap_bin_file(kn); + kernfs_drain_open_files(kn); mutex_lock(&kernfs_mutex); } @@ -694,6 +796,29 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, return NULL; } +static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, + const unsigned char *path, + const void *ns) +{ + static char path_buf[PATH_MAX]; /* protected by kernfs_mutex */ + size_t len = strlcpy(path_buf, path, PATH_MAX); + char *p = path_buf; + char *name; + + lockdep_assert_held(&kernfs_mutex); + + if (len >= PATH_MAX) + return NULL; + + while ((name = strsep(&p, "/")) && parent) { + if (*name == '\0') + continue; + parent = kernfs_find_ns(parent, name, ns); + } + + return parent; +} + /** * kernfs_find_and_get_ns - find and get kernfs_node with the given name * @parent: kernfs_node to search under @@ -719,6 +844,29 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns); /** + * kernfs_walk_and_get_ns - find and get kernfs_node with the given path + * @parent: kernfs_node to search under + * @path: path to look for + * @ns: the namespace tag to use + * + * Look for kernfs_node with path @path under @parent and get a reference + * if found. This function may sleep and returns pointer to the found + * kernfs_node on success, %NULL on failure. + */ +struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, + const char *path, const void *ns) +{ + struct kernfs_node *kn; + + mutex_lock(&kernfs_mutex); + kn = kernfs_walk_ns(parent, path, ns); + kernfs_get(kn); + mutex_unlock(&kernfs_mutex); + + return kn; +} + +/** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy * @flags: KERNFS_ROOT_* flags diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 6875bd5d35f6..7fb45ee36897 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -701,7 +701,8 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) if (error) goto err_free; - ((struct seq_file *)file->private_data)->private = of; + of->seq_file = file->private_data; + of->seq_file->private = of; /* seq_file clears PWRITE unconditionally, restore it if WRITE */ if (file->f_mode & FMODE_WRITE) @@ -710,13 +711,22 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) /* make sure we have open node struct */ error = kernfs_get_open_node(kn, of); if (error) - goto err_close; + goto err_seq_release; + + if (ops->open) { + /* nobody has access to @of yet, skip @of->mutex */ + error = ops->open(of); + if (error) + goto err_put_node; + } /* open succeeded, put active references */ kernfs_put_active(kn); return 0; -err_close: +err_put_node: + kernfs_put_open_node(kn, of); +err_seq_release: seq_release(inode, file); err_free: kfree(of->prealloc_buf); @@ -726,11 +736,41 @@ err_out: return error; } +/* used from release/drain to ensure that ->release() is called exactly once */ +static void kernfs_release_file(struct kernfs_node *kn, + struct kernfs_open_file *of) +{ + /* + * @of is guaranteed to have no other file operations in flight and + * we just want to synchronize release and drain paths. + * @kernfs_open_file_mutex is enough. @of->mutex can't be used + * here because drain path may be called from places which can + * cause circular dependency. + */ + lockdep_assert_held(&kernfs_open_file_mutex); + + if (!of->released) { + /* + * A file is never detached without being released and we + * need to be able to release files which are deactivated + * and being drained. Don't use kernfs_ops(). + */ + kn->attr.ops->release(of); + of->released = true; + } +} + static int kernfs_fop_release(struct inode *inode, struct file *filp) { struct kernfs_node *kn = filp->f_path.dentry->d_fsdata; struct kernfs_open_file *of = kernfs_of(filp); + if (kn->flags & KERNFS_HAS_RELEASE) { + mutex_lock(&kernfs_open_file_mutex); + kernfs_release_file(kn, of); + mutex_unlock(&kernfs_open_file_mutex); + } + kernfs_put_open_node(kn, of); seq_release(inode, filp); kfree(of->prealloc_buf); @@ -739,12 +779,12 @@ static int kernfs_fop_release(struct inode *inode, struct file *filp) return 0; } -void kernfs_unmap_bin_file(struct kernfs_node *kn) +void kernfs_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; struct kernfs_open_file *of; - if (!(kn->flags & KERNFS_HAS_MMAP)) + if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE))) return; spin_lock_irq(&kernfs_open_node_lock); @@ -756,10 +796,17 @@ void kernfs_unmap_bin_file(struct kernfs_node *kn) return; mutex_lock(&kernfs_open_file_mutex); + list_for_each_entry(of, &on->files, list) { struct inode *inode = file_inode(of->file); - unmap_mapping_range(inode->i_mapping, 0, 0, 1); + + if (kn->flags & KERNFS_HAS_MMAP) + unmap_mapping_range(inode->i_mapping, 0, 0, 1); + + if (kn->flags & KERNFS_HAS_RELEASE) + kernfs_release_file(kn, of); } + mutex_unlock(&kernfs_open_file_mutex); kernfs_put_open_node(kn, NULL); @@ -779,26 +826,35 @@ void kernfs_unmap_bin_file(struct kernfs_node *kn) * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ +unsigned int kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) +{ + struct kernfs_node *kn = of->file->f_path.dentry->d_fsdata; + struct kernfs_open_node *on = kn->attr.open; + + poll_wait(of->file, &on->poll, wait); + + if (of->event != atomic_read(&on->event)) + return DEFAULT_POLLMASK|POLLERR|POLLPRI; + + return DEFAULT_POLLMASK; +} + static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = filp->f_path.dentry->d_fsdata; - struct kernfs_open_node *on = kn->attr.open; + unsigned int ret; if (!kernfs_get_active(kn)) - goto trigger; + return DEFAULT_POLLMASK|POLLERR|POLLPRI; - poll_wait(filp, &on->poll, wait); + if (kn->attr.ops->poll) + ret = kn->attr.ops->poll(of, wait); + else + ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); - - if (of->event != atomic_read(&on->event)) - goto trigger; - - return DEFAULT_POLLMASK; - - trigger: - return DEFAULT_POLLMASK|POLLERR|POLLPRI; + return ret; } static void kernfs_notify_workfn(struct work_struct *work) @@ -957,6 +1013,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, kn->flags |= KERNFS_HAS_SEQ_SHOW; if (ops->mmap) kn->flags |= KERNFS_HAS_MMAP; + if (ops->release) + kn->flags |= KERNFS_HAS_RELEASE; rc = kernfs_add_one(kn); if (rc) { diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 6762bfbd8207..34d5a59ebd41 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -108,7 +108,7 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, */ extern const struct file_operations kernfs_file_fops; -void kernfs_unmap_bin_file(struct kernfs_node *kn); +void kernfs_drain_open_files(struct kernfs_node *kn); /* * symlink.c diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 8eaf417187f1..a71e996d6c55 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -14,6 +14,8 @@ #include <linux/magic.h> #include <linux/slab.h> #include <linux/pagemap.h> +#include <linux/namei.h> +#include <linux/seq_file.h> #include "kernfs-internal.h" @@ -39,6 +41,19 @@ static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry) return 0; } +static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry) +{ + struct kernfs_node *node = dentry->d_fsdata; + struct kernfs_root *root = kernfs_root(node); + struct kernfs_syscall_ops *scops = root->syscall_ops; + + if (scops && scops->show_path) + return scops->show_path(sf, node, root); + + seq_dentry(sf, dentry, " \t\n\\"); + return 0; +} + const struct super_operations kernfs_sops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, @@ -46,6 +61,7 @@ const struct super_operations kernfs_sops = { .remount_fs = kernfs_sop_remount_fs, .show_options = kernfs_sop_show_options, + .show_path = kernfs_sop_show_path, }; /** @@ -62,6 +78,74 @@ struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) return NULL; } +/* + * find the next ancestor in the path down to @child, where @parent was the + * ancestor whose descendant we want to find. + * + * Say the path is /a/b/c/d. @child is d, @parent is NULL. We return the root + * node. If @parent is b, then we return the node for c. + * Passing in d as @parent is not ok. + */ +static struct kernfs_node *find_next_ancestor(struct kernfs_node *child, + struct kernfs_node *parent) +{ + if (child == parent) { + pr_crit_once("BUG in find_next_ancestor: called with parent == child"); + return NULL; + } + + while (child->parent != parent) { + if (!child->parent) + return NULL; + child = child->parent; + } + + return child; +} + +/** + * kernfs_node_dentry - get a dentry for the given kernfs_node + * @kn: kernfs_node for which a dentry is needed + * @sb: the kernfs super_block + */ +struct dentry *kernfs_node_dentry(struct kernfs_node *kn, + struct super_block *sb) +{ + struct dentry *dentry; + struct kernfs_node *knparent = NULL; + + BUG_ON(sb->s_op != &kernfs_sops); + + dentry = dget(sb->s_root); + + /* Check if this is the root kernfs_node */ + if (!kn->parent) + return dentry; + + knparent = find_next_ancestor(kn, NULL); + if (WARN_ON(!knparent)) + return ERR_PTR(-EINVAL); + + do { + struct dentry *dtmp; + struct kernfs_node *kntmp; + + if (kn == knparent) + return dentry; + kntmp = find_next_ancestor(kn, knparent); + if (WARN_ON(!kntmp)) + return ERR_PTR(-EINVAL); + mutex_lock(&d_inode(dentry)->i_mutex); + dtmp = lookup_one_len(kntmp->name, dentry, strlen(kntmp->name)); + mutex_unlock(&d_inode(dentry)->i_mutex); + dput(dentry); + if (IS_ERR(dtmp)) + return dtmp; + knparent = kntmp; + dentry = dtmp; + } while (true); +} + static int kernfs_fill_super(struct super_block *sb, unsigned long magic) { struct kernfs_super_info *info = kernfs_info(sb); @@ -158,7 +242,8 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, info->root = root; info->ns = ns; - sb = sget(fs_type, kernfs_test_super, kernfs_set_super, flags, info); + sb = sget_userns(fs_type, kernfs_test_super, kernfs_set_super, flags, + &init_user_ns, info); if (IS_ERR(sb) || sb->s_fs_info != info) kfree(info); if (IS_ERR(sb)) |