diff options
Diffstat (limited to 'fs/kernfs')
| -rw-r--r-- | fs/kernfs/dir.c | 362 | ||||
| -rw-r--r-- | fs/kernfs/file.c | 166 | ||||
| -rw-r--r-- | fs/kernfs/inode.c | 163 | ||||
| -rw-r--r-- | fs/kernfs/kernfs-internal.h | 57 | ||||
| -rw-r--r-- | fs/kernfs/mount.c | 99 | ||||
| -rw-r--r-- | fs/kernfs/symlink.c | 30 |
6 files changed, 533 insertions, 344 deletions
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 935ef8cb02b2..5c0efd6b239f 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -17,7 +17,6 @@ #include "kernfs-internal.h" -static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to * call pr_cont() while holding rename_lock. Because sometimes pr_cont() @@ -27,7 +26,6 @@ static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ */ static DEFINE_SPINLOCK(kernfs_pr_cont_lock); static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by pr_cont_lock */ -static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */ #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb) @@ -51,22 +49,14 @@ static bool kernfs_lockdep(struct kernfs_node *kn) #endif } -static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen) -{ - if (!kn) - return strlcpy(buf, "(null)", buflen); - - return strlcpy(buf, kn->parent ? kn->name : "/", buflen); -} - /* kernfs_node_depth - compute depth from @from to @to */ static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to) { size_t depth = 0; - while (to->parent && to != from) { + while (rcu_dereference(to->__parent) && to != from) { depth++; - to = to->parent; + to = rcu_dereference(to->__parent); } return depth; } @@ -84,18 +74,18 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, db = kernfs_depth(rb->kn, b); while (da > db) { - a = a->parent; + a = rcu_dereference(a->__parent); da--; } while (db > da) { - b = b->parent; + b = rcu_dereference(b->__parent); db--; } /* worst case b and a will be the same at root */ while (b != a) { - b = b->parent; - a = a->parent; + b = rcu_dereference(b->__parent); + a = rcu_dereference(a->__parent); } return a; @@ -127,7 +117,7 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, * * [3] when @kn_to is %NULL result will be "(null)" * - * Return: the length of the full path. If the full length is equal to or + * Return: the length of the constructed path. If the path would have been * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ @@ -138,19 +128,17 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, struct kernfs_node *kn, *common; const char parent_str[] = "/.."; size_t depth_from, depth_to, len = 0; + ssize_t copied; int i, j; if (!kn_to) - return strlcpy(buf, "(null)", buflen); + return strscpy(buf, "(null)", buflen); if (!kn_from) kn_from = kernfs_root(kn_to)->kn; if (kn_from == kn_to) - return strlcpy(buf, "/", buflen); - - if (!buf) - return -EINVAL; + return strscpy(buf, "/", buflen); common = kernfs_common_ancestor(kn_from, kn_to); if (WARN_ON(!common)) @@ -161,18 +149,22 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, buf[0] = '\0'; - for (i = 0; i < depth_from; i++) - len += strlcpy(buf + len, parent_str, - len < buflen ? buflen - len : 0); + for (i = 0; i < depth_from; i++) { + copied = strscpy(buf + len, parent_str, buflen - len); + if (copied < 0) + return copied; + len += copied; + } /* Calculate how many bytes we need for the rest */ for (i = depth_to - 1; i >= 0; i--) { + const char *name; + 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); + kn = rcu_dereference(kn->__parent); + + name = rcu_dereference(kn->name); + len += scnprintf(buf + len, buflen - len, "/%s", name); } return len; @@ -185,24 +177,29 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, * @buflen: size of @buf * * Copies the name of @kn into @buf of @buflen bytes. The behavior is - * similar to strlcpy(). + * similar to strscpy(). * * Fills buffer with "(null)" if @kn is %NULL. * - * Return: the length of @kn's name and if @buf isn't long enough, - * it's filled up to @buflen-1 and nul terminated. + * Return: the resulting length of @buf. If @buf isn't long enough, + * it's filled up to @buflen-1 and nul terminated, and returns -E2BIG. * * This function can be called from any context. */ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { - unsigned long flags; - int ret; + struct kernfs_node *kn_parent; - spin_lock_irqsave(&kernfs_rename_lock, flags); - ret = kernfs_name_locked(kn, buf, buflen); - spin_unlock_irqrestore(&kernfs_rename_lock, flags); - return ret; + if (!kn) + return strscpy(buf, "(null)", buflen); + + guard(rcu)(); + /* + * KERNFS_ROOT_INVARIANT_PARENT is ignored here. The name is RCU freed and + * the parent is either existing or not. + */ + kn_parent = rcu_dereference(kn->__parent); + return strscpy(buf, kn_parent ? rcu_dereference(kn->name) : "/", buflen); } /** @@ -217,20 +214,24 @@ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) * path (which includes '..'s) as needed to reach from @from to @to is * returned. * - * Return: the length of the full path. If the full length is equal to or + * Return: the length of the constructed path. If the path would have been * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, char *buf, size_t buflen) { - unsigned long flags; - int ret; + struct kernfs_root *root; - spin_lock_irqsave(&kernfs_rename_lock, flags); - ret = kernfs_path_from_node_locked(to, from, buf, buflen); - spin_unlock_irqrestore(&kernfs_rename_lock, flags); - return ret; + guard(rcu)(); + if (to) { + root = kernfs_root(to); + if (!(root->flags & KERNFS_ROOT_INVARIANT_PARENT)) { + guard(read_lock_irqsave)(&root->kernfs_rename_lock); + return kernfs_path_from_node_locked(to, from, buf, buflen); + } + } + return kernfs_path_from_node_locked(to, from, buf, buflen); } EXPORT_SYMBOL_GPL(kernfs_path_from_node); @@ -268,12 +269,10 @@ void pr_cont_kernfs_path(struct kernfs_node *kn) sz = kernfs_path_from_node(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)"); + if (sz == -E2BIG) + pr_cont("(name too long)"); + else + pr_cont("(error)"); goto out; } @@ -295,12 +294,14 @@ out: struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) { struct kernfs_node *parent; + struct kernfs_root *root; unsigned long flags; - spin_lock_irqsave(&kernfs_rename_lock, flags); - parent = kn->parent; + root = kernfs_root(kn); + read_lock_irqsave(&root->kernfs_rename_lock, flags); + parent = kernfs_parent(kn); kernfs_get(parent); - spin_unlock_irqrestore(&kernfs_rename_lock, flags); + read_unlock_irqrestore(&root->kernfs_rename_lock, flags); return parent; } @@ -339,13 +340,13 @@ static int kernfs_name_compare(unsigned int hash, const char *name, return -1; if (ns > kn->ns) return 1; - return strcmp(name, kn->name); + return strcmp(name, kernfs_rcu_name(kn)); } static int kernfs_sd_compare(const struct kernfs_node *left, const struct kernfs_node *right) { - return kernfs_name_compare(left->hash, left->name, left->ns, right); + return kernfs_name_compare(left->hash, kernfs_rcu_name(left), left->ns, right); } /** @@ -363,8 +364,12 @@ static int kernfs_sd_compare(const struct kernfs_node *left, */ static int kernfs_link_sibling(struct kernfs_node *kn) { - struct rb_node **node = &kn->parent->dir.children.rb_node; struct rb_node *parent = NULL; + struct kernfs_node *kn_parent; + struct rb_node **node; + + kn_parent = kernfs_parent(kn); + node = &kn_parent->dir.children.rb_node; while (*node) { struct kernfs_node *pos; @@ -383,12 +388,14 @@ static int kernfs_link_sibling(struct kernfs_node *kn) /* add new node and rebalance the tree */ rb_link_node(&kn->rb, parent, node); - rb_insert_color(&kn->rb, &kn->parent->dir.children); + rb_insert_color(&kn->rb, &kn_parent->dir.children); /* successfully added, account subdir number */ + down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) - kn->parent->dir.subdirs++; - kernfs_inc_rev(kn->parent); + kn_parent->dir.subdirs++; + kernfs_inc_rev(kn_parent); + up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); return 0; } @@ -408,14 +415,19 @@ static int kernfs_link_sibling(struct kernfs_node *kn) */ static bool kernfs_unlink_sibling(struct kernfs_node *kn) { + struct kernfs_node *kn_parent; + if (RB_EMPTY_NODE(&kn->rb)) return false; + kn_parent = kernfs_parent(kn); + down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) - kn->parent->dir.subdirs--; - kernfs_inc_rev(kn->parent); + kn_parent->dir.subdirs--; + kernfs_inc_rev(kn_parent); + up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); - rb_erase(&kn->rb, &kn->parent->dir.children); + rb_erase(&kn->rb, &kn_parent->dir.children); RB_CLEAR_NODE(&kn->rb); return true; } @@ -528,6 +540,21 @@ void kernfs_get(struct kernfs_node *kn) } EXPORT_SYMBOL_GPL(kernfs_get); +static void kernfs_free_rcu(struct rcu_head *rcu) +{ + struct kernfs_node *kn = container_of(rcu, struct kernfs_node, rcu); + + /* If the whole node goes away, then name can't be used outside */ + kfree_const(rcu_access_pointer(kn->name)); + + if (kn->iattr) { + simple_xattrs_free(&kn->iattr->xattrs, NULL); + kmem_cache_free(kernfs_iattrs_cache, kn->iattr); + } + + kmem_cache_free(kernfs_node_cache, kn); +} + /** * kernfs_put - put a reference count on a kernfs_node * @kn: the target kernfs_node @@ -547,25 +574,21 @@ void kernfs_put(struct kernfs_node *kn) * Moving/renaming is always done while holding reference. * kn->parent won't change beneath us. */ - parent = kn->parent; + parent = kernfs_parent(kn); WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS, "kernfs_put: %s/%s: released with incorrect active_ref %d\n", - parent ? parent->name : "", kn->name, atomic_read(&kn->active)); + parent ? rcu_dereference(parent->name) : "", + rcu_dereference(kn->name), atomic_read(&kn->active)); if (kernfs_type(kn) == KERNFS_LINK) kernfs_put(kn->symlink.target_kn); - kfree_const(kn->name); - - if (kn->iattr) { - simple_xattrs_free(&kn->iattr->xattrs); - kmem_cache_free(kernfs_iattrs_cache, kn->iattr); - } - spin_lock(&kernfs_idr_lock); + spin_lock(&root->kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); - spin_unlock(&kernfs_idr_lock); - kmem_cache_free(kernfs_node_cache, kn); + spin_unlock(&root->kernfs_idr_lock); + + call_rcu(&kn->rcu, kernfs_free_rcu); kn = parent; if (kn) { @@ -574,7 +597,7 @@ void kernfs_put(struct kernfs_node *kn) } else { /* just released the root kn, free @root too */ idr_destroy(&root->ino_idr); - kfree(root); + kfree_rcu(root, rcu); } } EXPORT_SYMBOL_GPL(kernfs_put); @@ -616,13 +639,13 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, goto err_out1; idr_preload(GFP_KERNEL); - spin_lock(&kernfs_idr_lock); + spin_lock(&root->kernfs_idr_lock); ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC); if (ret >= 0 && ret < root->last_id_lowbits) root->id_highbits++; id_highbits = root->id_highbits; root->last_id_lowbits = ret; - spin_unlock(&kernfs_idr_lock); + spin_unlock(&root->kernfs_idr_lock); idr_preload_end(); if (ret < 0) goto err_out2; @@ -633,7 +656,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, atomic_set(&kn->active, KN_DEACTIVATED_BIAS); RB_CLEAR_NODE(&kn->rb); - kn->name = name; + rcu_assign_pointer(kn->name, name); kn->mode = mode; kn->flags = flags; @@ -652,13 +675,18 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, if (parent) { ret = security_kernfs_init_security(parent, kn); if (ret) - goto err_out3; + goto err_out4; } return kn; + err_out4: + simple_xattrs_free(&kn->iattr->xattrs, NULL); + kmem_cache_free(kernfs_iattrs_cache, kn->iattr); err_out3: + spin_lock(&root->kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); + spin_unlock(&root->kernfs_idr_lock); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: @@ -673,11 +701,23 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, { struct kernfs_node *kn; + if (parent->mode & S_ISGID) { + /* this code block imitates inode_init_owner() for + * kernfs + */ + + if (parent->iattr) + gid = parent->iattr->ia_gid; + + if (flags & KERNFS_DIR) + mode |= S_ISGID; + } + kn = __kernfs_new_node(kernfs_root(parent), parent, name, mode, uid, gid, flags); if (kn) { kernfs_get(parent); - kn->parent = parent; + rcu_assign_pointer(kn->__parent, parent); } return kn; } @@ -700,7 +740,7 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, ino_t ino = kernfs_id_ino(id); u32 gen = kernfs_id_gen(id); - spin_lock(&kernfs_idr_lock); + rcu_read_lock(); kn = idr_find(&root->ino_idr, (u32)ino); if (!kn) @@ -724,10 +764,10 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, if (unlikely(!__kernfs_active(kn) || !atomic_inc_not_zero(&kn->count))) goto err_unlock; - spin_unlock(&kernfs_idr_lock); + rcu_read_unlock(); return kn; err_unlock: - spin_unlock(&kernfs_idr_lock); + rcu_read_unlock(); return NULL; } @@ -745,18 +785,20 @@ err_unlock: */ int kernfs_add_one(struct kernfs_node *kn) { - struct kernfs_node *parent = kn->parent; - struct kernfs_root *root = kernfs_root(parent); + struct kernfs_root *root = kernfs_root(kn); struct kernfs_iattrs *ps_iattr; + struct kernfs_node *parent; bool has_ns; int ret; down_write(&root->kernfs_rwsem); + parent = kernfs_parent(kn); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", - has_ns ? "required" : "invalid", parent->name, kn->name)) + has_ns ? "required" : "invalid", + kernfs_rcu_name(parent), kernfs_rcu_name(kn))) goto out_unlock; if (kernfs_type(parent) != KERNFS_DIR) @@ -766,19 +808,22 @@ int kernfs_add_one(struct kernfs_node *kn) if (parent->flags & (KERNFS_REMOVING | KERNFS_EMPTY_DIR)) goto out_unlock; - kn->hash = kernfs_name_hash(kn->name, kn->ns); + kn->hash = kernfs_name_hash(kernfs_rcu_name(kn), kn->ns); ret = kernfs_link_sibling(kn); if (ret) goto out_unlock; /* Update timestamps on the parent */ + down_write(&root->kernfs_iattr_rwsem); + ps_iattr = parent->iattr; if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } + up_write(&root->kernfs_iattr_rwsem); up_write(&root->kernfs_rwsem); /* @@ -819,7 +864,7 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, if (has_ns != (bool)ns) { WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", - has_ns ? "required" : "invalid", parent->name, name); + has_ns ? "required" : "invalid", kernfs_rcu_name(parent), name); return NULL; } @@ -844,16 +889,16 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, const unsigned char *path, const void *ns) { - size_t len; + ssize_t len; char *p, *name; lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem); spin_lock_irq(&kernfs_pr_cont_lock); - len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf)); + len = strscpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf)); - if (len >= sizeof(kernfs_pr_cont_buf)) { + if (len < 0) { spin_unlock_irq(&kernfs_pr_cont_lock); return NULL; } @@ -922,6 +967,11 @@ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, return kn; } +unsigned int kernfs_root_flags(struct kernfs_node *kn) +{ + return kernfs_root(kn)->flags; +} + /** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy @@ -942,8 +992,12 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, return ERR_PTR(-ENOMEM); idr_init(&root->ino_idr); + spin_lock_init(&root->kernfs_idr_lock); init_rwsem(&root->kernfs_rwsem); + init_rwsem(&root->kernfs_iattr_rwsem); + init_rwsem(&root->kernfs_supers_rwsem); INIT_LIST_HEAD(&root->supers); + rwlock_init(&root->kernfs_rename_lock); /* * On 64bit ino setups, id is ino. On 32bit, low 32bits are ino. @@ -1080,9 +1134,10 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, return ERR_PTR(rc); } -static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) +static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - struct kernfs_node *kn; + struct kernfs_node *kn, *parent; struct kernfs_root *root; if (flags & LOOKUP_RCU) @@ -1090,8 +1145,6 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) /* Negative hashed dentry? */ if (d_really_is_negative(dentry)) { - struct kernfs_node *parent; - /* If the kernfs parent node has changed discard and * proceed to ->lookup. * @@ -1133,16 +1186,17 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) if (!kernfs_active(kn)) goto out_bad; + parent = kernfs_parent(kn); /* The kernfs node has been moved? */ - if (kernfs_dentry_node(dentry->d_parent) != kn->parent) + if (kernfs_dentry_node(dentry->d_parent) != parent) goto out_bad; /* The kernfs node has been renamed */ - if (strcmp(dentry->d_name.name, kn->name) != 0) + if (strcmp(dentry->d_name.name, kernfs_rcu_name(kn)) != 0) goto out_bad; /* The kernfs node has been moved to a different namespace */ - if (kn->parent && kernfs_ns_enabled(kn->parent) && + if (parent && kernfs_ns_enabled(parent) && kernfs_info(dentry->d_sb)->ns != kn->ns) goto out_bad; @@ -1200,24 +1254,24 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, return d_splice_alias(inode, dentry); } -static int kernfs_iop_mkdir(struct user_namespace *mnt_userns, - struct inode *dir, struct dentry *dentry, - umode_t mode) +static struct dentry *kernfs_iop_mkdir(struct mnt_idmap *idmap, + struct inode *dir, struct dentry *dentry, + umode_t mode) { struct kernfs_node *parent = dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(parent)->syscall_ops; int ret; if (!scops || !scops->mkdir) - return -EPERM; + return ERR_PTR(-EPERM); if (!kernfs_get_active(parent)) - return -ENODEV; + return ERR_PTR(-ENODEV); ret = scops->mkdir(parent, dentry->d_name.name, mode); kernfs_put_active(parent); - return ret; + return ERR_PTR(ret); } static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) @@ -1238,7 +1292,7 @@ static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) return ret; } -static int kernfs_iop_rename(struct user_namespace *mnt_userns, +static int kernfs_iop_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) @@ -1335,7 +1389,7 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, return kernfs_leftmost_descendant(rb_to_kn(rbn)); /* no sibling left, visit parent */ - return pos->parent; + return kernfs_parent(pos); } static void kernfs_activate_one(struct kernfs_node *kn) @@ -1347,7 +1401,7 @@ static void kernfs_activate_one(struct kernfs_node *kn) if (kernfs_active(kn) || (kn->flags & (KERNFS_HIDDEN | KERNFS_REMOVING))) return; - WARN_ON_ONCE(kn->parent && RB_EMPTY_NODE(&kn->rb)); + WARN_ON_ONCE(rcu_access_pointer(kn->__parent) && RB_EMPTY_NODE(&kn->rb)); WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); atomic_sub(KN_DEACTIVATED_BIAS, &kn->active); @@ -1417,7 +1471,7 @@ void kernfs_show(struct kernfs_node *kn, bool show) static void __kernfs_remove(struct kernfs_node *kn) { - struct kernfs_node *pos; + struct kernfs_node *pos, *parent; /* Short-circuit if non-root @kn has already finished removal. */ if (!kn) @@ -1429,10 +1483,10 @@ static void __kernfs_remove(struct kernfs_node *kn) * This is for kernfs_remove_self() which plays with active ref * after removal. */ - if (kn->parent && RB_EMPTY_NODE(&kn->rb)) + if (kernfs_parent(kn) && RB_EMPTY_NODE(&kn->rb)) return; - pr_debug("kernfs %s: removing\n", kn->name); + pr_debug("kernfs %s: removing\n", kernfs_rcu_name(kn)); /* prevent new usage by marking all nodes removing and deactivating */ pos = NULL; @@ -1455,21 +1509,24 @@ static void __kernfs_remove(struct kernfs_node *kn) kernfs_get(pos); kernfs_drain(pos); - + parent = kernfs_parent(pos); /* * kernfs_unlink_sibling() succeeds once per node. Use it * to decide who's responsible for cleanups. */ - if (!pos->parent || kernfs_unlink_sibling(pos)) { + if (!parent || kernfs_unlink_sibling(pos)) { struct kernfs_iattrs *ps_iattr = - pos->parent ? pos->parent->iattr : NULL; + parent ? parent->iattr : NULL; /* update timestamps on the parent */ + down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); + if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } + up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); kernfs_put(pos); } @@ -1528,8 +1585,9 @@ void kernfs_break_active_protection(struct kernfs_node *kn) * invoked before finishing the kernfs operation. Note that while this * function restores the active reference, it doesn't and can't actually * restore the active protection - @kn may already or be in the process of - * being removed. Once kernfs_break_active_protection() is invoked, that - * protection is irreversibly gone for the kernfs operation instance. + * being drained and removed. Once kernfs_break_active_protection() is + * invoked, that protection is irreversibly gone for the kernfs operation + * instance. * * While this function may be called at any point after * kernfs_break_active_protection() is invoked, its most useful location @@ -1685,11 +1743,11 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, { struct kernfs_node *old_parent; struct kernfs_root *root; - const char *old_name = NULL; + const char *old_name; int error; /* can't move or rename root */ - if (!kn->parent) + if (!rcu_access_pointer(kn->__parent)) return -EINVAL; root = kernfs_root(kn); @@ -1700,9 +1758,19 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, (new_parent->flags & KERNFS_EMPTY_DIR)) goto out; + old_parent = kernfs_parent(kn); + if (root->flags & KERNFS_ROOT_INVARIANT_PARENT) { + error = -EINVAL; + if (WARN_ON_ONCE(old_parent != new_parent)) + goto out; + } + error = 0; - if ((kn->parent == new_parent) && (kn->ns == new_ns) && - (strcmp(kn->name, new_name) == 0)) + old_name = kernfs_rcu_name(kn); + if (!new_name) + new_name = old_name; + if ((old_parent == new_parent) && (kn->ns == new_ns) && + (strcmp(old_name, new_name) == 0)) goto out; /* nothing to rename */ error = -EEXIST; @@ -1710,7 +1778,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, goto out; /* rename kernfs_node */ - if (strcmp(kn->name, new_name) != 0) { + if (strcmp(old_name, new_name) != 0) { error = -ENOMEM; new_name = kstrdup_const(new_name, GFP_KERNEL); if (!new_name) @@ -1723,27 +1791,32 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, * Move to the appropriate place in the appropriate directories rbtree. */ kernfs_unlink_sibling(kn); - kernfs_get(new_parent); - /* rename_lock protects ->parent and ->name accessors */ - spin_lock_irq(&kernfs_rename_lock); + /* rename_lock protects ->parent accessors */ + if (old_parent != new_parent) { + kernfs_get(new_parent); + write_lock_irq(&root->kernfs_rename_lock); - old_parent = kn->parent; - kn->parent = new_parent; + rcu_assign_pointer(kn->__parent, new_parent); - kn->ns = new_ns; - if (new_name) { - old_name = kn->name; - kn->name = new_name; - } + kn->ns = new_ns; + if (new_name) + rcu_assign_pointer(kn->name, new_name); - spin_unlock_irq(&kernfs_rename_lock); + write_unlock_irq(&root->kernfs_rename_lock); + kernfs_put(old_parent); + } else { + /* name assignment is RCU protected, parent is the same */ + kn->ns = new_ns; + if (new_name) + rcu_assign_pointer(kn->name, new_name); + } - kn->hash = kernfs_name_hash(kn->name, kn->ns); + kn->hash = kernfs_name_hash(new_name ?: old_name, kn->ns); kernfs_link_sibling(kn); - kernfs_put(old_parent); - kfree_const(old_name); + if (new_name && !is_kernel_rodata((unsigned long)old_name)) + kfree_rcu_mightsleep(old_name); error = 0; out: @@ -1751,12 +1824,6 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, return error; } -/* Relationship between mode and the DT_xxx types */ -static inline unsigned char dt_type(struct kernfs_node *kn) -{ - return (kn->mode >> 12) & 15; -} - static int kernfs_dir_fop_release(struct inode *inode, struct file *filp) { kernfs_put(filp->private_data); @@ -1768,7 +1835,8 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns, { if (pos) { int valid = kernfs_active(pos) && - pos->parent == parent && hash == pos->hash; + rcu_access_pointer(pos->__parent) == parent && + hash == pos->hash; kernfs_put(pos); if (!valid) pos = NULL; @@ -1833,8 +1901,8 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos); pos; pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) { - const char *name = pos->name; - unsigned int type = dt_type(pos); + const char *name = kernfs_rcu_name(pos); + unsigned int type = fs_umode_to_dtype(pos->mode); int len = strlen(name); ino_t ino = kernfs_ino(pos); @@ -1842,10 +1910,10 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) file->private_data = pos; kernfs_get(pos); - up_read(&root->kernfs_rwsem); - if (!dir_emit(ctx, name, len, ino, type)) + if (!dir_emit(ctx, name, len, ino, type)) { + up_read(&root->kernfs_rwsem); return 0; - down_read(&root->kernfs_rwsem); + } } up_read(&root->kernfs_rwsem); file->private_data = NULL; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e4a50e4ff0d2..9adf36e6364b 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -70,6 +70,24 @@ static struct kernfs_open_node *of_on(struct kernfs_open_file *of) !list_empty(&of->list)); } +/* Get active reference to kernfs node for an open file */ +static struct kernfs_open_file *kernfs_get_active_of(struct kernfs_open_file *of) +{ + /* Skip if file was already released */ + if (unlikely(of->released)) + return NULL; + + if (!kernfs_get_active(of->kn)) + return NULL; + + return of; +} + +static void kernfs_put_active_of(struct kernfs_open_file *of) +{ + return kernfs_put_active(of->kn); +} + /** * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn * @@ -139,7 +157,7 @@ static void kernfs_seq_stop_active(struct seq_file *sf, void *v) if (ops->seq_stop) ops->seq_stop(sf, v); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); } static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) @@ -152,7 +170,7 @@ static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return ERR_PTR(-ENODEV); ops = kernfs_ops(of->kn); @@ -238,7 +256,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; @@ -252,7 +270,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) else len = -EINVAL; - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len < 0) @@ -323,7 +341,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; @@ -335,7 +353,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) else len = -EINVAL; - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len > 0) @@ -357,13 +375,13 @@ static void kernfs_vma_open(struct vm_area_struct *vma) if (!of->vm_ops) return; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return; if (of->vm_ops->open) of->vm_ops->open(vma); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); } static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) @@ -375,14 +393,14 @@ static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) if (!of->vm_ops) return VM_FAULT_SIGBUS; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -395,7 +413,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) if (!of->vm_ops) return VM_FAULT_SIGBUS; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = 0; @@ -404,7 +422,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) else file_update_time(file); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -418,71 +436,22 @@ static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, if (!of->vm_ops) return -EINVAL; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return -EINVAL; ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write); - kernfs_put_active(of->kn); - return ret; -} - -#ifdef CONFIG_NUMA -static int kernfs_vma_set_policy(struct vm_area_struct *vma, - struct mempolicy *new) -{ - struct file *file = vma->vm_file; - struct kernfs_open_file *of = kernfs_of(file); - int ret; - - if (!of->vm_ops) - return 0; - - if (!kernfs_get_active(of->kn)) - return -EINVAL; - - ret = 0; - if (of->vm_ops->set_policy) - ret = of->vm_ops->set_policy(vma, new); - - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } -static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma, - unsigned long addr) -{ - struct file *file = vma->vm_file; - struct kernfs_open_file *of = kernfs_of(file); - struct mempolicy *pol; - - if (!of->vm_ops) - return vma->vm_policy; - - if (!kernfs_get_active(of->kn)) - return vma->vm_policy; - - pol = vma->vm_policy; - if (of->vm_ops->get_policy) - pol = of->vm_ops->get_policy(vma, addr); - - kernfs_put_active(of->kn); - return pol; -} - -#endif - static const struct vm_operations_struct kernfs_vm_ops = { .open = kernfs_vma_open, .fault = kernfs_vma_fault, .page_mkwrite = kernfs_vma_page_mkwrite, .access = kernfs_vma_access, -#ifdef CONFIG_NUMA - .set_policy = kernfs_vma_set_policy, - .get_policy = kernfs_vma_get_policy, -#endif }; static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) @@ -496,7 +465,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) * warnings and we don't want to add spurious locking dependency * between the two. Check whether mmap is actually implemented * without grabbing @of->mutex by testing HAS_MMAP flag. See the - * comment in kernfs_file_open() for more details. + * comment in kernfs_fop_open() for more details. */ if (!(of->kn->flags & KERNFS_HAS_MMAP)) return -ENODEV; @@ -504,7 +473,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) mutex_lock(&of->mutex); rc = -ENODEV; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) goto out_unlock; ops = kernfs_ops(of->kn); @@ -532,12 +501,14 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) goto out_put; rc = 0; - of->mmapped = true; - of_on(of)->nr_mmapped++; - of->vm_ops = vma->vm_ops; + if (!of->mmapped) { + of->mmapped = true; + of_on(of)->nr_mmapped++; + of->vm_ops = vma->vm_ops; + } vma->vm_ops = &kernfs_vm_ops; out_put: - kernfs_put_active(of->kn); + kernfs_put_active_of(of); out_unlock: mutex_unlock(&of->mutex); @@ -683,11 +654,18 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) * each file a separate locking class. Let's differentiate on * whether the file has mmap or not for now. * - * Both paths of the branch look the same. They're supposed to + * For similar reasons, writable and readonly files are given different + * lockdep key, because the writable file /sys/power/resume may call vfs + * lookup helpers for arbitrary paths and readonly files can be read by + * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs. + * + * All three cases look the same. They're supposed to * look that way and give @of->mutex different static lockdep keys. */ if (has_mmap) mutex_init(&of->mutex); + else if (file->f_mode & FMODE_WRITE) + mutex_init(&of->mutex); else mutex_init(&of->mutex); @@ -818,8 +796,9 @@ bool kernfs_should_drain_open_files(struct kernfs_node *kn) /* * @kn being deactivated guarantees that @kn->attr.open can't change * beneath us making the lockless test below safe. + * Callers post kernfs_unbreak_active_protection may be counted in + * kn->active by now, do not WARN_ON because of them. */ - WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); rcu_read_lock(); on = rcu_dereference(kn->attr.open); @@ -891,7 +870,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret; - if (!kernfs_get_active(kn)) + if (!kernfs_get_active_of(of)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (kn->attr.ops->poll) @@ -899,7 +878,34 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) else ret = kernfs_generic_poll(of, wait); - kernfs_put_active(kn); + kernfs_put_active_of(of); + return ret; +} + +static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) +{ + struct kernfs_open_file *of = kernfs_of(file); + const struct kernfs_ops *ops; + loff_t ret; + + /* + * @of->mutex nests outside active ref and is primarily to ensure that + * the ops aren't called concurrently for the same open file. + */ + mutex_lock(&of->mutex); + if (!kernfs_get_active_of(of)) { + mutex_unlock(&of->mutex); + return -ENODEV; + } + + ops = kernfs_ops(of->kn); + if (ops->llseek) + ret = ops->llseek(of, offset, whence); + else + ret = generic_file_llseek(file, offset, whence); + + kernfs_put_active_of(of); + mutex_unlock(&of->mutex); return ret; } @@ -922,11 +928,13 @@ repeat: root = kernfs_root(kn); /* kick fsnotify */ - down_write(&root->kernfs_rwsem); + down_read(&root->kernfs_supers_rwsem); + down_read(&root->kernfs_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *p_inode = NULL; + const char *kn_name; struct inode *inode; struct qstr name; @@ -940,7 +948,8 @@ repeat: if (!inode) continue; - name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name)); + kn_name = kernfs_rcu_name(kn); + name = QSTR(kn_name); parent = kernfs_get_parent(kn); if (parent) { p_inode = ilookup(info->sb, kernfs_ino(parent)); @@ -960,7 +969,8 @@ repeat: iput(inode); } - up_write(&root->kernfs_rwsem); + up_read(&root->kernfs_rwsem); + up_read(&root->kernfs_supers_rwsem); kernfs_put(kn); goto repeat; } @@ -1005,13 +1015,13 @@ EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { .read_iter = kernfs_fop_read_iter, .write_iter = kernfs_fop_write_iter, - .llseek = generic_file_llseek, + .llseek = kernfs_fop_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index eac0f210299a..a36aaee98dce 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -24,45 +24,46 @@ static const struct inode_operations kernfs_iops = { .listxattr = kernfs_iop_listxattr, }; -static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, int alloc) +static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, bool alloc) { - static DEFINE_MUTEX(iattr_mutex); - struct kernfs_iattrs *ret; + struct kernfs_iattrs *ret __free(kfree) = NULL; + struct kernfs_iattrs *attr; - mutex_lock(&iattr_mutex); + attr = READ_ONCE(kn->iattr); + if (attr || !alloc) + return attr; - if (kn->iattr || !alloc) - goto out_unlock; - - kn->iattr = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL); - if (!kn->iattr) - goto out_unlock; + ret = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL); + if (!ret) + return NULL; /* assign default attributes */ - kn->iattr->ia_uid = GLOBAL_ROOT_UID; - kn->iattr->ia_gid = GLOBAL_ROOT_GID; - - ktime_get_real_ts64(&kn->iattr->ia_atime); - kn->iattr->ia_mtime = kn->iattr->ia_atime; - kn->iattr->ia_ctime = kn->iattr->ia_atime; - - simple_xattrs_init(&kn->iattr->xattrs); - atomic_set(&kn->iattr->nr_user_xattrs, 0); - atomic_set(&kn->iattr->user_xattr_size, 0); -out_unlock: - ret = kn->iattr; - mutex_unlock(&iattr_mutex); - return ret; + ret->ia_uid = GLOBAL_ROOT_UID; + ret->ia_gid = GLOBAL_ROOT_GID; + + ktime_get_real_ts64(&ret->ia_atime); + ret->ia_mtime = ret->ia_atime; + ret->ia_ctime = ret->ia_atime; + + simple_xattrs_init(&ret->xattrs); + atomic_set(&ret->nr_user_xattrs, 0); + atomic_set(&ret->user_xattr_size, 0); + + /* If someone raced us, recognize it. */ + if (!try_cmpxchg(&kn->iattr, &attr, ret)) + return READ_ONCE(kn->iattr); + + return no_free_ptr(ret); } static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) { - return __kernfs_iattrs(kn, 1); + return __kernfs_iattrs(kn, true); } static struct kernfs_iattrs *kernfs_iattrs_noalloc(struct kernfs_node *kn) { - return __kernfs_iattrs(kn, 0); + return __kernfs_iattrs(kn, false); } int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) @@ -101,13 +102,13 @@ int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) int ret; struct kernfs_root *root = kernfs_root(kn); - down_write(&root->kernfs_rwsem); + down_write(&root->kernfs_iattr_rwsem); ret = __kernfs_setattr(kn, iattr); - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_iattr_rwsem); return ret; } -int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); @@ -119,8 +120,8 @@ int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, return -EINVAL; root = kernfs_root(kn); - down_write(&root->kernfs_rwsem); - error = setattr_prepare(&init_user_ns, dentry, iattr); + down_write(&root->kernfs_iattr_rwsem); + error = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (error) goto out; @@ -129,10 +130,10 @@ int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, goto out; /* this ignores size changes */ - setattr_copy(&init_user_ns, inode, iattr); + setattr_copy(&nop_mnt_idmap, inode, iattr); out: - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_iattr_rwsem); return error; } @@ -151,8 +152,7 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) static inline void set_default_inode_attr(struct inode *inode, umode_t mode) { inode->i_mode = mode; - inode->i_atime = inode->i_mtime = - inode->i_ctime = current_time(inode); + simple_inode_init_ts(inode); } static inline void set_inode_attr(struct inode *inode, @@ -160,16 +160,17 @@ static inline void set_inode_attr(struct inode *inode, { inode->i_uid = attrs->ia_uid; inode->i_gid = attrs->ia_gid; - inode->i_atime = attrs->ia_atime; - inode->i_mtime = attrs->ia_mtime; - inode->i_ctime = attrs->ia_ctime; + inode_set_atime_to_ts(inode, attrs->ia_atime); + inode_set_mtime_to_ts(inode, attrs->ia_mtime); + inode_set_ctime_to_ts(inode, attrs->ia_ctime); } static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode) { - struct kernfs_iattrs *attrs = kn->iattr; + struct kernfs_iattrs *attrs; inode->i_mode = kn->mode; + attrs = kernfs_iattrs_noalloc(kn); if (attrs) /* * kernfs_node has non-default attributes get them from @@ -181,7 +182,7 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode) set_nlink(inode, kn->dir.subdirs + 2); } -int kernfs_iop_getattr(struct user_namespace *mnt_userns, +int kernfs_iop_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -189,10 +190,10 @@ int kernfs_iop_getattr(struct user_namespace *mnt_userns, struct kernfs_node *kn = inode->i_private; struct kernfs_root *root = kernfs_root(kn); - down_read(&root->kernfs_rwsem); + down_read(&root->kernfs_iattr_rwsem); kernfs_refresh_inode(kn, inode); - generic_fillattr(&init_user_ns, inode, stat); - up_read(&root->kernfs_rwsem); + generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); + up_read(&root->kernfs_iattr_rwsem); return 0; } @@ -250,7 +251,7 @@ struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) struct inode *inode; inode = iget_locked(sb, kernfs_ino(kn)); - if (inode && (inode->i_state & I_NEW)) + if (inode && (inode_state_read_once(inode) & I_NEW)) kernfs_init_inode(kn, inode); return inode; @@ -272,7 +273,7 @@ void kernfs_evict_inode(struct inode *inode) kernfs_put(kn); } -int kernfs_iop_permission(struct user_namespace *mnt_userns, +int kernfs_iop_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct kernfs_node *kn; @@ -285,10 +286,10 @@ int kernfs_iop_permission(struct user_namespace *mnt_userns, kn = inode->i_private; root = kernfs_root(kn); - down_read(&root->kernfs_rwsem); + down_read(&root->kernfs_iattr_rwsem); kernfs_refresh_inode(kn, inode); - ret = generic_permission(&init_user_ns, inode, mask); - up_read(&root->kernfs_rwsem); + ret = generic_permission(&nop_mnt_idmap, inode, mask); + up_read(&root->kernfs_iattr_rwsem); return ret; } @@ -306,11 +307,19 @@ int kernfs_xattr_get(struct kernfs_node *kn, const char *name, int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags) { - struct kernfs_iattrs *attrs = kernfs_iattrs(kn); + struct simple_xattr *old_xattr; + struct kernfs_iattrs *attrs; + + attrs = kernfs_iattrs(kn); if (!attrs) return -ENOMEM; - return simple_xattr_set(&attrs->xattrs, name, value, size, flags, NULL); + old_xattr = simple_xattr_set(&attrs->xattrs, name, value, size, flags); + if (IS_ERR(old_xattr)) + return PTR_ERR(old_xattr); + + simple_xattr_free(old_xattr); + return 0; } static int kernfs_vfs_xattr_get(const struct xattr_handler *handler, @@ -324,7 +333,7 @@ static int kernfs_vfs_xattr_get(const struct xattr_handler *handler, } static int kernfs_vfs_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) @@ -340,9 +349,10 @@ static int kernfs_vfs_user_xattr_add(struct kernfs_node *kn, struct simple_xattrs *xattrs, const void *value, size_t size, int flags) { - atomic_t *sz = &kn->iattr->user_xattr_size; - atomic_t *nr = &kn->iattr->nr_user_xattrs; - ssize_t removed_size; + struct kernfs_iattrs *attr = kernfs_iattrs_noalloc(kn); + atomic_t *sz = &attr->user_xattr_size; + atomic_t *nr = &attr->nr_user_xattrs; + struct simple_xattr *old_xattr; int ret; if (atomic_inc_return(nr) > KERNFS_MAX_USER_XATTRS) { @@ -355,13 +365,18 @@ static int kernfs_vfs_user_xattr_add(struct kernfs_node *kn, goto dec_size_out; } - ret = simple_xattr_set(xattrs, full_name, value, size, flags, - &removed_size); - - if (!ret && removed_size >= 0) - size = removed_size; - else if (!ret) + old_xattr = simple_xattr_set(xattrs, full_name, value, size, flags); + if (!old_xattr) return 0; + + if (IS_ERR(old_xattr)) { + ret = PTR_ERR(old_xattr); + goto dec_size_out; + } + + ret = 0; + size = old_xattr->size; + simple_xattr_free(old_xattr); dec_size_out: atomic_sub(size, sz); dec_count_out: @@ -374,24 +389,26 @@ static int kernfs_vfs_user_xattr_rm(struct kernfs_node *kn, struct simple_xattrs *xattrs, const void *value, size_t size, int flags) { - atomic_t *sz = &kn->iattr->user_xattr_size; - atomic_t *nr = &kn->iattr->nr_user_xattrs; - ssize_t removed_size; - int ret; + struct kernfs_iattrs *attr = kernfs_iattrs_noalloc(kn); + atomic_t *sz = &attr->user_xattr_size; + atomic_t *nr = &attr->nr_user_xattrs; + struct simple_xattr *old_xattr; - ret = simple_xattr_set(xattrs, full_name, value, size, flags, - &removed_size); + old_xattr = simple_xattr_set(xattrs, full_name, value, size, flags); + if (!old_xattr) + return 0; - if (removed_size >= 0) { - atomic_sub(removed_size, sz); - atomic_dec(nr); - } + if (IS_ERR(old_xattr)) + return PTR_ERR(old_xattr); - return ret; + atomic_sub(old_xattr->size, sz); + atomic_dec(nr); + simple_xattr_free(old_xattr); + return 0; } static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) @@ -434,7 +451,7 @@ static const struct xattr_handler kernfs_user_xattr_handler = { .set = kernfs_vfs_user_xattr_set, }; -const struct xattr_handler *kernfs_xattr_handlers[] = { +const struct xattr_handler * const kernfs_xattr_handlers[] = { &kernfs_trusted_xattr_handler, &kernfs_security_xattr_handler, &kernfs_user_xattr_handler, diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 9046d9f39e63..6061b6f70d2a 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -38,6 +38,7 @@ struct kernfs_root { /* private fields, do not use outside kernfs proper */ struct idr ino_idr; + spinlock_t kernfs_idr_lock; /* root->ino_idr */ u32 last_id_lowbits; u32 id_highbits; struct kernfs_syscall_ops *syscall_ops; @@ -47,6 +48,13 @@ struct kernfs_root { wait_queue_head_t deactivate_waitq; struct rw_semaphore kernfs_rwsem; + struct rw_semaphore kernfs_iattr_rwsem; + struct rw_semaphore kernfs_supers_rwsem; + + /* kn->parent and kn->name */ + rwlock_t kernfs_rename_lock; + + struct rcu_head rcu; }; /* +1 to avoid triggering overflow warning when negating it */ @@ -60,11 +68,14 @@ struct kernfs_root { * * Return: the kernfs_root @kn belongs to. */ -static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn) +static inline struct kernfs_root *kernfs_root(const struct kernfs_node *kn) { + const struct kernfs_node *knp; /* if parent exists, it's always a dir; otherwise, @sd is a dir */ - if (kn->parent) - kn = kn->parent; + guard(rcu)(); + knp = rcu_dereference(kn->__parent); + if (knp) + kn = knp; return kn->dir.root; } @@ -93,6 +104,38 @@ struct kernfs_super_info { }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) +static inline bool kernfs_root_is_locked(const struct kernfs_node *kn) +{ + return lockdep_is_held(&kernfs_root(kn)->kernfs_rwsem); +} + +static inline bool kernfs_rename_is_locked(const struct kernfs_node *kn) +{ + return lockdep_is_held(&kernfs_root(kn)->kernfs_rename_lock); +} + +static inline const char *kernfs_rcu_name(const struct kernfs_node *kn) +{ + return rcu_dereference_check(kn->name, kernfs_root_is_locked(kn)); +} + +static inline struct kernfs_node *kernfs_parent(const struct kernfs_node *kn) +{ + /* + * The kernfs_node::__parent remains valid within a RCU section. The kn + * can be reparented (and renamed) which changes the entry. This can be + * avoided by locking kernfs_root::kernfs_rwsem or + * kernfs_root::kernfs_rename_lock. + * Both locks can be used to obtain a reference on __parent. Once the + * reference count reaches 0 then the node is about to be freed + * and can not be renamed (or become a different parent) anymore. + */ + return rcu_dereference_check(kn->__parent, + kernfs_root_is_locked(kn) || + kernfs_rename_is_locked(kn) || + !atomic_read(&kn->count)); +} + static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) { if (d_really_is_negative(dentry)) @@ -125,13 +168,13 @@ extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; /* * inode.c */ -extern const struct xattr_handler *kernfs_xattr_handlers[]; +extern const struct xattr_handler * const kernfs_xattr_handlers[]; void kernfs_evict_inode(struct inode *inode); -int kernfs_iop_permission(struct user_namespace *mnt_userns, +int kernfs_iop_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); -int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, +int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr); -int kernfs_iop_getattr(struct user_namespace *mnt_userns, +int kernfs_iop_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size); diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index e08e8d999807..3ac52e141766 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -16,11 +16,14 @@ #include <linux/namei.h> #include <linux/seq_file.h> #include <linux/exportfs.h> +#include <linux/uuid.h> +#include <linux/statfs.h> #include "kernfs-internal.h" -struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; -struct kernfs_global_locks *kernfs_locks; +struct kmem_cache *kernfs_node_cache __ro_after_init; +struct kmem_cache *kernfs_iattrs_cache __ro_after_init; +struct kernfs_global_locks *kernfs_locks __ro_after_init; static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry) { @@ -45,13 +48,35 @@ static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry) return 0; } +static int kernfs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + simple_statfs(dentry, buf); + buf->f_fsid = uuid_to_fsid(dentry->d_sb->s_uuid.b); + return 0; +} + const struct super_operations kernfs_sops = { - .statfs = simple_statfs, - .drop_inode = generic_delete_inode, + .statfs = kernfs_statfs, + .drop_inode = inode_just_drop, .evict_inode = kernfs_evict_inode, .show_options = kernfs_sop_show_options, .show_path = kernfs_sop_show_path, + + /* + * sysfs is built on top of kernfs and sysfs provides the power + * management infrastructure to support suspend/hibernate by + * writing to various files in /sys/power/. As filesystems may + * be automatically frozen during suspend/hibernate implementing + * freeze/thaw support for kernfs generically will cause + * deadlocks as the suspending/hibernation initiating task will + * hold a VFS lock that it will then wait upon to be released. + * If freeze/thaw for kernfs is needed talk to the VFS. + */ + .freeze_fs = NULL, + .unfreeze_fs = NULL, + .freeze_super = NULL, + .thaw_super = NULL, }; static int kernfs_encode_fh(struct inode *inode, __u32 *fh, int *max_len, @@ -115,9 +140,6 @@ static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb, inode = kernfs_get_inode(sb, kn); kernfs_put(kn); - if (!inode) - return ERR_PTR(-ESTALE); - return d_obtain_alias(inode); } @@ -138,8 +160,10 @@ static struct dentry *kernfs_fh_to_parent(struct super_block *sb, static struct dentry *kernfs_get_parent_dentry(struct dentry *child) { struct kernfs_node *kn = kernfs_dentry_node(child); + struct kernfs_root *root = kernfs_root(kn); - return d_obtain_alias(kernfs_get_inode(child->d_sb, kn->parent)); + guard(rwsem_read)(&root->kernfs_rwsem); + return d_obtain_alias(kernfs_get_inode(child->d_sb, kernfs_parent(kn))); } static const struct export_operations kernfs_export_ops = { @@ -179,10 +203,10 @@ static struct kernfs_node *find_next_ancestor(struct kernfs_node *child, return NULL; } - while (child->parent != parent) { - if (!child->parent) + while (kernfs_parent(child) != parent) { + child = kernfs_parent(child); + if (!child) return NULL; - child = child->parent; } return child; @@ -199,17 +223,28 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct super_block *sb) { struct dentry *dentry; - struct kernfs_node *knparent = NULL; + struct kernfs_node *knparent; + struct kernfs_root *root; BUG_ON(sb->s_op != &kernfs_sops); dentry = dget(sb->s_root); /* Check if this is the root kernfs_node */ - if (!kn->parent) + if (!rcu_access_pointer(kn->__parent)) return dentry; - knparent = find_next_ancestor(kn, NULL); + root = kernfs_root(kn); + /* + * As long as kn is valid, its parent can not vanish. This is cgroup's + * kn so it can't have its parent replaced. Therefore it is safe to use + * the ancestor node outside of the RCU or locked section. + */ + if (WARN_ON_ONCE(!(root->flags & KERNFS_ROOT_INVARIANT_PARENT))) + return ERR_PTR(-EINVAL); + scoped_guard(rcu) { + knparent = find_next_ancestor(kn, NULL); + } if (WARN_ON(!knparent)) { dput(dentry); return ERR_PTR(-EINVAL); @@ -218,17 +253,26 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, do { struct dentry *dtmp; struct kernfs_node *kntmp; + const char *name; if (kn == knparent) return dentry; - kntmp = find_next_ancestor(kn, knparent); - if (WARN_ON(!kntmp)) { + + scoped_guard(rwsem_read, &root->kernfs_rwsem) { + kntmp = find_next_ancestor(kn, knparent); + if (WARN_ON(!kntmp)) { + dput(dentry); + return ERR_PTR(-EINVAL); + } + name = kstrdup(kernfs_rcu_name(kntmp), GFP_KERNEL); + } + if (!name) { dput(dentry); - return ERR_PTR(-EINVAL); + return ERR_PTR(-ENOMEM); } - dtmp = lookup_positive_unlocked(kntmp->name, dentry, - strlen(kntmp->name)); + dtmp = lookup_noperm_positive_unlocked(&QSTR(name), dentry); dput(dentry); + kfree(name); if (IS_ERR(dtmp)) return dtmp; knparent = kntmp; @@ -254,9 +298,10 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k if (info->root->flags & KERNFS_ROOT_SUPPORT_EXPORTOP) sb->s_export_op = &kernfs_export_ops; sb->s_time_gran = 1; + sb->s_maxbytes = MAX_LFS_FILESIZE; /* sysfs dentries and inodes don't require IO to create */ - sb->s_shrink.seeks = 0; + sb->s_shrink->seeks = 0; /* get root inode, initialize and unlock it */ down_read(&kf_root->kernfs_rwsem); @@ -274,7 +319,7 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k return -ENOMEM; } sb->s_root = root; - sb->s_d_op = &kernfs_dops; + set_default_d_op(sb, &kernfs_dops); return 0; } @@ -351,9 +396,13 @@ int kernfs_get_tree(struct fs_context *fc) } sb->s_flags |= SB_ACTIVE; - down_write(&root->kernfs_rwsem); + uuid_t uuid; + uuid_gen(&uuid); + super_set_uuid(sb, uuid.b, sizeof(uuid)); + + down_write(&root->kernfs_supers_rwsem); list_add(&info->node, &info->root->supers); - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_supers_rwsem); } fc->root = dget(sb->s_root); @@ -380,9 +429,9 @@ void kernfs_kill_sb(struct super_block *sb) struct kernfs_super_info *info = kernfs_info(sb); struct kernfs_root *root = info->root; - down_write(&root->kernfs_rwsem); + down_write(&root->kernfs_supers_rwsem); list_del(&info->node); - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_supers_rwsem); /* * Remove the superblock from fs_supers/s_instances diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 45371a70caa7..0bd8a2143723 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -62,10 +62,10 @@ static int kernfs_get_target_path(struct kernfs_node *parent, /* go up to the root, stop at the base */ base = parent; - while (base->parent) { - kn = target->parent; - while (kn->parent && base != kn) - kn = kn->parent; + while (kernfs_parent(base)) { + kn = kernfs_parent(target); + while (kernfs_parent(kn) && base != kn) + kn = kernfs_parent(kn); if (base == kn) break; @@ -75,14 +75,14 @@ static int kernfs_get_target_path(struct kernfs_node *parent, strcpy(s, "../"); s += 3; - base = base->parent; + base = kernfs_parent(base); } /* determine end of target string for reverse fillup */ kn = target; - while (kn->parent && kn != base) { - len += strlen(kn->name) + 1; - kn = kn->parent; + while (kernfs_parent(kn) && kn != base) { + len += strlen(kernfs_rcu_name(kn)) + 1; + kn = kernfs_parent(kn); } /* check limits */ @@ -94,15 +94,16 @@ static int kernfs_get_target_path(struct kernfs_node *parent, /* reverse fillup of target string from target to base */ kn = target; - while (kn->parent && kn != base) { - int slen = strlen(kn->name); + while (kernfs_parent(kn) && kn != base) { + const char *name = kernfs_rcu_name(kn); + int slen = strlen(name); len -= slen; - memcpy(s + len, kn->name, slen); + memcpy(s + len, name, slen); if (len) s[--len] = '/'; - kn = kn->parent; + kn = kernfs_parent(kn); } return 0; @@ -111,12 +112,13 @@ static int kernfs_get_target_path(struct kernfs_node *parent, static int kernfs_getlink(struct inode *inode, char *path) { struct kernfs_node *kn = inode->i_private; - struct kernfs_node *parent = kn->parent; + struct kernfs_node *parent; struct kernfs_node *target = kn->symlink.target_kn; - struct kernfs_root *root = kernfs_root(parent); + struct kernfs_root *root = kernfs_root(kn); int error; down_read(&root->kernfs_rwsem); + parent = kernfs_parent(kn); error = kernfs_get_target_path(parent, target, path); up_read(&root->kernfs_rwsem); |