diff options
Diffstat (limited to 'fs/proc/proc_sysctl.c')
| -rw-r--r-- | fs/proc/proc_sysctl.c | 1112 |
1 files changed, 628 insertions, 484 deletions
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 71290463a1d3..49ab74e0bfde 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * /proc/sys support */ @@ -8,17 +9,56 @@ #include <linux/printk.h> #include <linux/security.h> #include <linux/sched.h> +#include <linux/cred.h> #include <linux/namei.h> #include <linux/mm.h> +#include <linux/uio.h> #include <linux/module.h> +#include <linux/bpf-cgroup.h> +#include <linux/mount.h> +#include <linux/kmemleak.h> +#include <linux/lockdep.h> #include "internal.h" +#define list_for_each_table_entry(entry, header) \ + entry = header->ctl_table; \ + for (size_t i = 0 ; i < header->ctl_table_size; ++i, entry++) + static const struct dentry_operations proc_sys_dentry_operations; static const struct file_operations proc_sys_file_operations; static const struct inode_operations proc_sys_inode_operations; static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; +/* + * Support for permanently empty directories. + * Must be non-empty to avoid sharing an address with other tables. + */ +static const struct ctl_table sysctl_mount_point[] = { + { } +}; + +/** + * register_sysctl_mount_point() - registers a sysctl mount point + * @path: path for the mount point + * + * Used to create a permanently empty directory to serve as mount point. + * There are some subtle but important permission checks this allows in the + * case of unprivileged mounts. + */ +struct ctl_table_header *register_sysctl_mount_point(const char *path) +{ + return register_sysctl_sz(path, sysctl_mount_point, 0); +} +EXPORT_SYMBOL(register_sysctl_mount_point); + +#define sysctl_is_perm_empty_ctl_header(hptr) \ + (hptr->type == SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY) +#define sysctl_set_perm_empty_ctl_header(hptr) \ + (hptr->type = SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY) +#define sysctl_clear_perm_empty_ctl_header(hptr) \ + (hptr->type = SYSCTL_TABLE_TYPE_DEFAULT) + void proc_sys_poll_notify(struct ctl_table_poll *poll) { if (!poll) @@ -28,12 +68,11 @@ void proc_sys_poll_notify(struct ctl_table_poll *poll) wake_up_interruptible(&poll->wait); } -static struct ctl_table root_table[] = { +static const struct ctl_table root_table[] = { { .procname = "", .mode = S_IFDIR|S_IRUGO|S_IXUGO, }, - { } }; static struct ctl_table_root sysctl_table_root = { .default_set.dir.header = { @@ -50,7 +89,7 @@ static DEFINE_SPINLOCK(sysctl_lock); static void drop_sysctl_table(struct ctl_table_header *header); static int sysctl_follow_link(struct ctl_table_header **phead, - struct ctl_table **pentry, struct nsproxy *namespaces); + const struct ctl_table **pentry); static int insert_links(struct ctl_table_header *head); static void put_links(struct ctl_table_header *header); @@ -63,27 +102,23 @@ static void sysctl_print_dir(struct ctl_dir *dir) static int namecmp(const char *name1, int len1, const char *name2, int len2) { - int minlen; int cmp; - minlen = len1; - if (minlen > len2) - minlen = len2; - - cmp = memcmp(name1, name2, minlen); + cmp = memcmp(name1, name2, min(len1, len2)); if (cmp == 0) cmp = len1 - len2; return cmp; } -/* Called under sysctl_lock */ -static struct ctl_table *find_entry(struct ctl_table_header **phead, +static const struct ctl_table *find_entry(struct ctl_table_header **phead, struct ctl_dir *dir, const char *name, int namelen) { struct ctl_table_header *head; - struct ctl_table *entry; + const struct ctl_table *entry; struct rb_node *node = dir->root.rb_node; + lockdep_assert_held(&sysctl_lock); + while (node) { struct ctl_node *ctl_node; @@ -108,7 +143,7 @@ static struct ctl_table *find_entry(struct ctl_table_header **phead, return NULL; } -static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) +static int insert_entry(struct ctl_table_header *head, const struct ctl_table *entry) { struct rb_node *node = &head->node[entry - head->ctl_table].node; struct rb_node **p = &head->parent->root.rb_node; @@ -118,7 +153,7 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) while (*p) { struct ctl_table_header *parent_head; - struct ctl_table *parent_entry; + const struct ctl_table *parent_entry; struct ctl_node *parent_node; const char *parent_name; int cmp; @@ -137,7 +172,7 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) else { pr_err("sysctl duplicate entry: "); sysctl_print_dir(head->parent); - pr_cont("/%s\n", entry->procname); + pr_cont("%s\n", entry->procname); return -EEXIST; } } @@ -147,7 +182,7 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) return 0; } -static void erase_entry(struct ctl_table_header *head, struct ctl_table *entry) +static void erase_entry(struct ctl_table_header *head, const struct ctl_table *entry) { struct rb_node *node = &head->node[entry - head->ctl_table].node; @@ -156,9 +191,10 @@ static void erase_entry(struct ctl_table_header *head, struct ctl_table *entry) static void init_header(struct ctl_table_header *head, struct ctl_table_root *root, struct ctl_table_set *set, - struct ctl_node *node, struct ctl_table *table) + struct ctl_node *node, const struct ctl_table *table, size_t table_size) { head->ctl_table = table; + head->ctl_table_size = table_size; head->ctl_table_arg = table; head->used = 0; head->count = 1; @@ -168,31 +204,51 @@ static void init_header(struct ctl_table_header *head, head->set = set; head->parent = NULL; head->node = node; + INIT_HLIST_HEAD(&head->inodes); if (node) { - struct ctl_table *entry; - for (entry = table; entry->procname; entry++, node++) + const struct ctl_table *entry; + + list_for_each_table_entry(entry, head) { node->header = head; + node++; + } } + if (table == sysctl_mount_point) + sysctl_set_perm_empty_ctl_header(head); } static void erase_header(struct ctl_table_header *head) { - struct ctl_table *entry; - for (entry = head->ctl_table; entry->procname; entry++) + const struct ctl_table *entry; + + list_for_each_table_entry(entry, head) erase_entry(head, entry); } static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header) { - struct ctl_table *entry; + const struct ctl_table *entry; + struct ctl_table_header *dir_h = &dir->header; int err; - dir->header.nreg++; + + /* Is this a permanently empty directory? */ + if (sysctl_is_perm_empty_ctl_header(dir_h)) + return -EROFS; + + /* Am I creating a permanently empty directory? */ + if (sysctl_is_perm_empty_ctl_header(header)) { + if (!RB_EMPTY_ROOT(&dir->root)) + return -EINVAL; + sysctl_set_perm_empty_ctl_header(dir_h); + } + + dir_h->nreg++; header->parent = dir; err = insert_links(header); if (err) goto fail_links; - for (entry = header->ctl_table; entry->procname; entry++) { + list_for_each_table_entry(entry, header) { err = insert_entry(header, entry); if (err) goto fail; @@ -202,31 +258,42 @@ fail: erase_header(header); put_links(header); fail_links: + if (header->ctl_table == sysctl_mount_point) + sysctl_clear_perm_empty_ctl_header(dir_h); header->parent = NULL; - drop_sysctl_table(&dir->header); + drop_sysctl_table(dir_h); return err; } -/* called under sysctl_lock */ static int use_table(struct ctl_table_header *p) { + lockdep_assert_held(&sysctl_lock); + if (unlikely(p->unregistering)) return 0; p->used++; return 1; } -/* called under sysctl_lock */ static void unuse_table(struct ctl_table_header *p) { + lockdep_assert_held(&sysctl_lock); + if (!--p->used) if (unlikely(p->unregistering)) complete(p->unregistering); } -/* called under sysctl_lock, will reacquire if has to wait */ +static void proc_sys_invalidate_dcache(struct ctl_table_header *head) +{ + proc_invalidate_siblings_dcache(&head->inodes, &sysctl_lock); +} + static void start_unregistering(struct ctl_table_header *p) { + /* will reacquire if has to wait */ + lockdep_assert_held(&sysctl_lock); + /* * if p->used is 0, nobody will ever touch that entry again; * we'll eliminate all paths to it before dropping sysctl_lock @@ -237,31 +304,22 @@ static void start_unregistering(struct ctl_table_header *p) p->unregistering = &wait; spin_unlock(&sysctl_lock); wait_for_completion(&wait); - spin_lock(&sysctl_lock); } else { /* anything non-NULL; we'll never dereference it */ p->unregistering = ERR_PTR(-EINVAL); + spin_unlock(&sysctl_lock); } /* + * Invalidate dentries for unregistered sysctls: namespaced sysctls + * can have duplicate names and contaminate dcache very badly. + */ + proc_sys_invalidate_dcache(p); + /* * do not remove from the list until nobody holds it; walking the * list in do_sysctl() relies on that. */ - erase_header(p); -} - -static void sysctl_head_get(struct ctl_table_header *head) -{ - spin_lock(&sysctl_lock); - head->count++; - spin_unlock(&sysctl_lock); -} - -void sysctl_head_put(struct ctl_table_header *head) -{ spin_lock(&sysctl_lock); - if (!--head->count) - kfree_rcu(head, rcu); - spin_unlock(&sysctl_lock); + erase_header(p); } static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head) @@ -284,20 +342,20 @@ static void sysctl_head_finish(struct ctl_table_header *head) } static struct ctl_table_set * -lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces) +lookup_header_set(struct ctl_table_root *root) { struct ctl_table_set *set = &root->default_set; if (root->lookup) - set = root->lookup(root, namespaces); + set = root->lookup(root); return set; } -static struct ctl_table *lookup_entry(struct ctl_table_header **phead, - struct ctl_dir *dir, - const char *name, int namelen) +static const struct ctl_table *lookup_entry(struct ctl_table_header **phead, + struct ctl_dir *dir, + const char *name, int namelen) { struct ctl_table_header *head; - struct ctl_table *entry; + const struct ctl_table *entry; spin_lock(&sysctl_lock); entry = find_entry(&head, dir, name, namelen); @@ -322,10 +380,10 @@ static struct ctl_node *first_usable_entry(struct rb_node *node) } static void first_entry(struct ctl_dir *dir, - struct ctl_table_header **phead, struct ctl_table **pentry) + struct ctl_table_header **phead, const struct ctl_table **pentry) { struct ctl_table_header *head = NULL; - struct ctl_table *entry = NULL; + const struct ctl_table *entry = NULL; struct ctl_node *ctl_node; spin_lock(&sysctl_lock); @@ -339,10 +397,10 @@ static void first_entry(struct ctl_dir *dir, *pentry = entry; } -static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentry) +static void next_entry(struct ctl_table_header **phead, const struct ctl_table **pentry) { struct ctl_table_header *head = *phead; - struct ctl_table *entry = *pentry; + const struct ctl_table *entry = *pentry; struct ctl_node *ctl_node = &head->node[entry - head->ctl_table]; spin_lock(&sysctl_lock); @@ -359,10 +417,6 @@ static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentr *pentry = entry; } -void register_sysctl_root(struct ctl_table_root *root) -{ -} - /* * sysctl_perm does NOT grant the superuser all rights automatically, because * some sysctl variables are readonly even to root. @@ -379,7 +433,7 @@ static int test_perm(int mode, int op) return -EACCES; } -static int sysctl_perm(struct ctl_table_header *head, struct ctl_table *table, int op) +static int sysctl_perm(struct ctl_table_header *head, const struct ctl_table *table, int op) { struct ctl_table_root *root = head->root; int mode; @@ -393,23 +447,33 @@ static int sysctl_perm(struct ctl_table_header *head, struct ctl_table *table, i } static struct inode *proc_sys_make_inode(struct super_block *sb, - struct ctl_table_header *head, struct ctl_table *table) + struct ctl_table_header *head, const struct ctl_table *table) { + struct ctl_table_root *root = head->root; struct inode *inode; struct proc_inode *ei; inode = new_inode(sb); if (!inode) - goto out; + return ERR_PTR(-ENOMEM); inode->i_ino = get_next_ino(); - sysctl_head_get(head); ei = PROC_I(inode); + + spin_lock(&sysctl_lock); + if (unlikely(head->unregistering)) { + spin_unlock(&sysctl_lock); + iput(inode); + return ERR_PTR(-ENOENT); + } ei->sysctl = head; ei->sysctl_entry = table; + hlist_add_head_rcu(&ei->sibling_inodes, &head->inodes); + head->count++; + spin_unlock(&sysctl_lock); - inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + simple_inode_init_ts(inode); inode->i_mode = table->mode; if (!S_ISDIR(table->mode)) { inode->i_mode |= S_IFREG; @@ -419,11 +483,27 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, inode->i_mode |= S_IFDIR; inode->i_op = &proc_sys_dir_operations; inode->i_fop = &proc_sys_dir_file_operations; + if (sysctl_is_perm_empty_ctl_header(head)) + make_empty_dir_inode(inode); } -out: + + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + if (root->set_ownership) + root->set_ownership(head, &inode->i_uid, &inode->i_gid); + return inode; } +void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) +{ + spin_lock(&sysctl_lock); + hlist_del_init_rcu(&PROC_I(inode)->sibling_inodes); + if (!--head->count) + kfree_rcu(head, rcu); + spin_unlock(&sysctl_lock); +} + static struct ctl_table_header *grab_header(struct inode *inode) { struct ctl_table_header *head = PROC_I(inode)->sysctl; @@ -437,8 +517,8 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry, { struct ctl_table_header *head = grab_header(dir); struct ctl_table_header *h = NULL; - struct qstr *name = &dentry->d_name; - struct ctl_table *p; + const struct qstr *name = &dentry->d_name; + const struct ctl_table *p; struct inode *inode; struct dentry *err = ERR_PTR(-ENOENT); struct ctl_dir *ctl_dir; @@ -454,20 +534,14 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry, goto out; if (S_ISLNK(p->mode)) { - ret = sysctl_follow_link(&h, &p, current->nsproxy); + ret = sysctl_follow_link(&h, &p); err = ERR_PTR(ret); if (ret) goto out; } - err = ERR_PTR(-ENOMEM); inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p); - if (!inode) - goto out; - - err = NULL; - d_set_d_op(dentry, &proc_sys_dentry_operations); - d_add(dentry, inode); + err = d_splice_alias_ops(inode, dentry, &proc_sys_dentry_operations); out: if (h) @@ -476,14 +550,15 @@ out: return err; } -static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, - size_t count, loff_t *ppos, int write) +static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter, + int write) { - struct inode *inode = file_inode(filp); + struct inode *inode = file_inode(iocb->ki_filp); struct ctl_table_header *head = grab_header(inode); - struct ctl_table *table = PROC_I(inode)->sysctl_entry; + const struct ctl_table *table = PROC_I(inode)->sysctl_entry; + size_t count = iov_iter_count(iter); + char *kbuf; ssize_t error; - size_t res; if (IS_ERR(head)) return PTR_ERR(head); @@ -501,33 +576,60 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, if (!table->proc_handler) goto out; + /* don't even try if the size is too large */ + error = -ENOMEM; + if (count >= KMALLOC_MAX_SIZE) + goto out; + kbuf = kvzalloc(count + 1, GFP_KERNEL); + if (!kbuf) + goto out; + + if (write) { + error = -EFAULT; + if (!copy_from_iter_full(kbuf, count, iter)) + goto out_free_buf; + kbuf[count] = '\0'; + } + + error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count, + &iocb->ki_pos); + if (error) + goto out_free_buf; + /* careful: calling conventions are nasty here */ - res = count; - error = table->proc_handler(table, write, buf, &res, ppos); - if (!error) - error = res; + error = table->proc_handler(table, write, kbuf, &count, &iocb->ki_pos); + if (error) + goto out_free_buf; + + if (!write) { + error = -EFAULT; + if (copy_to_iter(kbuf, count, iter) < count) + goto out_free_buf; + } + + error = count; +out_free_buf: + kvfree(kbuf); out: sysctl_head_finish(head); return error; } -static ssize_t proc_sys_read(struct file *filp, char __user *buf, - size_t count, loff_t *ppos) +static ssize_t proc_sys_read(struct kiocb *iocb, struct iov_iter *iter) { - return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0); + return proc_sys_call_handler(iocb, iter, 0); } -static ssize_t proc_sys_write(struct file *filp, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t proc_sys_write(struct kiocb *iocb, struct iov_iter *iter) { - return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1); + return proc_sys_call_handler(iocb, iter, 1); } static int proc_sys_open(struct inode *inode, struct file *filp) { struct ctl_table_header *head = grab_header(inode); - struct ctl_table *table = PROC_I(inode)->sysctl_entry; + const struct ctl_table *table = PROC_I(inode)->sysctl_entry; /* sysctl was unregistered */ if (IS_ERR(head)) @@ -541,17 +643,17 @@ static int proc_sys_open(struct inode *inode, struct file *filp) return 0; } -static unsigned int proc_sys_poll(struct file *filp, poll_table *wait) +static __poll_t proc_sys_poll(struct file *filp, poll_table *wait) { struct inode *inode = file_inode(filp); struct ctl_table_header *head = grab_header(inode); - struct ctl_table *table = PROC_I(inode)->sysctl_entry; - unsigned int ret = DEFAULT_POLLMASK; + const struct ctl_table *table = PROC_I(inode)->sysctl_entry; + __poll_t ret = DEFAULT_POLLMASK; unsigned long event; /* sysctl was unregistered */ if (IS_ERR(head)) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; if (!table->proc_handler) goto out; @@ -564,7 +666,7 @@ static unsigned int proc_sys_poll(struct file *filp, poll_table *wait) if (event != atomic_read(&table->poll->event)) { filp->private_data = proc_sys_poll_event(table->poll); - ret = POLLIN | POLLRDNORM | POLLERR | POLLPRI; + ret = EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } out: @@ -576,7 +678,7 @@ out: static bool proc_sys_fill_cache(struct file *file, struct dir_context *ctx, struct ctl_table_header *head, - struct ctl_table *table) + const struct ctl_table *table) { struct dentry *child, *dir = file->f_path.dentry; struct inode *inode; @@ -586,25 +688,31 @@ static bool proc_sys_fill_cache(struct file *file, qname.name = table->procname; qname.len = strlen(table->procname); - qname.hash = full_name_hash(qname.name, qname.len); + qname.hash = full_name_hash(dir, qname.name, qname.len); child = d_lookup(dir, &qname); if (!child) { - child = d_alloc(dir, &qname); - if (child) { + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + child = d_alloc_parallel(dir, &qname, &wq); + if (IS_ERR(child)) + return false; + if (d_in_lookup(child)) { + struct dentry *res; inode = proc_sys_make_inode(dir->d_sb, head, table); - if (!inode) { + res = d_splice_alias_ops(inode, child, + &proc_sys_dentry_operations); + d_lookup_done(child); + if (unlikely(res)) { dput(child); - return false; - } else { - d_set_d_op(child, &proc_sys_dentry_operations); - d_add(child, inode); + + if (IS_ERR(res)) + return false; + + child = res; } - } else { - return false; } } - inode = child->d_inode; + inode = d_inode(child); ino = inode->i_ino; type = inode->i_mode >> 12; dput(child); @@ -614,17 +722,17 @@ static bool proc_sys_fill_cache(struct file *file, static bool proc_sys_link_fill_cache(struct file *file, struct dir_context *ctx, struct ctl_table_header *head, - struct ctl_table *table) + const struct ctl_table *table) { bool ret = true; + head = sysctl_head_grab(head); + if (IS_ERR(head)) + return false; - if (S_ISLNK(table->mode)) { - /* It is not an error if we can not follow the link ignore it */ - int err = sysctl_follow_link(&head, &table, current->nsproxy); - if (err) - goto out; - } + /* It is not an error if we can not follow the link ignore it */ + if (sysctl_follow_link(&head, &table)) + goto out; ret = proc_sys_fill_cache(file, ctx, head, table); out: @@ -632,7 +740,7 @@ out: return ret; } -static int scan(struct ctl_table_header *head, ctl_table *table, +static int scan(struct ctl_table_header *head, const struct ctl_table *table, unsigned long *pos, struct file *file, struct dir_context *ctx) { @@ -656,7 +764,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx) { struct ctl_table_header *head = grab_header(file_inode(file)); struct ctl_table_header *h = NULL; - struct ctl_table *entry; + const struct ctl_table *entry; struct ctl_dir *ctl_dir; unsigned long pos; @@ -666,7 +774,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx) ctl_dir = container_of(head, struct ctl_dir, header); if (!dir_emit_dots(file, ctx)) - return 0; + goto out; pos = 2; @@ -676,18 +784,20 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx) break; } } +out: sysctl_head_finish(head); return 0; } -static int proc_sys_permission(struct inode *inode, int mask) +static int proc_sys_permission(struct mnt_idmap *idmap, + struct inode *inode, int mask) { /* * sysctl entries that are not writeable, * are _NOT_ writeable, capabilities or not. */ struct ctl_table_header *head; - struct ctl_table *table; + const struct ctl_table *table; int error; /* Executable files are not allowed under /proc/sys/ */ @@ -708,33 +818,35 @@ static int proc_sys_permission(struct inode *inode, int mask) return error; } -static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr) +static int proc_sys_setattr(struct mnt_idmap *idmap, + struct dentry *dentry, struct iattr *attr) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); int error; if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) return -EPERM; - error = inode_change_ok(inode, attr); + error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; - setattr_copy(inode, attr); - mark_inode_dirty(inode); + setattr_copy(&nop_mnt_idmap, inode, attr); return 0; } -static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +static int proc_sys_getattr(struct mnt_idmap *idmap, + const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(path->dentry); struct ctl_table_header *head = grab_header(inode); - struct ctl_table *table = PROC_I(inode)->sysctl_entry; + const struct ctl_table *table = PROC_I(inode)->sysctl_entry; if (IS_ERR(head)) return PTR_ERR(head); - generic_fillattr(inode, stat); + generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); if (table) stat->mode = (stat->mode & S_IFMT) | table->mode; @@ -745,14 +857,16 @@ static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct static const struct file_operations proc_sys_file_operations = { .open = proc_sys_open, .poll = proc_sys_poll, - .read = proc_sys_read, - .write = proc_sys_write, + .read_iter = proc_sys_read, + .write_iter = proc_sys_write, + .splice_read = copy_splice_read, + .splice_write = iter_file_splice_write, .llseek = default_llseek, }; static const struct file_operations proc_sys_dir_file_operations = { .read = generic_read_dir, - .iterate = proc_sys_readdir, + .iterate_shared = proc_sys_readdir, .llseek = generic_file_llseek, }; @@ -769,16 +883,17 @@ static const struct inode_operations proc_sys_dir_operations = { .getattr = proc_sys_getattr, }; -static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags) +static int proc_sys_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; - return !PROC_I(dentry->d_inode)->sysctl->unregistering; + return !PROC_I(d_inode(dentry))->sysctl->unregistering; } static int proc_sys_delete(const struct dentry *dentry) { - return !!PROC_I(dentry->d_inode)->sysctl->unregistering; + return !!PROC_I(d_inode(dentry))->sysctl->unregistering; } static int sysctl_is_seen(struct ctl_table_header *p) @@ -796,23 +911,27 @@ static int sysctl_is_seen(struct ctl_table_header *p) return res; } -static int proc_sys_compare(const struct dentry *parent, const struct dentry *dentry, +static int proc_sys_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { struct ctl_table_header *head; struct inode *inode; - /* Although proc doesn't have negative dentries, rcu-walk means - * that inode here can be NULL */ - /* AV: can it, indeed? */ - inode = ACCESS_ONCE(dentry->d_inode); - if (!inode) - return 1; if (name->len != len) return 1; if (memcmp(name->name, str, len)) return 1; - head = rcu_dereference(PROC_I(inode)->sysctl); + + // false positive is fine here - we'll recheck anyway + if (d_in_lookup(dentry)) + return 0; + + inode = d_inode_rcu(dentry); + // we just might have run into dentry in the middle of __dentry_kill() + if (!inode) + return 1; + + head = READ_ONCE(PROC_I(inode)->sysctl); return !head || !sysctl_is_seen(head); } @@ -826,7 +945,7 @@ static struct ctl_dir *find_subdir(struct ctl_dir *dir, const char *name, int namelen) { struct ctl_table_header *head; - struct ctl_table *entry; + const struct ctl_table *entry; entry = find_entry(&head, dir, name, namelen); if (!entry) @@ -845,19 +964,18 @@ static struct ctl_dir *new_dir(struct ctl_table_set *set, char *new_name; new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) + - sizeof(struct ctl_table)*2 + namelen + 1, + sizeof(struct ctl_table) + namelen + 1, GFP_KERNEL); if (!new) return NULL; node = (struct ctl_node *)(new + 1); table = (struct ctl_table *)(node + 1); - new_name = (char *)(table + 2); + new_name = (char *)(table + 1); memcpy(new_name, name, namelen); - new_name[namelen] = '\0'; table[0].procname = new_name; table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO; - init_header(&new->header, set->dir.header.root, set, node, table); + init_header(&new->header, set->dir.header.root, set, node, table, 1); return new; } @@ -911,11 +1029,11 @@ static struct ctl_dir *get_subdir(struct ctl_dir *dir, found: subdir->header.nreg++; failed: - if (unlikely(IS_ERR(subdir))) { + if (IS_ERR(subdir)) { pr_err("sysctl could not get directory: "); sysctl_print_dir(dir); - pr_cont("/%*.*s %ld\n", - namelen, namelen, name, PTR_ERR(subdir)); + pr_cont("%*.*s %ld\n", namelen, namelen, name, + PTR_ERR(subdir)); } drop_sysctl_table(&dir->header); if (new) @@ -938,19 +1056,18 @@ static struct ctl_dir *xlate_dir(struct ctl_table_set *set, struct ctl_dir *dir) } static int sysctl_follow_link(struct ctl_table_header **phead, - struct ctl_table **pentry, struct nsproxy *namespaces) + const struct ctl_table **pentry) { struct ctl_table_header *head; + const struct ctl_table *entry; struct ctl_table_root *root; struct ctl_table_set *set; - struct ctl_table *entry; struct ctl_dir *dir; int ret; - ret = 0; spin_lock(&sysctl_lock); root = (*pentry)->data; - set = lookup_header_set(root, namespaces); + set = lookup_header_set(root); dir = xlate_dir(set, (*phead)->parent); if (IS_ERR(dir)) ret = PTR_ERR(dir); @@ -971,7 +1088,7 @@ static int sysctl_follow_link(struct ctl_table_header **phead, return ret; } -static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...) +static int sysctl_err(const char *path, const struct ctl_table *table, char *fmt, ...) { struct va_format vaf; va_list args; @@ -987,55 +1104,96 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...) return -EINVAL; } -static int sysctl_check_table(const char *path, struct ctl_table *table) +static int sysctl_check_table_array(const char *path, const struct ctl_table *table) +{ + unsigned int extra; + int err = 0; + + if ((table->proc_handler == proc_douintvec) || + (table->proc_handler == proc_douintvec_minmax)) { + if (table->maxlen != sizeof(unsigned int)) + err |= sysctl_err(path, table, "array not allowed"); + } + + if (table->proc_handler == proc_dou8vec_minmax) { + if (table->maxlen != sizeof(u8)) + err |= sysctl_err(path, table, "array not allowed"); + + if (table->extra1) { + extra = *(unsigned int *) table->extra1; + if (extra > 255U) + err |= sysctl_err(path, table, + "range value too large for proc_dou8vec_minmax"); + } + if (table->extra2) { + extra = *(unsigned int *) table->extra2; + if (extra > 255U) + err |= sysctl_err(path, table, + "range value too large for proc_dou8vec_minmax"); + } + } + + if (table->proc_handler == proc_dobool) { + if (table->maxlen != sizeof(bool)) + err |= sysctl_err(path, table, "array not allowed"); + } + + return err; +} + +static int sysctl_check_table(const char *path, struct ctl_table_header *header) { + const struct ctl_table *entry; int err = 0; - for (; table->procname; table++) { - if (table->child) - err = sysctl_err(path, table, "Not a file"); - - if ((table->proc_handler == proc_dostring) || - (table->proc_handler == proc_dointvec) || - (table->proc_handler == proc_dointvec_minmax) || - (table->proc_handler == proc_dointvec_jiffies) || - (table->proc_handler == proc_dointvec_userhz_jiffies) || - (table->proc_handler == proc_dointvec_ms_jiffies) || - (table->proc_handler == proc_doulongvec_minmax) || - (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { - if (!table->data) - err = sysctl_err(path, table, "No data"); - if (!table->maxlen) - err = sysctl_err(path, table, "No maxlen"); + list_for_each_table_entry(entry, header) { + if (!entry->procname) + err |= sysctl_err(path, entry, "procname is null"); + if ((entry->proc_handler == proc_dostring) || + (entry->proc_handler == proc_dobool) || + (entry->proc_handler == proc_dointvec) || + (entry->proc_handler == proc_douintvec) || + (entry->proc_handler == proc_douintvec_minmax) || + (entry->proc_handler == proc_dointvec_minmax) || + (entry->proc_handler == proc_dou8vec_minmax) || + (entry->proc_handler == proc_dointvec_jiffies) || + (entry->proc_handler == proc_dointvec_userhz_jiffies) || + (entry->proc_handler == proc_dointvec_ms_jiffies) || + (entry->proc_handler == proc_doulongvec_minmax) || + (entry->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { + if (!entry->data) + err |= sysctl_err(path, entry, "No data"); + if (!entry->maxlen) + err |= sysctl_err(path, entry, "No maxlen"); + else + err |= sysctl_check_table_array(path, entry); } - if (!table->proc_handler) - err = sysctl_err(path, table, "No proc_handler"); + if (!entry->proc_handler) + err |= sysctl_err(path, entry, "No proc_handler"); - if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode) - err = sysctl_err(path, table, "bogus .mode 0%o", - table->mode); + if ((entry->mode & (S_IRUGO|S_IWUGO)) != entry->mode) + err |= sysctl_err(path, entry, "bogus .mode 0%o", + entry->mode); } return err; } -static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table *table, - struct ctl_table_root *link_root) +static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table_header *head) { - struct ctl_table *link_table, *entry, *link; + struct ctl_table *link_table, *link; struct ctl_table_header *links; + const struct ctl_table *entry; struct ctl_node *node; char *link_name; - int nr_entries, name_bytes; + int name_bytes; name_bytes = 0; - nr_entries = 0; - for (entry = table; entry->procname; entry++) { - nr_entries++; + list_for_each_table_entry(entry, head) { name_bytes += strlen(entry->procname) + 1; } links = kzalloc(sizeof(struct ctl_table_header) + - sizeof(struct ctl_node)*nr_entries + - sizeof(struct ctl_table)*(nr_entries + 1) + + sizeof(struct ctl_node)*head->ctl_table_size + + sizeof(struct ctl_table)*head->ctl_table_size + name_bytes, GFP_KERNEL); @@ -1043,33 +1201,41 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table return NULL; node = (struct ctl_node *)(links + 1); - link_table = (struct ctl_table *)(node + nr_entries); - link_name = (char *)&link_table[nr_entries + 1]; + link_table = (struct ctl_table *)(node + head->ctl_table_size); + link_name = (char *)(link_table + head->ctl_table_size); + link = link_table; - for (link = link_table, entry = table; entry->procname; link++, entry++) { + list_for_each_table_entry(entry, head) { int len = strlen(entry->procname) + 1; memcpy(link_name, entry->procname, len); link->procname = link_name; link->mode = S_IFLNK|S_IRWXUGO; - link->data = link_root; + link->data = head->root; link_name += len; + link++; } - init_header(links, dir->header.root, dir->header.set, node, link_table); - links->nreg = nr_entries; + init_header(links, dir->header.root, dir->header.set, node, link_table, + head->ctl_table_size); + links->nreg = head->ctl_table_size; return links; } static bool get_links(struct ctl_dir *dir, - struct ctl_table *table, struct ctl_table_root *link_root) + struct ctl_table_header *header, + struct ctl_table_root *link_root) { - struct ctl_table_header *head; - struct ctl_table *entry, *link; + struct ctl_table_header *tmp_head; + const struct ctl_table *entry, *link; + + if (header->ctl_table_size == 0 || + sysctl_is_perm_empty_ctl_header(header)) + return true; /* Are there links available for every entry in table? */ - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, header) { const char *procname = entry->procname; - link = find_entry(&head, dir, procname, strlen(procname)); + link = find_entry(&tmp_head, dir, procname, strlen(procname)); if (!link) return false; if (S_ISDIR(link->mode) && S_ISDIR(entry->mode)) @@ -1080,10 +1246,10 @@ static bool get_links(struct ctl_dir *dir, } /* The checks passed. Increase the registration count on the links */ - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, header) { const char *procname = entry->procname; - link = find_entry(&head, dir, procname, strlen(procname)); - head->nreg++; + link = find_entry(&tmp_head, dir, procname, strlen(procname)); + tmp_head->nreg++; } return true; } @@ -1091,7 +1257,7 @@ static bool get_links(struct ctl_dir *dir, static int insert_links(struct ctl_table_header *head) { struct ctl_table_set *root_set = &sysctl_table_root.default_set; - struct ctl_dir *core_parent = NULL; + struct ctl_dir *core_parent; struct ctl_table_header *links; int err; @@ -1102,13 +1268,13 @@ static int insert_links(struct ctl_table_header *head) if (IS_ERR(core_parent)) return 0; - if (get_links(core_parent, head->ctl_table, head->root)) + if (get_links(core_parent, head, head->root)) return 0; core_parent->header.nreg++; spin_unlock(&sysctl_lock); - links = new_links(core_parent, head->ctl_table, head->root); + links = new_links(core_parent, head); spin_lock(&sysctl_lock); err = -ENOMEM; @@ -1116,7 +1282,7 @@ static int insert_links(struct ctl_table_header *head) goto out; err = 0; - if (get_links(core_parent, head->ctl_table, head->root)) { + if (get_links(core_parent, head, head->root)) { kfree(links); goto out; } @@ -1129,34 +1295,64 @@ out: return err; } +/* Find the directory for the ctl_table. If one is not found create it. */ +static struct ctl_dir *sysctl_mkdir_p(struct ctl_dir *dir, const char *path) +{ + const char *name, *nextname; + + for (name = path; name; name = nextname) { + int namelen; + nextname = strchr(name, '/'); + if (nextname) { + namelen = nextname - name; + nextname++; + } else { + namelen = strlen(name); + } + if (namelen == 0) + continue; + + /* + * namelen ensures if name is "foo/bar/yay" only foo is + * registered first. We traverse as if using mkdir -p and + * return a ctl_dir for the last directory entry. + */ + dir = get_subdir(dir, name, namelen); + if (IS_ERR(dir)) + break; + } + return dir; +} + /** * __register_sysctl_table - register a leaf sysctl table * @set: Sysctl tree to register on * @path: The path to the directory the sysctl table is in. - * @table: the top-level table structure + * + * @table: the top-level table structure. This table should not be free'd + * after registration. So it should not be used on stack. It can either + * be a global or dynamically allocated by the caller and free'd later + * after sysctl unregistration. + * @table_size : The number of elements in table * * Register a sysctl table hierarchy. @table should be a filled in ctl_table - * array. A completely 0 filled entry terminates the table. + * array. * * The members of the &struct ctl_table structure are used as follows: - * * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not * enter a sysctl file - * - * data - a pointer to data for use by proc_handler - * - * maxlen - the maximum size in bytes of the data - * - * mode - the file permissions for the /proc/sys file - * - * child - must be %NULL. - * + * data - a pointer to data for use by proc_handler + * maxlen - the maximum size in bytes of the data + * mode - the file permissions for the /proc/sys file + * type - Defines the target type (described in struct definition) * proc_handler - the text handler routine (described below) * * extra1, extra2 - extra pointers usable by the proc handler routines + * XXX: we should eventually modify these to use long min / max [0] + * [0] https://lkml.kernel.org/87zgpte9o4.fsf@email.froward.int.ebiederm.org * * Leaf nodes in the sysctl tree will be represented by a single file - * under /proc; non-leaf nodes will be represented by directories. + * under /proc; non-leaf nodes are not allowed. * * There must be a proc_handler routine for any terminal nodes. * Several default handlers are available to cover common cases - @@ -1173,53 +1369,32 @@ out: */ struct ctl_table_header *__register_sysctl_table( struct ctl_table_set *set, - const char *path, struct ctl_table *table) + const char *path, const struct ctl_table *table, size_t table_size) { struct ctl_table_root *root = set->dir.header.root; struct ctl_table_header *header; - const char *name, *nextname; struct ctl_dir *dir; - struct ctl_table *entry; struct ctl_node *node; - int nr_entries = 0; - - for (entry = table; entry->procname; entry++) - nr_entries++; header = kzalloc(sizeof(struct ctl_table_header) + - sizeof(struct ctl_node)*nr_entries, GFP_KERNEL); + sizeof(struct ctl_node)*table_size, GFP_KERNEL_ACCOUNT); if (!header) return NULL; node = (struct ctl_node *)(header + 1); - init_header(header, root, set, node, table); - if (sysctl_check_table(path, table)) + init_header(header, root, set, node, table, table_size); + if (sysctl_check_table(path, header)) goto fail; spin_lock(&sysctl_lock); dir = &set->dir; - /* Reference moved down the diretory tree get_subdir */ + /* Reference moved down the directory tree get_subdir */ dir->header.nreg++; spin_unlock(&sysctl_lock); - /* Find the directory for the ctl_table */ - for (name = path; name; name = nextname) { - int namelen; - nextname = strchr(name, '/'); - if (nextname) { - namelen = nextname - name; - nextname++; - } else { - namelen = strlen(name); - } - if (namelen == 0) - continue; - - dir = get_subdir(dir, name, namelen); - if (IS_ERR(dir)) - goto fail; - } - + dir = sysctl_mkdir_p(dir, path); + if (IS_ERR(dir)) + goto fail; spin_lock(&sysctl_lock); if (insert_header(dir, header)) goto fail_put_dir_locked; @@ -1234,239 +1409,67 @@ fail_put_dir_locked: spin_unlock(&sysctl_lock); fail: kfree(header); - dump_stack(); return NULL; } /** - * register_sysctl - register a sysctl table - * @path: The path to the directory the sysctl table is in. - * @table: the table structure + * register_sysctl_sz - register a sysctl table + * @path: The path to the directory the sysctl table is in. If the path + * doesn't exist we will create it for you. + * @table: the table structure. The calller must ensure the life of the @table + * will be kept during the lifetime use of the syctl. It must not be freed + * until unregister_sysctl_table() is called with the given returned table + * with this registration. If your code is non modular then you don't need + * to call unregister_sysctl_table() and can instead use something like + * register_sysctl_init() which does not care for the result of the syctl + * registration. + * @table_size: The number of elements in table. * * Register a sysctl table. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. * * See __register_sysctl_table for more details. */ -struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table) +struct ctl_table_header *register_sysctl_sz(const char *path, const struct ctl_table *table, + size_t table_size) { return __register_sysctl_table(&sysctl_table_root.default_set, - path, table); -} -EXPORT_SYMBOL(register_sysctl); - -static char *append_path(const char *path, char *pos, const char *name) -{ - int namelen; - namelen = strlen(name); - if (((pos - path) + namelen + 2) >= PATH_MAX) - return NULL; - memcpy(pos, name, namelen); - pos[namelen] = '/'; - pos[namelen + 1] = '\0'; - pos += namelen + 1; - return pos; -} - -static int count_subheaders(struct ctl_table *table) -{ - int has_files = 0; - int nr_subheaders = 0; - struct ctl_table *entry; - - /* special case: no directory and empty directory */ - if (!table || !table->procname) - return 1; - - for (entry = table; entry->procname; entry++) { - if (entry->child) - nr_subheaders += count_subheaders(entry->child); - else - has_files = 1; - } - return nr_subheaders + has_files; -} - -static int register_leaf_sysctl_tables(const char *path, char *pos, - struct ctl_table_header ***subheader, struct ctl_table_set *set, - struct ctl_table *table) -{ - struct ctl_table *ctl_table_arg = NULL; - struct ctl_table *entry, *files; - int nr_files = 0; - int nr_dirs = 0; - int err = -ENOMEM; - - for (entry = table; entry->procname; entry++) { - if (entry->child) - nr_dirs++; - else - nr_files++; - } - - files = table; - /* If there are mixed files and directories we need a new table */ - if (nr_dirs && nr_files) { - struct ctl_table *new; - files = kzalloc(sizeof(struct ctl_table) * (nr_files + 1), - GFP_KERNEL); - if (!files) - goto out; - - ctl_table_arg = files; - for (new = files, entry = table; entry->procname; entry++) { - if (entry->child) - continue; - *new = *entry; - new++; - } - } - - /* Register everything except a directory full of subdirectories */ - if (nr_files || !nr_dirs) { - struct ctl_table_header *header; - header = __register_sysctl_table(set, path, files); - if (!header) { - kfree(ctl_table_arg); - goto out; - } - - /* Remember if we need to free the file table */ - header->ctl_table_arg = ctl_table_arg; - **subheader = header; - (*subheader)++; - } - - /* Recurse into the subdirectories. */ - for (entry = table; entry->procname; entry++) { - char *child_pos; - - if (!entry->child) - continue; - - err = -ENAMETOOLONG; - child_pos = append_path(path, pos, entry->procname); - if (!child_pos) - goto out; - - err = register_leaf_sysctl_tables(path, child_pos, subheader, - set, entry->child); - pos[0] = '\0'; - if (err) - goto out; - } - err = 0; -out: - /* On failure our caller will unregister all registered subheaders */ - return err; + path, table, table_size); } +EXPORT_SYMBOL(register_sysctl_sz); /** - * __register_sysctl_paths - register a sysctl table hierarchy - * @set: Sysctl tree to register on - * @path: The path to the directory the sysctl table is in. - * @table: the top-level table structure + * __register_sysctl_init() - register sysctl table to path + * @path: path name for sysctl base. If that path doesn't exist we will create + * it for you. + * @table: This is the sysctl table that needs to be registered to the path. + * The caller must ensure the life of the @table will be kept during the + * lifetime use of the sysctl. + * @table_name: The name of sysctl table, only used for log printing when + * registration fails + * @table_size: The number of elements in table * - * Register a sysctl table hierarchy. @table should be a filled in ctl_table - * array. A completely 0 filled entry terminates the table. + * The sysctl interface is used by userspace to query or modify at runtime + * a predefined value set on a variable. These variables however have default + * values pre-set. Code which depends on these variables will always work even + * if register_sysctl() fails. If register_sysctl() fails you'd just loose the + * ability to query or modify the sysctls dynamically at run time. Chances of + * register_sysctl() failing on init are extremely low, and so for both reasons + * this function does not return any error as it is used by initialization code. * - * See __register_sysctl_table for more details. + * Context: if your base directory does not exist it will be created for you. */ -struct ctl_table_header *__register_sysctl_paths( - struct ctl_table_set *set, - const struct ctl_path *path, struct ctl_table *table) +void __init __register_sysctl_init(const char *path, const struct ctl_table *table, + const char *table_name, size_t table_size) { - struct ctl_table *ctl_table_arg = table; - int nr_subheaders = count_subheaders(table); - struct ctl_table_header *header = NULL, **subheaders, **subheader; - const struct ctl_path *component; - char *new_path, *pos; - - pos = new_path = kmalloc(PATH_MAX, GFP_KERNEL); - if (!new_path) - return NULL; - - pos[0] = '\0'; - for (component = path; component->procname; component++) { - pos = append_path(new_path, pos, component->procname); - if (!pos) - goto out; - } - while (table->procname && table->child && !table[1].procname) { - pos = append_path(new_path, pos, table->procname); - if (!pos) - goto out; - table = table->child; - } - if (nr_subheaders == 1) { - header = __register_sysctl_table(set, new_path, table); - if (header) - header->ctl_table_arg = ctl_table_arg; - } else { - header = kzalloc(sizeof(*header) + - sizeof(*subheaders)*nr_subheaders, GFP_KERNEL); - if (!header) - goto out; - - subheaders = (struct ctl_table_header **) (header + 1); - subheader = subheaders; - header->ctl_table_arg = ctl_table_arg; - - if (register_leaf_sysctl_tables(new_path, pos, &subheader, - set, table)) - goto err_register_leaves; - } - -out: - kfree(new_path); - return header; + struct ctl_table_header *hdr = register_sysctl_sz(path, table, table_size); -err_register_leaves: - while (subheader > subheaders) { - struct ctl_table_header *subh = *(--subheader); - struct ctl_table *table = subh->ctl_table_arg; - unregister_sysctl_table(subh); - kfree(table); + if (unlikely(!hdr)) { + pr_err("failed when register_sysctl_sz %s to %s\n", table_name, path); + return; } - kfree(header); - header = NULL; - goto out; -} - -/** - * register_sysctl_table_path - register a sysctl table hierarchy - * @path: The path to the directory the sysctl table is in. - * @table: the top-level table structure - * - * Register a sysctl table hierarchy. @table should be a filled in ctl_table - * array. A completely 0 filled entry terminates the table. - * - * See __register_sysctl_paths for more details. - */ -struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, - struct ctl_table *table) -{ - return __register_sysctl_paths(&sysctl_table_root.default_set, - path, table); -} -EXPORT_SYMBOL(register_sysctl_paths); - -/** - * register_sysctl_table - register a sysctl table hierarchy - * @table: the top-level table structure - * - * Register a sysctl table hierarchy. @table should be a filled in ctl_table - * array. A completely 0 filled entry terminates the table. - * - * See register_sysctl_paths for more details. - */ -struct ctl_table_header *register_sysctl_table(struct ctl_table *table) -{ - static const struct ctl_path null_path[] = { {} }; - - return register_sysctl_paths(null_path, table); + kmemleak_not_leak(hdr); } -EXPORT_SYMBOL(register_sysctl_table); static void put_links(struct ctl_table_header *header) { @@ -1474,7 +1477,7 @@ static void put_links(struct ctl_table_header *header) struct ctl_table_root *root = header->root; struct ctl_dir *parent = header->parent; struct ctl_dir *core_parent; - struct ctl_table *entry; + const struct ctl_table *entry; if (header->set == root_set) return; @@ -1483,9 +1486,9 @@ static void put_links(struct ctl_table_header *header) if (IS_ERR(core_parent)) return; - for (entry = header->ctl_table; entry->procname; entry++) { + list_for_each_table_entry(entry, header) { struct ctl_table_header *link_head; - struct ctl_table *link; + const struct ctl_table *link; const char *name = entry->procname; link = find_entry(&link_head, core_parent, name, strlen(name)); @@ -1497,7 +1500,7 @@ static void put_links(struct ctl_table_header *header) else { pr_err("sysctl link missing during unregister: "); sysctl_print_dir(parent); - pr_cont("/%s\n", name); + pr_cont("%s\n", name); } } } @@ -1509,8 +1512,11 @@ static void drop_sysctl_table(struct ctl_table_header *header) if (--header->nreg) return; - put_links(header); - start_unregistering(header); + if (parent) { + put_links(header); + start_unregistering(header); + } + if (!--header->count) kfree_rcu(header, rcu); @@ -1520,35 +1526,18 @@ static void drop_sysctl_table(struct ctl_table_header *header) /** * unregister_sysctl_table - unregister a sysctl table hierarchy - * @header: the header returned from register_sysctl_table + * @header: the header returned from register_sysctl or __register_sysctl_table * * Unregisters the sysctl table and all children. proc entries may not * actually be removed until they are no longer used by anyone. */ void unregister_sysctl_table(struct ctl_table_header * header) { - int nr_subheaders; might_sleep(); if (header == NULL) return; - nr_subheaders = count_subheaders(header->ctl_table_arg); - if (unlikely(nr_subheaders > 1)) { - struct ctl_table_header **subheaders; - int i; - - subheaders = (struct ctl_table_header **)(header + 1); - for (i = nr_subheaders -1; i >= 0; i--) { - struct ctl_table_header *subh = subheaders[i]; - struct ctl_table *table = subh->ctl_table_arg; - unregister_sysctl_table(subh); - kfree(table); - } - kfree(header); - return; - } - spin_lock(&sysctl_lock); drop_sysctl_table(header); spin_unlock(&sysctl_lock); @@ -1561,7 +1550,7 @@ void setup_sysctl_set(struct ctl_table_set *set, { memset(set, 0, sizeof(*set)); set->is_seen = is_seen; - init_header(&set->dir.header, root, set, NULL, root_table); + init_header(&set->dir.header, root, set, NULL, root_table, 1); } void retire_sysctl_set(struct ctl_table_set *set) @@ -1575,8 +1564,163 @@ int __init proc_sys_init(void) proc_sys_root = proc_mkdir("sys", NULL); proc_sys_root->proc_iops = &proc_sys_dir_operations; - proc_sys_root->proc_fops = &proc_sys_dir_file_operations; + proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations; proc_sys_root->nlink = 0; - return sysctl_init(); + return sysctl_init_bases(); +} + +struct sysctl_alias { + const char *kernel_param; + const char *sysctl_param; +}; + +/* + * Historically some settings had both sysctl and a command line parameter. + * With the generic sysctl. parameter support, we can handle them at a single + * place and only keep the historical name for compatibility. This is not meant + * to add brand new aliases. When adding existing aliases, consider whether + * the possibly different moment of changing the value (e.g. from early_param + * to the moment do_sysctl_args() is called) is an issue for the specific + * parameter. + */ +static const struct sysctl_alias sysctl_aliases[] = { + {"hardlockup_all_cpu_backtrace", "kernel.hardlockup_all_cpu_backtrace" }, + {"hung_task_panic", "kernel.hung_task_panic" }, + {"numa_zonelist_order", "vm.numa_zonelist_order" }, + {"softlockup_all_cpu_backtrace", "kernel.softlockup_all_cpu_backtrace" }, + { } +}; + +static const char *sysctl_find_alias(char *param) +{ + const struct sysctl_alias *alias; + + for (alias = &sysctl_aliases[0]; alias->kernel_param != NULL; alias++) { + if (strcmp(alias->kernel_param, param) == 0) + return alias->sysctl_param; + } + + return NULL; +} + +bool sysctl_is_alias(char *param) +{ + const char *alias = sysctl_find_alias(param); + + return alias != NULL; +} + +/* Set sysctl value passed on kernel command line. */ +static int process_sysctl_arg(char *param, char *val, + const char *unused, void *arg) +{ + char *path; + struct vfsmount **proc_mnt = arg; + struct file_system_type *proc_fs_type; + struct file *file; + int len; + int err; + loff_t pos = 0; + ssize_t wret; + + if (strncmp(param, "sysctl", sizeof("sysctl") - 1) == 0) { + param += sizeof("sysctl") - 1; + + if (param[0] != '/' && param[0] != '.') + return 0; + + param++; + } else { + param = (char *) sysctl_find_alias(param); + if (!param) + return 0; + } + + if (!val) + return -EINVAL; + len = strlen(val); + if (len == 0) + return -EINVAL; + + /* + * To set sysctl options, we use a temporary mount of proc, look up the + * respective sys/ file and write to it. To avoid mounting it when no + * options were given, we mount it only when the first sysctl option is + * found. Why not a persistent mount? There are problems with a + * persistent mount of proc in that it forces userspace not to use any + * proc mount options. + */ + if (!*proc_mnt) { + proc_fs_type = get_fs_type("proc"); + if (!proc_fs_type) { + pr_err("Failed to find procfs to set sysctl from command line\n"); + return 0; + } + *proc_mnt = kern_mount(proc_fs_type); + put_filesystem(proc_fs_type); + if (IS_ERR(*proc_mnt)) { + pr_err("Failed to mount procfs to set sysctl from command line\n"); + return 0; + } + } + + path = kasprintf(GFP_KERNEL, "sys/%s", param); + if (!path) + panic("%s: Failed to allocate path for %s\n", __func__, param); + strreplace(path, '.', '/'); + + file = file_open_root_mnt(*proc_mnt, path, O_WRONLY, 0); + if (IS_ERR(file)) { + err = PTR_ERR(file); + if (err == -ENOENT) + pr_err("Failed to set sysctl parameter '%s=%s': parameter not found\n", + param, val); + else if (err == -EACCES) + pr_err("Failed to set sysctl parameter '%s=%s': permission denied (read-only?)\n", + param, val); + else + pr_err("Error %pe opening proc file to set sysctl parameter '%s=%s'\n", + file, param, val); + goto out; + } + wret = kernel_write(file, val, len, &pos); + if (wret < 0) { + err = wret; + if (err == -EINVAL) + pr_err("Failed to set sysctl parameter '%s=%s': invalid value\n", + param, val); + else + pr_err("Error %pe writing to proc file to set sysctl parameter '%s=%s'\n", + ERR_PTR(err), param, val); + } else if (wret != len) { + pr_err("Wrote only %zd bytes of %d writing to proc file %s to set sysctl parameter '%s=%s\n", + wret, len, path, param, val); + } + + err = filp_close(file, NULL); + if (err) + pr_err("Error %pe closing proc file to set sysctl parameter '%s=%s\n", + ERR_PTR(err), param, val); +out: + kfree(path); + return 0; +} + +void do_sysctl_args(void) +{ + char *command_line; + struct vfsmount *proc_mnt = NULL; + + command_line = kstrdup(saved_command_line, GFP_KERNEL); + if (!command_line) + panic("%s: Failed to allocate copy of command line\n", __func__); + + parse_args("Setting sysctl args", command_line, + NULL, 0, -1, -1, &proc_mnt, process_sysctl_arg); + + if (proc_mnt) + kern_unmount(proc_mnt); + + kfree(command_line); } |