diff options
| -rw-r--r-- | fs/binfmt_misc.c | 202 | ||||
| -rw-r--r-- | include/linux/binfmts.h | 10 | ||||
| -rw-r--r-- | include/linux/user_namespace.h | 8 | ||||
| -rw-r--r-- | kernel/user.c | 13 | ||||
| -rw-r--r-- | kernel/user_namespace.c | 3 |
5 files changed, 202 insertions, 34 deletions
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index cf5ed5cd4102..deacc105119d 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -40,9 +40,6 @@ enum { VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */ }; -static LIST_HEAD(entries); -static int enabled = 1; - enum {Enabled, Magic}; #define MISC_FMT_PRESERVE_ARGV0 (1UL << 31) #define MISC_FMT_OPEN_BINARY (1UL << 30) @@ -63,7 +60,6 @@ typedef struct { refcount_t users; /* sync removal with load_misc_binary() */ } Node; -static DEFINE_RWLOCK(entries_lock); static struct file_system_type bm_fs_type; /* @@ -91,13 +87,14 @@ static struct file_system_type bm_fs_type; * * Return: binary type list entry on success, NULL on failure */ -static Node *search_binfmt_handler(struct linux_binprm *bprm) +static Node *search_binfmt_handler(struct binfmt_misc *misc, + struct linux_binprm *bprm) { char *p = strrchr(bprm->interp, '.'); Node *e; /* Walk all the registered handlers. */ - list_for_each_entry(e, &entries, list) { + list_for_each_entry(e, &misc->entries, list) { char *s; int j; @@ -140,15 +137,16 @@ static Node *search_binfmt_handler(struct linux_binprm *bprm) * * Return: binary type list entry on success, NULL on failure */ -static Node *get_binfmt_handler(struct linux_binprm *bprm) +static Node *get_binfmt_handler(struct binfmt_misc *misc, + struct linux_binprm *bprm) { Node *e; - read_lock(&entries_lock); - e = search_binfmt_handler(bprm); + read_lock(&misc->entries_lock); + e = search_binfmt_handler(misc, bprm); if (e) refcount_inc(&e->users); - read_unlock(&entries_lock); + read_unlock(&misc->entries_lock); return e; } @@ -169,6 +167,35 @@ static void put_binfmt_handler(Node *e) } } +/** + * load_binfmt_misc - load the binfmt_misc of the caller's user namespace + * + * To be called in load_misc_binary() to load the relevant struct binfmt_misc. + * If a user namespace doesn't have its own binfmt_misc mount it can make use + * of its ancestor's binfmt_misc handlers. This mimicks the behavior of + * pre-namespaced binfmt_misc where all registered binfmt_misc handlers where + * available to all user and user namespaces on the system. + * + * Return: the binfmt_misc instance of the caller's user namespace + */ +static struct binfmt_misc *load_binfmt_misc(void) +{ + const struct user_namespace *user_ns; + struct binfmt_misc *misc; + + user_ns = current_user_ns(); + while (user_ns) { + /* Pairs with smp_store_release() in bm_fill_super(). */ + misc = smp_load_acquire(&user_ns->binfmt_misc); + if (misc) + return misc; + + user_ns = user_ns->parent; + } + + return &init_binfmt_misc; +} + /* * the loader itself */ @@ -176,13 +203,14 @@ static int load_misc_binary(struct linux_binprm *bprm) { Node *fmt; struct file *interp_file = NULL; - int retval; + int retval = -ENOEXEC; + struct binfmt_misc *misc; - retval = -ENOEXEC; - if (!enabled) + misc = load_binfmt_misc(); + if (!misc->enabled) return retval; - fmt = get_binfmt_handler(bprm); + fmt = get_binfmt_handler(misc, bprm); if (!fmt) return retval; @@ -240,9 +268,9 @@ ret: /* * If we actually put the node here all concurrent calls to * load_misc_binary() will have finished. We also know - * that for the refcount to be zero ->evict_inode() must have removed - * the node to be deleted from the list. All that is left for us is to - * close and free. + * that for the refcount to be zero someone must have concurently + * removed the binary type handler from the list and it's our job to + * free it. */ put_binfmt_handler(fmt); @@ -334,7 +362,7 @@ static Node *create_entry(const char __user *buffer, size_t count) err = -ENOMEM; memsize = sizeof(Node) + count + 8; - e = kmalloc(memsize, GFP_KERNEL); + e = kmalloc(memsize, GFP_KERNEL_ACCOUNT); if (!e) goto out; @@ -446,7 +474,7 @@ static Node *create_entry(const char __user *buffer, size_t count) if (e->mask) { int i; - char *masked = kmalloc(e->size, GFP_KERNEL); + char *masked = kmalloc(e->size, GFP_KERNEL_ACCOUNT); print_hex_dump_bytes( KBUILD_MODNAME ": register: mask[decoded]: ", @@ -600,6 +628,22 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) } /** + * i_binfmt_misc - retrieve struct binfmt_misc from a binfmt_misc inode + * @inode: inode of the relevant binfmt_misc instance + * + * This helper retrieves struct binfmt_misc from a binfmt_misc inode. This can + * be done without any memory barriers because we are guaranteed that + * user_ns->binfmt_misc is fully initialized. It was fully initialized when the + * binfmt_misc mount was first created. + * + * Return: struct binfmt_misc of the relevant binfmt_misc instance + */ +static struct binfmt_misc *i_binfmt_misc(struct inode *inode) +{ + return inode->i_sb->s_user_ns->binfmt_misc; +} + +/** * bm_evict_inode - cleanup data associated with @inode * @inode: inode to which the data is attached * @@ -619,10 +663,13 @@ static void bm_evict_inode(struct inode *inode) clear_inode(inode); if (e) { - write_lock(&entries_lock); + struct binfmt_misc *misc; + + misc = i_binfmt_misc(inode); + write_lock(&misc->entries_lock); if (!list_empty(&e->list)) list_del_init(&e->list); - write_unlock(&entries_lock); + write_unlock(&misc->entries_lock); put_binfmt_handler(e); } } @@ -677,11 +724,11 @@ static void unlink_binfmt_dentry(struct dentry *dentry) * to use writes to files in order to delete binary type handlers. But it has * worked for so long that it's not a pressing issue. */ -static void remove_binfmt_handler(Node *e) +static void remove_binfmt_handler(struct binfmt_misc *misc, Node *e) { - write_lock(&entries_lock); + write_lock(&misc->entries_lock); list_del_init(&e->list); - write_unlock(&entries_lock); + write_unlock(&misc->entries_lock); unlink_binfmt_dentry(e->dentry); } @@ -737,7 +784,7 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer, * actually remove the entry from the list. */ if (!list_empty(&e->list)) - remove_binfmt_handler(e); + remove_binfmt_handler(i_binfmt_misc(inode), e); inode_unlock(inode); break; @@ -763,6 +810,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, struct inode *inode; struct super_block *sb = file_inode(file)->i_sb; struct dentry *root = sb->s_root, *dentry; + struct binfmt_misc *misc; int err = 0; struct file *f = NULL; @@ -772,7 +820,18 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, return PTR_ERR(e); if (e->flags & MISC_FMT_OPEN_FILE) { + const struct cred *old_cred; + + /* + * Now that we support unprivileged binfmt_misc mounts make + * sure we use the credentials that the register @file was + * opened with to also open the interpreter. Before that this + * didn't matter much as only a privileged process could open + * the register file. + */ + old_cred = override_creds(file->f_cred); f = open_exec(e->interpreter); + revert_creds(old_cred); if (IS_ERR(f)) { pr_notice("register: failed to install interpreter file %s\n", e->interpreter); @@ -804,9 +863,10 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, inode->i_fop = &bm_entry_operations; d_instantiate(dentry, inode); - write_lock(&entries_lock); - list_add(&e->list, &entries); - write_unlock(&entries_lock); + misc = i_binfmt_misc(inode); + write_lock(&misc->entries_lock); + list_add(&e->list, &misc->entries); + write_unlock(&misc->entries_lock); err = 0; out2: @@ -833,26 +893,31 @@ static const struct file_operations bm_register_operations = { static ssize_t bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { - char *s = enabled ? "enabled\n" : "disabled\n"; + struct binfmt_misc *misc; + char *s; + misc = i_binfmt_misc(file_inode(file)); + s = misc->enabled ? "enabled\n" : "disabled\n"; return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s)); } static ssize_t bm_status_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { + struct binfmt_misc *misc; int res = parse_command(buffer, count); Node *e, *next; struct inode *inode; + misc = i_binfmt_misc(file_inode(file)); switch (res) { case 1: /* Disable all handlers. */ - enabled = 0; + misc->enabled = false; break; case 2: /* Enable all handlers. */ - enabled = 1; + misc->enabled = true; break; case 3: /* Delete all handlers. */ @@ -868,8 +933,8 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer, * read-only. So we only need to take the write lock when we * actually remove the entry from the list. */ - list_for_each_entry_safe(e, next, &entries, list) - remove_binfmt_handler(e); + list_for_each_entry_safe(e, next, &misc->entries, list) + remove_binfmt_handler(misc, e); inode_unlock(inode); break; @@ -888,32 +953,100 @@ static const struct file_operations bm_status_operations = { /* Superblock handling */ +static void bm_put_super(struct super_block *sb) +{ + struct user_namespace *user_ns = sb->s_fs_info; + + sb->s_fs_info = NULL; + put_user_ns(user_ns); +} + static const struct super_operations s_ops = { .statfs = simple_statfs, .evict_inode = bm_evict_inode, + .put_super = bm_put_super, }; static int bm_fill_super(struct super_block *sb, struct fs_context *fc) { int err; + struct user_namespace *user_ns = sb->s_user_ns; + struct binfmt_misc *misc; static const struct tree_descr bm_files[] = { [2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO}, [3] = {"register", &bm_register_operations, S_IWUSR}, /* last one */ {""} }; + if (WARN_ON(user_ns != current_user_ns())) + return -EINVAL; + + /* + * Lazily allocate a new binfmt_misc instance for this namespace, i.e. + * do it here during the first mount of binfmt_misc. We don't need to + * waste memory for every user namespace allocation. It's likely much + * more common to not mount a separate binfmt_misc instance than it is + * to mount one. + * + * While multiple superblocks can exist they are keyed by userns in + * s_fs_info for binfmt_misc. Hence, the vfs guarantees that + * bm_fill_super() is called exactly once whenever a binfmt_misc + * superblock for a userns is created. This in turn lets us conclude + * that when a binfmt_misc superblock is created for the first time for + * a userns there's no one racing us. Therefore we don't need any + * barriers when we dereference binfmt_misc. + */ + misc = user_ns->binfmt_misc; + if (!misc) { + /* + * If it turns out that most user namespaces actually want to + * register their own binary type handler and therefore all + * create their own separate binfm_misc mounts we should + * consider turning this into a kmem cache. + */ + misc = kzalloc(sizeof(struct binfmt_misc), GFP_KERNEL); + if (!misc) + return -ENOMEM; + + INIT_LIST_HEAD(&misc->entries); + rwlock_init(&misc->entries_lock); + + /* Pairs with smp_load_acquire() in load_binfmt_misc(). */ + smp_store_release(&user_ns->binfmt_misc, misc); + } + + /* + * When the binfmt_misc superblock for this userns is shutdown + * ->enabled might have been set to false and we don't reinitialize + * ->enabled again in put_super() as someone might already be mounting + * binfmt_misc again. It also would be pointless since by the time + * ->put_super() is called we know that the binary type list for this + * bintfmt_misc mount is empty making load_misc_binary() return + * -ENOEXEC independent of whether ->enabled is true. Instead, if + * someone mounts binfmt_misc for the first time or again we simply + * reset ->enabled to true. + */ + misc->enabled = true; + err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files); if (!err) sb->s_op = &s_ops; return err; } +static void bm_free(struct fs_context *fc) +{ + if (fc->s_fs_info) + put_user_ns(fc->s_fs_info); +} + static int bm_get_tree(struct fs_context *fc) { - return get_tree_single(fc, bm_fill_super); + return get_tree_keyed(fc, bm_fill_super, get_user_ns(fc->user_ns)); } static const struct fs_context_operations bm_context_ops = { + .free = bm_free, .get_tree = bm_get_tree, }; @@ -932,6 +1065,7 @@ static struct file_system_type bm_fs_type = { .owner = THIS_MODULE, .name = "binfmt_misc", .init_fs_context = bm_init_fs_context, + .fs_flags = FS_USERNS_MOUNT, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("binfmt_misc"); diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 8d51f69f9f5e..70f97f685bff 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -90,6 +90,16 @@ struct linux_binfmt { #endif } __randomize_layout; +#if IS_ENABLED(CONFIG_BINFMT_MISC) +struct binfmt_misc { + struct list_head entries; + rwlock_t entries_lock; + bool enabled; +} __randomize_layout; + +extern struct binfmt_misc init_binfmt_misc; +#endif + extern void __register_binfmt(struct linux_binfmt *fmt, int insert); /* Registration of default binfmt handlers */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 45f09bec02c4..6030a8235617 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -65,6 +65,10 @@ enum rlimit_type { UCOUNT_RLIMIT_COUNTS, }; +#if IS_ENABLED(CONFIG_BINFMT_MISC) +struct binfmt_misc; +#endif + struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -102,6 +106,10 @@ struct user_namespace { struct ucounts *ucounts; long ucount_max[UCOUNT_COUNTS]; long rlimit_max[UCOUNT_RLIMIT_COUNTS]; + +#if IS_ENABLED(CONFIG_BINFMT_MISC) + struct binfmt_misc *binfmt_misc; +#endif } __randomize_layout; struct ucounts { diff --git a/kernel/user.c b/kernel/user.c index d667debeafd6..03cedc366dc9 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -18,8 +18,18 @@ #include <linux/interrupt.h> #include <linux/export.h> #include <linux/user_namespace.h> +#include <linux/binfmts.h> #include <linux/proc_ns.h> +#if IS_ENABLED(CONFIG_BINFMT_MISC) +struct binfmt_misc init_binfmt_misc = { + .entries = LIST_HEAD_INIT(init_binfmt_misc.entries), + .enabled = true, + .entries_lock = __RW_LOCK_UNLOCKED(init_binfmt_misc.entries_lock), +}; +EXPORT_SYMBOL_GPL(init_binfmt_misc); +#endif + /* * userns count is 1 for root user, 1 for init_uts_ns, * and 1 for... ? @@ -67,6 +77,9 @@ struct user_namespace init_user_ns = { .keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list), .keyring_sem = __RWSEM_INITIALIZER(init_user_ns.keyring_sem), #endif +#if IS_ENABLED(CONFIG_BINFMT_MISC) + .binfmt_misc = &init_binfmt_misc, +#endif }; EXPORT_SYMBOL_GPL(init_user_ns); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 1d8e47bed3f1..d52a894ecf57 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -213,6 +213,9 @@ static void free_user_ns(struct work_struct *work) kfree(ns->projid_map.forward); kfree(ns->projid_map.reverse); } +#if IS_ENABLED(CONFIG_BINFMT_MISC) + kfree(ns->binfmt_misc); +#endif retire_userns_sysctls(ns); key_free_user_ns(ns); ns_free_inum(&ns->ns); |