diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 6421cca2daa9..826de7a12a20 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -22,6 +22,7 @@ struct uid_gid_map { /* 64 bytes -- 1 cache line */ #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED +struct ucounts; struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -44,15 +45,24 @@ struct user_namespace { struct ctl_table_set set; struct ctl_table_header *sysctls; #endif + struct ucounts *ucounts; int max_user_namespaces; +}; + +struct ucounts { + struct hlist_node node; + struct user_namespace *ns; + kuid_t uid; + atomic_t count; atomic_t user_namespaces; }; extern struct user_namespace init_user_ns; -extern bool setup_userns_sysctls(struct user_namespace *ns); -extern void retire_userns_sysctls(struct user_namespace *ns); -extern bool inc_user_namespaces(struct user_namespace *ns); -extern void dec_user_namespaces(struct user_namespace *ns); + +bool setup_userns_sysctls(struct user_namespace *ns); +void retire_userns_sysctls(struct user_namespace *ns); +struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid); +void dec_user_namespaces(struct ucounts *ucounts); #ifdef CONFIG_USER_NS diff --git a/kernel/fork.c b/kernel/fork.c index daa6a82b4900..d8cde533ace3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -322,7 +322,7 @@ void __init fork_init(void) init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; - init_user_ns.max_user_namespaces = max_threads; + init_user_ns.max_user_namespaces = max_threads/2; } int __weak arch_dup_task_struct(struct task_struct *dst, diff --git a/kernel/ucount.c b/kernel/ucount.c index 6c2205c0befd..33c418718304 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -8,8 +8,20 @@ #include #include #include +#include #include +#define UCOUNTS_HASHTABLE_BITS 10 +static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)]; +static DEFINE_SPINLOCK(ucounts_lock); + +#define ucounts_hashfn(ns, uid) \ + hash_long((unsigned long)__kuid_val(uid) + (unsigned long)(ns), \ + UCOUNTS_HASHTABLE_BITS) +#define ucounts_hashentry(ns, uid) \ + (ucounts_hashtable + ucounts_hashfn(ns, uid)) + + #ifdef CONFIG_SYSCTL static struct ctl_table_set * set_lookup(struct ctl_table_root *root) @@ -45,7 +57,7 @@ static struct ctl_table_root set_root = { static int zero = 0; static int int_max = INT_MAX; -static struct ctl_table userns_table[] = { +static struct ctl_table user_table[] = { { .procname = "max_user_namespaces", .data = &init_user_ns.max_user_namespaces, @@ -64,11 +76,11 @@ bool setup_userns_sysctls(struct user_namespace *ns) #ifdef CONFIG_SYSCTL struct ctl_table *tbl; setup_sysctl_set(&ns->set, &set_root, set_is_seen); - tbl = kmemdup(userns_table, sizeof(userns_table), GFP_KERNEL); + tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL); if (tbl) { tbl[0].data = &ns->max_user_namespaces; - ns->sysctls = __register_sysctl_table(&ns->set, "userns", tbl); + ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl); } if (!ns->sysctls) { kfree(tbl); @@ -91,6 +103,61 @@ void retire_userns_sysctls(struct user_namespace *ns) #endif } +static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struct hlist_head *hashent) +{ + struct ucounts *ucounts; + + hlist_for_each_entry(ucounts, hashent, node) { + if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns)) + return ucounts; + } + return NULL; +} + +static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) +{ + struct hlist_head *hashent = ucounts_hashentry(ns, uid); + struct ucounts *ucounts, *new; + + spin_lock(&ucounts_lock); + ucounts = find_ucounts(ns, uid, hashent); + if (!ucounts) { + spin_unlock(&ucounts_lock); + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return NULL; + + new->ns = ns; + new->uid = uid; + atomic_set(&new->count, 0); + + spin_lock(&ucounts_lock); + ucounts = find_ucounts(ns, uid, hashent); + if (ucounts) { + kfree(new); + } else { + hlist_add_head(&new->node, hashent); + ucounts = new; + } + } + if (!atomic_add_unless(&ucounts->count, 1, INT_MAX)) + ucounts = NULL; + spin_unlock(&ucounts_lock); + return ucounts; +} + +static void put_ucounts(struct ucounts *ucounts) +{ + if (atomic_dec_and_test(&ucounts->count)) { + spin_lock(&ucounts_lock); + hlist_del_init(&ucounts->node); + spin_unlock(&ucounts_lock); + + kfree(ucounts); + } +} + static inline bool atomic_inc_below(atomic_t *v, int u) { int c, old; @@ -105,44 +172,51 @@ static inline bool atomic_inc_below(atomic_t *v, int u) } } -bool inc_user_namespaces(struct user_namespace *ns) +struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid) { - struct user_namespace *pos, *bad; - for (pos = ns; pos; pos = pos->parent) { - int max = READ_ONCE(pos->max_user_namespaces); - if (!atomic_inc_below(&pos->user_namespaces, max)) + struct ucounts *ucounts, *iter, *bad; + struct user_namespace *tns; + ucounts = get_ucounts(ns, uid); + for (iter = ucounts; iter; iter = tns->ucounts) { + int max; + tns = iter->ns; + max = READ_ONCE(tns->max_user_namespaces); + if (!atomic_inc_below(&iter->user_namespaces, max)) goto fail; } - return true; + return ucounts; fail: - bad = pos; - for (pos = ns; pos != bad; pos = pos->parent) - atomic_dec(&pos->user_namespaces); + bad = iter; + for (iter = ucounts; iter != bad; iter = iter->ns->ucounts) + atomic_dec(&iter->user_namespaces); - return false; + put_ucounts(ucounts); + return NULL; } -void dec_user_namespaces(struct user_namespace *ns) +void dec_user_namespaces(struct ucounts *ucounts) { - struct user_namespace *pos; - for (pos = ns; pos; pos = pos->parent) { - int dec = atomic_dec_if_positive(&pos->user_namespaces); + struct ucounts *iter; + for (iter = ucounts; iter; iter = iter->ns->ucounts) { + int dec = atomic_dec_if_positive(&iter->user_namespaces); WARN_ON_ONCE(dec < 0); } + put_ucounts(ucounts); } + static __init int user_namespace_sysctl_init(void) { #ifdef CONFIG_SYSCTL - static struct ctl_table_header *userns_header; + static struct ctl_table_header *user_header; static struct ctl_table empty[1]; /* - * It is necessary to register the userns directory in the + * It is necessary to register the user directory in the * default set so that registrations in the child sets work * properly. */ - userns_header = register_sysctl("userns", empty); - BUG_ON(!userns_header); + user_header = register_sysctl("user", empty); + BUG_ON(!user_header); BUG_ON(!setup_userns_sysctls(&init_user_ns)); #endif return 0; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 7d87017a0040..58c67e5f851c 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -31,7 +31,6 @@ static bool new_idmap_permitted(const struct file *file, struct uid_gid_map *map); static void free_user_ns(struct work_struct *work); - static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) { /* Start with the same capabilities as init but useless for doing @@ -64,13 +63,15 @@ int create_user_ns(struct cred *new) struct user_namespace *ns, *parent_ns = new->user_ns; kuid_t owner = new->euid; kgid_t group = new->egid; + struct ucounts *ucounts; int ret; ret = -EUSERS; if (parent_ns->level > 32) goto fail; - if (!inc_user_namespaces(parent_ns)) + ucounts = inc_user_namespaces(parent_ns, owner); + if (!ucounts) goto fail; /* @@ -110,6 +111,7 @@ int create_user_ns(struct cred *new) ns->group = group; INIT_WORK(&ns->work, free_user_ns); ns->max_user_namespaces = INT_MAX; + ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ mutex_lock(&userns_state_mutex); @@ -133,7 +135,7 @@ fail_keyring: fail_free: kmem_cache_free(user_ns_cachep, ns); fail_dec: - dec_user_namespaces(parent_ns); + dec_user_namespaces(ucounts); fail: return ret; } @@ -164,6 +166,7 @@ static void free_user_ns(struct work_struct *work) container_of(work, struct user_namespace, work); do { + struct ucounts *ucounts = ns->ucounts; parent = ns->parent; retire_userns_sysctls(ns); #ifdef CONFIG_PERSISTENT_KEYRINGS @@ -171,7 +174,7 @@ static void free_user_ns(struct work_struct *work) #endif ns_free_inum(&ns->ns); kmem_cache_free(user_ns_cachep, ns); - dec_user_namespaces(parent); + dec_user_namespaces(ucounts); ns = parent; } while (atomic_dec_and_test(&parent->count)); }